SIFT-Bag Kernel for Video Event Analysis (2009)
In this work, we present a SIFT-Bag based generative-todiscriminative framework for addressing the problem of video event recognition in unconstrained news videos. In the generative stage, each video...
Recent advances and challenges of semantic image/video search (2009)
Shih-fu Chang, Wei-ying Ma, Arnold Smeulders
We present an overview of recent advances and major challenges in image and video search, with a specific focus on large-scale semantic concept detection and indexing. Such semantic indexing paradigm...
Abstract A Data Set of Authentic and Spliced Image Blocks (2008)
Image splicing is a simple process that crops and pastes regions from the same or separate sources. It is a fundamental step used in digital photomontage, which refers to a paste-up produced by...
Abstract--Human faces provide a useful cue in indexing video content. In this paper, we present a highly efficient system that can rapidly detect human face regions in MPEG video sequences. The...
Learning Random Attributed Relational Graph for Part-based Object Detection (2008)
Dong-qing Zhang, Shih-fu Chang
Part-based object detection methods have been shown intuitive and effective in detecting general object classes. However, their practical power is limited due to the need of part-level labels for...
EXPERIMENTS IN CONSTRUCTING BELIEF NETWORKS FOR IMAGE CLASSIFICATION SYSTEMS (2008)
We present procedures and experimental results in constructing belief networks for image classi cation systems based on probabilistic reasoning. In particular, we compare the performance of systems...
Quality-Optimized and Secure End-to-End Authentication for Media Delivery (2008)
Qibin Sun, John Apostolopoulos, Senior Member, Chang Wen Chen, Shih-fu Chang
Abstract—The need for security services, such as confidentiality and authentication, have become one of the major concerns in multimedia communication applications, such as video on demand and...
FGS+: A FINE-GRANULAR SPATIO-TEMPORAL-SNR SCALABLE VIDEO CODER (2008)
Raj Kumar Rajendran, Shih-fu Chang
To enable universal multimedia access, a framework that allows a video stream to be delivered to displays with different viewing resolutions under varying network conditions in real-time with minimal...
Using Geometry Invariants for Camera Response Function Estimation (2008)
In this paper, we present a new single-image camera response function (CRF) estimation method using geometry invariants (GI). We derive mathematical properties and geometric interpretation for GI,...
DETECTING GENERIC VISUAL EVENTS WITH TEMPORAL CUES (2008)
Lexing Xie, Dong Xu, Shahram Ebadollahi, Katya Scheinberg, Shih-fu Chang, John R. Smith
We present novel algorithms for detecting generic visual events from video. Target event models will produce binary decisions on each shot about classes of events involving object actions and their...
Methods for Visual Search (2008)
Most Semantic Video, Winston H. Hsu, Lyndon S. Kennedy, Shih-fu Chang
search methods use text-keyword queries or example video clips and images. But such methods have limitations. Here the authors introduce two reranking processes for image and video search that...
Abstract Blind Detection of Digital Photomontage using Higher Order Statistics (2008)
The advent of the modern digital technology has not only brought about the prevalent use of digital images in our daily activities but also the ease of creating image forgery such as digital...
Arnon Amir, Marco Berg, Shih-fu Chang, Winston Hsu, Giridharan Iyengar, Yung Lin, ...
In this paper we describe our participation in the NIST TRECVID-2003 evaluation. We participated in four tasks of the benchmark including shot boundary detection, high-level feature detection, story...
Image Source Identification (2008)
Tian-tsong Ng, Shih-fu Chang, Jessie Hsu, Mao-pei Tsui, Problem I
� Digital images is pliable to manipulation. � [WSJ 89] 10 % of color images published in US were altered. � Image forensic: to find out the condition of an image without any prior information....
Anchor Shot Detection in TRECVID-2005 Broadcast News Videos (2008)
Akira Yanagawa, Winston Hsu, Shih-fu Chang
In this paper, we discuss a new method for detecting anchor shots in broadcast news video. Our approach makes use of face information that includes the position, the size and the number of faces...
A robust and secure media signature scheme for JPEG images”, MMSP02 (2008)
Qibin Sun, Prof Yun, Q. Shi, Qibin Sun, Shih-fu Chang, ...
Abstract — In [1, 2, 3], we have briefly introduced a robust and secure digital signature solution for multimedia content authentication, by integrating content feature extraction, error correction...
A Framework for Sub-Window Shot Detection (2008)
Chuohao Yeo, Yong-wei Zhu, Qibin Sun, Shih-fu Chang
Browsing a digital video library can be very tedious especially with an ever expanding collection of multimedia material. We present a novel framework for extracting sub-window shots from MPEG...
Abstract — We presented a set of physics motivated features for classifying photographic and computer graphic images in our previous work [1]. We also deployed an online demo system for...
Header for SPIE use Motion Trajectory Matching of Video Objects (2008)
In this paper, we propose an efficient wavelet-based approach to achieve flexible and robust motion trajectory matching of video objects. By using the wavelet transform, our algorithm decomposes the...
Qibin Sun, Shuiming Ye, Ching-yung Lin, Shih-fu Chang
With the ambient use of digital images and the increasing concern on their integrity and originality, consumers are facing an emergent need of authenticating degraded images despite lossy compression...
Lecture Notes in Computer Science 1 MPEG-7 MDS Content Description Tools and Applications (2008)
Ana B. Benitez, Di Zhong, Shih-fu Chang, John R. Smith
Abstract. In this paper, we present the tools specified by the MDS part of the MPEG-7 standard for describing multimedia data such as images and video. In particular, we focus on the description...
Shih-fu Chang, John R. Smith, Jianhao Meng
Efficient, effective methods for indexing, searching, and retrieving images and videos from large archives are critical techniques required in visual information systems (VIS) applications. Users...
Element Rearrangement for Tensor-Based Subspace Learning (2008)
Shuicheng Yan, Dong Xu, Stephen Lin, Thomas S. Huang, Shih-fu Chang
The success of tensor-based subspace learning depends heavily on reducing correlations along the column vectors of the mode-k flattened matrix. In this work, we study the problem of rearranging...
Yong Wang, Shih-fu Chang, Er C. Loui
Video adaptation allows for direct manipulation of existing encoded video streams to meet new resource constraints without having to encode the video from scratch. Multi-dimensional scalable coding...
This paper presents novel methods for automatically discovering, summarizing and evaluating multimedia knowledge from annotated images in the form of images clusters, word senses and relationships...
ECHOCARDIOGRAM VIDEOS: SUMMARIZATION, TEMPORAL SEGMENTATION AND BROWSING (2008)
Shahram Ebadollahi, Shih-fu Chang
In this paper, we present a system for the temporal segmentation, summarization, and browsing of the Echocardiogram videos. Echocardiogram videos are video sequences produced by the ultrasound...
The growth of digital image and video archives is increasing the need for tools that e ectively lter and e ciently search through large amounts of visual data. Towards this goal we propose a...
Columbia University’s Semantic Video Search Engine (2008)
Shih-fu Chang, Lyndon S. Kennedy, Eric Zavesky
We briefly describe “CuVid, ” Columbia University’s video search engine, a system that enables semantic multimodal search over video broadcast news collections. The system was developed and...
ABSTRACT A Utility Framework for the Automatic Generation of Audio-Visual Skims (2008)
Hari Sundaram, Lexing Xie, Shih-fu Chang
In this paper, we present a novel algorithm for generating audiovisual skims from computable scenes. Skims are useful for browsing digital libraries, and for on-demand summaries in settop boxes. A...
Chapter 1 UNSUPERVISED MINING OF STATISTICAL TEMPORAL STRUCTURES IN VIDEO (2008)
Lexing Xie, Shih-fu Chang, Ajay Divakaran, Huifang Sun
Abstract In this paper, we present algorithms for unsupervised mining of structures in video using multi-scale statistical models. Video structure are repetitive segments in a video stream with...
Bibliography Published Papers by Dragomir R. Radev References (2008)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, James Allan, ...
retrieval and language modeling. SIGIR Forum, 37(1), March
Bibliography Published Papers by Dragomir R. Radev References (2008)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, James Allan, ...
retrieval and language modeling. SIGIR Forum, 37(1), March
DATABASE RESEARCH AT COLUMBIA UNIVERSITY (2007)
Shih-fu Chang, Luis Gravano, Gail E. Kaiser, Kenneth A. Ross, Salvatore J. Stolfo
Columbia University has a number of projects that
In bandwidth limited networks and network interfaces, dynamic resource allocation can substantially increase the link utilization and also decrease the required network buffering. In general, there...
New schemes for video transmission over wireless channels are described. Content based approaches for video segmentation and associated resource allocation are proposed. We argue that for transport...
Alejandro Jaimes, Ana B. Benitez, Shih-fu Chang, Corinne Jörgensen
ABSTRACT................................................................................................................................................................. 3
Caterina Saraceno, Adam Lindsay, Ana B. Benitez, Shih-fu Chang
2.1 SYNTACTIC DS................................................................................................................................................ 2 2.2 SEMANTIC...
Title: Conceptual Modeling of MPEG-7 Description Schemes (2007)
Source John, R. Smith, Patrick Brigger, Ana B. Benitez, Shih-fu Chang
The Moving Picture’s Experts Group (MPEG) has recently started work on a new standardization effort called the "Multimedia Content Description Interface, " also known as MPEG-7....
We have recently contributed to the development and validation of several description schemes for multimedia content, which have been integrated into the emerging MPEG-7 standard. This paper includes...
July Vancouver Canada, B. Benitez, Alejandro Jaimes, Shih-fu Chang, John R. Smith
................................................................................................................................................................. 2 1 INTRODUCTION...
Self-Describing Schemes for Interoperable MPEG-7 Multimedia Content Descriptions (2007)
Seungyup Paek Ana, Ana B. Benitez, Shih-fu Chang
In this paper, we present the self-describing schemes for interoperable image/video content descriptions, which are being developed as part of our proposal to the MPEG-7 standard. MPEG7 aims to...
October Melbourne Australia, B. Benitez, Di Zhong, Shih-fu Chang, Caterina Saraceno, Markus Kangas, ...
This document concerns Validation Experiments of the MPEG-7 DSs [2]. 2 Purpose
Proposal Id: P482 Proposal for MPEG-7 Archive Description Scheme Name: (2007)
Name Ana, Ana Benitez, SHIh-Fu Chang, Seungyup Paek, ...
MPEG-7 aims to standardize descriptors, descriptor schemes, and a description definition language for multimedia content in order to facilitate content applications such as multimedia searching,...
Content-Based Video Transmission Over Wireless Channels (2007)
This paper describes new schemes for video transmission over wireless channels. Traditionally data was segmented using headers and data type (e.g. motion vectors, low and high frequency DCT...
Shih-Fu Chang, Alexandros Eleftheriadis, and Dimitris Anastassiou (2007)
Shih-fu Chang, Ros Eleftheriadis, Dimitris Anastassiou
This paper reports on our progress in developing an advanced video-on-demand (VOD) testbed, which will accommodate various multimedia research and applications such as Electronic News on Demand,...
Authentication of Zero-Tree Wavelet Encoded Images (2007)
In this paper, we propose two novel digital signatures that can be used to authenticate zero-tree wavelet coded bitstreams. We provide theoretical analysis to show the effectiveness of these digital...
VisualSEEk: a Content-Based Image/Video Retrieval Tool - System Report And User's Manual (2007)
This project implements a "content-based" image /video retrieval system for the World Wide Web. The application, called VisualSEEk, provides a suite of tools with which a person may search...
Hybrid Object-Based/Block-Based Coding in Video Compression at Very Low Bitrate (2007)
Chung-Tao Chu, Dimitris Anastassiou, Shih-fu Chang
In this paper, an algorithmic architecture of video coding at very low bit rate is presented. This architecture incorporates block- and object-based coding algorithms into the same coder and manages...
Hierarchical Global Motion Estimation/Compensation in Low Bitrate Video Coding (2007)
Chung-Tao Chu, Dimitris Anastassiou, Shih-fu Chang
In this paper, we develop a hierarchical global motion estimation/compensation system which is used to improve the block-based motion compensation in the current low bitrate video coding standard...
Space Adaptive Wavelet Packet Image Compression (2007)
We present a technique for lossy image compression based on the joint-adaptive space and frequency decomposition of images. The algorithm adapts to image content by both developing wavelet packet...
Lexing Xie, Peng Xu, Shih-fu Chang, Ajay Divakaran, Huifang Sun
In this paper, we present statistical techniques for parsing the structure of produced soccer programs. The problem is important for applications such as personalized video streaming and browsing...
Alfred V. Aho, Shih-fu Chang, Kathleen R. Mckeown, Dragomir R. Radev, John R. Smith, Kazi A. Zaman
Abstract. In this paper we describe an ongoing research
Di Zhong, Shih-fu Chang, John R. Smith
Compression and caching are two important issues for a large online image server. In this paper, we propose a new approach to compression by exploring image similarity in large image archives. An...
ECHOCARDIOGRAM VIDEOS: SUMMARIZATION, TEMPORAL SEGMENTATION AND BROWSING (2007)
Shahram Ebadollahi, Shih-fu Chang, Henry Wlg
In this paper, we present a system for the temporal segmentation, summm4zation, and browsing of the Echocardiogram videos. Echocardiogram videos are video sequences produced by the ultrasound...
VISMAP: AN INTERACTIVE IMAGENIDEO RETRIEVAL SYSTEM USING VISUALIZATION AND CONCEPT MAPS (2007)
Images and videos can be indexed by multiple features at different levels, such as color, texture, motion, and text annotation. Organizing this information into a system so that users can query...
Experiments in Indexing Multimedia Data at Multiple Levels (2007)
Ro Jaimes, Aria B. Benitez, Corinne Joergensen, Shih-fu Chang
The increasing availability of digital images, video, and audio has created exciting new research challenges on the organization of multimedia data for a variety of purposes. While some of these...
Ana B. Benitez, Shih-fu Chang, John R. Smith
In this demo, we present the 1MKA system, which implements the innovative approach of integrating perceptual information such as low-level features and images, and symbolic information such as words...
Video Shot Detection Combining Multiple Visual Features (2007)
Shot based indexing techniques have been widely used to organize video data. Scene change detection is the most commonly used method to segment image sequences into coherent units for video indexing....
Header for SPIE use Motion Trajectory Matching of Video Objects (2007)
In this paper, we propose an efficient wavelet-based approach to achieve flexible and robust motion trajectory matching of video objects. By using the wavelet transform, our algorithm decomposes the...
Lecture Notes in Computer Science MPEG-7 MDS Content Description Tools and Applications (2007)
Ana B. Benitez, Di Zhong, Shih-fu Chang, John R. Smith
Abstract. In this paper, we present the tools specified by the MDS part of the MPEG-7 standard for describing multimedia data such as images and video. In particular, we focus on the description...
High performance digital video servers: storage and retrieval of compressed scalable video (2007)
Abstract.Developments in the fields of computing, computer networks and digital video compression technology have led to the emergence of unprecedented forms of video communications. In the future,...
Shih-fu Chang, Alexandros Eleftheriadis, Robert Mcclintock
Content creation, editing, and searching are extremely time consuming tasks that often require substantial training and experience, especially when high-quality audio and video are involved....
Ajay Divakaran, Anthony Vetro, Shih-fu Chang, Huifang Sun, Hualu Wang, Hualu Wang
In this paper, we attempt to provide a comprehensive and high-level review of audiovisual features that can be extracted from the standard compressed domains, such as MPEG-1 and MPEG-2. The paper is...
information in the form of images, graphics, animations, and videos is published on the
Ajay Divakaran, Anthony Vetro, Shih-fu Chang, Huifang Sun, Hualu Wang, Hualu Wang
This paper gives an overview of state of the art in algorithms and tools using video and audio features. In particular, we extensively survey the features that can be efficiently extracted from...
Web: www.ee.columbia.edu/~ajaimes (2007)
Alejandro Jaimes, Shih-fu Chang
In this paper, we propose a new framework for the dynamic construction of structured visual object/scene detectors for content-based retrieval. In the Visual Apprentice, a user defines visual...
Technique Global Distribution (2007)
Ro Jaimes, Ana B. Benitez, Corinne Joergensen, Shih-fu Chang
The increasing availability of digital images, video, and audio has created exciting new research challenges on the organization of multimedia data for a variety of purposes. While some of these...
DATABASE RESEARCH AT COLUMBIA UNIVERSITY (2007)
Shih-fu Chang, Luis Gravano, Gail E. Kaiser, Kenneth A. Ross, Salvatore J. Stolfo
Columbia University has a number of projects that
Ajay Divakaran, Huifang Sun, Lexing Xie, Lexing Xie, Shih-fu Chang, Shih-fu Chang
We present algorithms for automatic feature selection and model order identification based on our previous solution to unsupervised structure discovery from video sequences. The overall problem is...
Chapter 1 UNSUPERVISED MINING OF STATISTICAL TEMPORAL STRUCTURES IN VIDEO (2007)
Lexing Xie, Shih-fu Chang, Ajay Divakaran, Huifang Sun
Abstract In this paper, we present algorithms for unsupervised mining of structures in video using multi-scale statistical models. Video structure are repetitive segments in a video stream with...
International Journal on Digital Libraries Manuscript Nr. (2007)
Will Be Inserted, Shih-fu Chang, John R. Smith, ...
In this paper we describe an ongoing research project called the Columbia Digital News Project. The goal of this project is to develop a suite of effective interoperable tools with which people can...
Unsupervised Discovery Of Multilevel Statistical Video Structures (2007)
Using Hierarchical Hidden, Lexing Xie, Shih-fu Chang, Ajay Divakaran, Huifang Sun, Cambridge Ma
Structure elements in a time sequence (e.g. video) are repetitive segments with consistent deterministic or stochastic characteristics. While most existing work in detecting structures follow a...
Large-scale multimodal semantic concept detection for consumer video (2007)
Shih-fu Chang, Dan Ellis, Wei Jiang, Keansub Lee, Akira Yanagawa, Er C. Loui, ...
In this paper we present a systematic study of automatic classification of consumer videos into a large set of diverse semantic concept classes, which have been carefully selected based on user...
Bibliography Published Papers by Dragomir R. Radev References (2007)
Dragomir R. Radev, Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, Bruce Croft, ...
[5] Suresh Bhavnani, Karen Drabenstott, and Dragomir Radev. Towards a unified framework of IR tasks and strategies. In 2001 ASIST Annual
Large-scale multimodal semantic concept detection for consumer video (2007)
Shih-fu Chang, Dan Ellis, Wei Jiang, Keansub Lee, Akira Yanagawa, Er C. Loui, ...
In this paper we present a systematic study of automatic classification of consumer videos into a large set of diverse semantic concept classes, which have been carefully selected based on user...
Description of Submitted Runs (2007)
Shih-fu Chang, Winston Hsu, Wei Jiang, Lyndon Kennedy, Dong Xu, Akira Yanagawa, ...
� A_CL1_1: choose the best-performing classifier for each concept from all the following runs and an event detection method. � A_CL2_2: (visual-based) choose the best-performing visual-based...
Topic tracking across broadcast news videos with visual duplicates and semantic concepts (2006)
Videos from distributed sources (e.g., broadcasts, podcasts, blogs, etc.) have grown exponentially. Topic threading is very useful for organizing such large-volume information sources. Current...
Complexity adaptive H.264 encoding for light weight stream (2006)
Emerging video coding standard H.264 achieves significant efficiency improvements, at the expense of greatly increased computational complexity at both the encoder and the decoder. Most prior works...
Lyndon S. Kennedy, Shih-fu Chang, Igor V. Kozintsev
In this work we explore the trade-offs in acquiring training data for image classification models through automated web search as opposed to human annotation. Automated web search comes at no cost in...
Kurato Maeno, Qibin Sun, Shih-fu Chang, Masayuki Suto
Abstract—Semi-fragile watermarking techniques aim at detecting malicious manipulations on an image, while allowing acceptable manipulations such as lossy compression. Although both of these...
Passive-blind Image Forensics (2006)
Tian-tsong Ng, Shih-fu Chang, Ching-yung Lin, Qibin Sun
In this chapter, we will review the research area of passive-blind image forensics, i.e., an form of image analysis for finding out the condition of an image without relying on pre-registration or...
An online system for classifying computer graphics images from natural photographs (2006)
We describe an online system for classifying computer generated images and camera-captured photographic images, as part of our effort in building a complete passive-blind system for image tampering...
An Optimal Framework of Video Adaptation and Its Application to Rate Adaptation Transcoding (2005)
Kim, Jae-Gon, Wang, Yong, Chang, Shih-Fu, Kim, Hyung-Myung
The adaptation of video according to the heterogeneous and dynamic resource constraints on networks and devices, as well as on user preferences, is a promising approach for universal access and...
Video Search and High-Level Feature Extraction (2005)
Shih-fu Chang, Winston Hsu, Lyndon Kennedy, Lexing Xie, Akira Yanagawa, Eric Zavesky, ...
High-Level feature extraction
A crypto signature scheme for image authentication over wireless channel (2005)
Qibin Sun, Shuiming Ye, Ching-yung Lin, Shih-fu Chang
With the ambient use of digital images and the increasing concern on their integrity and originality, consumers are facing an emergent need of authenticating degraded images despite lossy compression...
Shih-fu Chang, Winston Hsu, Lyndon Kennedy, Lexing Xie, Akira Yanagawa, Eric Zavesky, ...
High-Level feature extraction � A_DCON1_1: Choose the best-performing classifier from the following runs for each concept. � A_DCON2_2: linear weighted fusion of 4 SVM classifiers using...
Shahram Ebadollahi, Shih-fu Chang
� Conclusion
Columbia-IBM news video story segmentation in trecvid 2004 (2005)
Winston H. Hsu, Lyndon S. Kennedy, Shih-fu Chang, Martin Franz, John R. Smith
In this technical report, we give an overview of our technical developments in the story segmentation task in TRECVID 2004. Among them, we propose an information-theoretic framework, visual cue...
A light scale concept ontology for multimedia understanding for trecvid 2005 (2005)
Milind R. Naphade, Lyndon Kennedy, John R. Kender, Shih-fu Chang, John R. Smith, Paul Over, ...
LIMITED DISTRIBUTION NOTICE: This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. Ithas been issued as a Research Report for...
Layered dynamic mixture model for pattern discovery in asynchronous multi-modal streams (2005)
Lexing Xie, Lexing Xie, Lyndon Kennedy, Lyndon Kennedy, Shih-fu Chang, Shih-fu Chang, ...
We propose a layered dynamic mixture model for asynchronous multi-modal fusion for unsupervised pattern discovery in video. The lower layer of the model uses generative temporal structures such as a...
Physics-motivated features for distinguishing photographic images and computer graphics (2005)
Tian-tsong Ng, Shih-fu Chang, Jessie Hsu, Lexing Xie
The increasing photorealism for computer graphics has made computer graphics a convincing form of image forgery. Therefore, classifying photographic images and photorealistic computer graphics has...
Layered dynamic mixture model for pattern discovery in asynchronous multi-modal streams (2005)
Lexing Xie, Lyndon Kennedy, Shih-fu Chang, Ajay Divakaran, Huifang Sun, Ching-yung Lin
We propose a layered dynamic mixture model for asynchronous multi-modal fusion for unsupervised pattern discovery in video. The lower layer of the model uses generative temporal structures such as a...
Video Adaptation: Concepts, Technologies, and Open Issues (2005)
Shih-fu Chang, Shih-fu Chang, Anthony Vetro, Anthony Vetro, Senior Member
Video adaptation is an emerging field that offers a rich body of techniques for answering challenging questions in pervasive media applications. It transforms the input video(s) to an output in video...
Video Adaptation: Concepts, Technologies, and Open Issues (2005)
Jun Xin, Chia-wen Lin, Ming-ting Sun, Shih-fu Chang, Anthony Vetro, Senior Member
Video transcoding, due to its high practical values for a wide range of networked video applications, has become an active research topic. In this review paper, we outline the technical issues and...
A crypto signature scheme for image authentication over wireless channel (2005)
Qibin Sun, Shuiming Ye, Ching-yung Lin, Shih-fu Chang
With the ambient use of digital images and the increasing concern on their integrity and originality, consumers are facing an emergent need of authenticating degraded images despite lossy compression...
photographic images and photorealistic computer graphics dataset (2005)
Tian-tsong Ng, Shih-fu Chang, Jessie Hsu, Martin Pepeljugoski
Passive-blind image authentication is a new area of research. A suitable dataset for experimentation and comparison of new techniques is important for the progress of the new research area. In...
A crypto signature scheme for image authentication over wireless channel (2005)
Qibin Sun, Shuiming Ye, Ching-yung Lin, Shih-fu Chang
With the ambient use of digital images and the increasing concern on their integrity and originality, consumers are facing an emergent need of authenticating degraded images despite lossy compression...
Abstract. Recent research in video analysis has shown a promising direction, in which mid-level features (e.g., people, anchor, indoor) are abstracted from low-level features (e.g., color, texture,...
Ibm research trecvid-2004 video retrieval system (2004)
Arnon Amir, Janne O Argill, Marco Berg, Shih-fu Chang, Martin Franz, Winston Hsu, ...
In this paper we describe our participation in the NIST TRECVID-2004 evaluation. We participated in four tasks of the benchmark including shot boundary detection, high-level feature detection, story...
As computer graphics (CG) is getting more photorealistic, for the purpose of image authentication, it becomes increasingly important to construct a detector for classifying photographic images (PIM)...
S.: Learning to detect scene text using a higher-order mrf with belief propagation (2004)
Dong-qing Zhang, Shih-fu Chang
Detecting text in natural 3D scenes is a challenging problem due to background clutter and photometric/gemetric variations of scene text. Most prior systems adopt approaches based on deterministic...
Blind Detection of Photomontage Using Higher Order Statistics (2004)
In this paper, we investigate the prospect of using bicoherence features for blind image splicing detection. Image splicing is an essential operation for digital photomontaging, which in turn is a...
A model for image splicing (2004)
The ease of creating image forgery using image-splicing techniques will soon make our naïve trust on image authenticity a thing of the past. In prior work, we observed the capability of the...
Discovery and fusion of salient multi-modal features towards news story segmentation (2004)
Winston Hsu, Shih-fu Chang, Chih-wei Huang, Lyndon Kennedy, Ching-yung Lin, Giridharan Iyengar
In this paper, we present our new results in news video story segmentation and classification in the context of TRECVID video retrieval benchmarking event 2003. We applied and extended the Maximum...
Blind Detection of Photomontage Using Higher Order Statistics (2004)
In this paper, we investigate the prospect of using bicoherence features for blind image splicing detection. Image splicing is an essential operation for digital photomontaging, which in turn is a...
Yong Wang, Shih-fu Chang, Er C. Loui
Video adaptation allows for direct manipulation of existing encoded video streams to meet new resource constraints without having to encode the video from scratch. Multi-dimensional scalable coding...
Tian-tsong Ng, Shih-fu Chang, Qibin Sun
digital images?
Mitsubishi Electric Research Laboratories (2004)
Http Www Merl, Lexing Xie, Peng Xu, Shih-fu Chang, Ajay Divakaran, Huifang Sun
In this paper, we present statistical techniques for parsing the structure of produced soccer programs. The problem is important for applications such as personalized video streaming and browsing...
Mitsubishi Electric Research Laboratories (2004)
Http Www Merl, Ajay Divakaran, Ajay Divakaran, Kadir A. Peker, Kadir A. Peker, Shih-fu Chang, ...
We examine the significance of video mining as pattern discovery in multimedia content. We examine the underlying issue of pattern discovery versus pattern recognition, since most past work has not...
Yong Wang, Tian-tsong Ng, Shih-fu Chang
Recently we have witnessed a growing interest in the development of the subband/wavelet coding (SBC) technology, partly due to the superior scalability of SBC. Scalable coding provides great synergy...
Real-Time View Recognition and Event Detection for Sports Video.” JVCIR (2004)
In this paper, we present a general framework and new effective algorithms to detect the syntactic structures that are at a level higher than shots. In sports video, such high-level structures are...
Structure Analysis of Soccer Video with Domain Knowledge and Hidden Markov Models (2004)
Lexing Xie, Peng Xu, Shih-Fu Chang, Ajay Divakaran, Huifang Sun
In this paper, we present statistical techniques for parsing the structure of produced soccer programs. The problem is important for applications such as personalized video streaming and browsing...
Discovery and fusion of salient multi-modal features towards news story segmentation (2004)
Winston Hsu, Shih-fu Chang, Chih-wei Huang, Lyndon Kennedy, Ching-yung Lin, Giridharan Iyengar
In this paper, we present our new results in news video story segmentation and classification in the context of TRECVID video retrieval benchmarking event 2003. We applied and extended the Maximum...
Stochastic attribute relational graph matching for image near-duplicate detection (2004)
Dong-qing Zhang, Shih-fu Chang
Attributed Relational Graph (ARG) is a useful model for representing many real-world relational patterns. Computing the similarity of ARGs is a fundamental problem for ARG based modelling. This...
Structure elements in a time sequence (e.g. video) are repetitive segments with consistent deterministic or stochastic characteristics. While most existing work in detecting structures follow a...
A Bayesian framework for fusing multiple word knowledge models in videotext recognition (2003)
Videotext recognition is challenging due to low resolution, diverse fonts/styles, and cluttered background. Past methods enhanced recognition by using multiple frame averaging, image interpolation...
Accurate Overlay Text Extraction for Digital Video Analysis (2003)
Dongqing Zhang, Belle L. Tseng, Ching-yung Lin, Shih-fu Chang
This paper presents a system to detect and extract overlay text in digital video. To overcome the problems of the previous approaches, we employed a multiple hypothesis filtering approach: The...
Image classification using multimedia knowledge networks (2003)
This paper presents novel methods for classifying images based on knowledge discovered from annotated images using WordNet. The novelty of this work is the automatic class discovery and the...
Unsupervised Mining Of, Lexing Xie, Shih-fu Chang, Ajay Divakaran, Huifang Sun
In this chapter we present algorithms for unsupervised mining of structures in video using multi-scale statistical models. Video structure are repetitive segments in a video stream with consistent...
Unsupervised Mining of Statistical Temporal Structures (2003)
Mitsubishi Electric Research, Lexing Xie, Shih-fu Chang, Ajay Divakaran, Huifang Sun
In this paper, we present algorithms for unsupervised mining of structures in video using multiscale statistical models. Video structure are repetitive segments in a video stream with consistent...
Detection of non-identical duplicate consumer photographs (2003)
Consumers often make more than one photograph of the same scene, creating non-identical “duplicates ” and similar “non-duplicates. ” In Kodak’s consumer photography database, 19 % of the...
Mpeg-4 real time fd-cd transcoding (2003)
Yong Wang, Jae-gon Kim, Shih-fu Chang
In this report we summarize our work on real time transcoding implementation combining frame dropping (FD) and DCT coefficient dropping (CD). FD can realize the temporal down sampling resulting in a...
Accurate Overlay Text Extraction for Digital Video Analysis (2003)
This report describes a system to detect and extract the overlay texts in digital video. Different from the previous approaches, the system used a multiple hypothesis testing approach: The...
Feature Selection For Unsupervised Discovery Of Statistical (2003)
Temporal Structures In, Lexing Xie, Shih-fu Chang
We present algorithms for automatic feature selection for unsupervised structure discovery from video sequences. Feature selection in this scenario is hard because of the absence of class labels to...
IBM research TRECVID-2003 video retrieval system (2003)
Arnon Amir, Marco Berg, Shih-fu Chang, Giridharan Iyengar, Ching-yung Lin, Apostol (paul Natsev, ...
In this paper we describe our participation in the NIST TRECVID-2003 evaluation. We participated in four tasks of the benchmark including shot boundary detection, high-level feature detection, story...
Optimal Video Adaptation and Skimming Using a Utility-Based Framework (2002)
Video adaptation uses various spatio-temporal adaptation techniques to transform video content in order to satisfy diverse resource constraints and user preferences. To explore systematic solutions,...
Semantic knowledge construction from annotated image collections (2002)
This paper presents new methods for extracting semantic knowledge from collections of annotated images. The proposed methods include novel automatic techniques for extracting semantic concepts by...
A Utility Framework for the Automatic Generation of Audio-Visual Skims (2002)
Hari Sundaram, Lexing Xie, Shih-fu Chang
In this paper, we present a novel algorithm for generating audiovisual skims from computable scenes. Skims are useful for browsing digital libraries, and for on-demand summaries in settop boxes. A...
FGS+: Optimizing the Joint SNR–Temporal Video Quality (2002)
Raj Kumar Rajendran, Shih-fu Chang
To enable video transmission over heterogeneous wireless networks, a highly scalable compression and streaming framework that can adapt to large and rapid bandwidth variations in realtime is...
Jae-gon Kim, Yong Wang, Shih-fu Chang, Kyeongok Kang
The MPEG has recently started work on standardization of Digital Item Adaptation as a part of the MPEG-21 multimedia framework. The concept of the Digital Item Adaptation is adaptation of resources...
Semi-fragile image authentication using generic wavelet domain features and ECC (2002)
In this paper we present a generic content-based solution targeting at authenticating image in a semi-fragile way, which integrates watermarking-based approach with signature-based approach. Robust...
Learning hierarchical hidden Markov models for video structure discovery (2002)
Lexing Xie, Shih-fu Chang, Ajay Divakaran, Huifang Sun
Structure elements in a time sequence are repetitive segments that bear consistent deterministic or stochastic characteristics. While most existing work in detecting structures follow a supervised...
Dongqing Zhang, Raj Kumar Rajendran, Shih-fu Chang
We have developed generic and domain-specific video algorithms for caption text extraction and recognition in digital video. Our system includes several unique features: for caption box location, we...
A new semi-fragile image authentication framework combining (2002)
Qibin Sun, Shih-fu Chang, Maeno Kurato, Masayuki Suto
This paper presents a new semi-fragile framework aiming at extending public key signature scheme from message level to content level. The content signing procedure includes signature generation and...
Learning hierarchical hidden Markov models for video structure discovery (2002)
Lexing Xie, Shih-fu Chang, Ajay Divakaran, Huifang Sun
Structure elements in a time sequence are repetitive segments that bear consistent deterministic or stochastic characteristics. While most existing work in detecting structures follow a super-vised...
Semantic knowledge construction from annotated image collections (2002)
Aria B. Benitez, Shih-fu Chang
This paper presents new methods for extracting semantic knowledge from collections of annotated images. The proposed methods include novel automatic techniques for extracting semantic concepts by...
A new semi-fragile image authentication framework combining (2002)
Qibin Sun, Shih-fu Chang, Kurato Maeno, Masayuki Suto
This paper presents a new semi-fragile framework aiming at extending public key signature scheme from message level to content level. The content signing procedure includes signature generation and...
Optimal Video Adaptation and Skimming Using a Utility-Based Framework (2002)
Video adaptation uses various spatio-temporal adaptation techniques to transform video content in order to satisfy diverse resource constraints and user preferences. To explore systematic solutions,...
Perceptual knowledge construction from annotated image collections (2002)
Aria B. Benitez, Shih-fu Chang
This paper presents and evaluates new methods for extracting perceptual knowledge from collections of annotated images. The proposed methods include automatic techniques for constructing perceptual...
Semi-fragile image authentication using generic wavelet domain features and ECC (2002)
In this paper we present a generic content-based solution targeting at authenticating image in a semi-fragile way, which integrates watermarking-based approach with signature-based approach. Robust...
FGS+: Optimizing the Joint SNR–Temporal Video Quality (2002)
Raj Kumar Rajendran, Shih-fu Chang
i Although this type of comparison may seem to be unfair to FGS- the non-scalable streams are optimized for particular bit-rates whereas FGS covers the same range of bandwidth with a single...
Structure analysis of soccer video with Hidden Markov Models (2002)
{xlx, fchang} @ ee.columbia. edu In this paper, we present algorithms for parsing the structure of produced soccer programs. The problem is important in the context of a personalized video streaming...
Dongqing Zhang, Raj Kumar Rajendran, Shih-fu Chang
We have developed generic and domain-specific video algorithms,/br caption text extraction and recognition in digital video. Our system includes several unique,/atures:,/br caption box location, we...
Duplicate detection in consumer photography and news video (2002)
Alejandro Jaimes, Shih-fu Chang, Alexander C. Loui
Consumers often make more than one photograph of the same scene, creating non-identical duplicates and near duplicates. In Kodak's consumer photography database, on average, 19 % of the
Learning Hierarchical Hidden Markov Models (2002)
For Video Structure, Lexing Xie, Shih-fu Chang, Ajay Divakaran, Huifang Sun
Structure elements in a time sequence are repetitive segments that bear consistent deterministic or stochastic characteristics. While most existing work in detecting structures follow a supervised...
Structure analysis of soccer video with Hidden Markov Models (2002)
In this paper, we present algorithms for parsing the structure of produced soccer programs. The problem is important in the context of a personalized video streaming and browsing system. While prior...
Perceptual knowledge construction from annotated image collections (2002)
This paper presents and evaluates new methods for extracting perceptual knowledge from collections of annotated images. The proposed methods include automatic techniques for constructing perceptual...
A quantitive semi-fragile JPEG2000 image authentication system (2002)
Qibin Sun, Shih-fu Chang, Maeno Kurato, Masayuki Suto
In this article, we propose a novel integrated approach to quantitative semi-fragile authentication of JPEG2000 images under a generic framework which combines ECC and PKI infrastructures [1][2]....
Using human observer eye movements in automatic image classifiers (2001)
Jaimes, Alejandro, Pelz, Jeff, Grabowski, Tim, Babcock, Jason, Chang, Shih-Fu
This article may also be accessed on the publisher's website at: http://spiedl.aip.org/getabs/servlet/GetabsServlet?prog=normal&id=PSISDG004299000001000373000001&idtype=cvips&gifs=yes Copyright 2001...
Using human observer eye movements in automatic image classifiers (2001)
Jaimes, Alejandro, Pelz, Jeff, Grabowski, Timothy, Babcock, Jason, Chang, Shih-Fu
This article may also be accessed on the publisher's website at: http://spiedl.aip.org/getabs/servlet/GetabsServlet?prog=normal&id=PSISDG004299000001000373000001&idtype=cvips&gifs=yes Copyright 2001...
Real-Time Content-Based Adaptive Streaming of Sports Video (2001)
Shih-fu Chang, Di Zhong, Raj Kumar
In this paper, we present a real-time software system for filtering live video content and then adaptively streaming the video over resource limited networks or devices. The rate adaptation is...
Constrained Utility Maximization for generating Visual Skims (2001)
In this paper, we present a novel algorithm to generate visual skims, that do not contain audio, from computable scenes. Visual skims are useful for browsing digital libraries, and for on-demand...
Learning Structured Visual Detectors From User Input at Multiple Levels (2001)
Alejandro Jaimes, Shih-fu Chang
In this paper, we propose a new framework for the dynamic construction of structured visual object/scene detectors for content-based retrieval. In the Visual Apprentice, a user defines visual...
Algorithms and system for segmentation and structure analysis in soccer video (2001)
Peng Xu, Lexing Xie, Shih-fu Chang
In this paper, we present a novel system and effective algorithms for soccer video segmentation. The output, about whether the ball is in play, reveals high-level structure of the content. The first...
SARI: self-authentication-and-recovery image watermarking system (2001)
Watermarking System, Shih-fu Chang
In this project, we designed a novel image authentication system based on our semi-fragile watermarking technique. The system, called SARI, can accept quantization-based lossy compression to a...
Using Human Observers' Eye Movements in Automatic Image Classifiers (2001)
Ro Jaimes, Jeff Pelz, Tim Grabowski, Jason Babcock, Shih-fu Chang
We explore the way in which people look at images of different semantic categories (e.g., handshake, landscape), and directly relate those results to computational approaches for automatic image...
Image authentication verifies the originality of an image by detecting malicious manipulations. This goal is different from that of image watermarking which embeds into the image a signature...
Structure Analysis of Sports Video Using Domain Models (2001)
In this paper, we present an effective framework for scene detection and structure analysis for sports videos, using tennis and baseball as examples. Sports video can be characterized by its...
Real-Time Content-Based Adaptive Streaming of Sports Video (2001)
Shih-fu Chang, Di Zhong, Raj Kumar
In this paper, we present a real-time software system for filtering live video content and then adaptively streaming the video over resource limited networks or devices. The rate adaptation is...
a system for personalized search and summarization over multimedia healthcare information (2001)
Kathleen R. Mckeown, Shih-fu Chang, James Cimino, Steven K. Feiner, Luis Gravano, Vasileios Hatzivassiloglou, ...
Using Human Observers' Eye Movements in Automatic Image Classifiers (2001)
Ro Jaimes, Jeff Pelz, Tim Grabowski, Jason Babcock, Shih-fu Chang
We explore the way in which people look at images of different semantic categories (e.g., handshake, landscape), and directly relate those results to computational approaches for automatic image...
Kathleen R. McKeown, Shih-Fu Chang, Shih-fu Changý, James Cimino, Carol Friedman, Steven K. Feiner, ...
In healthcare settings, patients need access to online information that can help them understand their medical situation. Physicians need information that is clinically relevant to an individual...
Algorithms and system for segmentation and structure analysis in soccer video (2001)
Peng Xu, Lexing Xie, Shih-fu Chang
In this paper, we present a novel system and effective algorithms for soccer video segmentation. The output, about whether the ball is in play, reveals high-level structure of the content. The first...
Condensing Computable Scenes using Visual Complexity and Film Syntax Analysis (2001)
In this paper, we present a novel algorithm to condense computable scenes. A computable scene is a chunk of data that exhibits consistencies with respect to chromaticity, lighting and sound. We...
Using Human Observers' Eye Movements in Automatic Image Classifiers (2001)
Ro Jaimes, Jeff Pelz, Tim Grabowski, Jason Babcock, Shih-fu Chang
We explore the way in which people look at images of different semantic categories (e.g., handshake, landscape), and directly relate those results to computational approaches for automatic image...
Constrained Utility Maximization for Generating Visual (2001)
Skims Hari Sundaram, Hari Sundaram, Shih-fu Chang
In this paper, we present a novel algorithm to generate visual skims, that do not contain audio, from computable scenes. Visual skims are useful for browsing digital libraries, and for on-demand...
Watermarking capacity of digital images based on domain-specific masking effects (2001)
Our objective is to nd a theoretical watermarking capac-ity bound of digital images based on domain-speci c masking e ects. In this paper, we rst show the capacity of private wa-termarking in which...
Hualu Wang, Ajay Divakaran, B Anthony Vetro, Shih-fu Chang, Huifang Sun B
In this paper, we attempt to provide a comprehensive and high-level review of audiovisual features that can be extracted from the standard compressed domains, such as MPEG-1 and MPEG-2. The paper is...
Zero-Error Information Hiding Capacity Of Digital Images (2001)
In this paper, we derive a theoretical capacity for digital image watermarking with zero transmission errors. We present three different discrete memoryless channel model to repreent the watermarking...
Structure Analysis of Sports Video Using Domain Models (2001)
In this paper, we present an effective framework for scene detection and structure analysis for sports videos, using tennis and baseball as examples. Sports video can be characterized by its...
We present a knowledge engineering approach for image classification that is based on probabilistic reasoning systems. The approach gives the knowledge engineer a systematic way to integrate multiple...
Experiments in constructing belief networks for image classification systems (2000)
sypee.columbia.edu, sfchangee.columbia.edu We present procedures and experimental results in constructing belief networks for image classification systems based on probabilistic reasoning. In...
Structure parsing and event detection for sports video (2000)
For video indexing, typically videos are first processed to obtain constituent objects and features.
Video scene segmentation using video and audio features (2000)
In this paper we present a novel algorithm for video scene segmentation. We model a scene as a semantically consistent chunk of audio-visual data. Central to the segmentation framework is the idea of...
syp @ ee.columbia.edu, sfchang @ ee.columbia.edu We present a knowledge engineering approach for image classification that is based on probabilistic reasoning systems. The approach gives the...
Principles and Applications of Content-Aware Video Communication (2000)
Most traditional video communication systems consider videos as low-level bit streams, ignoring the underlying visual content. Content-aware video communication is a new framework that explores the...
Structural and semantic analysis of video (2000)
In this paper we discuss our recent research and open issues in structural and semantic analysis of digital videos. Specifically, we focus on segmentation, summarization and classification of digital...
Semi-fragile watermarking for authenticating JPEG visual content (2000)
In this paper, we propose a semi-fragile watermarking technique that accepts JPEG lossy compression on the watermarked image to a pre-determined quality factor, and rejects malicious attacks. The...
Audio scene segmentation using multiple features, models and time scales (2000)
In this paper we present an algorithm for audio scene segmentation. An audio scene is a semantically consistent sound segment that is characterized by a few dominant sources of sound. A scene change...
Determining Computable Scenes in Films and their Structures using Audio-Visual Memory Models (2000)
In this paper we present novel algorithms for computing scenes and within-scene structures in films. We begin by mapping insights from film-making rules and experimental results from the psychology...
Discovering recurrent visual semantics in consumer photographs (2000)
Ro Jaimes, Ana B. Benitez, Shih-fu Chang, Er C. Loui
We present techniques to semi-automatically discover Recurrent Visual Semantics (RV3)-the repetitive appearance of visually similar elements such as objects and scenes- in consumer photographs....
Discovering recurrent visual semantics in consumer photographs (2000)
Ro Jaimes, Ana B. Benitez, Shih-fu Chang
We present techniques to semi-automatically discover Recurrent Visual Semantics (RVS)-the repetitive appearance of visually similar elements such as objects and scenes- in consumer photographs....
A Conceptual Framework for Indexing Visual Information at Multiple Levels (2000)
Alejandro Jaimes, Ro Jaimes, Shih-fu Chang
In this paper, we present a conceptual framework for indexing different aspects of visual information. Our framework unifies concepts from the literature in diverse fields such as cognitive...
Automatic Selection of Visual Features and Classifiers (2000)
Alejandro Jaimes, Ro Jaimes, Shih-fu Chang
In this paper, we propose a dynamic approach to feature and classifier selection. In our approach, based on performance, visual features and classifiers are selected automatically. In earlier work,...
Integrating Multiple Classifiers In Visual Object Detectors Learned From User Input (2000)
Alejandro Jaimes, Ro Jaimes, Shih-fu Chang
There have been many recent efforts in contentbased retrieval to perform automatic classification of images/visual objects. Most approaches, however, have focused on using individual classifiers. In...
Structural and Semantic Analysis of Video (2000)
In this paper we discuss our recent research and open issues in structural and semantic analysis of digital videos. Specifically, we focus on segmentation, summarization and classification of digital...
Semi-Fragile Watermarking for Authenticating JPEG Visual Content (2000)
In this paper, we propose a semi-fragile watermarking technique that accepts JPEG lossy compression on the watermarked image to a pre-determined lowest quality factor, and rejects...
Report of CE on Multi-Level Indexing Pyramid (2000)
Alejandro Jaimes, Ana B. Benitez, Shih-fu Chang, Corinne Jörgensen
Object"/> <enumeration value="Abstract Scene"/> </simpleType> <!-- ################################################ --> <!-- Text Annotation D with pyramid...
Audio Scene Segmentation Using Multiple Features, Models And Time Scales (2000)
In this paper we present an algorithm for audio scene segmentation. An audio scene is a semantically consistent sound segment that is characterized by a few dominant sources of sound. A scene change...
A conceptual framework for indexing visual information at multiple levels (2000)
In this paper, we present a conceptual framework for indexing different aspects of visual information. Our framework unifies concepts from the literature in diverse fields such as cognitive...
Integrating Multiple Classifiers in Visual Object Detectors Learned from User Input (2000)
There have been many recent efforts in contentbased retrieval to perform automatic classification of images/visual objects. Most approaches, however, have focused on using individual classifiers. In...
Automatic Selection of Visual Features and Classifiers (2000)
In this paper, we propose a dynamic approach to feature and classifier selection. In our approach, based on performance, visual features and classifiers are selected automatically. In earlier work,...
Structure parsing and event detection for sports video (2000)
For video indexing, typically videos are first processed to obtain constituent objects and features. These extracted entities provide an intermediate content model to effectively describe videos. In...
Issues and Solutions for Authenticating MPEG Video (1999)
Video authentication techniques are used to prove the originality of received video content and to detect malicious tampering. Existing authentication techniques protect every single bit of the video...
Efficient video sequence retrieval in large repositories (1999)
This paper presents algorithms to deal with problems associated with indexing high-dimensional feature vectors that characterize video data. Indexing high dimensional vectors is well known to be...
Archive Description Scheme (1999)
Seungyup Paek, Ana B. Benitez, Shih-fu Chang, Chung-sheng Li, John R. Smith, Lawrence D. Bergman, ...
1. Which media has your DS been developed for and/or applied to?
Self-describing schemes for interoperable MPEG-7 multimedia content descriptions (1999)
Seungyup Paek, Ana B. Benitez, Shih-fu Chang
In this paper, we present the self-describing schemes for interoperable image/video content descriptions, which are being developed as part of our proposal to the MPEG-7 standard. MPEG-7 aims to...
Archive Description Scheme (1999)
Seungyup Paek, Ana B. Benitez, Shih-fu Chang, Alexandros Eleftheriadis, Atul Puri, Qian Huang, ...
1. Which media has your DS been developed for and/or applied to?
Real-time Estimation of Subjective Utility Functions for MPEG-4 Video Objects (1999)
Paul Bocheck, Yasuyuki Nakajima, Shih-fu Chang
In this paper, we propose an original system for a subjective utility function estimation suitable for real-time video applications. In video networking applications, utility function is defined as a...
Model-Based Classification of Visual Information for Content-Based Retrieval (1999)
Alejandro Jaimes, Ro Jaimes, Shih-fu Chang
Most existing approaches to content-based retrieval rely on query by example or user sketch based on low-level features; these are not suitable for semantic (object level) distinctions. In other...
FaceTrack: Tracking and Summarizing Faces from Compressed Video (1999)
Hualu Wang, Harold S. Stone, Shih-fu Chang
In this paper, we present FaceTrack, a system that detects, tracks, and groups faces from compressed video data. We introduce the face tracking framework based on the Kalman filter and multiple...
Distortion modeling and invariant extraction for digital image print-and-scan process (1999)
After an image is printed-and-scanned, it is usually filtered, rotated, scaled, cropped, contrast-andluminance adjusted, as well as distorted by noises. This paper presents models for the...
Image retrieval: Current techniques, promising directions and open issues (1999)
Yong Rui, Thomas S. Huang, Shih-fu Chang
This paper provides a comprehensive survey of the technical achievements in the research area of Image Retrieval, especially Content-Based Image Retrieval, an area so active and prosperous in the...
Issues and Solutions for Authenticating MPEG Video (1999)
Video authentication techniques are used to prove the originality of received video content and to detect malicious tampering. Existing authentication techniques protect every single bit of the video...
Distortion Modeling and Invariant Extraction for Digital Image Print-and-Scan Process (1999)
After an image is printed-and-scanned, it is usually filtered, rotated, scaled, cropped, contrast-andluminance adjusted, as well as distorted by noises. This paper presents models for the...
Seungyup Paek, Carl L. Sable, Vasileios Hatzivassiloglou, Alejandro Jaimes, Barry H. Schiffman, Shih-fu Chang, ...
Annotating photographs automatically with content descriptions facilitates organization, storage, and search over visual information. We present an integrated approach for scene classification that...
Self-Describing Schemes for Interoperable MPEG-7 Multimedia Content Descriptions (1999)
Seungyup Paek, Ana B. Benitez, Shih-fu Chang
In this paper, we present the self-describing schemes for interoperable image/video content descriptions, which are being developed as part of our proposal to the MPEG-7 standard. MPEG7 aims to...
Seungyup Paek, Ana B. Benitez, and Shih-Fu Chang (1999)
Image Advanced Tv, Seungyup Paek, Ana B. Benitez, Shih-fu Chang
In this paper, we present the self-describing schemes for interoperable image/video content descriptions, which are being developed as part of our proposal to the MPEG-7 standard. MPEG-7 aims to...
Self-Describing Schemes for Interoperable MPEG-7 Multimedia Content Descriptions (1999)
Seungyup Paek, Ana B. Benitez, Shih-fu Chang
In this paper, we present the self-describing schemes for interoperable image/video content descriptions, which are being developed as part of our proposal to the MPEG-7 standard. MPEG-7 aims to...
FaceTrack: Tracking and Summarizing Faces from Compressed Video (1999)
Hualu Wang, Harold S. Stone, Shih-fu Chang
In this paper, we present FaceTrack, a system that detects, tracks, and groups faces from compressed video data. We introduce the face tracking framework based on the Kalman filter and multiple...
A robust image authentication method surviving JPEG lossy compression (1998)
Image authentication verifies the originality of an image by detecting malicious manipulations. This goal is different from that of image watermarking which embeds into the image a signature...
Metaseek: A content-based meta-search engine for images (1998)
Is Beigi, Ana B. Benitez, Shih-fu Chang
Search engines are the most powerful resources for finding information on the rapidly expanding World Wide Web (WWW). Finding the desired search engines and learning how to use them, however, can be...
Eective algorithms for video transmission over wireless channels (1998)
New schemes for video transmission over wireless channels are described. Content based approaches for video segmentation and associated resource allocation are proposed. We argue that for transport...
Semantic visual templates: Linking visual features to semantics (1998)
Shih-fu Chang, William Chen, Hari Sundaram
The rapid growth of visual data over the last few years has lead to many schemes for retrieving such data. With content-based systems today, there exists a significant gap between the user's...
Metaseek: A content-based meta-search engine for images (1998)
Is Beigi, Ana B. Benitez, Shih-fu Chang
Search engines are the most powerful resources for finding information on the rapidly expanding World Wide Web (WWW). Finding the desired search engines and learning how to use them, however, can be...
Content-based dynamic resource allocation for VBR video in bandwidth limited networks (1998)
In bandwidth limited access networks, dynamic resource allocation can increase the link utilization and decrease the required network buffering. In this paper, we propose a new policy in which the...
A fully automated content-based video search engine supporting spatiotemporal queries (1998)
Shih-fu Chang, William Chen, Horace J. Meng, Hari Sundaram, Di Zhong
Abstract—The rapidity with which digital information, particularly video, is being generated has necessitated the development of tools for efficient search of these media. Content-based visual...
Using Relevance Feedback In Contentbased Image Metasearch (1998)
Anna B Benitez, Mandis Beigi, Shih-fu Chang
this article with a review of the issues in content-based visual query, then describe the current MetaSeek implementation. We present the results of experiments that evaluated the implementation in...
Digital Image/Video Library And Mpeg-7: Standardization And Research Issues (1998)
Yong Rui, Thomas S. Huang, Shih-fu Chang
Much research activity and interest has emerged recently in two closely related areas: Digital Image/Video Library (DIVL) and MPEG-7. In this paper, we review the critical research issues in DIVL...
Semantic Visual Templates: Linking Visual Features to Semantics (1998)
Shih-fu Chang, William Chen, Hari Sundaram
The rapid growth of visual data over the last few years has lead to many schemes for retrieving such data. With content-based systems today, there exists a significant gap between the user's...
A Content-Based Image Meta-Search Engine using Relevance Feedback (1998)
Ana Benitez, Mandis Beigi, Is Beigi, Shih-fu Chang
Search engines are the most powerful resources for finding information on the rapidly expanding World-Wide Web. Finding the desired search engines and learning how to use them, however, can be very...
VideoQ: A Fully Automated Video Retrieval System Using Motion Sketches (1998)
Shih-fu Chang, William Chen, Hari Sundaram
The rapidity with which digital information, particularly video, is being generated, has necessitated the development of tools for efficient search of these media. Content based visual queries have...
VideoQ: a fully automated video retrieval system using motion sketches (1998)
Shih-fu Chang, William Chen, Hari Sundaram
The rapidity with which digital information, particularly video, is being generated, has necessitated the development of tools for efficient search of these media. Content based visual queries have...
Semantic visual templates: Linking visual features to semantics (1998)
Shih-fu Chang, William Chen, Hari Sundaram
The rapid growth of visual data over the last few years has lead to many schemes for retrieving such data. With content-based systems today, there exists a significant gap between the user’s...
Metaseek: A content-based meta-search engine for images (1998)
Is Beigi, Ana B. Benitez, Shih-fu Chang
Search engines are the most powerful resources for finding information on the rapidly expanding World Wide Web (WWW). Finding the desired search engines and learning how to use them, however, can be...
A highly efficient system for automatic face region detection in mpeg video (1997)
Hualu Wang, Student Member, Shih-fu Chang
Abstract—Human faces provide a useful cue in indexing video content. In this paper, we present a highly efficient system that can rapidly detect human face regions in MPEG video sequences. The...
Objective and Subjective Quality of Service Performance of Video-on-Demand in ATM-WAN (1997)
Javier Zamora, Dimitris Anastassiou, Shih-fu Chang
The Columbia VoD testbed is used to study the impact of a long distance and multi-switch connection and extreme conditions of impairments (delay variation, loss and error) on the objective and...
Javier Zamora, Dimitris Anastassiou, Shih-fu Chang, Koichi Shibata
:The Columbia VoD testbed is used to study the impact of extreme conditions of impairments (delay variation, loss and error) on the Quality of Service (QoS) for VoD. The goal of our experiments is to...
SaFe: A General Framework for Integrated Spatial and Feature Image Search (1997)
We present a system for querying for images by the spatial and feature attributes of regions 1 . The system enables the user to #nd the images that contain an arrangement of regions similar to that...
Shih-fu Chang, Alexandros Eleftheriadis, Ros Eleftheriadis, Robert McClintock
Content creation, editing, and searching are extremely time consuming tasks that often require substantial training and experience, especially when high-quality audio and video are involved....
Image Retrieval: Past, Present, And Future (1997)
Yong Rui, Thomas S. Huang, Shih-fu Chang
This paper provides a comprehensive survey of the technical achievements in the research area of Image Retrieval, especially Content-Based Image Retrieval, an area so active and prosperous in the...
Multi-stage Classification of Images from Features and Related Text (1997)
The synergy of textual and visual information in Web documents provides great opportunity for improving the image indexing and searching capabilities of Web image search engines. We explore a new...
Visual Information Retrieval from Large Distributed On-line Repositories (1997)
Shih-fu Chang, John R. Smith, Mandis Beigi, Is Beigi, Ana Benitez
ion --- VIR systems differ in the level of abstraction in which content is indexed. For example, images may be indexed at various levels, such as at the feature-level (e.g., color, texture, and...
Visual Information Retrieval from Large Distributed On-line Repositories (1997)
Shih-fu Chang, John R. Smith, Mandis Beigi, Is Beigi, Ana Benitez
ion --- Images may be indexed at various levels, including feature (e.g., color, texture, and shape), object (e.g., moving foreground object), syntax (e.g., video shot), and semantics (e.g., image...
Columbia's VoD and Multimedia Research Testbed with Heterogeneous Network Support (1997)
Shih-fu Chang, Alexandros Eleftheriadis, Ros Eleftheriadis, Dimitris Anastassiou, Stephen Jacobs, Hari Kalva, ...
This paper reports our progress in developing an advanced video-on-demand (VoD) testbed, which will be used to accommodate various multimedia research and applications such as Electronic News on...
A Practical Methodology for Guaranteeing Quality of Service for Video-on-Demand (1997)
Javier Zamora, Stephen Jacobs, Alexandros Eleftheriadis, Ros Eleftheriadis, Shih-fu Chang, Dimitris Anastassiou
A novel and simple approach for defining end-to-end Quality of Service (QoS) in Video-onDemand (VoD) services is presented. Using this approach we derive a schedulable region for a video server which...
An Image and Video Search Engine for the World-Wide Web (1997)
We describe a visual information system prototype for searching for images and videos on the WorldWide Web. New visual information in the form of images, graphics, animations and videos is being...
Joint Adaptive Space And Frequency Basis Selection (1997)
We develop a new method for building a representation of an image from a library of basis elements that is facilitated by a joint adaptive space and frequency (JASF) graph. The JASF graph combines...
Joint Adaptive Space And Frequency Basis Selection (1997)
We develop a new method for building a representation of an image from a library of basis elements that is facilitated by a joint adaptive space and frequency #JASF# graph. The JASF graph combines...
Clustering Methods for Video Browsing and Annotation (1997)
Di Zhong, Hongjiang Zhang, Shih-Fu Chang
ion Segmentation Key Frames Hierarchical Views of Videos Still Image Features Temporal/Motion Features Extraction Feature Clustering 3 1) RGB space is evenly divided (e.g. 16x16x16) and the color...
A Fully Automated Content Based Video Search Engine Supporting Spatio-Temporal Queries (1997)
Shih-Fu Chang, William Chen, Horace J. Meng, Hari Sundaram, Di Zhong
The rapidity with which digital information, particularly video, is being generated, has necessitated the development of tools for efficient search of these media. Content based visual queries have...
DAVIC and Interoperability Experiments (1997)
Hair Kalva, Shih-fu Chang, Alexandros Eleftheriadis, Ros Eleftheriadis
: To promote the development and deployment of broadband audio visual services, DAVIC has been working on specifying the standards and interfaces for end-to-end systems providing services to...
VideoQ: An Automated Content Based Video Search System Using Visual Cues (1997)
Shih-fu Chang, William Chen, Horace J. Meng, Hari Sundaram, Di Zhong
The rapidity with which digital information, particularly video, is being generated, has necessitated the development of tools for efficient search of these media. Content based visual queries have...
Alfred Aho, Shih-fu Chang, Kathleen Mckeown, Dragomir Radev, John Smith, Kazi Zaman
In this paper we describe an ongoing research project called the Columbia Digital News System. The goal of this project is to develop a suite of effective interoperable tools with which people can...
VideoQ: An Automated Content Based Video Search System Using Visual Cues (1997)
Shih-fu Chang, William Chen, Horace J. Meng, Hari Sundaram, Di Zhong
The rapidity with which digital information, particularly video is being generated, has necessitated the development of tools for efficient search of these digital media. Content based visual queries...
Image Retrieval: Past, Present, And Future (1997)
Yong Rui, Thomas S. Huang, Shih-Fu Chang
This paper provides a comprehensive survey of the technical achievements in the research area of Image Retrieval, especially Content-Based Image Retrieval, an area so active and prosperous in the...
VideoQ: An automated content based video search system using visual cues (1997)
Shih-fu Chang, William Chen, Horace J. Meng, Hari Sundaram, Di Zhong
The rapidity with which digital information, particularly video, is being generated, has necessitated the development of tools for efficient search of these media. Content based visual queries have...
VideoQ: An automated content based video search system using visual cues (1997)
Shih-fu Chang, William Chen, Horace J. Meng, Hari Sundaram, Di Zhong
The rapidity with which digitat information, particularly video, is being generated, has necessitated the development of tools for efficient search of these media. Content based visual queries have...
Multi-stage classification of images from features and related text (1997)
The synergy of textual and visual information in Web documents provides great opportunity for improving the image indexing and searching capabilities of Web image search engines. We explore a new...
ZAMORA ET. AL: A PRACTICAL METHODOLOGY FOR GUARANTEEING QOS FOR VOD 1 (1997)
Javier Zamora, Stephen Jacobs, Ros Eleftheriadis, Shih-fu Chang, Dimitris Anastassiou
Anovel and simple approach for de ning end-to-end Quality of Service (QoS) in Video-on-Demand (VoD) services is presented. Using this approach we derive aschedulable region for a video server which...
State of the art digital video compression produces bursty, variable bit rate video. The bursty nature of compressed video raises challenges in the design of video servers. In this paper, we first...
DAVIC and Interoperability Experiments (1997)
Hari Kalva, Shih-fu Chang, Ros Eleftheriadis
Abstract: To promote the development and deployment of broadband audio visual services, DAVIC has been working on specifying the standards and interfaces for end-to-end systems providing services to...
An image and video search engine for the world-wide web (1997)
We describe a visual information system prototype for searching for images and videos on the World-Wide Web. New visual information in the form of images, graphics, animations and videos is being...
VideoQ: An automated content based video search system using visual cues (1997)
Shih-fu Chang, William Chen, Horace J. Meng, Hari Sundaram, Di Zhong
The rapidity with which digital information, particularly video is being generated, has necessitated the development of tools for efficient search of these digital media. Content based visual queries...
Querying by color regions using the VisualSEEk content-based visual query system (1997)
VisualSEEk is a highly functional image database manipulation system that provides advanced user tools for searching, browsing and retrieving images. VisualSEEk is distinct from other content-based...
Chapter of the Assocation for Computational Linguistics, Madrid, Spain, (1997)
Dragomir Radev, Erin Doumpoulaki, Branimir Boguraev, Gael Dias, Hongyan Jing, Mark Kantrowitz, ...
This document contains a rather incomplete bibliography of research in text summarization. The list of references was compiled using materials provided
Searching for Images and Videos on the World-Wide Web (1996)
We describe a prototype visual information system for searching for images and videos on the World-Wide Web. New visual information in the form of images, graphics, animations and videos is being...
Efficient techniques for feature-based image/video access and manipulation (1996)
Shih-fu Chang, John R. Smith, Jianhao Meng
Efficient, effective methods for indexing, searching, and retrieving images and videos from large archives are critical techniques required in visual information systems (VIS) applications. Users...
Automated binary texture feature sets for image retrieval (1996)
Digital image and video libraries require new algorithms for the automated extraction and indexing of salient image features. Texture features provide one important cue for the visual perception and...
Searching for Images and Videos on the World-Wide Web (1996)
John R. Smith, John R. Smith, Shih-fu Chang, Shih-fu Chang
We describe a prototype visual information system for searching for images and videos on the World-Wide Web. New visual information in the form of images, graphics, animations and videos is being...
A content based approach to VBR Video Source Modeling (1996)
We are presenting a new framework of content based video (CBV) modeling, suitable for scalable variable bit rate (VBR) video traffic. Our approach differs form previous works in that it is not based...
A Content Based Video Traffic Model Using Camera Operations (1996)
We present our recent work on content based video (CBV) traffic modeling of variable bit rate (VBR) sources. CBV approach differs from previous works in that it is not based only on matching of...
Integrated Spatial and Feature Image Query (1996)
We present a new system for querying for images by regions and their spatial and feature attributes. The system enables the user to #nd the images that contain arrangements of regions similar to...
A Robust Content Based Digital Signature For Image Authentication (1996)
A methodology for designing content based digital signatures which can be used to authenticate images is presented. A continuous measure of authenticity is presented which forms the basis of this...
Columbia's VoD and Multimedia Research Testbed with Heterogeneous Network Support (1996)
Shih-fu Chang, Alexandros Eleftheriadis, Ros Eleftheriadis, Dimitris Anastassiou, Stephen Jacobs, Hari Kalva, ...
: This paper reports our progress in developing an advanced video-on-demand (VoD) testbed, which will be used to accommodate various multimedia research and applications such as Electronic News on...
A Practical Methodology for Guaranteeing Quality of Service for Video-on-Demand (1996)
Javier Zamora Stephen, Stephen Jacobs, Ros Eleftheriadis, Shih-fu Chang, Dimitris Anastassiou
A novel and simple approach for defining end-to-end Quality of Service (QoS) in Video-onDemand (VoD) services is presented. Using this approach we derive a schedulable region for a video server which...
VisualSEEk: a fully automated content-based image query system (1996)
1 We describe a highly functional prototype system for searching by visual features in an image database. The VisualSEEk system is novel in that the user forms the queries by diagramming spatial...
Automatic face region detection in MPEG video sequences (1996)
In this paper, we present a fast algorithm that automatically detects human face regions in MPEG video sequences. The algorithm takes the DCT coefficients of MPEG video frames as the input, and...
Development of Columbia's Video on Demand Testbed (1996)
Shih-fu Chang, Alexandros Eleftheriadis, Ros Eleftheriadis, Dimitris Anastassiou
This paper reports on our progress in developing an advanced video-on-demand (VOD) testbed, which will accommodate various multimedia research and applications such as Electronic News on Demand,...
Tools and Techniques for Color Image Retrieval (1996)
The growth of digital image and video archives is increasing the need for tools that effectively filter and efficiently search through large amounts of visual data. Towards this goal we propose a...
Querying by Color Regions using the VisualSEEk Content-Based Visual Query System (1996)
VisualSEEk is a highly functional image database manipulation system that provides advanced user tools for searching, browsing and retrieving images. VisualSEEk is distinct from other content-based...
Tools for compressed-domain video indexing and editing (1996)
Indexing and editing digital video directly in the compressed domain offer many advantages in terms of storage efficiency and processing speed. We have designed automatic tools in the compressed...
Shih-fu Chang, Ros Eleftheriadis, Dimitris Anastassiou, Stephen Jacobs, Hari Kalva, Javier Zamora
This paper reports our progress in developing an advanced video-on-demand (VoD) testbed, which will be used to accommodate various multimedia research and applications such as Electronic News on...
Adaptive image matching in the subband domain (1996)
In this paper we discuss image matching by correlation in the subband domain with prospective applications. Theoretical proof is given to show that the correlation of two signals equals the weighted...
Frequency and Spatially Adaptive Wavelet Packets (1995)
In this paper we consider a method for image compression based on frequency and spatially adaptive wavelet packets. We present a new fast directed acyclic graph (DAG) structured decomposition, with...
Automatic Feature Extraction and Indexing for Content-Based Visual Query (1995)
Shih-fu Chang, John Smith, Hualu Wang
: Content-based indexing and query has been considered as a powerful technique for accessing large visual information systems (databases and video servers). By extracting and indexing the visual...
Extracting Multi-Dimensional Signal Features for Content-Based Visual Query (1995)
Future large visual information systems (such as image databases and video servers) require effective and efficient methods for indexing, accessing, and manipulating images based on visual content....
Single Color Extraction and Image Query (1995)
In this paper we propose a method for automatic color extraction and indexing to support color queries of image and video databases. This approach identifies the regions within images that contain...
Manipulation and compositing of MC-DCT compressed video (1995)
Many advanced video applications require manipulations of compressed video signals. Popular video manipula-tion functions include overlap (opaque or semi-transparent), translation, scaling, linear...
Extracting multi-dimensional signal features for content-based visual query (1995)
Future large visual information systems (such as image databases and video servers) require effective and efficient methods for indexing, accessing, and manipulating images based on visual content....
Single color extraction and image query (1995)
In this paper we propose a method for automatic color extraction and indexing to support color queries of image and video databases. This approach identifies the regions within images that contain...
Compressed-domain content-based image and video retrieval (1995)
With more and more visual material produced and stored in visual information systems (VIS) (i.e., image databases or video servers), the need for efficient, effective methods for indexing, searching,...
Disk Partitioning Technique for Reducing Multimedia Access Delay (1994)
Paul Bocheck, Henry Meadows, Shih-fu Chang
With the introduction of future multimedia services such as HDTV, digital systems able to store and retrieve a huge amount of video and audio information will play an important role. One of the key...
Manipulation and Compositing of MC-DCT Compressed Video (1994)
Shih-Fu Chang, David G. Messerschmitt
Many advanced video applications require manipulations of compressed video signals. Popular video manipulation functions include overlap (opaque or semi-transparent), translation, scaling, linear...
Development of Advanced Image/Video Servers in . . . (1994)
This paper describes our current effort in building a video server with advanced capabilities of storage/indexing/ retrieval. The target application at this stage is Columbia University's Video...
Quad-tree segmentation for texture-based image query (1994)
In this paper we propose a technique for segmenting images by texture content with application to indexing images in a large image database. Using a quad-tree decomposition, texture features are...
Compositing and manipulation of video signals for multimedia network video services / (1993)
Thesis (Ph. D. in Electrical Engineering and Computer Sciences)--University of California, Berkeley, December 1993.
A New Approach to Devccoding and Compositing Motion-Compensated DCT-Based Images (1993)
Shih-Fu Chang, David Messerschmitt
Multi-point network video services require compositing several video sources into a single displayed video stream. Compositing video directly in the compressed domain can save computations by...
Comparison of Transform Coding Techniques for Two-Dimensional Arbitrarily-Shaped Images (1993)
Shih-fu Chang, David G. Messerschmitt
Envisioned advanced multimedia video services include arbitrarily-shaped (AS) image segments as well as regular rectangular images. Images segments of the TV weather reporter produced by the...
Visual Information Retrieval From Large Distributed Online Repositories (0000)
Provides information on WebSEEk, an Internet-based search system and MetaSEEk, an Internet meta-visual information retrieval system. Content-based visual query; Criteria for classifying visual...
Visual Information Retrieval From Large Distributed Online Repositories
Provides information on WebSEEk, an Internet-based search system and MetaSEEk, an Internet meta-visual information retrieval system. Content-based visual query; Criteria for classifying visual...