Wei Jiang, Mingjing Li, Hongjiang Zhang, Jinwei Gu
To really bridge the gap between high-level semantics and low-levelfeatures in content-based image retrieval (CBIR), a problem that must be solved is: which features are suit-able for explaining the...
Zhong Su, Qiang Yang, Hongjiang Zhang, Xiaowei Xu, Yu-hen Hu, Shaoping Ma
Abstract. A great challenge for web site designers is how to ensure users ’ easy access to important web pages efficiently. In this paper we present a clustering-based approach to address this...
7. Active Concept Learning for Image Retrieval in Dynamic Databases (2008)
Maneesh Singh, Xiaofeng Ren, Yuri Boykov, Jing Zhong, Shuicheng Yan, Mingjing Li, ...
Nebojsa Jojic, Brendan Frey, Anitha Kannan. Pages 34–41. See the CD-ROM for a video of epitome learning and the epitome webpage for further examples, comparisons and software.
SSD Tracking Using Dynamic Template and Log-polar Transformation (2008)
Qiang Zhu, Kwang-ting Cheng, Hongjiang Zhang
With the assumption of small motion displacements in sequences, templates can be matched successfully by SSD (sum-squared-difference) optimization technique. In this paper, two crucial modifications...
Wei-ying Ma, Ilja Bedner, Grace Chang, Allan Kuchinsky, Hongjiang Zhang
framework for adaptive content delivery in heterogeneous
Proof CONTENT-BASED IMAGE RETRIEVAL (2008)
Dr. Fuhui Long, Dr. Hongjiang Zhang, Prof David, Dagan Feng
We introduce in this chapter some fundamental theories for content-based image retrieval. Section 1.1, looks at the development of content-based image retrieval techniques. Then, as the emphasis of...
Rapid Inference on a Novel AND/OR graph for Object Detection, Segmentation and Parsing (2008)
Yuanhao Chen, Chenxi Lin, Long (leo Zhu, Alan Yuille, Hongjiang Zhang
In this paper we formulate a novel AND/OR graph representation capable of describing the different configurations of deformable articulated objects such as horses. The representation makes use of the...
AN APPROACH TO SEMANTICS-BASED IMAGE RETRIEVAL AND BROWSING * (2008)
Jun Yang, Liu Wenyin, Hongjiang Zhang, Yueting Zhuang
The state-of-the-art image retrieval approach is to incorporate image semantics with low-level features to enhance retrieval performance. Although many systems
Search and Retrieval—information filtering, retrieval models (2008)
Kai Yu, Wei-ying Ma, Volker Tresp, Zhao Xu, Xiaofei He, Hongjiang Zhang, ...
This paper aims to address the problem of art image retrieval (AIR), which aims to help users find their favorite painting images. AIR is of great interests to us because of its application...
AUTOMATED RED-EYE DETECTION AND CORRECTION IN DIGITAL PHOTOGRAPHS (2008)
Lei Zhang, Yanfeng Sun, Mingjing Li, Hongjiang Zhang
Caused by light reflected off the subject's retina, red-eye is a troublesome problem in consumer photography. Although most of the cameras have the red-eye reduction mode, the result reality is...
Parallel Image Matrix Compression for Face Recognition (2008)
Dong Xu, Shuicheng Yan, Lei Zhang, Mingjing Li, Weiying Ma, Zhengkai Liu, ...
The canonical face recognition algorithm Eigenface and Fisherface are both based on one dimensional vector representation. However, with the high feature dimensions and the small training data, face...
Stan Z. Li, Heung-yeung Shum, Zhenqiu Zhang, Hongjiang Zhang
AdaBoost [3] minimizes an upper error bound which is an exponential function of the margin on the training set [14]. However, the ultimate goal in applications of pattern classification is always...
An Online Learning Framework for Sports Video View Classification (2008)
Jun Wu, Xiansheng Hua, Jianmin Li, Bo Zhang, Hongjiang Zhang
Abstract. Sports videos have special characteristics such as well-defined video structure, specialized sports syntax, and some canonical view types. In this paper, we proposed an online learning...
Digital Object Identifier (DOI) 10.1007/s00530-003-0085-4 (2008)
Multimedia Systems Multimedia, Liu Wenyin, Zheng Chen, Fan Lin, Hongjiang Zhang, Wei-ying Ma
A novel idea and framework of ubiquitous media agents is presented for managing personal multimedia objects. Media agents are intelligent systems that can autonomously do the following tasks. They...
Aditya Vailaya, Anil K. Jain, Hongjiang Zhang
We address the issue of clustering of video images. We assume that video clips have been segmented into shots which are further represented by a set of keyframes. Video clustering is thus reduced to...
Learning topographic representation for multi-view object appearances (2007)
Stan Z. Li, Xiaoguang Lv, Hongjiang Zhang
In 3D object detection and recognition, the object of interest in an image is subject to changes in view-point as well as illumination. It is benifit for the detection and recognition if a...
Zheng Chen, Liu Wenyin, Rui Yang, Mingjing Li, Hongjiang Zhang
A web media agent is presented, which can make a user’s web surfing experience more productive. Once the user visits a web page, semantic descriptions of the media objects on the page are...
Learning topographic representation for multi-view object appearances (2007)
Stan Z. Li, Xiaoguang Lv, Hongjiang Zhang
In 3D object detection and recognition, the object of interest in an image is subject to changes in view-point as well as illumination. It is benifit for the detection and recognition if a...
Text Area Detection from Video Frames 1 Text Area Detection from Video Frames (2007)
Xiangrong Chen, Hongjiang Zhang
Abstract. Text area detection from video frame is an essential step for Video OCR. The key problem is the complex background of the video frames. This paper proposes a novel approach to this problem....
PROOF COPY 002104JEI PROOF (2007)
Xingquan Zhu, Hongjiang Zhang, Wenyin Liu, Chun-hui Hu, Lide Wu
New query refinement and semantics integrated image retrieval system with semiautomatic annotation scheme
Search and Retrieval—information filtering, retrieval models (2007)
Kai Yu, Wei-ying Ma, Volker Tresp, Zhao Xu, Xiaofei He, Hongjiang Zhang, ...
This paper aims to address the problem of art image retrieval (AIR), which aims to help users find their favorite painting images. AIR is of great interests to us because of its application...
Efficient 3D reconstruction for face recognition (2005)
Dalong Jiang, Yuxiao Hu, Shuicheng Yan, Lei Zhang, Hongjiang Zhang, Wen Gao
� This work was performed while the authors were visiting Microsoft Research Asia.
Organizing WWW Images Based on The Analysis of Page Layout and Web Link Structure (2004)
Deng Cai, Xiaofei He, Wei-ying Ma, Ji-rong Wen, Hongjiang Zhang
Due to the rapid growth of the number of digital images on the Web, there is an increasing demand for effective and efficient method for organizing and retrieving the images available. This paper...
Efficient propagation for face annotation in family albums (2004)
Lei Zhang, Yuxiao Hu, Mingjing Li, Weiying Ma, Hongjiang Zhang
In this paper, we propose and investigate a new user scenario for face annotation, in which users are allowed to multi-select a group of photographs and assign names to these photographs. The system...
Organizing WWW Images Based on The Analysis of Page Layout and Web Link Structure (2004)
Deng Cai, Xiaofei He, Wei-ying Ma, Ji-rong Wen, Hongjiang Zhang
Due to the rapid growth of the number of digital images on the Web, there is an increasing demand for effective and efficient method for organizing and retrieving the images available. This paper...
Automatic 3d reconstruction for face recognition (2004)
Yuxiao Hu, Dalong Jiang, Shuicheng Yan, Lei Zhang, Hongjiang Zhang
An analysis-by-synthesis framework for face recognition with variant pose, illumination and expression (PIE) is proposed in this paper. First, an efficient 2D-to-3D integrated face reconstruction...
Xuezheng Liu, Lei Zhang, Mingjing Li, Hongjiang Zhang, Dingxing Wang
Image classification is of great importance for digital photograph management. In this paper we propose a general statistical learning method based on boosting algorithm to perform image...
Efficient propagation for face annotation in family albums (2004)
Lei Zhang, Yuxiao Hu, Mingjing Li, Weiying Ma, Hongjiang Zhang
In this paper, we propose and investigate a new user scenario for face annotation, in which users are allowed to multi-select a group of photographs and assign names to these photographs. The system...
Q.Cheng, Face Alignment Using View-Based Direct Appearance Models (2003)
Shuicheng Yan T, Xinwen Hou, Stan Z. Li, Hongjiang Zhang, Qiansheng Cheng T
Accurate face alignment is the prerequisite for many computer vision problems, such as face recognition, synthesis and 3-D face modeling. In this paper, a novel appearance model, called Direct...
ImageRank: spectral techniques for structural analysis of image database (2003)
Xiaofei He, Wei-ying Ma, Hongjiang Zhang
Drawing on the correspondence between spectral clustering, spectral dimensionality reduction, and the connections to the Markov Chain theory, we present a novel unified framework for structural...
Retrieval Using Relevance, Ye Lu, Hongjiang Zhang, Liu Wenyin, Senior Member, Senior Member, ...
Relevance feedback is a powerful technique for image retrieval and has been an active research direction for the past few years. Various ad hoc parameter estimation techniques have been proposed for...
Automated Annotation of Human Faces in Family Albums (2003)
Automatic annotation of photographs is one of the most desirable needs in family photograph management systems. In this paper, we present a learning framework to automate the face annotation in...
FloatBoost Learning for Classification (2003)
Stan Li Zhenqiu, Stan Z. Li, Heung-yeung Shum, Zhenqiu Zhang Ý, Hongjiang Zhang
AdaBoost [3] minimizes an upper error bound which is an exponential function of the margin on the training set [14]. However, the ultimate goal in applications of pattern classification is always...
Bayesian Face Annotation in Family Albums (2003)
Lei Zhang, Longbin Chen, Mingjing Li, Hongjiang Zhang
Automatic annotation of photographs is one of the most desirable needs in family photograph management systems. This paper presents a new framework for semiautomated face annotation in family photo...
Kai Yu, Anton Schwaighofer, Volker Tresp, Wei-Ying Ma, HongJiang Zhang
Collaborative filtering (CF) and contentbased filtering (CBF) have widely been used in information filtering applications, both approaches having their individual strengths and weaknesses. This paper...
Ranking Prior Likelihood Distributions for Bayesian Shape Localization Framework (2003)
Shuicheng Yan, Mingjing Li, Hongjiang Zhang, Qiansheng Cheng
In this paper, we formulate the shape localization problem in the Bayesian framework. In the learning stage, we propose the Constrained RankBoost approach to model the likelihood of local features...
Learning and inferring a semantic space from user’s relevance feedback for image retrieval (2002)
Xiaofei He, Wei-ying Ma, Oliver King, Mingjing Li, Hongjiang Zhang
As current methods for content-based retrieval are incapable of capturing the semantics of images, we experiment with using spectral methods to infer a semantic space from user’s relevance...
Statistical learning of multi-view face detection (2002)
Stan Z. Li, Long Zhu, Zhenqiu Zhang, Andrew Blake, Hongjiang Zhang, Harry Shum
1 Introduction Pattern recognition problems has two essential issues: (i) feature selection, and (ii) classifier design based on selected features. Boosting is a method which attempts to boost the...
International Journal of Image and Graphics (2002)
Longbin Chen, Baogang Hu, Lei Zhang, Mingjing Li, Hongjiang Zhang
this paper, we propose a framework to semi-automatically annotate faces in family photo albums. The core of the framework is the features used to define face similarity and this results in the...
MyPhotos - A System for Home Photo Management and Processing (2002)
Yanfeng Sun, Hongjiang Zhang, Lei Zhang, Mingjing Li
MyPhotos is a prototype system for home photo management and processing. Several home user orientated image processing and analysis tools are provided. And several auto grouping methods can help user...
Function-based Object Model Towards Website Adaptation (2001)
Chen, Jinlin, Zhou, Baoyao, Shi, Jin, Zhang, Hongjiang, Wu, Qiufeng
Content understanding is a crucial issue for website adaptation. In this paper we present a Function-based Object Model (FOM) that attempts to understand authors' intention by identifying Object...
iFind: a web image search engine (2001)
Zheng Chen, Liu Wenyin, Chunhui Hu, Mingjing Li, Hongjiang Zhang
Web mining for Web image retrieval (2001)
Zheng Chen, Liu Wenyin, Feng Zhang, Mingjing Li, Hongjiang Zhang
The popularity of digital images is rapidly increasing due to improving digital imaging technologies and convenient availability facilitated by the Internet. However, how to find user-intended images...
Correlation-based Document Clustering using Web Logs (2001)
Zhong Su, Qiang Yang, Hongjiang Zhang
A problem facing information retrieval on the web is how to effectively cluster large amounts of web documents. One approach is to cluster the documents based on information provided only by users...
Thesaurus-Aided Approach for Image Browsing and Retrieval (2001)
Jun Yang, Liu Wenyin, Hongjiang Zhang, Yueting Zhuang
The current trend of image retrieval is to incorporate image semantics with visual features to enhance retrieval performance. Although many approaches annotate images with keywords and process query...
User modeling for efficient use of multimedia files (2001)
Fan Lin, Liu Wenyin, Zheng Chen, Hongjiang Zhang, Tang Long
Abstract. It is very common that a user likes to collect many multimedia files of their interests from the web or other sources for his/her daily use, such as in emails, presentations, and technical...
Direct appearance models (2001)
Xinwen Hou, Stan Z. Li, Hongjiang Zhang, Qiansheng Cheng
Active appearance model (AAM), which makes ingenious use of both shape and texture constraints, is a powerful tool for face modeling, alignment and facial feature extraction under shape deformations...
View-subspace analysis of multi-view face patterns (2001)
Stan Z. Li, Xiaoguang Lv, Hongjiang Zhang
Multi-view face detection and recognition has been a challenging problem. The challenge is due to the fact that the distribution of multi-view faces in a feature space is more dispersed and more...
A robust audio classification and segmentation method (2001)
Lie Lu, Hao Jiang, Hongjiang Zhang
In this paper, we present a robust algorithm for audio classification that is capable of segmenting and classifying an audio stream into speech, music, environment sound and silence. Audio...
Learning Spatially Localized, Parts-Based Representation (2001)
Stan Z. Li, Xinwen Hou, Hongjiang Zhang, Qiansheng Cheng
In this paper, we propose a novel method, called local nonnegative matrix factorization (LNMF), for learning spatially localized, parts-based subspace representation of visual patterns. An objective...
View-based clustering of object appearances based on independent subspace analysis (2001)
Stan Z. Li, Xiaoguang Lv, Hongjiang Zhang
In 3D object detection and recognition, an object of interest is subject to changes in view as well as in illumination and shape. For image classification purpose, it is desirable to derive a...
Stan Z. Li, Rong Xiao, Zeyu Li, Hongjiang Zhang
When face patterns are subject to changes in view and illumination and facial shape, their distribution is highly nonlinear and complex in any space linear to the original image space. In this paper,...
Stan Z. Li, Jie Yan, Xinwen Hou, Zeyu Li, Hongjiang Zhang
In this paper, we propose an invariant signature representation for appearances of 3-D object under varying view and illumination, and a method for learning the signature from multi-view appearance...
Correlation-based Document Clustering using Web Logs (2001)
Zhong Su, Qiang Yang, Hongjiang Zhang
A problem facing information retrieval on the web is how to effectively cluster large amounts of web documents. One approach is to cluster the documents based on information provided only by users...
A performance evaluation protocol for content-based image retrieval (2001)
Liu Wenyin, Zhong Su, Stan Li, Yan-feng Sun, Hongjiang Zhang
In this paper, we address an important yet controversial issue in content-based image retrieval (CBIR): performance evaluation (PE). The goal is to develop an objective and comprehensive protocol for...
Ubiquitous media agents for managing personal multimedia files (2001)
Liu Wenyin, Zheng Chen, Fan Lin, Rui Yang, Mingjing Li, Hongjiang Zhang
A novel idea of ubiquitous media agents is presented. Media agents are intelligent systems that are able to automatically collect and build personalized semantic indices of multimedia data on behalf...
Function-based Object Model Towards Website Adaptation (2001)
Content understanding is a crucial issue for website adaptation. In this paper we present a Function-based Object Model (FOM) that attempts to understand authors ’ intention by identifying Object...
Semi-automatic image annotation (2001)
Liu Wenyin, Susan Dumais, Yanfeng Sun, Hongjiang Zhang, Mary Czerwinski, Brent Field
Abstract: A novel approach to semi-automatically and progressively annotating images with keywords is presented. The progressive annotation process is embedded in the course of integrated...
Correlation-based Document Clustering using Web Logs (2001)
Zhong Su, Qiang Yang, Hongjiang Zhang
A problem facing information retrieval on the web is how to effectively cluster large amounts of web documents. One approach is to cluster the documents based on information provided only by users...
Correlation-based Document Clustering using Web Logs (2001)
Zhong Su, Qiang Yang, Hongjiang Zhang
A problem facing information retrieval on the web is how to effectively cluster large amounts of web documents. One approach is to cluster the documents based on information provided only by users...
Real-time multi-view face detection, tracking, pose estimation, alignment, and recognition (2001)
Stan Z. Li, Xinli Zou, Yuxiao Hu, Zhengqiu Zhang, Shuicheng Yan, Xianhua Peng, ...
Semi-automatic image annotation (2001)
Liu Wenyin, Susan Dumais, Yanfeng Sun, Hongjiang Zhang, Mary Czerwinski, Brent Field
Abstract: A novel approach to semi-automatically and progressively annotating images with keywords is presented. The progressive annotation process is embedded in the course of integrated...
iFind-a system for semantics and feature based image retrieval over internet (2000)
Hongjiang Zhang, Liu Wenyin, Chunhui Hu
iFind © (v1.0) is a web based image retrieval system developed at Microsoft Research China. It provides the functionalities of
Ye Lu, Chunhui Hu, Xingquan Zhu, Hongjiang Zhang, Qiang Yang
The relevance feedback approach to image retrieval is a powerful technique and has been an active research direction for the past few years. Various ad hoe parameter estimation techniques have been...
Using Bayesian classifier in relevant feedback of image retrieval (2000)
Zhong Su, Hongjiang Zhang, Shaoping Ma
Relevance feedback is a powerful technique in contentbased image retrieval (CBIR) and has been an active research area for the past few years. In this paper, we propose a new relevance feedback...
Ye Lu, Chunhui Hu, Xingquan Zhu, Hongjiang Zhang, Qiang Yang
The relevance feedback approach to image retrieval is a powerful technique and has been an active research direction for the past few years. Various ad hoc parameter estimation techniques have been...
Ye Lu, Chunhui Hu, Xingquan Zhu, Hongjiang Zhang, Qiang Yang
The relevance feedback approach to image retrieval is a powerful technique and has been an active research direction for the past few years. Various ad hoc parameter estimation techniques have been...
Automatic image orientation detection (1999)
Aditya Vailaya, Hongjiang Zhang, Senior Member, Changjiang Yang, Feng-i Liu, Anil K. Jain
Abstract—We present an algorithm for automatic image orientation estimation using a Bayesian learning framework. We demonstrate that a small codebook (the optimal size of codebook is selected using...
A Bayesian Framework for Semantic Classification of Outdoor Vacation Images (1999)
Aditya Vailaya, Mário Figueiredo, Anil Jain, Hongjiang Zhang
Grouping images into (semantically) meaningful categories using low-level visual features is a challenging and important problem in content-based image retrieval. Based on these groupings, effective...
Automatic Image Orientation Detection (1999)
Aditya Vailaya, Hongjiang Zhang, Anil Jain
We present an algorithm for automatic image orientation estimation using a Bayesian learning framework. We demonstrate that a small codebook (the optimal size of codebook is selected using a modified...
A Bayesian framework for semantic classification of outdoor vacation images (1999)
Aditya Vailaya, Mário Figueiredo, Anil Jain, Hongjiang Zhang
Grouping images into (semantically) meaningful categories using low-level visual features is a challenging and important problem in content-based image retrieval. Based on these groupings, effective...
Clustering Methods for Video Browsing and Annotation (1997)
The large amount of video data makes it a tedious and hard job to browse and annotate them by just fast forward and rewind. Recent works in video parsing provide a foundation for building interactive...
Content-Based Video Retrieval and Compression: A Unified Solution (1997)
Hongjiang Zhang, Yucel Altunbasak
Video compression and retrieval have been treated as separate problems in the past. In this paper, we present an object-based video representation that facilitates both compression and retrieval....
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...
Content-based representation and retrieval of visual media: A state-of-the-art review (1996)
Hongjiang Zhang, Dragutin Petkovic
This paper reviews a number of recently available techniques in contentanalysis of visual media and their application to the indexing, retrieval,abstracting, relevance assessment, interactive...
Content-based Representation and Retrieval of Visual Media: A State-of-the-Art Review (1996)
Philippe Aigrain, Hongjiang Zhang, Dragutin Petkovic
This paper reviews a number of recently available techniques incontent37420 of visual media and their application to the indexing,retrieval,92-36020 relevance assessment, interactive perception,...