AUTOMATIC VIDEO ANNOTATION THROUGH SEARCH AND MINING (2009)
Emily Moxley, Tao Mei, Xian-sheng Hua, Wei-ying Ma, B. S. Manjunath
Conventional approaches to video annotation predominantly focus on supervised identification of a limited set of concepts, while unsupervised annotation with infinite vocabulary remains unexplored....
VideoReach: An Online Video Recommendation System (2009)
Tao Mei, Bo Yang, Xian-sheng Hua, Linjun Yang, Shi-qiang Yang, Shipeng Li
This paper presents a novel online video recommendation system called VideoReach, which alleviates users ’ efforts on finding the most relevant videos according to current viewings without a...
EFFICIENT VIDEO MOSAICING BASED ON MOTION ANALYSIS (2008)
Tao Mei, Xian-sheng Hua, He-qin Zhou, Shipeng Li, Hong-jiang Zhang
Presenting more comprehensive information than key frame and any subset of frames, mosaic has attracted a growing attention in recent years as a useful element for a variety of vision tasks. In this...
HIGH-LEVEL FEATURE EXTRACTION AND RUSHES EXPLOITATION (2008)
Xian-sheng Hua, Tao Mei, Wei Lai, Meng Wang, Jinhui Tang, Guo-jun Qi, ...
In this paper, we describe the MSRA experiments for TRECVID 2006, including details of the approaches and performance analyses for high-level feature extraction task and rushes exploitation task. For...
MSRA-USTC-SJTU AT TRECVID 2007: HIGH-LEVEL FEATURE EXTRACTION AND SEARCH (2008)
Tao Mei, Xian-sheng Hua, Wei Lai, Linjun Yang, Zheng-jun Zha, Yuan Liu, ...
This paper describes the MSRA-USTC-SJTU experiments for TRECVID 2007. We performed the experiments in high-level feature extraction and automatic search tasks. For high-level feature extraction, we...
ABSTRACT Multi-Layer Multi-Instance Kernel for Video Concept Detection ∗ (2008)
Zhiwei Gu, Xian-sheng Hua, Jinhui Tang, Xiuqing Wu
In video concept detection, most existing methods have not well studied the intrinsic hierarchical structure of video content. However, unlike flat attribute-value data used in many existing methods,...
Online Video Recommendation Based on Multimodal Fusion and Relevance Feedback ∗ (2008)
Bo Yang, Tao Mei, Xian-sheng Hua, Linjun Yang, Shi-qiang Yang, Mingjing Li
With Internet delivery of video content surging to an unprecedented level, video recommendation has become a very popular online service. The capability of recommending relevant videos to targeted...
To Construct Optimal Training Set For Video Annotation ABSTRACT (2008)
Jinhui Tang, Yan Song, Xian-sheng Hua, Tao Mei, Xiuqing Wu
This paper exploits the criteria to optimize the training set construction for video annotation. Most existing learningbased semantic annotation approaches require a large training set to achieve...
An Online Learning Framework for Sports Video View Classification (2008)
Jun Wu, Xian-sheng Hua, Jian-min Li, Bo Zhang, Hong-jiang 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...
Free-Shaped Video Collage ⋆ (2008)
Bo Yang, Tao Mei, Li-feng Sun, Shi-qiang Yang, Xian-sheng Hua
tsinghua.edu.cn Abstract. With the explosive growth of multimedia data, video presentation has become an important technology for fast browsing of video content. In this paper, we present a novel...
An Efficient Automatic Video Shot Size Annotation Scheme* (2008)
Meng Wang, Xian-sheng Hua, Yan Song, Wei Lai, Li-rong Dai, Ren-hua Wang
Abstract. This paper presents an efficient learning scheme for automatic annotation of video shot size. Instead of existing methods that applied in sports videos using domain knowledge, we are aiming...
Building a Comprehensive Ontology To Refine Video Concept Detection ∗ (2008)
Zheng-jun Zha, Zengfu Wang, Xian-sheng Hua
Recent research has discovered that leveraging ontology is an effective way to facilitate semantic video concept detection. As an explicit knowledge representation, a formal ontology definition...
Video Histogram: A Novel Video Signature for Efficient Web Video Duplicate Detection (2008)
Lu Liu, Wei Lai, Xian-sheng Hua, Shi-qiang Yang
Abstract. The explosive growth of information technology and digital content industry stimulates various video applications over the Internet. Since it is quite easy to copy, reformat, modify and...
AUTOMATIC VIDEO GENRE CATEGORIZATION USING HIERARCHICAL SVM (2008)
Xun Yuan, Wei Lai, Tao Mei, Xian-sheng Hua, Xiu-qing Wu, Shipeng Li
This paper presents an automatic video genre categorization scheme based on the hierarchical ontology on video genres. Ten computable spatio-temporal features are extracted to distinguish the...
MILC 2: A Multi-Layer Multi-Instance Learning Approach to Video Concept Detection ⋆ (2008)
Zhiwei Gu, Tao Mei, Jinhui Tang, Xiuqing Wu, Xian-sheng Hua
Abstract. Video is a kind of structured data with multi-layer (ML) information, e.g., a shot is consisted of three layers including shot, keyframe, and region. Moreover, multi-instance (MI) relation...
268 To Mine Capture Intention of Camcorder Users (2008)
Tao Mei, Xian-sheng Hua, He-qin Zhou, Shipeng Li
In this paper, we present a learning-based approach to mining the capture intention of camcorder users, aiming at providing a novel viewpoint in terms of home video content analysis. In contrast to...
Tracking Concept Drifting with Gaussian Mixture Model (2008)
Jun Wu, Xian-sheng Hua, Bo Zhang
This paper mainly addresses the issue of semantic concept drifting in temporal sequences, such as video streams, over an extended period of time. Gaussian Mixture Model (GMM) is applied to model the...
ABSTRACT Optimizing Multi-Graph Learning: Towards A Unified Video Annotation Scheme (2008)
Meng Wang, Xian-sheng Hua, Xun Yuan, Yan Song, Li-rong Dai
Learning based semantic video annotation is a promising approach for enabling content-based video search. However, severe difficulties, such as insufficiency of training data and curse of...
Cai-zhi Zhu, Xian-sheng Hua, Tao Mei, Xiu-qing Wu
In this paper, we propose a novel system, named Video Booklet, which enables efficient and natural personal video browsing and searching. In the system, firstly representative thumbnails of a...
ABSTRACT Structure-Sensitive Manifold Ranking for Video Concept Detection (2008)
Jinhui Tang, Xian-sheng Hua, Meng Wang, Tao Mei, Guo-jun Qi, Xiuqing Wu
Pairwise similarity of samples is an essential factor in graph propagation based semi-supervised learning methods. Usually it is estimated based on Euclidean distance. However, the structural...
Semi-Automatic Video Semantic Annotation Based on Active Learning (2008)
Yan Song, Xian-sheng Hua, Li-rong Dai, Ren-hua Wang
In this paper, we propose a novel semi-automatic annotation scheme for home videos based on active learning. It is well-known that there is a large gap between semantics and low-level features. To...
Xueliang Liu, Tao Mei, Xian-sheng Hua, Bo Yang, He-qin Zhou
In this work, we present Video Collage system, which automatically constructs a compact and visually appealing synthesized collage from a video sequence for efficient video browsing. Given a video,...
Application in Video Summarization 1 ABSTRACT Author(s): (2008)
Yu-fei Ma, Xian-sheng Hua, Lie Lu, Hong-jiang Zhang
Due to the information redundancy of video, automatically extracting essential video content is one of key techniques for accessing and managing video library. In this paper, we present a generic...
Optimizing Training Set Construction for Video Semantic Classification (2008)
Jinhui Tang, Xian-Sheng Hua, Yan Song, Tao Mei, Xiuqing Wu
We exploit the criteria to optimize training set construction for the large-scale video semantic classification. Due to the large gap between low-level features and higher-level semantics, as well as...
Optimizing Training Set Construction for Video Semantic Classification (2007)
Jinhui Tang, Xian-Sheng Hua, Yan Song, Tao Mei, Xiuqing Wu
We exploit the criteria to optimize training set construction for the large-scale video semantic classification. Due to the large gap between low-level features and higher-level semantics, as well as...
Video collage: A novel presentation of video sequence (2007)
Tang Wang, Xian-sheng Hua, Xue-liang Liu, He-qin Zhou
This paper presents an automatic procedure for constructing a compact synthesized collage from a video sequence. The synthesized image called Video Collage, is a kind of static video summary – to...
Modeling and mining of users’ capture intention for home videos (2007)
Tao Mei, Xian-sheng Hua, He-qin Zhou, Shipeng Li, Senior Member
Abstract — With rapid adoption of consumer digital video recorders and increase of home video data, content analysis has become an interesting and key research issue to provide personalized...
Concurrent multiple instance learning for image categorization (2007)
Guo-jun Qi, Xian-sheng Hua, Yong Rui, Tao Mei, Jinhui Tang, Hong-jiang Zhang
We propose a new multiple instance learning (MIL) algorithm to learn image categories. Unlike existing MIL algorithms, in which the individual instances in a bag are assumed to be independent with...
Yan Song, Xian-sheng Hua, Li-rong Dai, Meng Wang
In this paper, we will propose a novel semi-automatic annotation scheme for video semantic classification. It is well known that the large gap between high-level semantics and low-level features is...
Tracking Users’ Capture Intention: A Novel Complementary View for Home Video Content Analysis (2005)
Tao Mei, Xian-sheng Hua, He-qin Zhou
In this paper, we present a novel view to home video content analysis, which aims at tracking the capture intention of camcorder users. Based on the study of intention mechanism in psychology, a set...
Spatio-Temporal Quality Assessment for Home Videos (2005)
Tao Mei, Cai-zhi Zhu, He-qin Zhou, Xian-sheng Hua
Compared with the video programs taken by professionals, home videos are always with low-quality content resulted from lack of professional capture skills. In this paper, we present a novel...
Cai-Zhi Zhu, Tao Mei, Xian-Sheng Hua
In this demonstration, we show a novel system, Video Booklet, which enables nature personal video browsing and searching.
Tracking Users' Capture Intention: A Novel Complementary View for Home Video Content Analysis (2005)
Tao Mei, Xian-Sheng Hua, He-qin Zhou
In this paper, we present a novel view to home video content analysis, which aims at tracking the capture intention of camcorder users. Based on the study of intention mechanism in psychology, a set...
Efficient Video Mosaicing Based On Motion Analysis (2005)
Tao Mei, Xian-sheng Hua, He-qin Zhou, Shipeng Li, Hong-jiang Zhang
Presenting more comprehensive information than key frame and any subset of frames, mosaic has attracted a growing attention in recent years as a useful element for a variety of vision tasks. In this...
Spatio-Temporal Quality Assessment for Home Videos (2005)
Tao Mei, Cai-zhi Zhu, He-qin Zhou, Xian-sheng Hua
Compared with the video programs taken by professionals, home videos are always with low-quality content resulted from lack of professional capture skills. In this paper, we present a novel...
LazyCut - Content-Aware Template-Based Video Authoring (2005)
Xian-Sheng Hua, Zengzhi Wang, Shipeng Li
Though there are many commercial video authoring tools available today, video authoring remains as a tedious and extremely time consuming task that often requires trained professional skills. To...
Intention-Based Home Video Browsing (2005)
This demonstration presents an e#cient home video browsing system from a novel viewpoint -- capture intention. We extend our previous work to build up a comprehensive scheme to mine the capture...
Personal Media Sharing and Authoring on the Web (2005)
In this paper, we propose a novel system working on the Web for personal media sharing and authoring. Three primary technologies enable this end-to-end system, including scalable video coding,...
Intention-Based Home Video Browsing (2005)
This demonstration presents an e#cient home video browsing system from a novel viewpoint -- capture intention. We extend our previous work to build up a comprehensive scheme to mine the capture...
An automatic performance evaluation protocol for video text detection algorithms (2004)
Xian-sheng Hua, Liu Wenyin, Senior Member, Hong-jiang Zhang
Abstract—Text presented in videos provides important supplemental information for video indexing and retrieval. Many efforts have been made for text detection in videos. However, there is still a...
Online Play Segmentation for (2004)
Broadcasted American Football, Liexian Gu, Xiaoqing Ding, Xian-sheng Hua
This paper proposes an online segmentation scheme for broadcasted American football TV programs. The TV video streams are online partitioned into a series of play-break patterns with a relatively...
An Attention-Based Decision Fusion Scheme for Multimedia Information Retrieval (2004)
Xian-Sheng Hua, Hong-Jiang Zhang
In this paper, we proposed a novel decision fusion scheme based on the psychological observations on human beings' visual and aural attention characteristics, which combines a set of decisions...
P-Karaoke: Personalized Karaoke System (2004)
Xian-sheng Hua, Lie Lu, Hong-jiang Zhang
In this demonstration, a personalized Karaoke system, P-Karaoke, is proposed. In the P-Karaoke system, personal home videos and photographs, which are automatically selected from users’ multimedia...
Optimization-based automated home video editing system (2004)
Xian-sheng Hua, Lie Lu, Hong-jiang Zhang
Abstract—In this paper, we present an optimization-based system that automates home video editing (AVE). This system automatically selects suitable or desirable highlight segments from a set of raw...
An automatic performance evaluation protocol for video text detection algorithms (2004)
Xian-sheng Hua, Liu Wenyin, Hong-jiang Zhang
Abstract—Text presented in the videos provides important supplemental information for video indexing and retrieval. Many efforts have been made for text detection in videos. However, there is still...
Robust Video Signature Based on Ordinal Measure (2004)
Xian-sheng Hua, Xian Chen, Hong-jiang Zhang
In this paper we proposed a video signature based on ordinal measure of resampled video frames, which is robust to changing compression formats, compression ratios, frame sizes and frame rates. To...
Automatically Converting Photographic Series into Video (2004)
Xian-sheng Hua, Lie Lu, Hong-jiang Zhang
In this paper, we proposed a novel way to browse a series of photographs, which can be regarded as a system exploring the new medium between photograph and video. The scheme exploits the rich content...
An automatic performance evaluation protocol for video text detection algorithms (2004)
Xian-sheng Hua, Liu Wenyin, Hong-jiang Zhang
Abstract—Text presented in the videos provides important supplemental information for video indexing and retrieval. Many efforts have been made for text detection in videos. However, there is still...
An attention-based decision fusion scheme for multimedia information retrieval (2004)
Xian-sheng Hua, Hong-jiang Zhang
Abstract. In this paper, we proposed a novel decision fusion scheme based on the psychological observations on human beings ’ visual and aural attention characteristics, which combines a set of...
Automatic Music Video Generation Based on Temporal Pattern Analysis (2004)
Xian-sheng Hua, Lie Lu, Hong-jiang Zhang
Music video (MV) is a short film meant to present a visual representation of a popular music song. In this paper, we present a system that automatically generates MV-like videos from personal home...
Automated Home Video Editing (2003)
Xian-sheng Hua, Lie Lu, Hong-jiang Zhang
In this paper, we present a system that automates home video editing. This system automatically extracts a set of highlight segments from a set of raw home videos and aligns them with user supplied...
Xian-sheng Hua, Lie Lu, Hong-jiang Zhang
To exploit rich content embedded in a single photograph, a system named Photo2Video was developed to automatically convert a photographic series into a video by simulating camera motions, set to...
AVE - Automated Home Video Editing (2003)
Xian-sheng Hua, Lie Lu, Hong-jiang Zhang
In this paper, we present a system that automates home video editing. This system automatically extracts a set of highlight segments from a set of raw home videos and aligns them with user supplied...
Performance Evaluation Protocol for Video Scene Detection Algorithms (2002)
Xian-Sheng Hua, Dong Zhang, Mingjing Li, Hong-Jiang Zhang
In this paper, we address the problem of performance evaluation (PE) of video scene detection algorithms. An objective and comprehensive protocol for performance evaluation and comparison of...
MSR-Asia at TREC-11 Video Track (2002)
Xian-Sheng Hua, Pei Yin, Huajian Wang, Junfeng Chen, Mingjing Li, ...
The Media Computing Group of Microsoft Research Asia participated in all the three tasks of Video tracks of TREC-11, including automatic Shot Boundary Determination, Semantic Feature Extraction and...
Efficient Video Text Recognition Using Multiple Frame Integration (2002)
Xian-Sheng Hua, Pei Yin, Hong-Jiang Zhang
Text superimposed on the video frames provides supplemental but important information for video indexing and retrieval. Many efforts have been made for videotext detection and recognition (Video...
Automatic location of text in video frames (2001)
Xian-sheng Hua, Xiang-rong Chen, Liu Wenyin, Hong-jiang Zhang
A new automatic text location approach for videos is proposed. First of all, the corner points of the selected video frames are detected. After deleting some isolate corners, we merge the remaining...
Automatic location of text in video frames (2001)
Xian-sheng Hua, Xiang-rong Chen, Liu Wenyin, Hong-jiang Zhang
A new automatic text location approach for videos is proposed. First of all, the corner points of the selected video frames are detected. After deleting some isolate corners, we merge the remaining...
Automatic Performance Evaluation for Video Text Detection (2001)
Xian-sheng Hua, Liu Wenyin, Hong-jiang Zhang
In this paper, we propose an objective, comprehensive and difficulty-independent performance evaluation protocol for video text detection algorithms. The protocol includes a positive set and a...
Automatic Location of Text in Video Frames (2001)
Xian-Sheng Hua, Xiang-rong Chen, Liu Wenyin, Hong-Jiang Zhang
A new automatic text location approach for videos is proposed. First of all, the corner points of the selected video frames are detected. After deleting some isolate corners, we merge the remaining...
A video text detection and recognition system (2001)
Jie Xi, Xian-sheng Hua, Xiang-rong Chen, Liu Wenyin, Hong-jiang Zhang
In this paper, we propose a new system for text information extraction from news videos. First of all, a method that integrates text detecting and text tracking is developed to locate text areas in...
A video text detection and recognition system (2001)
Jie Xi, Xian-sheng Hua, Xiang-rong Chen, Liu Wenyin, Hong-jiang Zhang
In this paper, we propose a new system for text information extraction from news videos. First of all, a method that integrates text detecting and text tracking is developed to locate text areas in...
Position: Lead Researcher in Internet Media Group (1973)
Oversee a four-member team working on video search (including indexing, ranking, presentation, and management), multimedia advertising and multimedia content analysis. Research Area: Multimedia...
a team working on video search (including indexing, ranking, presentation, management), multimedia advertising and multimedia content analysis. Owned Research Project: Multimedia content analysis and...