Search For:

Displaying 1-50 out of 70 total
Identify Sports Video Shots with
Found in: Multimedia and Expo, IEEE International Conference on
By Jinjun Wang, Engsiong Chng, Changsheng Xu, Hanqing Lu, Xiaofeng Tong
Issue Date:July 2006
pp. 877-880
Semantic video content extraction and selection are critical steps in sports video analysis and editing. The identification of video segments can be from various semantic perspec-tives, e.g. certain event, player or emotional state. In this paper, we exami...
 
A Matlab-Based Simulation of System Stability In Frequency-Field Analysis
Found in: Innovative Computing ,Information and Control, International Conference on
By Zhigang Xu, Changsheng Xu
Issue Date:September 2006
pp. 529-532
The frequency-field analysis to a control system says the system?s steady-state response when it has a sine signal input. Use this analytic method, control system?s specification can be found directly and the method is very simple. Under this we can solve ...
 
Creating audio keywords for event detection in soccer video
Found in: Multimedia and Expo, IEEE International Conference on
By Min Xu, N.C. Maddage, Changsheng Xu, M. Kankanhalli, Qi Tian
Issue Date:July 2003
pp. 281-284
This paper presents a novel framework called audio keywords to assist event detection in soccer video. Audio keyword is a middle-level representation that can bridge the gap between low-level features and high-level semantics. Audio keywords are created fr...
 
Low-Rank Sparse Coding for Image Classification
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Tianzhu Zhang,Bernard Ghanem,Si Liu,Changsheng Xu,Narendra Ahuja
Issue Date:December 2013
pp. 281-288
In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information among features in an image for the purpose of image-level classification. LRSC represents densely sampled SIFT descriptors, in a spatial neighborhood...
 
Cross-Space Affinity Learning with Its Application to Movie Recommendation
Found in: IEEE Transactions on Knowledge and Data Engineering
By Jinhui Tang,Guo-Jun Qi,Liyan Zhang,Changsheng Xu
Issue Date:July 2013
pp. 1510-1519
In this paper, we propose a novel cross-space affinity learning algorithm over different spaces with heterogeneous structures. Unlike most of affinity learning algorithms on the homogeneous space, we construct a cross-space tensor model to learn the affini...
 
Web-Scale Near-Duplicate Search: Techniques and Applications
Found in: IEEE MultiMedia
By Chong-Wah Ngo,Changsheng Xu,Wessel Kraaij,Abdulmotaleb El Saddik
Issue Date:July 2013
pp. 10-12
As the bandwidth accessible to average users has increased, audio-visual material has become the fastest growing data type on the Internet. The impressive growth of the social Web, where users can exchange user-generated content, contributes to the overwhe...
 
Saliency Aware Locality-preserving Coding for Image Classification
Found in: 2012 IEEE International Conference on Multimedia and Expo (ICME)
By Quan Fang,Jitao Sang,Changsheng Xu
Issue Date:July 2012
pp. 260-265
The Bag-of-Features (BOF) model is widely used for image classification. Most BOF models incorporate a step of maximum pooling to generate the raw image representation, where salient atoms with maximum response are reserved for final representation. Howeve...
 
Street-to-shop: Cross-scenario clothing retrieval via parts alignment and auxiliary set
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Si Liu, Zheng Song, Guangcan Liu, Changsheng Xu, Hanqing Lu, Shuicheng Yan
Issue Date:June 2012
pp. 3330-3337
In this paper, we address a practical problem of cross-scenario clothing retrieval - given a daily human photo captured in general environment, e.g., on street, finding similar clothing in online shops, where the photos are captured more professionally and...
 
Robust movie character identification and the sensitivity analysis
Found in: Multimedia and Expo, IEEE International Conference on
By Jitao Sang,Chao Liang,Changsheng Xu,Jian Cheng
Issue Date:July 2011
pp. 1-6
Automatic face identification of characters in movies has drawn significant research interests and led to various applications. It is a challenging problem due to the huge variation in the appearance of each character. Although existing methods demonstrate...
 
Image classification by non-negative sparse coding, low-rank and sparse decomposition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Chunjie Zhang, Jing Liu, Qi Tian, Changsheng Xu, Hanqing Lu, Songde Ma
Issue Date:June 2011
pp. 1673-1680
We propose an image classification framework by leveraging the non-negative sparse coding, low-rank and sparse matrix decomposition techniques (LR-Sc^+ SPM). First, we propose a new non-negative sparse coding along with max pooling and spatial pyramid matc...
 
TVParser: An automatic TV video parsing method
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Chao Liang, Changsheng Xu, Jian Cheng, Hanqing Lu
Issue Date:June 2011
pp. 3377-3384
In this paper, we propose an automatic approach to simultaneously name faces and discover scenes in TV shows. We follow the multi-modal idea of utilizing script to assist video content understanding, but without using timestamp (provided by script-subtitle...
 
Compact Codebook Generation Towards Scale-Invariance
Found in: Image and Video Technology, Pacific-Rim Symposium on
By Si Liu, Shuicheng Yan, Changsheng Xu, Hanqing Lu
Issue Date:November 2010
pp. 376-380
In this paper, we present a novel visual codebook learning approach towards compactness and scale-invariance for dense patch image encoding. Firstly, each image is described as a bag of orderless gridding local patches, each of which is expressed in three ...
 
Extracting Key Sub-trajectory Features for Supervised Tactic Detection in Sports Video
Found in: Pattern Recognition, International Conference on
By Yi Zhang, Changsheng Xu, Hanqing Lu
Issue Date:August 2010
pp. 125-128
Tactic analysis is receiving more attention in sports video analysis for its assistance to coaches and players. This paper proposes an efficient key sub-trajectory feature representation of ball trajectory for tactic analysis. Ball trajectories are modeled...
 
Video based 3D reconstruction using spatio-temporal attention analysis
Found in: Multimedia and Expo, IEEE International Conference on
By Xian Xiao, Changsheng Xu, Yong Rui
Issue Date:July 2010
pp. 1091-1096
3D reconstruction has been widely used in many important applications. While extensive research has been done in 3D reconstruction, several key issues are still open and the precision of the recovered regions is still far from satisfaction. In this paper, ...
 
Event based news video people classification and ranking using multimodality features
Found in: Multimedia and Expo, IEEE International Conference on
By Chunxi Liu, Qingming Huang, Shuqiang Jiang, Changsheng Xu
Issue Date:July 2010
pp. 149-154
Existing research on news video analysis mainly concentrates on structure analysis, semantic concept detection, annotation and search. However, little work has been contributed to news video people community analysis, which is helpful for users to understa...
 
Reliable Video Clock Time Recognition
Found in: Pattern Recognition, International Conference on
By Yiqun Li, Changsheng Xu, Kong Wah Wan, Xin Yan, Xinguo Yu
Issue Date:August 2006
pp. 128-131
We propose a novel approach to read the video clock in real time by recognizing the clock digits using a few techniques relative to the transition patterns of the clock. With these techniques, the clock digits are located without recognizing all the text c...
 
Automatic Sports Video Genre Classification using Pseudo-2D-HMM
Found in: Pattern Recognition, International Conference on
By Jinjun Wang, Changsheng Xu, Engsiong Chng
Issue Date:August 2006
pp. 778-781
Building a generic content-based sports video analysis system remains a challenging problem because of the diversity in sports rules and game features which makes it difficult to discover generic low-level features or high-level modeling algorithms. One po...
 
Action Recognition in Broadcast Tennis Video
Found in: Pattern Recognition, International Conference on
By Guangyu Zhu, Changsheng Xu, Qingming Huang, Wen Gao
Issue Date:August 2006
pp. 251-254
Motion analysis in broadcast sports video is a challenging problem especially for player action recognition due to the low resolution of players in the frames. This paper presents a novel approach to recognize the basic player actions in broadcast tennis v...
 
Local Motion Analysis and Its Application in Video based Swimming Style Recognition
Found in: Pattern Recognition, International Conference on
By Xiaofeng Tong, Lingyu Duan, Changsheng Xu, Qi Tian, Hanqing Lu
Issue Date:August 2006
pp. 1258-1261
In this paper we study the problem of local motion analysis and apply it to swimming style recognition in broadcast sports video. Local motion analysis is challenging for two reasons: 1) local motion is usually buried in clutters involving complex motion f...
 
Predominant Vocal Pitch Detection in Polyphonic Music
Found in: Multimedia and Expo, IEEE International Conference on
By Xi Shao, Changsheng Xu, Mohan Kankanhalli
Issue Date:July 2006
pp. 897-900
We present a novel method for predominant vocal pitch detection in two-channel polyphonic music. The proposed method contains two stages. In the first stage, we apply the Frequency Domain Independent Component Analysis (FD-ICA) for the two-channel polyphon...
 
Automatic Content Placement in Sports Highlights
Found in: Multimedia and Expo, IEEE International Conference on
By Kongwah Wan, Changsheng Xu
Issue Date:July 2006
pp. 1893-1896
To be viable advertising platforms, methods for in-program content placement in sports video must balance against clutter. We propose viewer relevance (VR) measures of video frames in the temporal and spatial domain. Video sub-segments with low temporal VR...
 
Fully and Semi-Automatic Music Sports Video Composition
Found in: Multimedia and Expo, IEEE International Conference on
By Jinjun Wang, Engsiong Chng, Changsheng Xu
Issue Date:July 2006
pp. 1897-1900
Video composition is important for music video production. In this paper we propose an automatic method to assist the music sports video composition operation. Our approach is based on Dynamic Programming algorithm which finds a set of video shots that bes...
 
Automatic Multi-Player Detection and Tracking in Broadcast Sports Video using Support Vector Machine and Particle Filter
Found in: Multimedia and Expo, IEEE International Conference on
By Guangyu Zhu, Changsheng Xu, Qingming Huang, Wen Gao
Issue Date:July 2006
pp. 1629-1632
In this paper, a novel multiple objects detection and tracking approach based on support vector machine and particle filter is proposed to track players in broadcast sports video. Compared with previous work, the contributions of this paper are focused on ...
 
Replay Scene Classification in Soccer Video Using Web Broadcast Text
Found in: Multimedia and Expo, IEEE International Conference on
By Jinhui Dai, Lingyu Duan, Xiaofeng Tong, Changsheng Xu, Qi Tian, Hanqing Lu, J.S. Jin
Issue Date:July 2005
pp. 1098-1101
The automatic extraction of sports video highlights is a typical kind of personalized media production process. Many ways have been studied from the viewpoints of low-level audio/visual processing (e. g. detection of excited commentator speech), event dete...
 
A Mid-level Visual Concept Generation Framework for Sports Analysis
Found in: Multimedia and Expo, IEEE International Conference on
By Xiaofeng Tong, Lingyu Duan, Hanqing Lu, Changsheng Xu, Qi Tian, J.S. Jin
Issue Date:July 2005
pp. 646-649
The development of mid-level concepts helps to bridge the gap between low-level feature and high-level semantics in video analysis. Most existing work combines the customized mid-level concepts and statistical models to detect particular events. Based on b...
 
Periodicity Detection of Local Motion
Found in: Multimedia and Expo, IEEE International Conference on
By Xiaofeng Tong, Lingyu Duan, Changsheng Xu, Qi Tian, Hanqing Lu, Jinjun Wang, J.S. Jin
Issue Date:July 2005
pp. 650-653
Periodicity is useful for compact representation of periodic motion and a reasonable selection of a proper temporal scale for periodic motion analysis. In this paper, we concern the periodicity detection of local motion within an interesting region and pre...
 
Singer Identification Based on Vocal and Instrumental Models
Found in: Pattern Recognition, International Conference on
By Namunu Chinthaka Maddage, Changsheng Xu, Ye Wang
Issue Date:August 2004
pp. 375-378
In this paper, we propose a novel method to identify the singer of a query song from the audio database. The database contains over 100 popular songs of solo singers. The rhythm structure of the song is analyzed using our proposed rhythm tracking method an...
 
Efficient Multimodal Features for Automatic Soccer Highlight Generation
Found in: Pattern Recognition, International Conference on
By Kongwah Wan, Changsheng Xu
Issue Date:August 2004
pp. 973-976
We describe efficient audio/visual features and their multimodal combination to detect highlights in soccer video. A novel audio feature first detects dominant speech portions in the commentary coincident with segments of high excitement in the game. Verif...
 
The security flaws in some authentication watermarking schemes
Found in: Multimedia and Expo, IEEE International Conference on
By Yongdong Wu, Feng Bao, ChangSheng Xu
Issue Date:July 2003
pp. 493-496
Watermarking technology was originally proposed for copyright protection. Recently it has been applied to media authentication so that a proof of authenticity is inserted into the media instead of being appended to the media as a separated attachment. Howe...
 
A ROBUST AND FAST WATERMARKING SCHEME FOR COMPRESSED AUDIO
Found in: Multimedia and Expo, IEEE International Conference on
By Changsheng Xu, Yongwei Zhu, David Dagan Feng
Issue Date:August 2001
pp. 48
This paper proposes a method to embed and extract the watermark into and from digital compressed audio. The watermark is embedded in partially uncompressed domain and the embedding scheme is high related to audio content. The watermark embedding can be don...
 
Multimodal Spatio-Temporal Theme Modeling for Landmark Analysis
Found in: IEEE MultiMedia
By Weiqing Min,Bing-Kun Bao,Changsheng Xu
Issue Date:July 2014
pp. 20-29
The authors propose a theme model that differentiates three kinds of landmark themes: temporal themes, which happen at a specific moment; local themes, which characterize local characteristics; and general themes, which most landmarks share. Based on the m...
 
MELODY CURVE PROCESSING FOR MUSIC RETRIEVAL
Found in: Multimedia and Expo, IEEE International Conference on
By Yongwei Zhu, Changsheng Xu, Mohan Kankanhalli
Issue Date:August 2001
pp. 73
There have been several query-by-humming techniques developed for music retrieval. The techniques either are errorprone due to the inaccuracy of the hummed query or force the users to hum according to a metronome. This paper presents a new slope-based quer...
 
Landmark recognition and retrieval: from 2D to 3D
Found in: Proceedings of the 2011 joint ACM workshop on Human gesture and behavior understanding (J-HGBU '11)
By ChangSheng Xu, JinQiao Wang, Min Xu, Xian Xiao
Issue Date:December 2011
pp. 77-78
Existing landmark retrieval methods cannot provide a comprehensive solution, by which user can view different angles of landmark. In this paper, we propose a novel approach to reconstruct and retrieve 3D landmark models by direct 2D to 3D matching. In an o...
     
Audio keywords generation for sports video analysis
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Changsheng Xu, Jesse S. Jin, Lingyu Duan, Min Xu, Suhuai Luo
Issue Date:May 2008
pp. 1-23
Sports video has attracted a global viewership. Research effort in this area has been focused on semantic event detection in sports video to facilitate accessing and browsing. Most of the event detection methods in sports video are based on visual features...
     
Enhancing news organization for convenient retrieval and browsing
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Changsheng Xu, Hanqing Lu, Jing Liu, Meng Wang, Zechao Li
Issue Date:December 2013
pp. 1-20
To facilitate users to access news quickly and comprehensively, we design a news search and browsing system named GeoVisNews, in which the news elements of “Where”, “Who”, “What” and “When” are enhanced via n...
     
Latent feature learning in social media network
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Changsheng Xu, Zhaoquan Yuan, Jitao Sang, Yan Liu
Issue Date:October 2013
pp. 253-262
The current trend in social media analysis and application is to use the pre-defined features and devoted to the later model development modules to meet the end tasks. In this work, we claim that representation is critical to the end tasks and contributes ...
     
GIANT: geo-informative attributes for location recognition and exploration
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Changsheng Xu, Jitao Sang, Quan Fang
Issue Date:October 2013
pp. 13-22
This paper considers the problem of automatically discovering geo-informative attributes for location recognition and exploration. The attribute is expected to be both discriminative and representative, which corresponds to a distinctive visual pattern and...
     
Social influence analysis and application on multimedia sharing websites
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Changsheng Xu, Jitao Sang
Issue Date:October 2013
pp. 1-24
Social media is becoming popular these days, where users necessarily interact with each other to form social networks. Influence network, as one special case of social network, has been recognized as significantly impacting social activities and user decis...
     
Locality discriminative coding for image classification
Found in: Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service (ICIMCS '13)
By Changsheng Xu, Tianzhu Zhang, Xiaoshan Yang
Issue Date:August 2013
pp. 52-55
The Bag-of-Words (BOW) based methods are widely used in image classification. However, huge number of visual information is omitted inevitably in the quantization step of the BOW. Recently, NBNN and its improved methods like Local NBNN were proposed to sol...
     
Probabilistic sequential POIs recommendation via check-in data
Found in: Proceedings of the 20th International Conference on Advances in Geographic Information Systems (SIGSPATIAL '12)
By Changsheng Xu, Jian-Tao Sun, Jitao Sang, Shipeng Li, Tao Mei
Issue Date:November 2012
pp. 402-405
While on the go, people are using their phones as a personal concierge discovering what is around and deciding what to do. Mobile phone has become a recommendation terminal customized for individuals. While existing research predominantly focuses on one-st...
     
Chat with illustration: a chat system with visual aids
Found in: Proceedings of the 4th International Conference on Internet Multimedia Computing and Service (ICIMCS '12)
By Changsheng Xu, Hanqing Lu, Jing Liu, Yu Jiang, Zechao Li
Issue Date:September 2012
pp. 96-99
Traditional instant messaging service mainly transfers textual message, while the visual message is ignored to a great extent. In this paper, we propose a novel instant messaging scheme with visual aids named Chat with Illustration (CWI), which presents us...
     
Extended MHT algorithm for multiple object tracking
Found in: Proceedings of the 4th International Conference on Internet Multimedia Computing and Service (ICIMCS '12)
By Changsheng Xu, Long Ying, Wen Guo
Issue Date:September 2012
pp. 75-79
In this paper, we propose an improved efficient MHT algorithm integrated with HSV-LBP appearance and repulsion-inertia model for multi-object tracking. Simultaneously tracking multiple objects is critical to video content analysis and virtual reality. The ...
     
Kinect-based visual communication system
Found in: Proceedings of the 4th International Conference on Internet Multimedia Computing and Service (ICIMCS '12)
By Bing-Kun Bao, Changsheng Xu, Chao Sun, Tao Mei
Issue Date:September 2012
pp. 55-59
Nowadays, most existing online instant messaging tools, such as Live Messenger, Google Talk, Yahoo Messenger, ICQ, enable people to communicate with each other no matter where and when they are. However, it is still difficult for people who speak different...
     
News contextualization with geographic and visual information
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Changsheng Xu, Hanqing Lu, Jing Liu, Meng Wang, Zechao Li
Issue Date:November 2011
pp. 133-142
In this paper, we investigate the contextualization of news documents with geographic and visual information. We propose a matrix factorization approach to analyze the location relevance for each news document. We also propose a method to enrich the docume...
     
Exploiting user information for image tag refinement
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Changsheng Xu, Jing Liu, Jitao Sang
Issue Date:November 2011
pp. 1129-1132
Photo sharing websites allow users to describe images with freely chosen tags. The user-generated tags not only facilitate the users in sharing and organizing images, but also provide large scale meaningful data for image retrieval and management. Extensiv...
     
Learning "verb-object" concepts for semantic image annotation
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Changsheng Xu, Xinming Zhang, Zheng-Jun Zha
Issue Date:November 2011
pp. 1077-1080
In real-world image understanding and retrieval applications, there exists a large number of images containing "verb-object" semantic. The most existing image annotation approaches which mainly focus on annotating images with "object" concepts may not well...
     
Snap & play: auto-generate personalized find-the-difference mobile game
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Changsheng Xu, Hanqing Lu, Jian Dong, Qiang Chen, Shuicheng Yan, Si Liu
Issue Date:November 2011
pp. 993-996
According to the year 2010 report of the Entertainment Software Association [5], 42% of USA heads of households reported playing games on mobile devices, rising quickly from the 20% in 2002 and bringing huge market for mobile games. In this paper, by takin...
     
Browse by chunks: Topic mining and organizing on web-scale social media
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Changsheng Xu, Jitao Sang, Jitao Sang
Issue Date:October 2011
pp. 1-18
The overwhelming amount of Web videos returned from search engines makes effective browsing and search a challenging task. Rather than conventional ranked list, it becomes necessary to organize the retrieved videos in alternative ways. In this article, we ...
     
Fast feature selection and training for AdaBoost-based concept detection with large scale datasets
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Changsheng Xu, Hanqing Lu, Jinqiao Wang, Shi Chen, Yang Liu
Issue Date:October 2010
pp. 1179-1182
AdaBoost has been proved a successful statistical learning method for concept detection with high performance of discrimination and generalization. However, it is computationally expensive to train a concept detector using boosting, especially on large sca...
     
Character-based movie summarization
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Changsheng Xu, Jitao Sang
Issue Date:October 2010
pp. 855-858
A decent movie summary is helpful for movie producer to promote the movie as well as audience to capture the theme of the movie before watching the whole movie. Most exiting automatic movie summarization approaches heavily rely on video content only, which...
     
 1  2 Next >>