Search For:

Displaying 1-23 out of 23 total
Content is Dead . Long Live Content: The New Age of Multimedia-Hard Problems
Found in: IEEE MultiMedia
By Lexing Xie,David A. Shamma,Cees Snoek
Issue Date:January 2014
pp. 4-8
Using the ACM Multimedia 2012 panel on metadata as a jumping-off point, the authors investigate whether content can continue to play a dominant role in multimedia research in the age of social, local, and mobile media. In this article, they propose that th...
Scalable Mobile Video Retrieval with Sparse Projection Learning and Pseudo Label Mining
Found in: IEEE MultiMedia
By Guan-Long Wu,Yin-Hsi Kuo,Tzu-Hsuan Chiu,Winston H. Hsu,Lexing Xie
Issue Date:July 2013
pp. 47-57
Retrieving relevant videos from a large corpus on mobile devices is a vital challenge. This article addresses two key issues for mobile search on user-generated videos. The first is the lack of good relevance measurement for learning semantically rich repr...
Media Lifecycle and Content Analysis in Social Media Communities
Found in: 2012 IEEE International Conference on Multimedia and Expo (ICME)
By Lexing Xie,Hari Sundaram
Issue Date:July 2012
pp. 55-60
This paper examines the role of content analysis in media-rich online communities. We highlight changes in the multimedia generation and consumption process that has occurred the past decade, and discuss several new angles this has brought to multimedia an...
Visual saliency with side information
Found in: Acoustics, Speech, and Signal Processing, IEEE International Conference on
By Wei Jiang, Lexing Xie, Shih-Fu Chang
Issue Date:April 2009
pp. 1765-1768
We propose novel algorithms for organizing large image and video datasets using both the visual content and the associated side-information, such as time, location, authorship, and so on. Earlier research have used side-information as pre-filter before vis...
Fast kernel learning for spatial pyramid matching
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Junfeng He, Shih-Fu Chang, Lexing Xie
Issue Date:June 2008
pp. 1-7
Spatial pyramid matching (SPM) is a simple yet effective approach to compute similarity between images. Similarity kernels at different regions and scales are usually fused by some heuristic weights. In this paper, we develop a novel and fast approach to i...
Visual Event Detection using Multi-Dimensional Concept Dynamics
Found in: Multimedia and Expo, IEEE International Conference on
By Shahram Ebadollahi, Lexing Xie, Shih-fu Chang, John Smith
Issue Date:July 2006
pp. 881-884
A novel framework is introduced for visual event detection. Visual events are viewed as stochastic temporal processes in the semantic concept space. In this concept-centered approach to visual event modeling, the dynamic pattern of an event is modeled thro...
Slightly Supervised Learning of Part-Based Appearance Models
Found in: Computer Vision and Pattern Recognition Workshop
By Lexing Xie, Patrick PĂ©rez
Issue Date:July 2004
pp. 107
We extend the GMM-based approach of [Selection of scale-invariant parts for object class recognition], for learning part-based appearance models of object categories, to the unsupervised case where positive examples are corrupted with clutter. To this end,...
Unsupervised discovery of multilevel statistical video structures using hierarchical hidden Markov models
Found in: Multimedia and Expo, IEEE International Conference on
By Lexing Xie, Shih-Fu Chang, A. Divakaran, Huifang Sun
Issue Date:July 2003
pp. 29-32
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 follows a supervised paradigm, we propose a fully unsupervised statisti...
SCENT: Scalable compressed monitoring of evolving multirelational social networks
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Hari Sundaram, K. Selccuk Candan, K. Selccuk Candan, Lexing Xie, Lexing Xie, Yu-Ru Lin, Yu-Ru Lin
Issue Date:October 2011
pp. 1-22
We propose SCENT, an innovative, scalable spectral analysis framework for internet scale monitoring of multirelational social media data, encoded in the form of tensor streams. In particular, a significant challenge is to detect key changes in the social m...
Differential Topic Models
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Changyou Chen,Wray Buntine,Nan Ding,Lexing Xie,Lan Du
Issue Date:March 2014
pp. 1
In applications we may want to compare different document collections: they could have shared content but also different and unique aspects in particular collections. This task has been called comparative text mining or cross-collection modeling. We presen...
Optimal-Scaling-Factor Assignment for Patch-wise Image Retargeting
Found in: IEEE Computer Graphics and Applications
By Yun Liang, Yong-Jin Liu, Xiao-Nan Luo, Lexing Xie, Xiaolan Fu
Issue Date:September 2013
pp. 68-78
Image retargeting adjusts images to arbitrary sizes such that they can be viewed on different displays. Content-aware image retargeting has been receiving increased attention. In particular, researchers have improved a patch-wise scaling method for image r...
ImageHive: Interactive Content-Aware Image Summarization
Found in: IEEE Computer Graphics and Applications
By Li Tan, Yangqiu Song, Shixia Liu, Lexing Xie
Issue Date:January 2012
pp. 46-55
ImageHive communicates information about an image collection by generating a summary image that preserves the relationships between images and avoids occluding their salient parts. It uses a constrained graph-layout algorithm first, to preserve image simil...
Found in: Multimedia and Expo, IEEE International Conference on
By Peng Xu, Lexing Xie, Shih-Fu Chang, Ajay Divakaran, Anthony Vetro, Huifang Sun
Issue Date:August 2001
pp. 184
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 step is to classify each sample frame into 3 kinds of vie...
Picture tags and world knowledge: learning tag relations from visual semantic sources
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Xuming He, Lexing Xie
Issue Date:October 2013
pp. 967-976
This paper studies the use of everyday words to describe images. The common saying has it that 'a picture is worth a thousand words', here we ask which thousand? The proliferation of tagged social multimedia data presents a challenge to understanding colle...
Improving LDA topic models for microblogs via tweet pooling and automatic labeling
Found in: Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval (SIGIR '13)
By Lexing Xie, Rishabh Mehrotra, Scott Sanner, Wray Buntine
Issue Date:July 2013
pp. 889-892
Twitter, or the world of 140 characters poses serious challenges to the efficacy of topic models on short, messy text. While topic models such as Latent Dirichlet Allocation (LDA) have a long history of successful application to news articles and academic ...
New objective functions for social collaborative filtering
Found in: Proceedings of the 21st international conference on World Wide Web (WWW '12)
By Ehsan Abbasnejad, Nicolas Della Penna, Peter Christen, Scott Sanner, Edwin V. Bonilla, Joseph Noel, Khoi-Nguyen Tran, Lexing Xie
Issue Date:April 2012
pp. 859-868
This paper examines the problem of social collaborative filtering (CF) to recommend items of interest to users in a social network setting. Unlike standard CF algorithms using relatively simple user and item features, recommendation in social networks pose...
Visual memes in social media: tracking real-world news in YouTube videos
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Apostol Natsev, John R. Kender, John R. Smith, Lexing Xie, Matthew Hill
Issue Date:November 2011
pp. 53-62
We propose visual memes, or frequently reposted short video segments, for tracking large-scale video remix in social media. Visual memes are extracted by novel and highly scalable detection algorithms that we develop, with over 96% precision and 80% recall...
Video genetics: a case study from YouTube
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Apostol (Paul) Natsev, John R. Kender, John R. Smith, Lexing Xie, Matthew L. Hill
Issue Date:October 2010
pp. 1253-1258
We explore in a single but large case study how videos within YouTube, competing for view counts, are like organisms within an ecology, competing for survival. We develop this analogy, whose core idea shows that short video clips, best detected across vide...
The accuracy and value of machine-generated image tags: design and user evaluation of an end-to-end image tagging system
Found in: Proceedings of the ACM International Conference on Image and Video Retrieval (CIVR '10)
By Alex Phillips, Apostol Natsev, John R. Smith, Lexing Xie, Matthew Hill
Issue Date:July 2010
pp. 58-65
Automated image tagging is a problem of great interest, due to the proliferation of photo sharing services. Researchers have achieved considerable advances in understanding motivations and usage of tags, recognizing relevant tags from image content, and le...
IBM multimedia analysis and retrieval system
Found in: Proceedings of the 2008 international conference on Content-based image and video retrieval (CIVR '08)
By Apostol Natsev, Jelena Tesie, John R. Smith, Lexing Xie, Rong Yan
Issue Date:July 2008
pp. 569-570
IBM Multimedia Analysis and Retrieval System is a Web-based technology that makes digital photos and video searchable through automated classification and indexing.
Modeling personal and social network context for event annotation in images
Found in: Proceedings of the 2007 conference on Digital libraries (JCDL '07)
By Bageshree Shevade, Hari Sundaram, Lexing Xie
Issue Date:June 2007
pp. 127-134
This paper describes a framework to annotate images using personal and social network contexts. The problem is important as the correct context reduces the number of image annotation choices.. Social network context is useful as real-world activities of me...
Physics-motivated features for distinguishing photographic images and computer graphics
Found in: Proceedings of the 13th annual ACM international conference on Multimedia (MULTIMEDIA '05)
By Jessie Hsu, Lexing Xie, Mao-Pei Tsui, Shih-Fu Chang, Tian-Tsong Ng
Issue Date:November 2005
pp. 239-248
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 become an important problem for image forgery detection. In...
A utility framework for the automatic generation of audio-visual skims
Found in: Proceedings of the tenth ACM international conference on Multimedia (MULTIMEDIA '02)
By Hari Sundaram, Lexing Xie, Shih-Fu Chang
Issue Date:December 2002
pp. 189-198
In this paper, we present a novel algorithm for generating audio-visual skims from computable scenes. Skims are useful for browsing digital libraries, and for on-demand summaries in set-top boxes. A computable scene is a chunk of data that exhibits consist...