Open Access. Powered by Scholars. Published by Universities.®

Databases and Information Systems Commons™

Open Access. Powered by Scholars. Published by Universities.®

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year

Articles 2551 - 2580 of 3436

Full-Text Articles in Databases and Information Systems

Enhancing Bag-Of-Words Models By Efficient Semantics-Preserving Metric Learning, Lei Wu, Steven C. H. Hoi Jan 2011

Enhancing Bag-Of-Words Models By Efficient Semantics-Preserving Metric Learning, Lei Wu, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

The authors present an online semantics preserving, metric learning technique for improving the bag-of-words model and addressing the semantic-gap issue. This article investigates the challenge of reducing the semantic gap for building BoW models for image representation; propose a novel OSPML algorithm for enhancing BoW by minimizing the semantic loss, which is efficient and scalable for enhancing BoW models for large-scale applications; apply the proposed technique for large-scale image annotation and object recognition; and compare it to the state of the art.

Go to article

An Effective Approach To Pose Invariant 3d Face Recognition, Dayong Wang, Steven C. H. Hoi, Ying He Jan 2011

An Effective Approach To Pose Invariant 3d Face Recognition, Dayong Wang, Steven C. H. Hoi, Ying He

Research Collection School Of Computing and Information Systems

One critical challenge encountered by existing face recognition techniques lies in the difficulties of handling varying poses. In this paper, we propose a novel pose invariant 3D face recognition scheme to improve regular face recognition from two aspects. Firstly, we propose an effective geometry based alignment approach, which transforms a 3D face mesh model to a well-aligned 2D image. Secondly, we propose to represent the facial images by a Locality Preserving Sparse Coding (LPSC) algorithm, which is more effective than the regular sparse coding algorithm for face representation. We conducted a set of extensive experiments on both 2D and 3D …

Go to article

Identity-Based Strong Designated Verifier Signature Revisited, Qiong Huang, Guomin Yang, Duncan S. Wong, Willy Susilo Jan 2011

Identity-Based Strong Designated Verifier Signature Revisited, Qiong Huang, Guomin Yang, Duncan S. Wong, Willy Susilo

Research Collection School Of Computing and Information Systems

Designated verifier signature (DVS) allows the signer to persuade a verifier the validity of a statement but prevent the verifier from transferring the conviction. Strong designated verifier signature (SDVS) is a variant of DVS, which only allows the verifier to privately check the validity of the signer’s signature. In this work we observe that the unforgeability model considered in the existing identity-based SDVS schemes is not strong enough to capture practical attacks, and propose to consider another model which is shown to be strictly stronger than the old one. We then propose a new efficient construction of identity-based SDVS scheme, …

Go to article

Near-Duplicate Keyframe Retrieval By Semi-Supervised Learning And Nonrigid Image Matching, Jianke Zhu, Steven C. H. Hoi, Michael R. Lyu, Shuicheng Yan Jan 2011

Near-Duplicate Keyframe Retrieval By Semi-Supervised Learning And Nonrigid Image Matching, Jianke Zhu, Steven C. H. Hoi, Michael R. Lyu, Shuicheng Yan

Research Collection School Of Computing and Information Systems

Near-duplicate keyframe (NDK) retrieval techniques are critical to many real-world multimedia applications. Over the last few years, we have witnessed a surge of attention on studying near-duplicate image/keyframe retrieval in multimedia community. To facilitate an effective approach to NDK retrieval on large-scale data, we suggest an effective Multi-Level Ranking (MLR) scheme that effectively retrieves NDKs in a coarse-to-fine manner. One key stage of the MLR ranking scheme is how to learn an effective ranking function with extremely small training examples in a near-duplicate detection task. To attack this challenge, we employ a semi-supervised learning method, semi-supervised support vector machines, which …

Go to article

Randomly Projected Kd-Trees With Distance Metric Learning For Image Retrieval, Pengcheng Wu, Steven Hoi, Duc Dung Nguyen, Ying He Jan 2011

Randomly Projected Kd-Trees With Distance Metric Learning For Image Retrieval, Pengcheng Wu, Steven Hoi, Duc Dung Nguyen, Ying He

Research Collection School Of Computing and Information Systems

Efficient nearest neighbor (NN) search techniques for highdimensional data are crucial to content-based image retrieval (CBIR). Traditional data structures (e.g., kd-tree) usually are only efficient for low dimensional data, but often perform no better than a simple exhaustive linear search when the number of dimensions is large enough. Recently, approximate NN search techniques have been proposed for high-dimensional search, such as Locality-Sensitive Hashing (LSH), which adopts some random projection approach. Motivated by similar idea, in this paper, we propose a new high dimensional NN search method, called Randomly Projected kd-Trees (RP-kd-Trees), which is to project data points into a lower-dimensional …

Go to article

Efficient Strong Designated Verifier Signature Schemes Without Random Oracle Or With Non-Delegatability, Qiong Huang, Guomin Yang, Duncan S. Wong, Willy Susilo Jan 2011

Efficient Strong Designated Verifier Signature Schemes Without Random Oracle Or With Non-Delegatability, Qiong Huang, Guomin Yang, Duncan S. Wong, Willy Susilo

Research Collection School Of Computing and Information Systems

Designated verifier signature (DVS) allows a signer to convince a designated verifier that a signature is generated by the signer without letting the verifier transfer the conviction to others, while the public can still tell that the signature must be generated by one of them. Strong DVS (SDVS) strengthens the latter part by restricting the public from telling whether the signature is generated by one of them or by someone else. In this paper, we propose two new SDVS schemes. Compared with existing SDVS schemes, the first new scheme has almost the same signature size and meanwhile, is proven secure …

Go to article

Development Of An Instrument To Measure The Adoption Of Mobile Services, Shang Gao, John Krogstie, Keng Siau Jan 2011

Development Of An Instrument To Measure The Adoption Of Mobile Services, Shang Gao, John Krogstie, Keng Siau

Research Collection School Of Computing and Information Systems

Currently, there is no standard instrument for measuring user adoption of mobile services. Based on the mobile service acceptance model, this paper reports on the development of a survey instrument designed to measure user perception on mobile services acceptance. A survey instrument was developed by using some existing scales from prior instruments and by creating additional items which might appear to fit the construct definitions. In addition, a pilot study was conducted by distributing the survey to 25 users of a mobile service called Mobile Student Information Systems. As a result, a survey instrument containing 22 items were retained. Furthermore, …

Go to article

A Usability Study Of A Mobile Content Sharing System, Alton Yeow-Kuan Chua, Dion Hoe-Lian Goh, Khasfariyati Razikin, Ee Peng Lim Jan 2011

A Usability Study Of A Mobile Content Sharing System, Alton Yeow-Kuan Chua, Dion Hoe-Lian Goh, Khasfariyati Razikin, Ee Peng Lim

Research Collection School Of Computing and Information Systems

We investigate the usability of MobiTOP (Mobile Tagging of Objects and People), a mobile location-based content sharing system. MobiTOP allows users to annotate real world locations with both multimedia and textual content and concurrently, share the annotations among its users. In addition, MobiTOP provides additional functionality such as clustering of annotations and advanced search and filtering options. A usability evaluation of the system was conducted in the context of a travel companion for tourists. The results suggested the potential of the system in terms of functionality for mobile content sharing. Participants agreed that the features in MobiTOP were generally usable …

Go to article

Exploiting Intensity Inhomogeneity To Extract Textured Objects From Natural Scenes, Jundi Ding, Jialie Shen, Hwee Hwa Pang, Songcan Chen, Jingyu Yang Dec 2010

Exploiting Intensity Inhomogeneity To Extract Textured Objects From Natural Scenes, Jundi Ding, Jialie Shen, Hwee Hwa Pang, Songcan Chen, Jingyu Yang

Research Collection School Of Computing and Information Systems

Extracting textured objects from natural scenes is a challenging task in computer vision. The main difficulties arise from the intrinsic randomness of natural textures and the high-semblance between the objects and the background. In this paper, we approach the extraction problem with a seeded region-growing framework that purely exploits the statistical properties of intensity inhomogeneity. The pixels in the interior of potential textured regions are first found as texture seeds in an unsupervised manner. The labels of the texture seeds are then propagated through their respective inhomogeneous neighborhoods, to eventually cover the different texture regions in the image. Extensive experiments …

Go to article

Evaluation Of Protein Backbone Alphabets : Using Predicted Local Structure For Fold Recognition, Kyong Jin Shim Dec 2010

Evaluation Of Protein Backbone Alphabets : Using Predicted Local Structure For Fold Recognition, Kyong Jin Shim

Research Collection School Of Computing and Information Systems

Optimally combining available information is one of the key challenges in knowledge-driven prediction techniques. In this study, we evaluate six Phi and Psi-based backbone alphabets. We show that the addition of predicted backbone conformations to SVM classifiers can improve fold recognition. Our experimental results show that the inclusion of predicted backbone conformations in our feature representation leads to higher overall accuracy compared to when using amino acid residues alone.

Go to article

Traffic Velocity Prediction Using Gps Data: Ieee Icdm Contest Task 3 Report, Wei Shen, Yiannis Kamarianakis, Laura Wynter, Jingrui He, Qing He, Rick Lawrence, Grzegorz Swirszcz Dec 2010

Traffic Velocity Prediction Using Gps Data: Ieee Icdm Contest Task 3 Report, Wei Shen, Yiannis Kamarianakis, Laura Wynter, Jingrui He, Qing He, Rick Lawrence, Grzegorz Swirszcz

Research Collection School Of Computing and Information Systems

This report summarizes the methodologies and techniques we developed and applied for tackling task 3 of the IEEE ICDM Contest on predicting traffic velocity based on GPS data. The major components of our solution include 1) A pre-processing procedure to map GPS data to the network, 2) A K-nearest neighbor approach for identifying the most similar training hours for every test hour, and 3) A heuristic evaluation framework for optimizing parameters and avoiding over-fitting. Our solution finished Second in the final evaluation.

Go to article

3-D Virtual World Education: An Empirical Comparison With Face-To-Face Classroom, Xiaofeng Chen, Keng Siau, Fiona Fui-Hoon Nah Dec 2010

3-D Virtual World Education: An Empirical Comparison With Face-To-Face Classroom, Xiaofeng Chen, Keng Siau, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

3-D virtual worlds are increasing in popularity as a means of pedagogical delivery in higher education. In this research, we assess the relative effectiveness of a 3-D virtual world learning environment, Second Life, and traditional face-to-face learning environment. We also assess the efficacy of instructional strategies in these two learning environments and their effects on interactivity, perceived learning, and satisfaction. Our findings suggest that there is an interaction effect of learning environment and instructional strategy. Pair-wise comparisons indicate that when interactive instructional strategy is used, there is no significant difference for perceived learning and satisfaction between 3-D virtual world and …

Go to article

Sequence Alignment Based Analysis Of Player Behavior In Massively Multiplayer Online Role-Playing Games (Mmorpgs), Kyong Jin Shim, Jaideep Srivastava Dec 2010

Sequence Alignment Based Analysis Of Player Behavior In Massively Multiplayer Online Role-Playing Games (Mmorpgs), Kyong Jin Shim, Jaideep Srivastava

Research Collection School Of Computing and Information Systems

This study proposes a sequence alignment-based behavior analysis framework (SABAF) developed for predicting inactive game players that either leave the game permanently or stop playing the game for a long period of time. Sequence similarity scores and derived statistics form profile databases of inactive players and active players from the past. SABAF uses global and local sequence alignment algorithms and a unique scoring scheme to measure similarity between activity sequences. SABAF is tested on the game player activity data of Ever Quest II, a popular massively multiplayer online role-playing game developed by Sony Online Entertainment. SABAF consists of the following …

Go to article

Ibm Power Systems And Service Oriented Architecture At Bank Of America’S Foreign Items Systems Office, Keng Siau, D. Dewester Dec 2010

Ibm Power Systems And Service Oriented Architecture At Bank Of America’S Foreign Items Systems Office, Keng Siau, D. Dewester

Research Collection School Of Computing and Information Systems

This is a teaching case on a real life scenario in an organization involving IT solution evaluation and selection. This case involves the Bank of America’s Foreign Items Systems office in Toronto. The officers from the Bank of America’s Foreign Items Systems office in Toronto were discussing how to respond to a Request for Proposal (RFP) from a major U.S. bank to provide foreign currency services. The case discusses three options: Standard J2EE Web Application Global Foreign Currency, Modified J2EE Web Application with Single Sign On, and Service-Oriented Architecture (SOA) via Web Services. The case can be used to complement …

Go to article

Understanding Gender Differences In Media Perceptions: A Comparison Of 2d Versus 3d Media, Fiona Fui-Hoon Nah, David Dewester, Brenda Eschenbrenner Dec 2010

Understanding Gender Differences In Media Perceptions: A Comparison Of 2d Versus 3d Media, Fiona Fui-Hoon Nah, David Dewester, Brenda Eschenbrenner

Research Collection School Of Computing and Information Systems

We examine gender differences in 2D versus 3D media perceptions. Using the Hunter-Gatherer Theory of Spatial Gender Differences and Jung’s Theory of Psychological Types, we hypothesize differences in men’s and women’s perceptions of skill, challenge, telepresence, and satisfaction with online experiences in 2D versus 3D media interaction. The findings suggest that even though women perceive lower skill levels and greater challenges in using 2D and 3D media than men, women’s sense of telepresence is higher than men in both 2D and 3D media. Women are also more satisfied with their interaction in 2D and 3D media than men.

Go to article

A Multi-User Steganographic File System On Untrusted Shared Storage, Jin Han, Meng Pan, Debin Gao, Hwee Hwa Pang Dec 2010

A Multi-User Steganographic File System On Untrusted Shared Storage, Jin Han, Meng Pan, Debin Gao, Hwee Hwa Pang

Research Collection School Of Computing and Information Systems

Existing steganographic file systems enable a user to hide the existence of his secret data by claiming that they are (static) dummy data created during disk initialization. Such a claim is plausible if the adversary only sees the disk content at the point of attack. In a multi-user computing environment that employs untrusted shared storage, however, the adversary could have taken multiple snapshots of the disk content over time. Since the dummy data are static, the differences across snapshots thus disclose the locations of user data, and could even reveal the user passwords. In this paper, we introduce a Dummy-Relocatable …

Go to article

Vireo At Trecvid 2010: Semantic Indexing, Known-Item Search, And Content-Based Copy Detection, Chong-Wah Ngo, Shi-Ai Zhu, Hung-Khoon Tan, Wan-Lei Zhao Nov 2010

Vireo At Trecvid 2010: Semantic Indexing, Known-Item Search, And Content-Based Copy Detection, Chong-Wah Ngo, Shi-Ai Zhu, Hung-Khoon Tan, Wan-Lei Zhao

Research Collection School Of Computing and Information Systems

This paper presents our approaches and the comparative analysis of our results for the three TRECVID 2010 tasks that we participated in: semantic indexing, known-item search and content-based copy detection.

Go to article

Smu-Sis At Tac 2010 - Kbp Track Entity Linking, Swapna Gottipati, Jing Jiang Nov 2010

Smu-Sis At Tac 2010 - Kbp Track Entity Linking, Swapna Gottipati, Jing Jiang

Research Collection School Of Computing and Information Systems

Entity linking task is a process of linking the named entity within the unstructured text to the entity in the Knowledge Base. Entity liking to the relevant knowledge is useful in various information extraction and natural language processing applications that improve the user experiences such as search, summarization and so on. We propose the two way entity linking approach to reformulate query, disambiguate the entity and link to the relevant KB repository. This paper describes the details of our participation in TAC 2010 - Knowledge Base Population track. We provided an innovative approach to disambiguate the entity by query reformulation …

Go to article

Wsm'10: Second Acm Workshop On Social Media, Susanne Boll, Steven C. H. Hoi, Roelof Van Zwol, Jiebo Luo Oct 2010

Wsm'10: Second Acm Workshop On Social Media, Susanne Boll, Steven C. H. Hoi, Roelof Van Zwol, Jiebo Luo

Research Collection School Of Computing and Information Systems

The ACM SIGMM International Workshop on Social Media (WSM'10) is the second workshop held in conjunction with the ACM International Multimedia Conference (MM'10) at Firenze, Italy, 2010. This workshop provides a forum for researchers and practitioners from all over the world to share information on their latest investigations on social media analysis, exploration, search, mining, and emerging new social media applications.

Go to article

Youth Olympic Village Co-Space, Zin-Yan Chua, Yilin Kang, Xing Jiang, Kah-Hoe Pang, Andrew C. Gregory, Chi-Yun Tan, Wai-Lun Wong, Ah-Hwee Tan, Yew-Soon Ong, Chunyan Miao Oct 2010

Youth Olympic Village Co-Space, Zin-Yan Chua, Yilin Kang, Xing Jiang, Kah-Hoe Pang, Andrew C. Gregory, Chi-Yun Tan, Wai-Lun Wong, Ah-Hwee Tan, Yew-Soon Ong, Chunyan Miao

Research Collection School Of Computing and Information Systems

We have designed and implemented a 3D virtual world based on the Co-Space concept encompasses the Youth Olympic Village (YOV) and several sports competition venues. It is a massively multiplayer online (MMO) virtual world built according to the actual, physical locations of the YOV and sports competition venues. On top of that, the Co-Space is being populated with human-like avatars, which are created according to the actual human size and appearance; they perform their activities and interact with the users in realworld context. In addition, autonomous intelligent agents are integrated into the Co-Space to provide context-aware and personalized services to …

Go to article

Modeling 3d Facial Expressions Using Geometry Videos, Jiazhi Xia, Ying He, Dao T. P. Quynh, Xiaoming Chen, Steven C. H. Hoi Oct 2010

Modeling 3d Facial Expressions Using Geometry Videos, Jiazhi Xia, Ying He, Dao T. P. Quynh, Xiaoming Chen, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

The significant advances in developing high-speed shape acquisition devices make it possible to capture the moving and deforming objects at video speeds. However, due to its complicated nature, it is technically challenging to effectively model and store the captured motion data. In this paper, we present a set of algorithms to construct geometry videos for 3D facial expressions, including hole filling, geodesic-based face segmentation, and expression-invariant parametrization. Our algorithms are efficient and robust, and can guarantee the exact correspondence of the salient features (eyes, mouth and nose). Geometry video naturally bridges the 3D motion data and 2D video, and provides …

Go to article

Effects Of National Culture On Types Of Knowledge Sharing In Virtual Communities, Keng Siau, J. Erickson, Fiona Fui-Hoon Nah Oct 2010

Effects Of National Culture On Types Of Knowledge Sharing In Virtual Communities, Keng Siau, J. Erickson, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Organizations are using virtual communities to facilitate knowledge management and to enhance communication among employees, customers, and other interested individuals. Individual users can use virtual communities to engage in knowledge sharing. Professional communicators need to understand and adapt to a globalized and “flat” world, where people across different cultures interact freely and easily with one another in virtual communities. An intriguing question regarding virtual communities relates to whether national culture affects communication and types of knowledge sharing. This study examines the influence of US and Chinese national cultures on types of knowledge-sharing activities in virtual communities. The findings indicate that …

Go to article

Finding Unusual Review Patterns Using Unexpected Rules, Nitin Jindal, Bing Liu, Ee Peng Lim Oct 2010

Finding Unusual Review Patterns Using Unexpected Rules, Nitin Jindal, Bing Liu, Ee Peng Lim

Research Collection School Of Computing and Information Systems

In recent years, opinion mining attracted a great deal of research attention. However, limited work has been done on detecting opinion spam (or fake reviews). The problem is analogous to spam in Web search [1, 9 11]. However, review spam is harder to detect because it is very hard, if not impossible, to recognize fake reviews by manually reading them [2]. This paper deals with a restricted problem, i.e., identifying unusual review patterns which can represent suspicious behaviors of reviewers. We formulate the problem as finding unexpected rules. The technique is domain independent. Using the technique, we analyzed an Amazon.com …

Go to article

Business Network-Based Value Creation In Electronic Commerce, Robert John Kauffman, Ting Li, Eric Van Heck Oct 2010

Business Network-Based Value Creation In Electronic Commerce, Robert John Kauffman, Ting Li, Eric Van Heck

Research Collection School Of Computing and Information Systems

Information technologies (IT) have affected economic activities within and beyond the boundaries of the firm, changing the face of e-commerce. This article explores the circumstances under which value is created in business networks made possible by IT. Business networks combine the capabilities of multiple firms to produce and deliver products and services that none of them could more economically produce on its own and for which there is demand in the market. We call this business network-based value creation. We apply economic theory to explain the conditions under which business networks will exist and are able to sustain their value-producing …

Go to article

Mining Interesting Link Formation Rules In Social Networks, Cane Wing-Ki Leung, Ee Peng Lim, David Lo, Jianshu Weng Oct 2010

Mining Interesting Link Formation Rules In Social Networks, Cane Wing-Ki Leung, Ee Peng Lim, David Lo, Jianshu Weng

Research Collection School Of Computing and Information Systems

Link structures are important patterns one looks out for when modeling and analyzing social networks. In this paper, we propose the task of mining interesting Link Formation rules (LF-rules) containing link structures known as Link Formation patterns (LF-patterns). LF-patterns capture various dyadic and/or triadic structures among groups of nodes, while LF-rules capture the formation of a new link from a focal node to another node as a postcondition of existing connections between the two nodes. We devise a novel LF-rule mining algorithm, known as LFR-Miner, based on frequent subgraph mining for our task. In addition to using a support-confidence framework …

Go to article

Jointly Modeling Aspects And Opinions With A Maxent-Lda Hybrid, Xin Zhao, Jing Jiang, Hongfei Yan, Xiaoming Li Oct 2010

Jointly Modeling Aspects And Opinions With A Maxent-Lda Hybrid, Xin Zhao, Jing Jiang, Hongfei Yan, Xiaoming Li

Research Collection School Of Computing and Information Systems

Discovering and summarizing opinions from online reviews is an important and challenging task. A commonly-adopted framework generates structured review summaries with aspects and opinions. Recently topic models have been used to identify meaningful review aspects, but existing topic models do not identify aspect-specific opinion words. In this paper, we propose a MaxEnt-LDA hybrid model to jointly discover both aspects and aspect-specific opinion words. We show that with a relatively small amount of training data, our model can effectively identify aspect and opinion words simultaneously. We also demonstrate the domain adaptability of our model.

Go to article

Online Multiple Kernel Learning: Algorithms And Mistake Bounds, Rong Jin, Steven C. H. Hoi, Tianbao Yang Oct 2010

Online Multiple Kernel Learning: Algorithms And Mistake Bounds, Rong Jin, Steven C. H. Hoi, Tianbao Yang

Research Collection School Of Computing and Information Systems

Online learning and kernel learning are two active research topics in machine learning. Although each of them has been studied extensively, there is a limited effort in addressing the intersecting research. In this paper, we introduce a new research problem, termed Online Multiple Kernel Learning (OMKL), that aims to learn a kernel based prediction function from a pool of predefined kernels in an online learning fashion. OMKL is generally more challenging than typical online learning because both the kernel classifiers and their linear combination weights must be learned simultaneously. In this work, we consider two setups for OMKL, i.e. combining …

Go to article

Detecting Product Review Spammers Using Rating Behaviors, Ee Peng Lim, Viet-An Nguyen, Nitin Jindal, Bing Liu, Hady Wirawan Lauw Oct 2010

Detecting Product Review Spammers Using Rating Behaviors, Ee Peng Lim, Viet-An Nguyen, Nitin Jindal, Bing Liu, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

This paper aims to detect users generating spam reviews or review spammers. We identify several characteristic be- haviors of review spammers and model these behaviors so as to detect the spammers. In particular, we seek to model the following behaviors. First, spammers may target specific products or product groups in order to maximize their im- pact. Second, they tend to deviate from the other reviewers in their ratings of products. We propose scoring methods to measure the degree of spam for each reviewer and apply them on an Amazon review dataset. We then select a sub- set of highly suspicious …

Go to article

Cast2face: Character Identification In Movie With Actor-Character Correspondence, Mengdi Xu, Xiaotong Yuan, Jialie Shen, Shuicheng Yan Oct 2010

Cast2face: Character Identification In Movie With Actor-Character Correspondence, Mengdi Xu, Xiaotong Yuan, Jialie Shen, Shuicheng Yan

Research Collection School Of Computing and Information Systems

We investigate the problem of automatically identifying characters in a movie with the supervision of actor-character name correspondence provided by the movie cast. Our proposed framework, namely Cast2Face, is featured by: (i) we restrict the names to assign within the set of character names in the cast; (ii) for each character, by using the corresponding actor's name as a key word, we retrieve from Google image search a group of face images to form the gallery set; and (iii) the probe face tracks in the movie are then identified as one of the actors by robust multi-task joint sparse representation …

Go to article

Trajectory-Based Visualization Of Web Video Topics, Juan Cao, Chong-Wah Ngo, Yong-Dong Zhang, Dong-Ming Zhang, Liang Ma Oct 2010

Trajectory-Based Visualization Of Web Video Topics, Juan Cao, Chong-Wah Ngo, Yong-Dong Zhang, Dong-Ming Zhang, Liang Ma

Research Collection School Of Computing and Information Systems

While there have been research efforts in organizing largescale web videos into topics, efficient browsing of web video topics remains a challenging problem not yet addressed. The related issues include how to efficiently browse and track the evolution of topics and eventually locate the videos of interest. In this paper, we introduce a novel interface for visualizing video topics as evolution trajectories. The trajectory visualization is capable of highlighting milestone events and depicting the topical hotness over time. The interface also allows multi-level browsing from topics to events and to videos, resulting in search exploration could be more efficiently conducted …

Go to article

First Prev Next Last