Search For:

Displaying 1-50 out of 58 total
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...
 
Mining Event Structures from Web Videos
Found in: IEEE Multimedia
By Xiao Wu, Yi-Jie Lu, Qiang Peng, Chong-Wah Ngo
Issue Date:January 2011
pp. 38-51
<p>This article explores the issues of mining event structures from Web video search results using text analysis, burst detection, clustering, and other techniques.</p>
 
Data-Driven Approaches to Community-Contributed Video Applications
Found in: IEEE Multimedia
By Xiao Wu, Chong-Wah Ngo, Wan-Lei Zhao
Issue Date:October 2010
pp. 58-69
<p>The authors demonstrate three social media applications that are built around data-driven and context-based analysis.</p>
 
Semantic context modeling with maximal margin Conditional Random Fields for automatic image annotation
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yu Xiang, Xiangdong Zhou, Zuotao Liu, Tat-Seng Chua, Chong-Wah Ngo
Issue Date:June 2010
pp. 3368-3375
Context modeling for Vision Recognition and Automatic Image Annotation (AIA) has attracted increasing attentions in recent years. For various contextual information and resources, semantic context has been exploited in AIA and brings promising results. How...
 
A revisit of Generative Model for Automatic Image Annotation using Markov Random Fields
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yu Xiang, Xiangdong Zhou, Tat-Seng Chua, Chong-Wah Ngo
Issue Date:June 2009
pp. 1153-1160
Much research effort on automatic image annotation (AIA) has been focused on generative model, due to its well formed theory and competitive performance as compared with many well designed and sophisticated methods. However, when considering semantic conte...
 
Prediction-Based Gesture Detection in Lecture Videos by Combining Visual, Speech and Electronic Slides
Found in: Multimedia and Expo, IEEE International Conference on
By Feng Wang, Chong-wah Ngo, Ting-chuen Pong
Issue Date:July 2006
pp. 653-656
This paper presents an efficient algorithm for gesture detection in lecture videos by combining visual, speech and electronic slides. Besides accuracy, response time is also considered to cope with the efficiency requirements of real-time applications. Can...
 
Common Pattern Discovery Using Earth Mover?s Distance and Local Flow Maximization
Found in: Computer Vision, IEEE International Conference on
By Hung-Khoon Tan, Chong-Wah Ngo
Issue Date:October 2005
pp. 1222-1229
In this paper, we present a novel segmentation-insensitive approach for mining common patterns from 2 images. We develop an algorithm using the Earth Movers Distance (EMD) framework, unary and adaptive neighborhood color similarity. We then propose a novel...
 
Co-Clustering of Time-Evolving News Story with Transcript and Keyframe
Found in: Multimedia and Expo, IEEE International Conference on
By Xiao Wu, Chong-Wah Ngo, Qing Li
Issue Date:July 2005
pp. 117-120
This paper presents techniques in clustering the same topic news stories according to event themes. We model the relationship of stories with textual and visual concepts under the representation of bipartite graph. The textual and visual concepts are extra...
 
Deformable Geometry Model Matching by Topological and Geometric Signatures
Found in: Pattern Recognition, International Conference on
By Kwok-Leung Tam, Rynson W. H. Lau, Chong-Wah Ngo
Issue Date:August 2004
pp. 910-913
In this paper, we present a novel method for efficient 3D model comparison. The method matches highly deformed models by comparing topological and geometric features. First, we propose
 
Novel Seed Selection for Multiple Objects Detection and Tracking
Found in: Pattern Recognition, International Conference on
By Zailiang Pan, Chong-Wah Ngo
Issue Date:August 2004
pp. 744-747
This paper proposes a unified approach for initializing, detecting and tracking of multiple moving objects. Object initialization is achieved through novel seed selection which is adaptively activated, depending on the quality of tracking, to select the be...
 
Graph Based Image Matching
Found in: Pattern Recognition, International Conference on
By Hui Jiang, Chong-Wah Ngo
Issue Date:August 2004
pp. 658-661
Given two or more images, we can define different but related problems on pattern matching such as image registration, pattern detection and localization, and common pattern discovery. These problems have different levels of purpose and difficulties, as a ...
 
ICA-FX Features for Classification of Singing Voice and Instrumental Sound
Found in: Pattern Recognition, International Conference on
By Tat-Wan Leung, Chong-Wah Ngo, Rynson W. H. Lau
Issue Date:August 2004
pp. 367-370
This paper describes a new approach in locating the segments of singing voice in pop musical songs. Initially, GLR distance measure is employed to temporally detect the boundaries of singing voices and instrumental sounds. ICA-FX is then adopted to extract...
 
Deformable Object Model Matching by Topological and Geometric Similarity
Found in: Computer Graphics International Conference
By Kwok-Leung Tam, Rynson W.H. Lau, Chong-Wah Ngo
Issue Date:June 2004
pp. 335-342
In this paper, we present a novel method for efficient 3D model comparison. The method is designed to match highly deformed models through capturing two types of information. First, we propose a feature point extraction algorithm, which is based on
 
Structuring Lecture Videos for Distance Learning Applications
Found in: Multimedia Software Engineering, International Symposium on
By Chong-Wah Ngo, Feng Wang, Ting-Chuen Pong
Issue Date:December 2003
pp. 215
This paper presents an automatic and novel approach in structuring and indexing lecture videos for distance learning applications. By structuring video content, we can support both topic indexing and semantic querying of multimedia documents. In this paper...
 
Automatic Video Summarization by Graph Modeling
Found in: Computer Vision, IEEE International Conference on
By Chong-Wah Ngo, Yu-Fei Ma, Hong-Jiang Zhang
Issue Date:October 2003
pp. 104
We propose a unified approach for summarization based on the analysis of video structures and video highlights. Our approach emphasizes both the content balance and perceptual quality of a summary. Normalized cut algorithm is employed to globally and optim...
 
Video clip retrieval by maximal matching and optimal matching in graph theory
Found in: Multimedia and Expo, IEEE International Conference on
By Yu-Xin Peng, Chong-Wah Ngo, Qing-Jie Dong, Zong-Ming Guo, Jian-Guo Xiao
Issue Date:July 2003
pp. 317-320
In this paper, a novel approach for automatic matching, ranking and retrieval of video clips is proposed. Motivated by the maximal and optimal matching theories in graph analysis, a new similarity measure of video clips is defined based on the representati...
 
Motion Retrieval by Temporal Slices Analysis
Found in: Pattern Recognition, International Conference on
By Chong-Wah Ngo, Ting-Chuen Pong, Hong-Jiang Zhang
Issue Date:August 2002
pp. 40064
In this papel; we investigate video shots retrieval based on the analysis of temporal slice images. Temporal slices are a set of2D images extracted along the time dimension of image sequences. They encode rich set of motion clues for shot similarity measur...
 
Near-duplicate Video Retrieval: Current Research and Future Trends
Found in: IEEE Multimedia
By Heng Tao Shen,Jiajun Liu,Zi Huang,Chong-Wah Ngo,Wei Wang
Publication Date: May 2011
pp. N/A
Note: Document Withdrawn from CSDL. The document that would normally appear here has been withdrawn at the request of the authors. Reasonable effort should be made to remove all past references to this document. We regret any inconvenience.          The ex...
   
Multibiometrics Based on Palmprint and Handgeometry
Found in: Computer and Information Science, ACIS International Conference on
By Xiao-Yong Wei, Dan Xu, Chong-Wah Ngo
Issue Date:July 2005
pp. 495-500
This paper described our approach of multibiometrics in a single image. Firstly, a new method for capturing the key points of hand geometry is proposed. Then, we described our new method of palmprint feature extracting. By using projection transform and wa...
 
Motion-Based Video Representation for Scene Change Detection
Found in: Pattern Recognition, International Conference on
By Chong-Wah Ngo, Ting-Chuen Pong, Roland T. Chin, Hong-Jiang Zhang
Issue Date:September 2000
pp. 1827
We present a newly developed scheme for automatically partitioning videos into scenes. A scene is generally referred to as a group of shots taken place in the same site. In this paper, we first propose a motion annotation algorithm based on the analysis of...
 
Motion Characterization by Temporal Slices Analysis
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Chong-Wah Ngo, Ting-Chuen Pong, Hong-Jiang Zhang, Roland T. Chin
Issue Date:June 2000
pp. 2768
This paper describes an approach to characterize camera and object motions based on the analysis of spatio-temporal image volumes. In the spatio-temporal slices of image volumes, motion is depicted as oriented patterns. We propose a tensor histogram comput...
 
A Hamming Embedding Kernel with Informative Bag-of-Visual Words for Video Semantic Indexing
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Bernard Merialdo, Chong-Wah Ngo, Feng Wang, Wan-Lei Zhao
Issue Date:April 2014
pp. 1-20
In this article, we propose a novel Hamming embedding kernel with informative bag-of-visual words to address two main problems existing in traditional BoW approaches for video semantic indexing. First, Hamming embedding is employed to alleviate the informa...
     
Image search by graph-based label propagation with image representation from DNN
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Chong-Wah Ngo, Houqiang Li, Jingdong Wang, Yingwei Pan, Kuiyuan Yang, Tao Mei, Ting Yao
Issue Date:October 2013
pp. 397-400
Our objective is to estimate the relevance of an image to a query for image search purposes. We address two limitations of the existing image search engines in this paper. First, there is no straightforward way of bridging the gap between semantic textual ...
     
Error recovered hierarchical classification
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Shiai Zhu, Xiao-Yong Wei, Chong-Wah Ngo
Issue Date:October 2013
pp. 697-700
Hierarchical classification (HC) is a popular and efficient way for detecting the semantic concepts from the images. However, the conventional HC, which always selects the branch with the highest classification response to go on, has the risk of propagatin...
     
Annotation for free: video tagging by mining user search behavior
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Shipeng Li, Chong-Wah Ngo, Tao Mei, Ting Yao
Issue Date:October 2013
pp. 977-986
The problem of tagging is mostly considered from the perspectives of machine learning and data-driven philosophy. A fundamental issue that underlies the success of these approaches is the visual similarity, ranging from the nearest neighbor search to manif...
     
Near-duplicate video retrieval: Current research and future trends
Found in: ACM Computing Surveys (CSUR)
By Chong Wah Ngo, Heng Tao Shen, Hongyun Cai, Jiajun Liu, Wei Wang, Zi Huang
Issue Date:August 2013
pp. 1-23
The exponential growth of online videos, along with increasing user involvement in video-related activities, has been observed as a constant phenomenon during the last decade. User's time spent on video capturing, editing, uploading, searching, and viewing...
     
Click-boosting random walk for image search reranking
Found in: Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service (ICIMCS '13)
By Chong-Wah Ngo, Ting Yao, Xiaopeng Yang, Yongdong Zhang, Zheng-Jun Zha
Issue Date:August 2013
pp. 1-6
Image reranking is an effective way for improving the retrieval performance of keyword-based image search engines. A fundamental issue underlying the success of existing image reranking approaches is the ability in identifying potentially useful recurrent ...
     
Galaxy browser: exploratory search of web videos
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Chong Wah Ngo, Hung Khoon Tan, Lei Pang, Song Tan
Issue Date:November 2011
pp. 803-804
Most search engines return a ranked list of items in response to a query. The list however tells very little about the relationship among items. For videos especially, users often read to spend significant amount of time to navigate the search result. Expl...
     
Towards textually describing complex video contents with audio-visual concept classifiers
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Chong-Wah Ngo, Chun Chet Tan, Yu-Gang Jiang
Issue Date:November 2011
pp. 655-658
Automatically generating compact textual descriptions of complex video contents has wide applications. With the recent advancements in automatic audio-visual content recognition, in this paper we explore the technical feasibility of the challenging issue o...
     
Cross media hyperlinking for search topic browsing
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Chong-Wah Ngo, Hung-Khoon Tan, Lei Pang, Song Tan
Issue Date:November 2011
pp. 243-252
With the rapid growth of social media, there are plenty of information sources freely available online for use. Nevertheless, how to synchronize and leverage these diverse forms of information for multimedia applications remains a problem yet to be serious...
     
On the pooling of positive examples with ontology for visual concept learning
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Chong-Wah Ngo, Shiai Zhu, Yu-Gang Jiang
Issue Date:November 2011
pp. 1045-1048
A common obstacle in effective learning of visual concept classifiers is the scarcity of positive training examples due to expensive labeling cost. This paper explores the sampling of weakly tagged web images for concept learning without human assistance. ...
     
Context-based friend suggestion in online photo-sharing community
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Chong-Wah Ngo, Tao Mei, Ting Yao
Issue Date:November 2011
pp. 945-948
With the popularity of social media, web users tend to spend more time than before for sharing their experience and interest in online photo-sharing sites. The wide variety of sharing behaviors generate different metadata which pose new opportunities for t...
     
Beyond search: Event-driven summarization for web videos
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Chong-Wah Ngo, Hung-Khoon Tan, Jinhui Tang, Richang Hong, Shuicheng Yan, Tat-Seng Chua
Issue Date:November 2011
pp. 1-18
The explosive growth of Web videos brings out the challenge of how to efficiently browse hundreds or even thousands of videos at a glance. Given an event-driven query, social media Web sites usually return a large number of videos that are diverse and nois...
     
Trajectory-based visualization of web video topics
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Chong-Wah Ngo, DongMing Zhang, Juan Cao, Liang Ma, YongDong Zhang
Issue Date:October 2010
pp. 1639-1642
While there have been research efforts in organizing large scale web videos into clusters or 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 ...
     
Topical summarization of web videos by visual-text time-dependent alignment
Found in: Proceedings of the international conference on Multimedia (MM '10)
By Chong-Wah Ngo, Hung-Khoon Tan, Song Tan
Issue Date:October 2010
pp. 1095-1098
Search engines are used to return a long list of hundreds or even thousands of videos in response to a query topic. Efficient navigation of videos becomes difficult and users often need to painstakingly explore the search list for a gist of the search resu...
     
Coherent bag-of audio words model for efficient large-scale video copy detection
Found in: Proceedings of the ACM International Conference on Image and Video Retrieval (CIVR '10)
By Chang-Sheng Xu, Chong-Wah Ngo, Han-Qing Lu, Wan-Lei Zhao, Yang Liu
Issue Date:July 2010
pp. 89-96
Current content-based video copy detection approaches mostly concentrate on the visual cues and neglect the audio information. In this paper, we attempt to tackle the video copy detection task resorting to audio information, which is equivalently important...
     
On the sampling of web images for learning visual concept classifiers
Found in: Proceedings of the ACM International Conference on Image and Video Retrieval (CIVR '10)
By Chong-Wah Ngo, Gang Wang, Shiai Zhu, Yu-Gang Jiang
Issue Date:July 2010
pp. 50-57
Visual concept learning often requires a large set of training images. In practice, nevertheless, acquiring noise-free training labels with sufficient positive examples is always expensive. A plausible solution for training data collection is by sampling t...
     
Co-reranking by mutual reinforcement for image search
Found in: Proceedings of the ACM International Conference on Image and Video Retrieval (CIVR '10)
By Chong-Wah Ngo, Tao Mei, Ting Yao
Issue Date:July 2010
pp. 34-41
Most existing reranking approaches to image search focus solely on mining "visual" cues within the initial search results. However, the visual information cannot always provide enough guidance to the reranking process. For example, different images with si...
     
Towards google challenge: combining contextual and social information for web video categorization
Found in: Proceedings of the seventeen ACM international conference on Multimedia (MM '09)
By Chong-Wah Ngo, Wan-Lei Zhao, Xiao Wu
Issue Date:October 2009
pp. 1109-1110
Web video categorization is a fundamental task for web video search. In this paper, we explore the Google challenge from a new perspective by combing contextual and social information under the scenario of social web. The semantic meaning of text (title an...
     
Distribution-based concept selection for concept-based video retrieval
Found in: Proceedings of the seventeen ACM international conference on Multimedia (MM '09)
By Chong-Wah Ngo, HongFang Jing, Juan Cao, YongDong Zhang
Issue Date:October 2009
pp. 645-648
Query-to-concept mapping plays one of the keys to concept-based video retrieval. Conventional approaches try to find concepts that are likely to co-occur in the relevant shots from the lexical or statistical aspects. However, the high probability of co-occ...
     
Localizing volumetric motion for action recognition in realistic videos
Found in: Proceedings of the seventeen ACM international conference on Multimedia (MM '09)
By Chong-Wah Ngo, Jintao Li, Xiao Wu, Yongdong Zhang
Issue Date:October 2009
pp. 505-508
This paper presents a novel motion localization approach for recognizing actions and events in real videos. Examples include StandUp and Kiss in Hollywood movies. The challenge can be attributed to the large visual and motion variations imposed by realisti...
     
Semantic context transfer across heterogeneous sources for domain adaptive video search
Found in: Proceedings of the seventeen ACM international conference on Multimedia (MM '09)
By Chong-Wah Ngo, Shih-Fu Chang, Yu-Gang Jiang
Issue Date:October 2009
pp. 155-164
Automatic video search based on semantic concept detectors has recently received significant attention. Since the number of available detectors is much smaller than the size of human vocabulary, one major challenge is to select appropriate detectors to res...
     
Scalable detection of partial near-duplicate videos by visual-temporal consistency
Found in: Proceedings of the seventeen ACM international conference on Multimedia (MM '09)
By Chong-Wah Ngo, Hung-Khoon Tan, Richard Hong, Tat-Seng Chua
Issue Date:October 2009
pp. 145-154
Following the exponential growth of social media, there now exist huge repositories of videos online. Among the huge volumes of videos, there exist large numbers of near-duplicate videos. Most existing techniques either focus on the fast retrieval of full ...
     
Exploring inter-concept relationship with context space for semantic video indexing
Found in: Proceeding of the ACM International Conference on Image and Video Retrieval (CIVR '09)
By Chong-Wah Ngo, Xiao-Yong Wei, Yu-Gang Jiang
Issue Date:July 2009
pp. 1-8
Semantic concept detectors are often individually and independently developed. Using peripherally related concepts for leveraging the power of joint detection, which is referred to as context-based concept fusion (CBCF), has been one of the focus studies i...
     
Accelerating near-duplicate video matching by combining visual similarity and alignment distortion
Found in: Proceeding of the 16th ACM international conference on Multimedia (MM '08)
By Chong-Wah Ngo, Hung-Khoon Tan, Wan-Lei Zhao, Xiao Wu
Issue Date:October 2008
pp. 40-42
In this paper, we investigate a novel approach to accelerate the matching of two video clips by exploiting the temporal coherence property inherent in the keyframe sequence of a video. Motivated by the fact that keyframe correspondences between near-duplic...
     
Modeling video hyperlinks with hypergraph for web video reranking
Found in: Proceeding of the 16th ACM international conference on Multimedia (MM '08)
By Chong-Wah Ngo, Hung-Khoon Tan, Xiao Wu
Issue Date:October 2008
pp. 40-42
In this paper, we investigate a novel approach of exploiting visual-duplicates for web video reranking using hypergraph. Current graph-based reranking approaches consider mainly the pair-wise linking of keyframes and ignore reliability issues that are inhe...
     
Video event detection using motion relativity and visual relatedness
Found in: Proceeding of the 16th ACM international conference on Multimedia (MM '08)
By Chong-Wah Ngo, Feng Wang, Yu-Gang Jiang
Issue Date:October 2008
pp. 40-42
Event detection plays an essential role in video content analysis. However, the existing features are still weak in event detection because: i) most features just capture what is involved in an event or how the event evolves separately, and thus cannot com...
     
Fusing semantics, observability, reliability and diversity of concept detectors for video search
Found in: Proceeding of the 16th ACM international conference on Multimedia (MM '08)
By Chong-Wah Ngo, Xiao-Yong Wei
Issue Date:October 2008
pp. 40-42
Effective utilization of semantic concept detectors for large-scale video search has recently become a topic of intensive studies. One of main challenges is the selection and fusion of appropriate detectors, which considers not only semantics but also the ...
     
Bag-of-visual-words expansion using visual relatedness for video indexing
Found in: Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval (SIGIR '08)
By Chong-Wah Ngo, Yu-Gang Jiang
Issue Date:July 2008
pp. 2-2
Bag-of-visual-words (BoW) has been popular for visual classification in recent years. In this paper, we propose a novel BoW expansion method to alleviate the effect of visual word correlation problem. We achieve this by diffusing the weights of visual word...
     
Towards optimal bag-of-features for object categorization and semantic video retrieval
Found in: Proceedings of the 6th ACM international conference on Image and video retrieval (CIVR '07)
By Chong-Wah Ngo, Jun Yang, Yu-Gang Jiang
Issue Date:July 2007
pp. 494-501
Bag-of-features (BoF) deriving from local keypoints has recently appeared promising for object and scene classification. Whether BoF can naturally survive the challenges such as reliability and scalability of visual classification, nevertheless, remains un...
     
 1  2 Next >>