Search For:

Displaying 1-24 out of 24 total
Joint multi-label multi-instance learning for image classification
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Zheng-Jun Zha, Xian-Sheng Hua, Tao Mei, Jingdong Wang, Guo-Jun Qi, Zengfu Wang
Issue Date:June 2008
pp. 1-8
In real world, an image is usually associated with multiple labels which are characterized by different regions in the image. Thus image classification is naturally posed as both a multi-label learning and multi-instance learning problem. Different from ex...
 
Product Aspect Ranking and Its Applications
Found in: IEEE Transactions on Knowledge and Data Engineering
By Zheng-Jun Zha,Jianxing Yu,Jinhui Tang,Meng Wang,Tat-Seng Chua
Issue Date:May 2014
pp. 1-1
Numerous consumer reviews of products are now available on the Internet. Consumer reviews contain rich and valuable knowledge for both firms and users. However, the reviews are often disorganized, leading to difficulties in information navigation and knowl...
 
Partial-Duplicate Image Retrieval via Saliency-Guided Visual Matching
Found in: IEEE MultiMedia
By Liang Li,Shuqiang Jiang,Zheng-Jun Zha,Zhipeng Wu,Qingming Huang
Issue Date:July 2013
pp. 13-23
This article proposes a novel partial-duplicate image-retrieval scheme based on saliency-guided visual matching, where the localization of duplicates is done simultaneously. The image is abstracted by visually salient and rich regions (VSRRs), which are of...
 
Multimedia Question Answering
Found in: IEEE MultiMedia
By Richang Hong,Meng Wang,Guangda Li,Liqiang Nie,Zheng-Jun Zha,Tat-Seng Chua
Issue Date:October 2012
pp. 72-78
By surveying recent research in multimedia question answering, this article explores QA's evolution from text to multimedia and identifies the challenges in the field.
 
Robust Non-negative Graph Embedding: Towards noisy data, unreliable graphs, and noisy labels
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Hanwang Zhang, Zheng-Jun Zha, Shuicheng Yan, Meng Wang, Tat-Seng Chua
Issue Date:June 2012
pp. 2464-2471
Non-negative data factorization has been widely used recently. However, existing techniques, such as Non-negative Graph Embedding (NGE), often suffer from noisy data, unreliable graphs, and noisy labels, which are commonly encountered in real-world applica...
 
Matching Content-based Saliency Regions for partial-duplicate image retrieval
Found in: Multimedia and Expo, IEEE International Conference on
By Liang Li,Zhipeng Wu,Zheng-Jun Zha,Shuqiang Jiang,Qingming Huang
Issue Date:July 2011
pp. 1-6
In traditional partial-duplicate image retrieval, images are commonly represented using the Bag-of-Visual-Words (BOV) model built from image local features, such as SIFT. Actually, there is only a small similar portion between partial-duplicate images so t...
 
Evaluation of histogram based interest point detector in web image classification and search
Found in: Multimedia and Expo, IEEE International Conference on
By Junjie Cai, Zheng-Jun Zha, Yinghai Zhao, Zengfu Wang
Issue Date:July 2010
pp. 613-618
Local image feature has received increasing attention in various applications, such as web image classification and search. The process of local feature extraction consists of two main steps: interest point detection and local feature description. A wealth...
 
GPSView: A scenic driving route planner
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Ramesh Jain, Shuicheng Yan, Tat-Seng Chua, Xiangdong Zhou, Yan-Tao Zheng, Yiqun Li, Zheng-Jun Zha
Issue Date:February 2013
pp. 1-18
GPS devices have been widely used in automobiles to compute navigation routes to destinations. The generated driving route targets the minimal traveling distance, but neglects the sightseeing experience of the route. In this study, we propose an augmented ...
     
Mining Travel Patterns from Geotagged Photos
Found in: ACM Transactions on Intelligent Systems and Technology (TIST)
By Tat-Seng Chua, Yan-Tao Zheng, Zheng-Jun Zha
Issue Date:May 2012
pp. 1-18
Recently, the phenomenal advent of photo-sharing services, such as Flickr and Panoramio, have led to volumous community-contributed photos with text tags, timestamps, and geographic references on the Internet. The photos, together with their time- and geo-...
     
Learning concept bundles for video search with complex queries
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Jin Yuan, Meng Wang, Tat-Seng Chua, Xiangdong Zhou, Yao-Tao Zheng, Zheng-Jun Zha
Issue Date:November 2011
pp. 453-462
Classifiers for primitive visual concepts like "car", "sky" have been well developed and widely used to support video search on simple queries. However, it is usually ineffective for complex queries like "one or more people at a table or desk with a comput...
     
Product comparison using comparative relations
Found in: Proceedings of the 34th international ACM SIGIR conference on Research and development in Information (SIGIR '11)
By Jun Guo, Meng Wang, Si Li, Tat-Seng Chua, Weiran Xu, Zhaoyan Ming, Zheng-Jun Zha
Issue Date:July 2011
pp. 1151-1152
This paper proposes a novel Product Comparison approach. The comparative relations between products are first mined from both user reviews on multiple review websites and community-based question answering pairs containing product comparison information. A...
     
An efficient sparse metric learning in high-dimensional space via l1-penalized log-determinant regularization
Found in: Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09)
By Guo-Jun Qi, Hong-Jiang Zhang, Jinhui Tang, Tat-Seng Chua, Zheng-Jun Zha
Issue Date:June 2009
pp. 1-8
This paper proposes an efficient sparse metric learning algorithm in high dimensional space via an l1-penalized log-determinant regularization. Compare to the most existing distance metric learning algorithms, the proposed algorithm exploits the sparsity n...
     
Attribute-augmented semantic hierarchy: towards bridging semantic gap and intention gap in image retrieval
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Hanwang Zhang, Shuicheng Yan, Tat-Seng Chua, Yang Yang, Yue Gao, Zheng-Jun Zha
Issue Date:October 2013
pp. 33-42
This paper presents a novel Attribute-augmented Semantic Hierarchy (A2 SH) and demonstrates its effectiveness in bridging both the semantic and intention gaps in Content-based Image Retrieval (CBIR). A2 SH organizes the semantic concepts into multiple sema...
     
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 ...
     
Automatic labeling hierarchical topics
Found in: Proceedings of the 21st ACM international conference on Information and knowledge management (CIKM '12)
By Hongfei Yan, Tat-Seng Chua, Xian-Ling Mao, Xiaoming Li, Zhao-Yan Ming, Zheng-Jun Zha
Issue Date:October 2012
pp. 2383-2386
Recently, statistical topic modeling has been widely applied in text mining and knowledge management due to its powerful ability. A topic, as a probability distribution over words, is usually difficult to be understood. A common, major challenge in applyin...
     
Integrating rich information for video recommendation with multi-task rank aggregation
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Guangda Li, Jin Yuan, Meng Wang, Tat-Seng Chua, Xiaojian Zhao, Zheng-Jun Zha, Zhoujun Li
Issue Date:November 2011
pp. 1521-1524
Video recommendation is an important approach for helping people to access interesting videos. In this paper, we propose a scheme to integrate rich information for video recommendation. We regard video recommendation as a ranking problem and generate multi...
     
Difficulty guided image retrieval using linear multiview embedding
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Bo Geng, Chao Xu, Dacheng Tao, Linjun Yang, Yangxi Li, Zheng-Jun Zha
Issue Date:November 2011
pp. 1169-1172
Existing image retrieval systems suffer from a radical performance variance for different queries. The bad initial search results for "difficult" queries may greatly degrade the performance of their subsequent refinements, especially the refinement that ut...
     
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...
     
Optimizing multimodal reranking for web image search
Found in: Proceedings of the 34th international ACM SIGIR conference on Research and development in Information (SIGIR '11)
By Hao Li, Jialie Shen, Meng Wang, Zheng-Jun Zha, Zhisheng Li
Issue Date:July 2011
pp. 1119-1120
In this poster, we introduce a web image search reranking approach with exploring multiple modalities. Diff erent from the conventional methods that build graph with one feature set for reranking, our approach integrates multiple feature sets that describe...
     
Hierarchical organization of unstructured consumer reviews
Found in: Proceedings of the 20th international conference companion on World wide web (WWW '11)
By Jianxing Yu, Meng Wang, Tat-Seng Chua, Zheng-Jun Zha
Issue Date:March 2011
pp. 171-172
In this paper, we propose to organize the aspects of a specific product into a hierarchy by simultaneously taking advantages of domain structure knowledge as well as consumer reviews. Based on the derived hierarchy, we generate a hierarchical organization ...
     
Visual query suggestion: Towards capturing user intent in internet image search
Found in: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
By Linjun Yang, Meng Wang, Tao Mei, Tat-Seng Chua, Xian-Sheng Hua, Zengfu Wang, Zheng-Jun Zha
Issue Date:August 2010
pp. 1-19
Query suggestion is an effective approach to bridge the Intention Gap between the users' search intents and queries. Most existing search engines are able to automatically suggest a list of textual query terms based on users' current query input, which can...
     
Utilizing related samples to learn complex queries in interactive concept-based video search
Found in: Proceedings of the ACM International Conference on Image and Video Retrieval (CIVR '10)
By Jin Yuan, Tat-Seng Chua, Xiangdong Zhou, Zheng-Jun Zha, Zhengdong Zhao
Issue Date:July 2010
pp. 66-73
One of the main challenges in interactive concept-based video search is the insufficient relevant sample problem, especially for queries with complex semantics. To address this problem, in this paper, we propose to utilize "related samples" to learn the co...
     
Visual query suggestion
Found in: Proceedings of the seventeen ACM international conference on Multimedia (MM '09)
By Linjun Yang, Meng Wang, Tao Mei, Zengfu Wang, Zheng-Jun Zha
Issue Date:October 2009
pp. 15-24
Query suggestion is an effective approach to improve the usability of image search. Most existing search engines are able to automatically suggest a list of textual query terms based on users' current query input, which can be called Textual Query Suggesti...
     
Query expansion by spatial co-occurrence for image retrieval
Found in: Proceedings of the 19th ACM international conference on Multimedia (MM '11)
By Bo Geng, Chao Xu, Dacheng Tao, Yangxi Li, Yingfei Li, Zheng-jun Zha
Issue Date:November 2011
pp. 1177-1180
The well-known bag-of-features (BoF) model is widely utilized for large scale image retrieval. However, BoF model lacks the spatial information of visual words, which is informative for local features to build up meaningful visual patches. To compensate fo...
     
 1