Yu-Gang Jiang

PhD Candidate in Computer Science Dept.
City University of Hong Kong

Office:
Email:		 MMW 1407
yjiang at cs.cityu.edu.hk

I am a 3rd year Ph.D. student in Department of Computer Science at City University of Hong Kong, where I work in the Video Retrieval Group (VIREO) under my advisor Prof. Chong-Wah Ngo. From May 2008 to April 2009, I worked in the Digital Video and Multimedia Lab (DVMM) at Columbia University as a visiting student, under the direction of Prof. Shih-Fu Chang.

My research interests include multimedia information retrieval and video content analysis, with strong connections to computer vision and machine learning. I am currently investigating techniques for automatically indexing and searching large-scale video databases.

Downloads

- VIREO-374: keypoint-based detectors for 374 LSCOM semantic concepts. (Aug. 2007)
- 374 concept detectors (SVM models) trained on TRECVID 05 development set.
- Features (color/texture/keypoint) and detection scores of TRECVID 06 testset.
- Recent extension:
- Features and detection scores of TRECVID 2007/2008 dataset.

Publications

Conference papers:
  • Yu-Gang Jiang, Jun Wang, Shih-Fu Chang, Chong-Wah Ngo
    Domain Adaptive Semantic Diffusion for Large Scale Context-Based Video Annotation
    IEEE ICCV (ICCV'09), Kyoto, Japan, Sept. 29-Oct. 2, 2009.
     
  • Xiao-Yong Wei, Yu-Gang Jiang, Chong-Wah Ngo
    Exploring Inter-Concept Relationship with Context Space for Semantic Video Indexing
    ACM Int'l Conference on Image and Video Retrieval (CIVR'09), Island of Santorini, Greece, July 8-10, 2009. (Oral)
     
  • Feng Wang, Yu-Gang Jiang, Chong-Wah Ngo
    Video Event Detection Using Motion Relativity and Visual Relatedness
    ACM Multimedia (ACM MM'08), Vancouver, Canada, Oct. 27-Nov. 1, 2008. (Oral)
  • Yu-Gang Jiang, Chong-Wah Ngo
    Bag-of-Visual-Words Expansion Using Visual Relatedness for Video Indexing
    ACM SIGIR Conference on Research & Development on Information Retrieval (SIGIR'08), Singapore, Jul. 20-24, 2008.
  • Yu-Gang Jiang, Chong-Wah Ngo
    Ontology-Based Visual Word Matching for Near-Duplicate Retrieval
    IEEE International Conference on Multimedia & Expo (ICME'08), Hannover, Germany, Jun. 23-26, 2008. (Oral)
  • Jun Yang, Yu-Gang Jiang, Alexander G. Hauptmann, Chong-Wah Ngo
    Evaluating Bag-of-Visual-Words Representations in Scene Classification [pdf]
    ACM SIGMM Workshop on Multimedia Information Retrieval (MIR'07), in conjunction with ACM Multimedia, Germany, 2007.
  • Yu-Gang Jiang, Chong-Wah Ngo, Jun Yang
    Towards Optimal Bag-of-Features for Object Categorization and Semantic Video Retrieval [pdf]
    ACM International Conference on Image and Video Retrieval (CIVR'07), Amsterdam, The Netherlands, Jul. 9-11, 2007.
  • Chong-Wah Ngo, Wan-Lei Zhao, Yu-Gang Jiang
    Fast Tracking of Near-Duplicate Keyframes in Broadcast Domain with Transitivity Propagation [pdf]
    ACM Multimedia (ACM MM'06), Santa Barbara, CA, USA, Oct. 23-27, 2006. (Oral)
  • Yu-Gang Jiang, Wan-Lei Zhao, Chong-Wah Ngo
    Exploring Semantic Concept Using Local Invariant Features [pdf]
    Asia-Pacific Workshop on Visual Information Processing, Beijing, China, Nov. 7-9, 2006. (Invited paper, oral)
     
  • Wanlei Zhao, Yu-Gang Jiang, Chong-Wah Ngo
    Keyframe Retrieval by Keypoints: Can Point-to-Point Matching Help? [pdf]
    International Conference on Image and Video Retrieval (CIVR'06), Tempe, AZ, USA, Jul. 13-15, 2006. (Oral)

  Journal papers:
  • Yu-Gang Jiang, Jun Yang, Chong-Wah Ngo, Alexander G. Hauptmann
    Representation Choices of Keypoint-Based Semantic Concept Detection: A Comprehensive Study
    IEEE Transactions on Multimedia, 2009,     under revision.
    Extended version for CIVR'07 and MIR'07 papers.
  • Yu-Gang Jiang, Chong-Wah Ngo
    Visual Word Proximity and Linguistics for Semantic Video Indexing and Near-Duplicate Retrieval 
    Computer Vision and Image Understanding, vol. 113, pp. 405-414, 2009.
  • Xiao-Yong Wei, Chong-Wah Ngo, Yu-Gang Jiang
    Selection of Concept Detectors for Video Search by Ontology-Enriched Semantic Spaces 
    IEEE Transactions on Multimedia, vol. 10, issue 6, pp. 1085-1096, 2008.
     

  TRECVID notebook papers:

  • Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky
    Columbia University/VIREO-CityU/IRIT TRECVID2008 High-Level Feature Extraction and Interactive Video Search 
    NIST TRECVID Workshop (TRECVID'08), Gaithersburg, MD, USA, Nov. 17-18, 2008.
  • Chong-Wah Ngo, Yu-Gang Jiang, Xiaoyong Wei, Wanlei Zhao, Feng Wang, Xiao Wu, Hung-Khoon Tan
    Beyond Semantic Search: What You Observe May Not Be What You Think 
    NIST TRECVID Workshop (TRECVID'08), Gaithersburg, MD, USA, Nov. 17-18, 2008.
  • Chong-Wah Ngo, Yu-Gang Jiang, Xiaoyong Wei, Feng Wang, Wanlei Zhao, Hung-Khoon Tan, Xiao Wu
    Experimenting VIREO-374: Bag-of-Visual-Words and Visual-Based Ontology for Semantic Video Indexing and Search [pdf]
    NIST TRECVID Workshop (TRECVID'07), Gaithersburg, MD, USA, Nov. 5-6, 2007.
  • Yu-Gang Jiang, Xiaoyong Wei, Chong-Wah Ngo, Hung-Khoon Tan, Wanlei Zhao, Xiao Wu
    Modeling Local Interest Points for Semantic Detection and Video Search at TRECVID 2006 [pdf]
    NIST TRECVID Workshop (TRECVID'06), Gaithersburg, MD, USA, Nov. 13-14, 2006.
Technical report:
  • Yu-Gang Jiang, Akira Yanagawa, Shih-Fu Chang, Chong-Wah Ngo
    Fusing Columbia374 and VIREO-374 for Large Scale Semantic Concept Detection [pdf]
    Columbia University ADVENT Technical Report #223-2008-1, Aug. 2008.

Yu-Gang Jiang -