Feng Wang
East China Normal University
37 Papers
339 Citations
Feng Wang is an academic researcher from East China Normal University. The author has contributed to research in topics: Computer science & TRECVID. The author has an hindex of 14, co-authored 36 publications. Previous affiliations of Feng Wang include City University of Hong Kong & Hong Kong University of Science and Technology.
Chat about Author
Papers
Video event detection using motion relativity and visual relatedness
Feng Wang,Yu-Gang Jiang,Chong-Wah Ngo +2 more
- 26 Oct 2008
TL;DR: A new motion feature, namely Expanded Relative Motion Histogram of Bag-of-Visual-Words (ERMH-BoW) to employ motion relativity and visual relatedness for event detection and to alleviate the visual word correlation problem in BoW is proposed.
Summarizing Rushes Videos by Motion, Object, and Event Understanding
Feng Wang,Chong-Wah Ngo +1 more
TL;DR: A hierarchical hidden Markov model (HHMM) is proposed to model the motion feature distribution and classify video segments into different categories to decide their potential for reuse and significantly outperforms other methods based on SVM, FSM, and HMM.
Structuring lecture videos for distance learning applications
Chong-Wah Ngo,Feng Wang,Ting-Chuen Pong +2 more
- 01 Jan 2003
TL;DR: By structuring video content, this work can support both topic indexing and semantic querying of multimedia documents and two major techniques in this proposed approach include video text analysis and speech recognition.
47
Structuring low-quality videotaped lectures for cross-reference browsing by video text analysis
TL;DR: The goal in this paper is to automatically construct the cross references of lecture videos and textual documents so as to facilitate the synchronized browsing and presentation of multimedia information.
44
Video Event Detection Using Motion Relativity and Feature Selection
TL;DR: This paper proposes a new motion feature, namely Expanded Relative Motion Histogram of Bag-of-Visual-Words (ERMH-BoW) to employ motion relativity for event detection and proposes an approach based on information gain and informativeness weighting to select a cleaner and more discriminative set of features.
40