| Paper: | MLSP-P4.11 | ||
| Session: | Machine Learning Applications | ||
| Time: | Thursday, May 20, 09:30 - 11:30 | ||
| Presentation: | Poster | ||
| Topic: | Machine Learning for Signal Processing: Image and Video Processing Applications | ||
| Title: | MEAN SHIFT BASED VIDEO SEGMENT REPRESENTATION AND APPLICATIONS TO REPLAY DETECTION | ||
| Authors: | Ling-Yu Duan; Institute for Infocomm Research | ||
| Min Xu; Institute for Infocomm Research | |||
| Qi Tian; Institute for Infocomm Research | |||
| Chang-Sheng Xu; Institute for Infocomm Research | |||
| Abstract: | Effective and efficient representation of the low-level features of groups of frames or shots is an important yet challenging task for video analysis and retrieval. Key frame-based representation is limited by the difficulties in shot boundary detection of gradual transition and a variety of ways in key frame extraction. In this paper, we employ the mean shift-based mode seeking function to develop a new approach for compact representation of the video segment. The proposed video representation is motivated by recognizing that, on the global level, humans perceive images only as a combination of few most prominent colors. We exploit the spatiotemporal mode seeking in feature space to simulate “subjectivity” of human decisions to video segment retrieval and identification. The effectiveness of video representation and matching scheme is shown by initial experiments on replay detection in broadcast sports video. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops