記錄 47 之 6058
Record:   Prev Next
作者 Sadanand, Sreemanananth
書名 Action Bank: A High-Level Representation of Activity in Video
國際標準書號 9781267184320
book jacket
說明 42 p
附註 Source: Masters Abstracts International, Volume: 50-04, page: 2495
Adviser: Jason J. Corso
Thesis (M.S.)--State University of New York at Buffalo, 2012
Activity recognition in video is dominated by low and mid-level features, and while demonstrably capable, by nature, these features carry little semantic meaning. We present Action Bank, a conceptually simple yet effectively powerful method for carrying out high-level activity recognition on a wide variety of realistic videos "in the wild."
The method leverages on the fact that a large number of smaller action detectors, when pooled appropriately, can provide high-level semantically rich features that are superior to low-level features in discriminating videos. Our method builds a high-level representation using the output of a large bank of individual, viewpoint-tuned action detectors. This high-level representation has rich applicability in a wide-variety of video understanding problems, and we have shown its capability on activity recognition by means of exhaustive experimentation on most of the benchmark activity datasets in use by the vision community
Our results shows a significant improvement on every major benchmark dataset we have attempted. This encourages further research on this subject in terms of optimization for speed and ability to run in real time. Findings in this research topic have been submitted to the IEEE conference on Computer Vision and Pattern Recognition, 2012 (CVPR)
School code: 0656
Host Item Masters Abstracts International 50-04
主題 Artificial Intelligence
Computer Science
0800
0984
Alt Author State University of New York at Buffalo. Computer Science and Engineering
記錄 47 之 6058
Record:   Prev Next