Name
Abstract | ||
|---|---|---|
Combining multiple low-level visual features is a proven and effective strategy for a range of computer vision tasks. However, limited attention has been paid to combining such features with information from other modalities, such as audio and videotext, for large scale analysis of web videos. In our work, we rigorously analyze and combine a large set of low-level features that capture appearance, color, motion, audio and audio-visual co-occurrence patterns in videos. We also evaluate the utility of high-level (i.e., semantic) visual information obtained from detecting scene, object, and action concepts. Further, we exploit multimodal information by analyzing available spoken and videotext content using state-of-the-art automatic speech recognition (ASR) and videotext recognition systems. We combine these diverse features using a two-step strategy employing multiple kernel learning (MKL) and late score level fusion methods. Based on the TRECVID MED 2011 evaluations for detecting 10 events in a large benchmark set of ∼45000 videos, our system showed the best performance among the 19 international teams. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/CVPR.2012.6247814 | CVPR |
Keywords | Field | DocType |
web video,videotext recognition system,large scale analysis,multiple kernel learning,large set,robust event detection,effective strategy,large benchmark,multimodal feature fusion,low-level feature,videotext content,visual information,multimodal information,internet,vectors,kernel,speech,feature extraction,speech recognition,learning artificial intelligence,encoding,computer vision | Computer science,Artificial intelligence,The Internet,Kernel (linear algebra),Object detection,Computer vision,Pattern recognition,TRECVID,Multiple kernel learning,Feature extraction,Exploit,Speech recognition,Encoding (memory) | Conference |
Volume | Issue | ISSN |
2012 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
978-1-4673-1227-1 | 106 | 2.76 |
References | Authors | |
25 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Premkumar Natarajan | 1 | 874 | 79.46 |
| Shuang Wu | 2 | 171 | 7.23 |
| Shiv Naga Prasad Vitaladevuni | 3 | 272 | 18.18 |
| Xiaodan Zhuang | 4 | 433 | 24.71 |
| Stavros Tsakalidis | 5 | 213 | 13.83 |
| Unsang Park | 6 | 815 | 36.32 |
| Rohit Prasad | 7 | 465 | 39.06 |