Back to Search
Start Over
Exploring Feature Representation and Training strategies in Temporal Action Localization
- Source :
- ICIP
- Publication Year :
- 2019
-
Abstract
- Temporal action localization has recently attracted significant interest in the Computer Vision community. However, despite the great progress, it is hard to identify which aspects of the proposed methods contribute most to the increase in localization performance. To address this issue, we conduct ablative experiments on feature extraction methods, fixed-size feature representation methods and training strategies, and report how each influences the overall performance. Based on our findings, we propose a two-stage detector that outperforms the state of the art in THUMOS14, achieving a mAP@tIoU=0.5 equal to 44.2%.<br />ICIP19 Camera Ready
- Subjects :
- FOS: Computer and information sciences
Computer science
business.industry
Computer Vision and Pattern Recognition (cs.CV)
05 social sciences
Feature extraction
Representation (systemics)
Computer Science - Computer Vision and Pattern Recognition
010501 environmental sciences
Machine learning
computer.software_genre
01 natural sciences
Training (civil)
Action (philosophy)
Feature (computer vision)
0502 economics and business
State (computer science)
Artificial intelligence
050207 economics
business
computer
0105 earth and related environmental sciences
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- ICIP
- Accession number :
- edsair.doi.dedup.....a85b3dd7ff1806e59ec7b19dd5a9e84f