Back to Search
Start Over
Boundary Adjusted Network Based on Cosine Similarity for Temporal Action Proposal Generation
- Source :
- Neural Processing Letters. 53:2813-2828
- Publication Year :
- 2021
- Publisher :
- Springer Science and Business Media LLC, 2021.
-
Abstract
- Detecting temporal actions in long and untrimmed videos is a challenging and important field in computer vision. Generating high-quality proposals is a key step in temporal action detection. A high-quality proposal usually contains two main characteristics. One is the temporal overlaps between proposals and action instances should be as large as possible. The another one is the number of generated proposals should be as few as possible. Inspired by the similarity comparison in face recognition and the similarity of action in same action segment, we design a module to compare the similarity for visual features extracted from visual feature encoder. We find out time points where the similarity of features changes shapely to generate candidate proposals. Then, we train a classifier to evaluate the candidate proposals whether contains or not contains action instances. The experiments suggest that our method outperforms other temporal action proposal generation methods in THUMOS-14 dataset and ActivityNet-v1.3 dataset. In addition, our method still outperforms other methods when using different visual features extracted from different networks.
- Subjects :
- 0209 industrial biotechnology
Computer Networks and Communications
Computer science
business.industry
General Neuroscience
Cosine similarity
Computational intelligence
Pattern recognition
02 engineering and technology
Facial recognition system
020901 industrial engineering & automation
Similarity (network science)
Action (philosophy)
Artificial Intelligence
0202 electrical engineering, electronic engineering, information engineering
Feature (machine learning)
020201 artificial intelligence & image processing
Artificial intelligence
business
Classifier (UML)
Encoder
Software
Subjects
Details
- ISSN :
- 1573773X and 13704621
- Volume :
- 53
- Database :
- OpenAIRE
- Journal :
- Neural Processing Letters
- Accession number :
- edsair.doi...........cca2c461ce4fdf392809b79fa8ec4488