BROWSE
Detail
Journal Article
SRG: Snippet Relatedness-based Temporal Action Proposal Generator
Cited 19 time in 
Share 
Share
- Authors
- Hyunjun Eun, Sumin Lee, Jinyoung Moon, Jongyoul Park, Chanho Jung, Changick Kim
- Issue Date
- 2020-11
- Citation
- IEEE Transactions on Circuits and Systems for Video Technology, v.30, no.11, pp.4232-4244
- ISSN
- 1051-8215
- Publisher
- IEEE
- Language
- English
- Type
- Journal Article
- Abstract
- Recent temporal action proposal generation approaches have suggested integrating segment- A nd snippet score-based methodologies to produce proposals with high recall and accurate boundaries. In this paper, different from such a hybrid strategy, we focus on the potential of the snippet score-based approach. Specifically, we propose a new snippet score-based method, named Snippet Relatedness-based Generator (SRG), with a novel concept of 'snippet relatedness'. Snippet relatedness represents which snippets are related to a specific action instance. To effectively learn this snippet relatedness, we present 'pyramid non-local operations' for locally and globally capturing long-range dependencies among snippets. By employing these components, SRG first produces a 2D relatedness score map that enables the generation of various temporal intervals reliably covering most action instances with high overlap. Then, SRG evaluates the action confidence scores of these temporal intervals and refines their boundaries to obtain temporal action proposals. On THUMOS-14 and ActivityNet-1.3 datasets, SRG outperforms state-of-the-art methods for temporal action proposal generation. Furthermore, compared to competing proposal generators, SRG leads to significant improvements in temporal action detection.
- KSP Keywords
- Based Approach, High recall, Hybrid Strategy, Non-local, Temporal intervals, action detection, long-range dependencies, proposal generation, state-of-The-Art