Actor-multi-scale context bidirectional higher order interactive relation Network for spatial-temporal action localization
Abstract
References
Index Terms
- Actor-multi-scale context bidirectional higher order interactive relation Network for spatial-temporal action localization
Recommendations
GCRNet: Global Context Relation Network for Weakly-Supervised Temporal Action Localization: Identify the target actions in a long untrimmed video and find the corresponding action start point and end point.
ICVIP '21: Proceedings of the 2021 5th International Conference on Video and Image ProcessingWeakly-Supervised Temporal Action Localization is a very challenging task of classifying and locating all actions in an untrimmed video because the frame-wise label is not given during the training stage while the only label is action class. Due to the ...
Multi-scale Feature and Spatial Relation Inference for Object Detection
Image and GraphicsAbstractReal scene images contain rich contextual visual cues. How to use contextual information is a fundamental problem in object recognition task. Contextual information mainly includes visual relevance and spatial relations. In this work we propose a ...
Action recognition and localization with spatial and temporal contexts
AbstractLocating human action in spatio-temporal domain among untrimmed videos is an important but challenging task. Recent works have shown that incorporating contextual information leads to a significant improvement in action recognition, but there is ...
Comments
Information & Contributors
Information
Published In
Sponsors
- International Joint Conferences on Artifical Intelligence (IJCAI)
Publisher
Unknown publishers
Publication History
Qualifiers
- Research-article
- Research
- Refereed limited
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0