Overview of temporal action detection based on deep learning
Open Access
- 1 February 2024
- journal article
- research article
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 57 (2) , 1-77
Abstract
Temporal Action Detection (TAD) aims to accurately capture each action interval in an untrimmed video and to understand human actions. This paper comprehensively surveys the state-of-the-art techniques and models used for TAD task. Firstly, it conducts comprehensive research on this field through Citespace and comprehensively introduce relevant dataset. Secondly, it summarizes three types of methods, i.e., anchor-based, boundary-based, and query-based, from the design method level. Thirdly, it summarizes three types of supervised learning methods from the level of learning methods, i.e., fully supervised, weakly supervised, and unsupervised. Finally, this paper explores the current problems, and proposes prospects in TAD task.Keywords
Funding Information
- Funding of Special Development Project of Tianchang Intelligent Equipment and Instrument Research Institute (tzy202221, tzy202221, tzy202221)
- National Natural Science Foundation of China (61876079, 61876079)
This publication has 168 references indexed in Scilit:
- Dense Trajectories and Motion Boundary Descriptors for Action RecognitionInternational Journal of Computer Vision, 2013
- Recognizing 50 human action categories of web videosMachine Vision and Applications, 2012
- The structure and dynamics of cocitation clusters: A multiple‐perspective cocitation analysisJournal of the American Society for Information Science and Technology, 2010
- Machine learning: a review of classification and combining techniquesArtificial Intelligence Review, 2006
- CiteSpace II: Detecting and visualizing emerging trends and transient patterns in scientific literatureJournal of the American Society for Information Science and Technology, 2005
- On Space-Time Interest PointsInternational Journal of Computer Vision, 2005
- Searching for intellectual turning points: Progressive knowledge domain visualizationProceedings of the National Academy of Sciences, 2004
- Neural mechanisms of form and motion processing in the primate visual systemNeuron, 1994
- Distributed Hierarchical Processing in the Primate Cerebral CortexCerebral Cortex, 1991
- Segregation of Form, Color, Movement, and Depth: Anatomy, Physiology, and PerceptionScience, 1988