Recent Advances in Modeling, Methodology and Applications of Action Recognition and Detection

in Special Issue   Posted on June 1, 2020 

Information for the Special Issue

Special Issue Call for Papers:


Action recognition and detection in untrimmed videos is a challenging task with the goal to not only recognize the category a video belongs to, but also infer the start and end times of action instances. Action recognition and detection has found applications in critical domains such as unmanned driving, medical robotics, sports analysis, and safety monitoring. There is still significant room for improvement, for example by applying weakly- and self-supervised learning techniques to reduce annotation costs, adversarial learning to improve model robustness, or incremental leaning for online action detection.

This special issue will feature the most recent advances in modeling, methodology and applications for action recognition and detection. It targets both academic researchers and industrial practitioners from machine learning and computer vision communities. We encourage novel and advanced techniques of action recognition and detection.



Topics should be related to action recognition and detection include, but are not limited to:

  • Novel models and methodologies for action recognition and detection
  • New neural architectures for video understanding
  • Weakly supervised learning
  • Self-supervised learning
  • Self-paced learning
  • Reinforcement learning
  • Adversarial learning
  • Graph-based learning
  • Online/incremental learning
  • Multi-label/multi-task learning
  • Representation learning
  • Spatio-temporal processing
  • New applications, including human behavior analysis in shops, safety monitoring, service robotics, unmanned driving and other scenarios


Sep 15, 2020 submission

Jan 15, 2021 first decision

Apr 15, 2021 revision

Sep 2021 publication


  1. Changsheng Li, Professor, Beijing Institute of Technology, China, Email: [email protected]
  2. Wenhan Luo, Technical Lead, Tencent, China, Email: [email protected]
  3. Hyung Jin Chang, Assistant Professor, University of Birmingham, UK, Email: [email protected]
  4. Xi Peng, Assistant Professor, University of Delaware, USA, Email: [email protected]
  5. Björn Stenger, Lead Scientist, Rakuten Institute of Technology (RIT), Japan, Email: [email protected]
  6. Huanhuan Chen, Professor, University of Science and Technology of China, China, Email: [email protected]
  7. Ivan Laptev, Senior Researcher INRIA Paris and head of scientific board at VisionLabs, Email: [email protected]
  8. Roberto Cipolla, Professor, University of Cambridge, Email: [email protected]

Closed Special Issues