Relation Modeling in Spatio-Temporal Action Localization
This work addresses action detection in videos for computer vision applications, representing an incremental improvement in performance.
The paper tackles spatio-temporal action localization by integrating multiple relation modeling methods and training strategies, achieving 40.67 mAP on the AVA-Kinetics test set.
This paper presents our solution to the AVA-Kinetics Crossover Challenge of ActivityNet workshop at CVPR 2021. Our solution utilizes multiple types of relation modeling methods for spatio-temporal action detection and adopts a training strategy to integrate multiple relation modeling in end-to-end training over the two large-scale video datasets. Learning with memory bank and finetuning for long-tailed distribution are also investigated to further improve the performance. In this paper, we detail the implementations of our solution and provide experiments results and corresponding discussions. We finally achieve 40.67 mAP on the test set of AVA-Kinetics.