A solution for the 6th Aicity challenge workshop track 3. Temporal action localization is an important problem in computer vision. It is challenge to infer the start and end of action instances on small-scale datasets covering multi-view information accurately. In this paper, we propose an effective action temporal localization method to localize the temporal boundaries. Our approach in-cludes (i) a method integrating an action recognition network and a temporal action localization network, (ii) a post-processing method for selecting and correcting temporal boxes to ensure that the model finds accurate boundaries. In addition, the frame-level object detection information is also utilized. Extensive experiments prove the effectiveness of our method and we rank the 6th on the Test-A2 of the 6th AI City Challenge Track 3.
I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial Intelligence Conference in Shanghai. We invite you to upgrade your algorithm library to OpenMMLab 2.0 using MMEngine, which can be used for both research and commercial purposes. If you have any questions, please feel free to join us on the OpenMMLab Discord at https://discord.gg/amFNsyUBvm or add me on WeChat (van-sin) and I will invite you to the OpenMMLab WeChat group.