1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020
2020-06-16Code Available1· sign in to hype
Siyu Chen, Junting Pan, Guanglu Song, Manyuan Zhang, Hao Shao, Ziyi Lin, Jing Shao, Hongsheng Li, Yu Liu
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/Siyu-C/ACAR-NetOfficialIn paperpytorch★ 214
- github.com/Mind23-2/MindCode-12mindspore★ 0
- github.com/MindSpore-scientific/code-12/tree/main/AVA_hpamindspore★ 0
Abstract
This technical report introduces our winning solution to the spatio-temporal action localization track, AVA-Kinetics Crossover, in ActivityNet Challenge 2020. Our entry is mainly based on Actor-Context-Actor Relation Network. We describe technical details for the new AVA-Kinetics dataset, together with some experimental results. Without any bells and whistles, we achieved 39.62 mAP on the test set of AVA-Kinetics, which outperforms other entries by a large margin. Code will be available at: https://github.com/Siyu-C/ACAR-Net.