no code implementations • 5 Oct 2023 • Luoying Hao, Yan Hu, Wenjun Lin, Qun Wang, Heng Li, Huazhu Fu, Jinming Duan, Jiang Liu
In this paper, to accurately detect fine-grained actions that happen at every moment, we propose an anchor-context action detection network (ACTNet), including an anchor-context detection (ACD) module and a class conditional diffusion (CCD) module, to answer the following questions: 1) where the actions happen; 2) what actions are; 3) how confidence predictions are.
no code implementations • 24 Mar 2021 • Arnaud Huaulmé, Duygu Sarikaya, Kévin Le Mut, Fabien Despinoy, Yonghao Long, Qi Dou, Chin-Boon Chng, Wenjun Lin, Satoshi Kondo, Laura Bravo-Sánchez, Pablo Arbeláez, Wolfgang Reiter, Manoru Mitsuishi, Kanako Harada, Pierre Jannin
The best models achieved more than 95% AD-Accuracy for phase recognition, 80% for step recognition, 60% for activity recognition, and 75% for all granularity levels.