Journal
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
Volume -, Issue -, Pages 469-478Publisher
IEEE
DOI: 10.1109/CVPR.2018.00056
Keywords
-
Categories
Funding
- ANR [ANR-15-CE23-0029, STPGP-479356-15]
- NSERC [ANR-15-CE23-0029, STPGP-479356-15]
- Agence Nationale de la Recherche (ANR) [ANR-15-CE23-0029] Funding Source: Agence Nationale de la Recherche (ANR)
Ask authors/readers for more resources
We propose a method for human activity recognition from RGB data that does not rely on any pose information during test time, and does not explicitly calculate pose information internally. Instead, a visual attention module learns to predict glimpse sequences in each frame. These glimpses correspond to interest points in the scene that are relevant to the classified activities. No spatial coherence is forced on the glimpse locations, which gives the attention module liberty to explore different points at each frame and better optimize the process of scrutinizing visual information. Tracking and sequentially integrating this kind of unstructured data is a challenge, which we address by separating the set of glimpses from a set of recurrent tracking/recognition workers. These workers receive glimpses, jointly performing subsequent motion tracking and activity prediction. The glimpses are soft-assigned to the workers, optimizing coherence of the assignments in space, time and feature space using an external memory module. No hard decisions are taken, i.e. each glimpse point is assigned to all existing workers, albeit with different importance. Our methods outperform the state-of-the-art on the largest human activity recognition dataset available to-date, NTU RGB+D, and on the Northwestern-UCLA Multiview Action 3D Dataset.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available