Actor Conditioned Attention Maps for Video Action Detection

Oytun Ulutan, Swati Rallapalli, Mudhakar Srivatsa, Carlos Torres, B. S. Manjunath; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 527-536

Abstract


While observing complex events with multiple actors, humans do not assess each actor separately, but infer from the context. The surrounding context provides essential information for understanding actions. To this end, we propose to replace region of interest(RoI) pooling with an attention module, which ranks each spatio-temporal region's relevance to a detected actor instead of cropping. We refer to these as Actor-Conditioned Attention Maps (ACAM), which amplify/dampen the features extracted from the entire scene. The resulting actor-conditioned features focus the model on regions that are relevant to the conditioned actor. For actor localization, we leverage pre-trained object detectors, which transfer better. The proposed model is efficient and our action detection pipeline achieves near real-time performance. Experimental results on AVA 2.1 and JHMDB demonstrate the effectiveness of attention maps, with improvements of 7 mAP on AVA and 4 mAP on JHMDB.

Related Material


[pdf]
[bibtex]
@InProceedings{Ulutan_2020_WACV,
author = {Ulutan, Oytun and Rallapalli, Swati and Srivatsa, Mudhakar and Torres, Carlos and Manjunath, B. S.},
title = {Actor Conditioned Attention Maps for Video Action Detection},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = {March},
year = {2020}
}