# Actor Conditioned Attention Maps for Video Action Detection

## TL;DR

This paper introduces Actor-Conditioned Attention Maps (ACAM), a novel attention-based approach for video action detection that leverages scene context to improve actor localization and action recognition.

## Contribution

It replaces RoI pooling with an attention module that emphasizes relevant scene regions conditioned on actors, enhancing detection accuracy.

## Key findings

- Achieves 7 mAP improvement on AVA 2.1
- Achieves 4 mAP improvement on JHMDB
- Operates near real-time performance

## 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.