Multi-agent Attentional Activity Recognition
This work addresses activity recognition for applications like healthcare or surveillance, but it is incremental as it builds on existing attention and multi-agent approaches.
The authors tackled the problem of sensor-based activity recognition by proposing a multi-agent spatial-temporal attention model that intelligently selects informative modalities and their active periods, and demonstrated that it outperforms state-of-the-art methods on four real-world datasets.
Multi-modality is an important feature of sensor based activity recognition. In this work, we consider two inherent characteristics of human activities, the spatially-temporally varying salience of features and the relations between activities and corresponding body part motions. Based on these, we propose a multi-agent spatial-temporal attention model. The spatial-temporal attention mechanism helps intelligently select informative modalities and their active periods. And the multiple agents in the proposed model represent activities with collective motions across body parts by independently selecting modalities associated with single motions. With a joint recognition goal, the agents share gained information and coordinate their selection policies to learn the optimal recognition model. The experimental results on four real-world datasets demonstrate that the proposed model outperforms the state-of-the-art methods.