Human-Object Interaction Detection with Channel Aware Attention

Human-object interaction detection (HOI) is a fundamental task in computer vision, which requires locating instances and predicting their interactions. To tackle HOI, we attempt to capture the global context information in HOI scenes by explicitly encoding the global features using our novel channel aware attention mechanism. Our observation is that the context of an image, including people, objects and background plays important roles in HOI prediction. To leverage such information, we propose a channel aware attention, which applies global average pooling on the features to learn their channel-wise inter-dependency. Based on the channel aware attention, we develop a channel aware module and a channel aware encoder. Handling features in channel dimensions makes it convenient to encode the global features as well as to learn semantic features. Empirically, our model outstrips the strong baseline by 3.2 points on V-COCO and 0.79 points on HICO-DET respectively. The visual analysis demonstrates that our method is able to capture abundant interaction-related features by attending to relevant regions.