Deep Contextual Attention for Human-Object Interaction Detection
This work addresses the problem of detecting subtle human-object interactions in images for scene understanding, representing an incremental improvement over existing methods.
The paper tackles human-object interaction detection by proposing a contextual attention framework that leverages context information to improve recognition, achieving a 4.4% relative gain in role mean average precision on the V-COCO dataset compared to the state-of-the-art.
Human-object interaction detection is an important and relatively new class of visual relationship detection tasks, essential for deeper scene understanding. Most existing approaches decompose the problem into object localization and interaction recognition. Despite showing progress, these approaches only rely on the appearances of humans and objects and overlook the available context information, crucial for capturing subtle interactions between them. We propose a contextual attention framework for human-object interaction detection. Our approach leverages context by learning contextually-aware appearance features for human and object instances. The proposed attention module then adaptively selects relevant instance-centric context information to highlight image regions likely to contain human-object interactions. Experiments are performed on three benchmarks: V-COCO, HICO-DET and HCVRD. Our approach outperforms the state-of-the-art on all datasets. On the V-COCO dataset, our method achieves a relative gain of 4.4% in terms of role mean average precision ($mAP_{role}$), compared to the existing best approach.