Exploring Predicate Visual Context in Detecting Human-Object Interactions
This work improves detection of complex or ambiguous human-object interactions for computer vision applications, but it is incremental as it builds on existing transformer-based approaches.
The paper tackled the problem of human-object interaction detection by addressing the lack of fine-grained contextual information in existing methods, resulting in a model that outperforms state-of-the-art on HICO-DET and V-COCO benchmarks while maintaining low training cost.
Recently, the DETR framework has emerged as the dominant approach for human--object interaction (HOI) research. In particular, two-stage transformer-based HOI detectors are amongst the most performant and training-efficient approaches. However, these often condition HOI classification on object features that lack fine-grained contextual information, eschewing pose and orientation information in favour of visual cues about object identity and box extremities. This naturally hinders the recognition of complex or ambiguous interactions. In this work, we study these issues through visualisations and carefully designed experiments. Accordingly, we investigate how best to re-introduce image features via cross-attention. With an improved query design, extensive exploration of keys and values, and box pair positional embeddings as spatial guidance, our model with enhanced predicate visual context (PViC) outperforms state-of-the-art methods on the HICO-DET and V-COCO benchmarks, while maintaining low training cost.