Deep Contextual Attention for Human-Object Interaction Detection

TL;DR

This paper introduces a contextual attention framework for human-object interaction detection that leverages context-aware features and adaptive attention to improve detection accuracy across multiple benchmarks.

Contribution

The paper presents a novel attention-based approach that incorporates context information for better human-object interaction detection, outperforming previous methods.

Findings

Outperforms state-of-the-art on V-COCO, HICO-DET, and HCVRD datasets.

Achieves a 4.4% relative gain in role mAP on V-COCO.

Effectively utilizes context to capture subtle human-object interactions.

Abstract

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.