Pose-aware Multi-level Feature Network for Human Object Interaction Detection

Abstract

Reasoning human object interactions is a core problem in human-centric scene understanding and detecting such relations poses a unique challenge to vision systems due to large variations in human-object configurations, multiple co-occurring relation instances and subtle visual difference between relation categories. To address those challenges, we propose a multi-level relation detection strategy that utilizes human pose cues to capture global spatial configurations of relations and as an attention mechanism to dynamically zoom into relevant regions at human part level. Specifically, we develop a multi-branch deep network to learn a pose-augmented relation representation at three semantic levels, incorporating interaction context, object features and detailed semantic part cues. As a result, our approach is capable of generating robust predictions on fine-grained human object interactions with interpretable outputs. Extensive experimental evaluations on public benchmarks show that our model outperforms prior methods by a considerable margin, demonstrating its efficacy in handling complex scenes.

arXiv commentInternational Conference on Computer Vision 2019

References in corpus (6)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Action Recognition using Visual Attention
• Visual Semantic Role Labeling
• iCAN: Instance-Centric Attention Network for Human-Object Interaction Detection
• Transferable Interactiveness Knowledge for Human-Object Interaction Detection
• Interact as You Intend: Intention-Driven Human-Object Interaction Detection

Cited by in corpus (2)

• Detailed 2D-3D Joint Representation for Human-Object Interaction
• Zero-Shot Human-Object Interaction Recognition via Affordance Graphs