Zoom

Pattern recognition (psychology)

Lens (geology)

Spatial relation

Feature (linguistics)

Cognitive neuroscience of visual object recognition

Margin (machine learning)

Biology

Politics

Data mining

Machine learning

Engineering

Philosophy

Political science

Paleontology

Artificial intelligence

Relation (database)

Object detection

Representation (politics)

Context (archaeology)

Computer science

Linguistics

Pose

Spatial contextual awareness

Object (grammar)

Petroleum engineering

Computer vision

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. 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.

Pose-Aware Multi-Level Feature Network for Human Object Interaction Detection