Interact as You Intend: Intention-Driven Human-Object Interaction Detection
Citations Over TimeTop 10% of 2019 papers
Abstract
The recent advances in instance-level detection tasks lay strong foundation for genuine comprehension of the visual scenes. However, the ability to fully comprehend a social scene is still in its preliminary stage. In this work, we focus on detecting human-object interactions (HOIs) in social scene images, which is demanding in terms of research and increasingly useful for practical applications. To undertake social tasks interacting with objects, humans direct their attention and move their body based on their intention. Based on this observation, we provide a unique computational perspective to explore human intention in HOI detection. Specifically, the proposed human intention-driven HOI detection (iHOI) framework models human pose with the relative distances from body joints to the object instances. It also utilizes human gaze to guide the attended contextual regions in a weakly-supervised setting. In addition, we propose a hard negative sampling strategy to address the problem of mis-grouping. We perform extensive experiments on two benchmark datasets, namely V-COCO and HICO-DET. The efficacy of each proposed component has also been validated.
Related Papers
- → Messages embedded in gaze of interface agents --- impression management with agent's gaze(2002)114 cited
- → The third gaze: de-constructing the host gaze in the psychoanalysis of tourism.(2012)8 cited
- → Messages embedded in gaze of interface agents --- impression management with agent's gaze(2002)11 cited
- → Emergence of Agent Gaze Behavior using Interactive Kinetics-Based Gaze Direction Model(2020)1 cited
- Theoretical Analysis of the Benchmark for Choosing Manipulative Instruments of Monetary Policies(2009)