人間の手をプローブとしたインタラクティブ物体理解
Human Hands as Probes for Interactive Object Understanding
一人称視点動画で人間の手の動きを観察するだけで、物体の状態に敏感な特徴とアフォーダンス（相互作用領域や把持可能な形）を学習できることを示した論文。
著者: Mohit Goyal, Sahil Modi, Rishabh Goyal, Saurabh Gupta
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
Interactive object understanding, or what we can do to objects and how is a long-standing goal of computer vision. In this paper, we tackle this problem through observation of human hands in in-the-wild egocentric videos. We demonstrate that observation of what human hands interact with and how can provide both the relevant data and the necessary supervision. Attending to hands, readily localizes and stabilizes active objects for learning and reveals places where interactions with objects occur. Analyzing the hands shows what we can do to objects and how. We apply these basic principles on the EPIC-KITCHENS dataset, and successfully learn state-sensitive features, and object affordances (regions of interaction and afforded grasps), purely by observing hands in egocentric videos.
