Diagnosing Rarity in Human-Object Interaction Detection
This addresses the long-tailed recognition challenge in computer vision for HOI detection, but it is incremental as it focuses on analysis rather than a new solution.
The paper tackles the problem of rare human-object interaction categories in HOI detection by diagnosing limiting factors, finding that detection and identification steps are hindered by interaction signals like occlusion and relative location.
Human-object interaction (HOI) detection is a core task in computer vision. The goal is to localize all human-object pairs and recognize their interactions. An interaction defined by a <verb, noun> tuple leads to a long-tailed visual recognition challenge since many combinations are rarely represented. The performance of the proposed models is limited especially for the tail categories, but little has been done to understand the reason. To that end, in this paper, we propose to diagnose rarity in HOI detection. We propose a three-step strategy, namely Detection, Identification and Recognition where we carefully analyse the limiting factors by studying state-of-the-art models. Our findings indicate that detection and identification steps are altered by the interaction signals like occlusion and relative location, as a result limiting the recognition accuracy.