Spatial-Temporal Human-Object Interaction Detection
This addresses the need for human-centric video content understanding, though it appears incremental as it builds on existing HOI detection tasks.
The paper tackles the problem of detecting fine-grained human-object interactions and their trajectories in videos, proposing a new task called ST-HOID and a method that outperforms baselines from state-of-the-art approaches.
In this paper, we propose a new instance-level human-object interaction detection task on videos called ST-HOID, which aims to distinguish fine-grained human-object interactions (HOIs) and the trajectories of subjects and objects. It is motivated by the fact that HOI is crucial for human-centric video content understanding. To solve ST-HOID, we propose a novel method consisting of an object trajectory detection module and an interaction reasoning module. Furthermore, we construct the first dataset named VidOR-HOID for ST-HOID evaluation, which contains 10,831 spatial-temporal HOI instances. We conduct extensive experiments to evaluate the effectiveness of our method. The experimental results demonstrate that our method outperforms the baselines generated by the state-of-the-art methods of image human-object interaction detection, video visual relation detection and video human-object interaction recognition.