DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection

2 Oct 2020  ·  Hao-Shu Fang, Yichen Xie, Dian Shao, Cewu Lu ·

Recent years, human-object interaction (HOI) detection has achieved impressive advances. However, conventional two-stage methods are usually slow in inference. On the other hand, existing one-stage methods mainly focus on the union regions of interactions, which introduce unnecessary visual information as disturbances to HOI detection. To tackle the problems above, we propose a novel one-stage HOI detection approach DIRV in this paper, based on a new concept called interaction region for the HOI problem. Unlike previous methods, our approach concentrates on the densely sampled interaction regions across different scales for each human-object pair, so as to capture the subtle visual features that is most essential to the interaction. Moreover, in order to compensate for the detection flaws of a single interaction region, we introduce a novel voting strategy that makes full use of those overlapped interaction regions in place of conventional Non-Maximal Suppression (NMS). Extensive experiments on two popular benchmarks: V-COCO and HICO-DET show that our approach outperforms existing state-of-the-arts by a large margin with the highest inference speed and lightest network architecture. We achieved 56.1 mAP on V-COCO without addtional input. Our code is publicly available at: https://github.com/MVIG-SJTU/DIRV

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Human-Object Interaction Detection HICO-DET DIRV mAP 21.81 # 43
Time Per Frame (ms) 68 # 5
Human-Object Interaction Detection V-COCO DIRV AP(S1) 56.1 # 15
Time Per Frame(ms) 68 # 6

Methods


No methods listed for this paper. Add relevant methods here