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

10/02/2020
by   Hao-Shu Fang, et al.
0

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 will be made publicly available.

READ FULL TEXT

page 1

page 3

page 5

page 11

page 13

research
08/11/2021

Mining the Benefits of Two-stage and One-stage HOI Detection

Two-stage methods have dominated Human-Object Interaction (HOI) detectio...
research
03/31/2020

Learning Human-Object Interaction Detection using Interaction Points

Understanding interactions between humans and objects is one of the fund...
research
12/01/2021

Human-Object Interaction Detection via Weak Supervision

The goal of this paper is Human-object Interaction (HO-I) detection. HO-...
research
07/05/2022

Distance Matters in Human-Object Interaction Detection

Human-Object Interaction (HOI) detection has received considerable atten...
research
02/07/2017

An Implementation of Faster RCNN with Study for Region Sampling

We adapted the join-training scheme of Faster RCNN framework from Caffe ...
research
02/24/2022

Effective Actor-centric Human-object Interaction Detection

While Human-Object Interaction(HOI) Detection has achieved tremendous ad...
research
01/09/2023

Parallel Reasoning Network for Human-Object Interaction Detection

Human-Object Interaction (HOI) detection aims to learn how human interac...

Please sign up or login with your details

Forgot password? Click here to reset