Spatial-Temporal Human-Object Interaction Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Xu, He, Yunqing, Ren, Tongwei, Wu, Gangshan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916914243043328
author Sun, Xu
He, Yunqing
Ren, Tongwei
Wu, Gangshan
author_facet Sun, Xu
He, Yunqing
Ren, Tongwei
Wu, Gangshan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17270
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Spatial-Temporal Human-Object Interaction Detection
Sun, Xu
He, Yunqing
Ren, Tongwei
Wu, Gangshan
Computer Vision and Pattern Recognition
Multimedia
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.
title Spatial-Temporal Human-Object Interaction Detection
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2508.17270