arrow
返回

Spatial-Net for Human-Object Interaction Detection

delete2022-01-01
delete3
delete
OA
AI
A
Ahmed E. Mansour *
A
Ammar Mohammed
H
Hussein A. Elsayed
S
Salwa Elramly
DOI:10.1109/ACCESS.2022.3199380delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Human-object interaction (HOI) detection is the detection of a human's relationship with an object in still images and videos. The majority of HOI detection methods rely on appearance features as the primary feature for detecting the relationship between humans and objects. Furthermore, the model's performance is affected by the abundance of false-positive pairs generated by the image's non-interactive human-object pairs and human-object mis-grouping. In this paper, we propose Spatial-Net, a new HOI detection approach in still images. In the proposed approach, the HOI problem is divided into two main tasks, namely pair-prediction and global-rejection. In the pair-prediction task, the spatial relationship is adopted to predict the human-object interaction for each human-object pair using spatial features that contains spatial map which is a single channel image that represents human-object pairs including body parts and object masks, relative geometry features such as relative size, relative distance, and intersection-over-union between body part and objects, and weighted distance that is used as body part attention deterministic model. In the global-rejection task, an augmented model is employed to reject false positive pairs. We use the Hungarian matching technique to assign human-object pairs for each action and human-centric model to reject the non-interaction human-object pairs according to semantic co-occurrence between human and object. The experimental results on the V-COCO dataset demonstrate that the proposed Spatial-Net outperforms many state-of-the-art HOI models with less inference time.
Keyword:
Artificial neural network
deep neural network
learning challenges
visual relationship

期刊

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
29.4W

机构

E
egyptian knowledge bank (ekb)
学者数:
11.6W
论文数: 9.3W
被引数: 84
A
Ain Shams University
学者数:
6.4K
论文数: 5.5K
被引数: 8.9K
引用论文

引用论文

err分享
err收藏
Introduction to Polymers
err
IF0
err1981-01-01
err0
PREAI
errRobert J. Young
err分享
err收藏
A Data Mining Approach to Analyze Occupant Behavior Motivation
err2017-01-01
err0
errOAAI
errXinyuyang Ren; Yang Zhao; Wim Zeiler; Gert Boxem; Tingting Li
err分享
err收藏
Modelling the accumulation of hydrophobic organic chemicals in earthworms模拟蚯蚓中疏水性有机化学物质的积累
err1995-07-01
err0
PREAI
errAngélique C. Belfroid; Willem Scinen; Kees C. A. M. van Gestel; Joop L. M. Hermens; Kees J. van Leeuwen
err分享
err收藏
Race differences in the association of spiritual experiences and life satisfaction in older age
err2013-09-01
err0
errOAAI
errKimberly A. Skarupski; George Fitchett; Denis A. Evans; Carlos F. Mendes de Leon
err分享
err收藏
学者 查看更多内容