VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions

Comprehensive visual understanding requires detection frameworks that can effectively learn and utilize object interactions while analyzing objects individually. This is the main objective in Human-Object Interaction (HOI) detection task. In particular, relative spatial reasoning and structural conn...

Full description

Saved in:
Bibliographic Details
Main Authors: Ulutan, Oytun, Iftekhar, A S M, Manjunath, B. S.
Format: Conference Proceeding
Language:English
Subjects:
Convolutional codes
Feature extraction
Image edge detection
Object detection
Proposals
Task analysis
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Comprehensive visual understanding requires detection frameworks that can effectively learn and utilize object interactions while analyzing objects individually. This is the main objective in Human-Object Interaction (HOI) detection task. In particular, relative spatial reasoning and structural connections between objects are essential cues for analyzing interactions, which is addressed by the proposed Visual-Spatial-Graph Network (VSGNet) architecture. VSGNet extracts visual features from the human-object pairs, refines the features with spatial configurations of the pair, and utilizes the structural connections between the pair via graph convolutions. The performance of VSGNet is thoroughly evaluated using the Verbs in COCO (V-COCO) dataset. Experimental results indicate that VSGNet outperforms state-of-the-art solutions by 8% or 4 mAP.
ISSN:2575-7075
DOI:10.1109/CVPR42600.2020.01363