Video Visual Relation Detection via 3D Convolutional Neural Network

Video visual relation detection, which aims to detect the visual relations between objects in the form of relation triplet <subject, predicate, object> ( e.g. , "person-ride-bike", "dog-toward-car", etc. ), is a significant and fundamental task in computer vision. However,...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access Vol. 10; pp. 23748 - 23756
Main Authors: Qu, Mingcheng, Cui, Jianxun, Su, Tonghua, Deng, Ganlin, Shao, Wenkai
Format: Journal Article
Language:English
Published: Piscataway IEEE 2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
3D convolutional neural network
Annotations
Artificial neural networks
Computer vision
Convolutional neural networks
Datasets
Feature extraction
Neural networks
Object detection
Object recognition
Task analysis
Three-dimensional displays
Trajectory
Video
video visual relation detection
Visualization
ISSN:2169-3536, 2169-3536
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Video visual relation detection, which aims to detect the visual relations between objects in the form of relation triplet <subject, predicate, object> ( e.g. , "person-ride-bike", "dog-toward-car", etc. ), is a significant and fundamental task in computer vision. However, most of the existing works about visual relation instances are focused on static images. Modeling the non-static relationships in videos has drawn little attention due to lacking large-scale video dataset support. In our work, we propose a video dataset named Video Predicate Detection and Reasoning (VidPDR) for dynamic video visual relation detection, which consists of 1,000 videos with dense manually dynamic labeled annotations on 21 object classes and 37 predicates classes. Moreover, we propose a novel spatio-temporal feature extraction framework with 3D Convolutional Neural Networks (ST3DCNN), which includes three modules 1) object trajectory, 2) short-term relation prediction, and 3) greedy relational association. We conducted appropriate experiments on public datasets and our own dataset (VidPDR). Results demonstrate that our proposed method has a great improvement in comparison to the state-of-the-art baselines.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2022.3154423