Saved in:
Bibliographic Details
Main Authors: Liu, Yunze, Chen, Changxi, Wang, Zifan, Yi, Li
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.09057
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911766696427520
author Liu, Yunze
Chen, Changxi
Wang, Zifan
Yi, Li
author_facet Liu, Yunze
Chen, Changxi
Wang, Zifan
Yi, Li
contents This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding. Traditional supervised learning methods encounter limitations due to data scarcity and challenges in label acquisition. To address these issues, we propose a self-supervised learning method that leverages the cross-modal relationship between point cloud videos and image videos to acquire meaningful feature representations. Intra-modal and cross-modal contrastive learning techniques are employed to facilitate effective comprehension of point cloud video. We also propose a multi-level contrastive approach for both modalities. Through extensive experiments, we demonstrate that our method significantly surpasses previous state-of-the-art approaches, and we conduct comprehensive ablation studies to validate the effectiveness of our proposed designs.
format Preprint
id arxiv_https___arxiv_org_abs_2401_09057
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding
Liu, Yunze
Chen, Changxi
Wang, Zifan
Yi, Li
Computer Vision and Pattern Recognition
This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding. Traditional supervised learning methods encounter limitations due to data scarcity and challenges in label acquisition. To address these issues, we propose a self-supervised learning method that leverages the cross-modal relationship between point cloud videos and image videos to acquire meaningful feature representations. Intra-modal and cross-modal contrastive learning techniques are employed to facilitate effective comprehension of point cloud video. We also propose a multi-level contrastive approach for both modalities. Through extensive experiments, we demonstrate that our method significantly surpasses previous state-of-the-art approaches, and we conduct comprehensive ablation studies to validate the effectiveness of our proposed designs.
title CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2401.09057