Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |