# CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding Source: [CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding]() Collection index: [llms.txt]() Data updated: 2025-10-26T02:16:25.405Z Authors: Yunze Liu, Changxi Chen, Zifan Wang, Li Yi Published: 2024-01-17T08:46:47.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Action Segmentation on HOI4D official (test)](): Action Segmentation; HOI4D official (test); Accuracy: 83.7. ## Original sources and implementation [Original paper]() [PDF]()