{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["11"],"submitter":["Wang F"],"pubmed_abstract":["We propose a self-supervised point cloud representation learning framework CrossAlignNet based on cross-modal mask alignment strategy, to solve the problems of imbalance between global semantic and local geometric feature learning, as well as cross-modal information asymmetry in existing methods. A geometrically consistent mask region is established between the point cloud patches and the corresponding image patches through a synchronized mask alignment strategy to ensure cross-modal information symmetry. A dual-task learning framework is designed: the global semantic alignment task enhances the cross-modal semantic consistency through contrastive learning, and the local mask reconstruction task fuses the image cues using the cross-attention mechanism to recover the local geometric structu"],"journal":["PeerJ. Computer science"],"pagination":["e3194"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12453720"],"repository":["biostudies-literature"],"pubmed_title":["CrossAlignNet: a self-supervised feature learning framework for 3D point cloud understanding."],"pmcid":["PMC12453720"],"pubmed_authors":["Zhang W","Wu J","Dong X","Wang F","Zhou T"],"additional_accession":[]},"is_claimable":false,"name":"CrossAlignNet: a self-supervised feature learning framework for 3D point cloud understanding.","description":"We propose a self-supervised point cloud representation learning framework CrossAlignNet based on cross-modal mask alignment strategy, to solve the problems of imbalance between global semantic and local geometric feature learning, as well as cross-modal information asymmetry in existing methods. A geometrically consistent mask region is established between the point cloud patches and the corresponding image patches through a synchronized mask alignment strategy to ensure cross-modal information symmetry. A dual-task learning framework is designed: the global semantic alignment task enhances the cross-modal semantic consistency through contrastive learning, and the local mask reconstruction task fuses the image cues using the cross-attention mechanism to recover the local geometric structu","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025","modification":"2026-04-30T03:15:41.994Z","creation":"2026-04-30T03:11:13.519Z"},"accession":"S-EPMC12453720","cross_references":{"pubmed":["40989413"],"doi":["10.7717/peerj-cs.3194"]}}