{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/context-aware-alignment-and-mutual-masking","title":"Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training","arxiv_id":null,"date":"2023-01-01","proceeding":"CVPR 2023 1","authors":["Zhao Jin","Munawar Hayat","Yuwei Yang","Yulan Guo","Yinjie Lei"],"abstract":"    3D visual language reasoning plays an important role in effective human-computer interaction. The current approaches for 3D visual reasoning are task-specific, and lack pre-training methods to learn generic representations that can transfer across various tasks. Despite the encouraging progress in vision-language pre-training for image-text data, 3D-language pre-training is still an open issue due to limited 3D-language paired data, highly sparse and irregular structure of point clouds and ambiguities in spatial relations of 3D objects with viewpoint changes. In this paper, we present a generic 3D-language pre-training approach, that tackles multiple facets of 3D-language reasoning by learning universal representations. Our learning objective constitutes two main parts. 1) Context aware spatial-semantic alignment to establish fine-grained correspondence between point clouds and texts. It reduces relational ambiguities by aligning 3D spatial relationships with textual semantic context. 2) Mutual 3D-Language Masked modeling to enable cross-modality information exchange. Instead of reconstructing sparse 3D points for which language can hardly provide cues, we propose masked proposal reasoning to learn semantic class and mask-invariant representations. Our proposed 3D-language pre-training method achieves promising results once adapted to various downstream tasks, including 3D visual grounding, 3D dense captioning and 3D question answering. Our codes are available at https://github.com/leolyj/3D-VLP    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2023/html/Jin_Context-Aware_Alignment_and_Mutual_Masking_for_3D-Language_Pre-Training_CVPR_2023_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2023/papers/Jin_Context-Aware_Alignment_and_Mutual_Masking_for_3D-Language_Pre-Training_CVPR_2023_paper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"context-aware-alignment-and-mutual-masking","repo_url":"https://github.com/leolyj/3d-vlp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-dense-captioning","task_name":"3D dense captioning"},{"task_slug":"3d-visual-grounding","task_name":"3D visual grounding"},{"task_slug":"dense-captioning","task_name":"Dense Captioning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[{"method_slug":"aware","method_name":"AWARE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-dense-captioning-on-scanrefer-dataset","task":"3D dense captioning","dataset":"ScanRefer Dataset","model":"3D-VLP","rank_in_archive_order":11,"of":12,"metrics":{"BLEU-4":"31.87","CIDEr":"50.02","METEOR":"24.53","ROUGE-L":"51.17"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}