{"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/multi-level-representation-learning-with","title":"Multi-Level Representation Learning With Semantic Alignment for Referring Video Object Segmentation","arxiv_id":null,"date":"2022-01-01","proceeding":"CVPR 2022 1","authors":["Dongming Wu","Xingping Dong","Ling Shao","Jianbing Shen"],"abstract":"    Referring video object segmentation (RVOS) is a challenging language-guided video grounding task, which requires comprehensively understanding the semantic information of both video content and language queries for object prediction. However, existing methods adopt multi-modal fusion at a frame-based spatial granularity. The limitation of visual representation is prone to causing vision-language mismatching and producing poor segmentation results. To address this, we propose a novel multi-level representation learning approach, which explores the inherent structure of the video content to provide a set of discriminative visual embedding, enabling more effective vision-language semantic alignment. Specifically, we embed different visual cues in terms of visual granularity, including multi-frame long-temporal information at video level, intra-frame spatial semantics at frame level, and enhanced object-aware feature prior at object level. With the powerful multi-level visual embedding and carefully-designed dynamic alignment, our model can generate a robust representation for accurate video object segmentation. Extensive experiments on Refer-DAVIS_ 17  and Refer-YouTube-VOS demonstrate that our model achieves superior performance both in segmentation accuracy and inference speed.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2022/html/Wu_Multi-Level_Representation_Learning_With_Semantic_Alignment_for_Referring_Video_Object_CVPR_2022_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2022/papers/Wu_Multi-Level_Representation_Learning_With_Semantic_Alignment_for_Referring_Video_Object_CVPR_2022_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":[],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"referring-video-object-segmentation","task_name":"Referring Video Object Segmentation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-grounding","task_name":"Video Grounding"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-expression-segmentation-on-refer-1","task":"Referring Expression Segmentation","dataset":"Refer-YouTube-VOS (2021 public validation)","model":"MLRLSA","rank_in_archive_order":30,"of":33,"metrics":{"F":"48.43","J":"50.96","J&F":"49.70"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}