{"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/modeling-motion-with-multi-modal-features-for","title":"Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation","arxiv_id":"2204.02547","date":"2022-04-06","proceeding":"CVPR 2022 1","authors":["Wangbo Zhao","Kai Wang","Xiangxiang Chu","Fuzhao Xue","Xinchao Wang","Yang You"],"abstract":"Text-based video segmentation aims to segment the target object in a video based on a describing sentence. Incorporating motion information from optical flow maps with appearance and linguistic modalities is crucial yet has been largely ignored by previous work. In this paper, we design a method to fuse and align appearance, motion, and linguistic features to achieve accurate segmentation. Specifically, we propose a multi-modal video transformer, which can fuse and aggregate multi-modal and temporal features between frames. Furthermore, we design a language-guided feature fusion module to progressively fuse appearance and motion features in each feature level with guidance from linguistic features. Finally, a multi-modal alignment loss is proposed to alleviate the semantic gap between features from different modalities. Extensive experiments on A2D Sentences and J-HMDB Sentences verify the performance and the generalization ability of our method compared to the state-of-the-art methods.","url_abs":"https://arxiv.org/abs/2204.02547v1","url_pdf":"https://arxiv.org/pdf/2204.02547v1.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":"modeling-motion-with-multi-modal-features-for","repo_url":"https://github.com/wangbo-zhao/2022cvpr-mmmmtbvs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-expression-segmentation-on-a2d","task":"Referring Expression Segmentation","dataset":"A2D Sentences","model":"mmmmtbvs","rank_in_archive_order":10,"of":27,"metrics":{"AP":"0.419","IoU mean":"0.558","IoU overall":"0.673","Precision@0.5":"0.645","Precision@0.6":"0.597","Precision@0.7":"0.523","Precision@0.8":"0.375","Precision@0.9":"0.13"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.02547","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}