{"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/video-text-retrieval-by-supervised-multi","title":"Video-Text Retrieval by Supervised Sparse Multi-Grained Learning","arxiv_id":"2302.09473","date":"2023-02-19","proceeding":null,"authors":["Yimu Wang","Peng Shi"],"abstract":"While recent progress in video-text retrieval has been advanced by the exploration of better representation learning, in this paper, we present a novel multi-grained sparse learning framework, S3MA, to learn an aligned sparse space shared between the video and the text for video-text retrieval. The shared sparse space is initialized with a finite number of sparse concepts, each of which refers to a number of words. With the text data at hand, we learn and update the shared sparse space in a supervised manner using the proposed similarity and alignment losses. Moreover, to enable multi-grained alignment, we incorporate frame representations for better modeling the video modality and calculating fine-grained and coarse-grained similarities. Benefiting from the learned shared sparse space and multi-grained similarities, extensive experiments on several video-text retrieval benchmarks demonstrate the superiority of S3MA over existing methods. Our code is available at https://github.com/yimuwangcs/Better_Cross_Modal_Retrieval.","url_abs":"https://arxiv.org/abs/2302.09473v2","url_pdf":"https://arxiv.org/pdf/2302.09473v2.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":"video-text-retrieval-by-supervised-multi","repo_url":"https://github.com/yimuwangcs/Better_Cross_Modal_Retrieval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"sparse-learning","task_name":"Sparse Learning"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"video-text-retrieval","task_name":"Video-Text Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-retrieval-on-msr-vtt-1ka","task":"Video Retrieval","dataset":"MSR-VTT-1kA","model":"SuMA (ViT-B/16)","rank_in_archive_order":17,"of":63,"metrics":{"text-to-video R@1":"49.8","text-to-video R@10":"83.9","text-to-video R@5":"75.1","video-to-text R@1":"47.3","video-to-text R@10":"84.3","video-to-text R@5":"76"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2302.09473","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}