{"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/a-clip-hitchhiker-s-guide-to-long-video","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","arxiv_id":"2205.08508","date":"2022-05-17","proceeding":null,"authors":["Max Bain","Arsha Nagrani","Gül Varol","Andrew Zisserman"],"abstract":"Our goal in this paper is the adaptation of image-text models for long video retrieval. Recent works have demonstrated state-of-the-art performance in video retrieval by adopting CLIP, effectively hitchhiking on the image-text representation for video tasks. However, there has been limited success in learning temporal aggregation that outperform mean-pooling the image-level representations extracted per frame by CLIP. We find that the simple yet effective baseline of weighted-mean of frame embeddings via query-scoring is a significant improvement above all prior temporal modelling attempts and mean-pooling. In doing so, we provide an improved baseline for others to compare to and demonstrate state-of-the-art performance of this simple baseline on a suite of long video retrieval benchmarks.","url_abs":"https://arxiv.org/abs/2205.08508v1","url_pdf":"https://arxiv.org/pdf/2205.08508v1.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":"a-clip-hitchhiker-s-guide-to-long-video","repo_url":"https://github.com/m-bain/clip-hitchhiker","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/zero-shot-action-recognition-on-charades-1","task":"Zero-Shot Action Recognition","dataset":"Charades","model":"CLIP-Hitchhiker (ViT-B/16, 32 frames)","rank_in_archive_order":4,"of":4,"metrics":{"mAP":"21.1"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.08508","atlas_url":"https://app.syntology.ai/?focus=2205.08508","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}