{"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/fitclip-refining-large-scale-pretrained-image","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","arxiv_id":"2203.13371","date":"2022-03-24","proceeding":null,"authors":["Santiago Castro","Fabian Caba Heilbron"],"abstract":"Large-scale pretrained image-text models have shown incredible zero-shot performance in a handful of tasks, including video ones such as action recognition and text-to-video retrieval. However, these models have not been adapted to video, mainly because they do not account for the time dimension but also because video frames are different from the typical images (e.g., containing motion blur, and less sharpness). In this paper, we present a fine-tuning strategy to refine these large-scale pretrained image-text models for zero-shot video understanding tasks. We show that by carefully adapting these models we obtain considerable improvements on two zero-shot Action Recognition tasks and three zero-shot Text-to-video Retrieval tasks. The code is available at https://github.com/bryant1410/fitclip","url_abs":"https://arxiv.org/abs/2203.13371v2","url_pdf":"https://arxiv.org/pdf/2203.13371v2.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":"fitclip-refining-large-scale-pretrained-image","repo_url":"https://github.com/bryant1410/fitclip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fitclip-refining-large-scale-pretrained-image","repo_url":"https://github.com/bryant1410/tclip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"text-to-video-retrieval","task_name":"Text to Video Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.13371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13371"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bryant1410/tclip","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bryant1410/fitclip","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c72545d9dfb70811","entry":"nce_loss","repo":"bryant1410/fitclip","repo_kind":"official","path":"aligner/loss.py","file_url":"https://github.com/bryant1410/fitclip/blob/HEAD/aligner/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c72545d9dfb70811"}},{"code_sha256_prefix":"3b1b1e5d067f9b50","entry":"teacher_student_nce_loss","repo":"bryant1410/fitclip","repo_kind":"official","path":"aligner/loss.py","file_url":"https://github.com/bryant1410/fitclip/blob/HEAD/aligner/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b1b1e5d067f9b50"}},{"code_sha256_prefix":"f03eb236feebe458","entry":"wise","repo":"bryant1410/fitclip","repo_kind":"official","path":"aligner/wise.py","file_url":"https://github.com/bryant1410/fitclip/blob/HEAD/aligner/wise.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f03eb236feebe458"}},{"code_sha256_prefix":"69e0855edb30e771","entry":"wise_state_dict","repo":"bryant1410/fitclip","repo_kind":"official","path":"aligner/wise.py","file_url":"https://github.com/bryant1410/fitclip/blob/HEAD/aligner/wise.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"69e0855edb30e771"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}