{"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/vita-clip-video-and-text-adaptive-clip-via","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","arxiv_id":"2304.03307","date":"2023-04-06","proceeding":"CVPR 2023 1","authors":["Syed Talal Wasim","Muzammal Naseer","Salman Khan","Fahad Shahbaz Khan","Mubarak Shah"],"abstract":"Adopting contrastive image-text pretrained models like CLIP towards video classification has gained attention due to its cost-effectiveness and competitive performance. However, recent works in this area face a trade-off. Finetuning the pretrained model to achieve strong supervised performance results in low zero-shot generalization. Similarly, freezing the backbone to retain zero-shot capability causes significant drop in supervised accuracy. Because of this, recent works in literature typically train separate models for supervised and zero-shot action recognition. In this work, we propose a multimodal prompt learning scheme that works to balance the supervised and zero-shot performance under a single unified training. Our prompting approach on the vision side caters for three aspects: 1) Global video-level prompts to model the data distribution; 2) Local frame-level prompts to provide per-frame discriminative conditioning; and 3) a summary prompt to extract a condensed video representation. Additionally, we define a prompting scheme on the text side to augment the textual context. Through this prompting scheme, we can achieve state-of-the-art zero-shot performance on Kinetics-600, HMDB51 and UCF101 while remaining competitive in the supervised setting. By keeping the pretrained backbone frozen, we optimize a much lower number of parameters and retain the existing general representation which helps achieve the strong zero-shot performance. Our codes/models are released at https://github.com/TalalWasim/Vita-CLIP.","url_abs":"https://arxiv.org/abs/2304.03307v1","url_pdf":"https://arxiv.org/pdf/2304.03307v1.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":"vita-clip-video-and-text-adaptive-clip-via","repo_url":"https://github.com/talalwasim/vita-clip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"prompt-learning","task_name":"Prompt Learning"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"zero-shot-action-recognition","task_name":"Zero-Shot Action Recognition"},{"task_slug":"zero-shot-generalization","task_name":"Zero-shot Generalization"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.03307","atlas_url":"https://app.syntology.ai/?focus=2304.03307","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.03307"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/talalwasim/vita-clip","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/TalalWasim/Vita-CLIP","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":5,"unverified":4},"by_repo_kind":{"official":{"samples":9,"ran":5,"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":"a56eadb4eb339fa4","entry":"Attention","repo":"TalalWasim/Vita-CLIP","repo_kind":"official","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a56eadb4eb339fa4"}},{"code_sha256_prefix":"f3a723388670dcd6","entry":"CLIPTextEncoder","repo":"TalalWasim/Vita-CLIP","repo_kind":"official","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f3a723388670dcd6"}},{"code_sha256_prefix":"1a832e4c6c8b2f46","entry":"ImagePatchEmbed2D","repo":"TalalWasim/Vita-CLIP","repo_kind":"official","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a832e4c6c8b2f46"}},{"code_sha256_prefix":"00dbc8b2c1c18083","entry":"Transformer","repo":"TalalWasim/Vita-CLIP","repo_kind":"official","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"00dbc8b2c1c18083"}},{"code_sha256_prefix":"efd12a8a6dd436d0","entry":"TransformerEncoderLayer","repo":"TalalWasim/Vita-CLIP","repo_kind":"official","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"efd12a8a6dd436d0"}},{"code_sha256_prefix":"361eae115fda48da","entry":"CLIPVisionEncoder","repo":"TalalWasim/Vita-CLIP","repo_kind":"official","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","link_basis":"first_harvest_node","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":"361eae115fda48da"}},{"code_sha256_prefix":"e44ed626654a81f6","entry":"TextPromptLearner","repo":"TalalWasim/Vita-CLIP","repo_kind":"official","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","link_basis":"first_harvest_node","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":"e44ed626654a81f6"}},{"code_sha256_prefix":"fece7e5714da3475","entry":"VitaCLIP","repo":"TalalWasim/Vita-CLIP","repo_kind":"official","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","link_basis":"first_harvest_node","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":"fece7e5714da3475"}},{"code_sha256_prefix":"65edded4bd70a9ab","entry":"tokenize","repo":"TalalWasim/Vita-CLIP","repo_kind":"official","path":"training/VitaCLIP_model.py","file_url":"https://github.com/TalalWasim/Vita-CLIP/blob/HEAD/training/VitaCLIP_model.py","link_basis":"first_harvest_node","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":"65edded4bd70a9ab"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}