{"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/prompting-visual-language-models-for","title":"Prompting Visual-Language Models for Efficient Video Understanding","arxiv_id":"2112.04478","date":"2021-12-08","proceeding":null,"authors":["Chen Ju","Tengda Han","Kunhao Zheng","Ya zhang","Weidi Xie"],"abstract":"Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation. This paper presents a simple but strong baseline to efficiently adapt the pre-trained I-VL model, and exploit its powerful ability for resource-hungry video understanding tasks, with minimal training. Specifically, we propose to optimise a few random vectors, termed as continuous prompt vectors, that convert video-related tasks into the same format as the pre-training objectives. In addition, to bridge the gap between static images and videos, temporal information is encoded with lightweight Transformers stacking on top of frame-wise visual features. Experimentally, we conduct extensive ablation studies to analyse the critical components. On 10 public benchmarks of action recognition, action localisation, and text-video retrieval, across closed-set, few-shot, and zero-shot scenarios, we achieve competitive or state-of-the-art performance to existing methods, despite optimising significantly fewer parameters.","url_abs":"https://arxiv.org/abs/2112.04478v2","url_pdf":"https://arxiv.org/pdf/2112.04478v2.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":"prompting-visual-language-models-for","repo_url":"https://github.com/ju-chen/Efficient-Prompt","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"video-retrieval","task_name":"Video Retrieval"},{"task_slug":"video-understanding","task_name":"Video Understanding"},{"task_slug":"zero-shot-action-detection","task_name":"Zero-Shot Action Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.04478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.04478"}},"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/ju-chen/Efficient-Prompt","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":"98f385d847636a3e","entry":"basic_clean","repo":"ju-chen/Efficient-Prompt","repo_kind":"official","path":"src/clip/simple_tokenizer.py","file_url":"https://github.com/ju-chen/Efficient-Prompt/blob/HEAD/src/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"d919ae32e5e4e616","entry":"get_pairs","repo":"ju-chen/Efficient-Prompt","repo_kind":"official","path":"src/clip/simple_tokenizer.py","file_url":"https://github.com/ju-chen/Efficient-Prompt/blob/HEAD/src/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d919ae32e5e4e616"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"ju-chen/Efficient-Prompt","repo_kind":"official","path":"src/clip/simple_tokenizer.py","file_url":"https://github.com/ju-chen/Efficient-Prompt/blob/HEAD/src/clip/simple_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"4fde7b8d1567b2c6","entry":"build_model","repo":"ju-chen/Efficient-Prompt","repo_kind":"official","path":"src/clip/model.py","file_url":"https://github.com/ju-chen/Efficient-Prompt/blob/HEAD/src/clip/model.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":"4fde7b8d1567b2c6"}},{"code_sha256_prefix":"04fa741687486d3d","entry":"get_videos","repo":"ju-chen/Efficient-Prompt","repo_kind":"official","path":"feat/visfeat.py","file_url":"https://github.com/ju-chen/Efficient-Prompt/blob/HEAD/feat/visfeat.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":"04fa741687486d3d"}},{"code_sha256_prefix":"e57958d4f7945fcc","entry":"load","repo":"ju-chen/Efficient-Prompt","repo_kind":"official","path":"src/clip/clip.py","file_url":"https://github.com/ju-chen/Efficient-Prompt/blob/HEAD/src/clip/clip.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":"e57958d4f7945fcc"}},{"code_sha256_prefix":"b5a6a77a5da30e95","entry":"readtxt","repo":"ju-chen/Efficient-Prompt","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/ju-chen/Efficient-Prompt/blob/HEAD/src/utils.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":"b5a6a77a5da30e95"}},{"code_sha256_prefix":"8597b6dc29aa211d","entry":"setup_dataloader","repo":"ju-chen/Efficient-Prompt","repo_kind":"official","path":"src/config.py","file_url":"https://github.com/ju-chen/Efficient-Prompt/blob/HEAD/src/config.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":"8597b6dc29aa211d"}},{"code_sha256_prefix":"9d146718de7e05be","entry":"setup_path","repo":"ju-chen/Efficient-Prompt","repo_kind":"official","path":"src/config.py","file_url":"https://github.com/ju-chen/Efficient-Prompt/blob/HEAD/src/config.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":"9d146718de7e05be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}