{"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/kronecker-mask-and-interpretive-prompts-are","title":"Kronecker Mask and Interpretive Prompts are Language-Action Video Learners","arxiv_id":"2502.03549","date":"2025-02-05","proceeding":null,"authors":["Jingyi Yang","Zitong Yu","Xiuming Ni","Jia He","Hui Li"],"abstract":"Contrastive language-image pretraining (CLIP) has significantly advanced image-based vision learning. A pressing topic subsequently arises: how can we effectively adapt CLIP to the video domain? Recent studies have focused on adjusting either the textual or visual branch of CLIP for action recognition. However, we argue that adaptations of both branches are crucial. In this paper, we propose \\textbf{CLAVER}: a \\textbf{C}ontrastive \\textbf{L}anguage-\\textbf{A}ction \\textbf{V}ideo Learn\\textbf{er}, designed to shift CLIP's focus from the alignment of static visual objects and concrete nouns to the alignment of dynamic action behaviors and abstract verbs. Specifically, we introduce a novel Kronecker mask attention for temporal modeling. Our tailored Kronecker mask offers three benefits 1) it expands the temporal receptive field for each token, 2) it serves as an effective spatiotemporal heterogeneity inductive bias, mitigating the issue of spatiotemporal homogenization, and 3) it can be seamlessly plugged into transformer-based models. Regarding the textual branch, we leverage large language models to generate diverse, sentence-level and semantically rich interpretive prompts of actions, which shift the model's focus towards the verb comprehension. Extensive experiments on various benchmarks and learning scenarios demonstrate the superiority and generality of our approach. The code will be available soon.","url_abs":"https://arxiv.org/abs/2502.03549v2","url_pdf":"https://arxiv.org/pdf/2502.03549v2.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":"kronecker-mask-and-interpretive-prompts-are","repo_url":"https://github.com/yjyddq/CLAVER","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"focus","method_name":"Focus"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.03549","atlas_url":"https://app.syntology.ai/?focus=2502.03549","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.03549"}},"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":"deterministic:regex_extraction","url":"https://github.com/yjyddq/CLAVER","reach":null}],"summary":{"ran":9,"unverified":2},"by_repo_kind":{"official":{"samples":11,"ran":9,"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":11,"samples":[{"code_sha256_prefix":"ea3373815e1a7a63","entry":"CLIP","repo":"yjyddq/CLAVER","repo_kind":"official","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea3373815e1a7a63"}},{"code_sha256_prefix":"02c3d66d7386b4ce","entry":"DropPath","repo":"yjyddq/CLAVER","repo_kind":"official","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"02c3d66d7386b4ce"}},{"code_sha256_prefix":"07f83dd5e1159854","entry":"LayerNorm","repo":"yjyddq/CLAVER","repo_kind":"official","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"07f83dd5e1159854"}},{"code_sha256_prefix":"23a40303b56bf120","entry":"ResidualAttentionBlock","repo":"yjyddq/CLAVER","repo_kind":"official","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"23a40303b56bf120"}},{"code_sha256_prefix":"923f5373bf4e3656","entry":"SpatialAttentionBlock","repo":"yjyddq/CLAVER","repo_kind":"official","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"923f5373bf4e3656"}},{"code_sha256_prefix":"0ed72504b4471f32","entry":"SpatialTransformer","repo":"yjyddq/CLAVER","repo_kind":"official","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ed72504b4471f32"}},{"code_sha256_prefix":"404e08757bf09cdc","entry":"TemporalAttentionBlock","repo":"yjyddq/CLAVER","repo_kind":"official","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"404e08757bf09cdc"}},{"code_sha256_prefix":"1df85a83617ec2e9","entry":"TemporalTransformer","repo":"yjyddq/CLAVER","repo_kind":"official","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1df85a83617ec2e9"}},{"code_sha256_prefix":"54f791f044d7891c","entry":"Transformer","repo":"yjyddq/CLAVER","repo_kind":"official","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"54f791f044d7891c"}},{"code_sha256_prefix":"ecee626d87b97fac","entry":"CLAVER","repo":"yjyddq/CLAVER","repo_kind":"official","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ecee626d87b97fac"}},{"code_sha256_prefix":"33ddf59a02be66bf","entry":"VideoVisionTransformer","repo":"yjyddq/CLAVER","repo_kind":"official","path":"models/claver.py","file_url":"https://github.com/yjyddq/CLAVER/blob/HEAD/models/claver.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"33ddf59a02be66bf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}