{"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/verbs-in-action-improving-verb-understanding","title":"Verbs in Action: Improving verb understanding in video-language models","arxiv_id":"2304.06708","date":"2023-04-13","proceeding":"ICCV 2023 1","authors":["Liliane Momeni","Mathilde Caron","Arsha Nagrani","Andrew Zisserman","Cordelia Schmid"],"abstract":"Understanding verbs is crucial to modelling how people and objects interact with each other and the environment through space and time. Recently, state-of-the-art video-language models based on CLIP have been shown to have limited verb understanding and to rely extensively on nouns, restricting their performance in real-world video applications that require action and temporal understanding. In this work, we improve verb understanding for CLIP-based video-language models by proposing a new Verb-Focused Contrastive (VFC) framework. This consists of two main components: (1) leveraging pretrained large language models (LLMs) to create hard negatives for cross-modal contrastive learning, together with a calibration strategy to balance the occurrence of concepts in positive and negative pairs; and (2) enforcing a fine-grained, verb phrase alignment loss. Our method achieves state-of-the-art results for zero-shot performance on three downstream tasks that focus on verb understanding: video-text matching, video question-answering and video classification. To the best of our knowledge, this is the first work which proposes a method to alleviate the verb understanding problem, and does not simply highlight it.","url_abs":"https://arxiv.org/abs/2304.06708v1","url_pdf":"https://arxiv.org/pdf/2304.06708v1.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":"verbs-in-action-improving-verb-understanding","repo_url":"https://github.com/google-research/scenic/tree/main/scenic/projects/verbs_in_action","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-matching","task_name":"Text Matching"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"zeroshot-video-question-answer","task_name":"Zero-Shot Video Question Answer"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-next-qa","task":"Video Question Answering","dataset":"NExT-QA","model":"VFC","rank_in_archive_order":39,"of":47,"metrics":{"Accuracy":"58.6"},"uses_additional_data":true},{"leaderboard":"/sota/zero-shot-video-question-answer-on-next-qa","task":"Zero-Shot Video Question Answer","dataset":"NExT-QA","model":"VFC","rank_in_archive_order":26,"of":27,"metrics":{"Accuracy":"51.5"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2304.06708","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06708"}},"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/google-research/scenic/tree/main/scenic/projects/verbs_in_action","reach":null}],"summary":{"ran_fixture":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"c69cabcefea1515a","entry":"get_contrastive_labels","repo":"google-research/scenic","repo_kind":"official","path":"scenic/projects/verbs_in_action/losses.py","file_url":"https://github.com/google-research/scenic/blob/HEAD/scenic/projects/verbs_in_action/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c69cabcefea1515a"}},{"code_sha256_prefix":"565678aafb6bf2e9","entry":"hn_nce_loss_with_hardnegs","repo":"google-research/scenic","repo_kind":"official","path":"scenic/projects/verbs_in_action/losses.py","file_url":"https://github.com/google-research/scenic/blob/HEAD/scenic/projects/verbs_in_action/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"565678aafb6bf2e9"}},{"code_sha256_prefix":"f9dbdd085cd8749d","entry":"verb_hard_neg_nce","repo":"google-research/scenic","repo_kind":"official","path":"scenic/projects/verbs_in_action/losses.py","file_url":"https://github.com/google-research/scenic/blob/HEAD/scenic/projects/verbs_in_action/losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f9dbdd085cd8749d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}