{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/boosting-audio-visual-zero-shot-learning-with","title":"Boosting Audio-visual Zero-shot Learning with Large Language Models","arxiv_id":"2311.12268","date":"2023-11-21","proceeding":null,"authors":["Haoxing Chen","Yaohui Li","Yan Hong","Zizheng Huang","Zhuoer Xu","Zhangxuan Gu","Jun Lan","Huijia Zhu","Weiqiang Wang"],"abstract":"Audio-visual zero-shot learning aims to recognize unseen classes based on paired audio-visual sequences. Recent methods mainly focus on learning multi-modal features aligned with class names to enhance the generalization ability to unseen categories. However, these approaches ignore the obscure event concepts in class names and may inevitably introduce complex network structures with difficult training objectives. In this paper, we introduce a straightforward yet efficient framework called KnowleDge-Augmented audio-visual learning (KDA), which aids the model in more effectively learning novel event content by leveraging an external knowledge base. Specifically, we first propose to utilize the knowledge contained in large language models (LLMs) to generate numerous descriptive sentences that include important distinguishing audio-visual features of event classes, which helps to better understand unseen categories. Furthermore, we propose a knowledge-aware adaptive margin loss to help distinguish similar events, further improving the generalization ability towards unseen classes. Extensive experimental results demonstrate that our proposed KDA can outperform state-of-the-art methods on three popular audio-visual zero-shot learning datasets.Our code will be avaliable at \\url{https://github.com/chenhaoxing/KDA}.","url_abs":"https://arxiv.org/abs/2311.12268v2","url_pdf":"https://arxiv.org/pdf/2311.12268v2.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":"boosting-audio-visual-zero-shot-learning-with","repo_url":"https://github.com/chenhaoxing/KDA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"descriptive","task_name":"Descriptive"},{"task_slug":"gzsl-video-classification","task_name":"GZSL Video Classification"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":"audio-visual-learning","task_name":"audio-visual learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/gzsl-video-classification-on-activitynet-gzsl","task":"GZSL Video Classification","dataset":"ActivityNet-GZSL (cls)","model":"KDA","rank_in_archive_order":1,"of":4,"metrics":{"HM":"17.95","ZSL":"11.85"},"uses_additional_data":false},{"leaderboard":"/sota/gzsl-video-classification-on-activitynet-gzsl-1","task":"GZSL Video Classification","dataset":"ActivityNet-GZSL(main)","model":"KDA","rank_in_archive_order":1,"of":7,"metrics":{"HM":"19.67","ZSL":"14.00"},"uses_additional_data":false},{"leaderboard":"/sota/gzsl-video-classification-on-ucf-gzsl-cls","task":"GZSL Video Classification","dataset":"UCF-GZSL (cls)","model":"KDA","rank_in_archive_order":1,"of":4,"metrics":{"HM":"54.84","ZSL":"52.66"},"uses_additional_data":false},{"leaderboard":"/sota/gzsl-video-classification-on-ucf-gzsl-main","task":"GZSL Video Classification","dataset":"UCF-GZSL(main)","model":"KDA","rank_in_archive_order":1,"of":7,"metrics":{"HM":"41.10","ZSL":"28.05"},"uses_additional_data":false},{"leaderboard":"/sota/gzsl-video-classification-on-vggsound-gzsl","task":"GZSL Video Classification","dataset":"VGGSound-GZSL (cls)","model":"KDA","rank_in_archive_order":1,"of":4,"metrics":{"HM":"9.78","ZSL":"8.32"},"uses_additional_data":false},{"leaderboard":"/sota/gzsl-video-classification-on-vggsound-gzsl-1","task":"GZSL Video Classification","dataset":"VGGSound-GZSL(main)","model":"KDA","rank_in_archive_order":1,"of":7,"metrics":{"HM":"10.45","ZSL":"8.43"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.12268","atlas_url":"https://app.syntology.ai/?focus=2311.12268","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2311.12268"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2311.12268\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2311.12268"},"call":"get_concepts_for_paper(arxiv_id=\"2311.12268\")"}],"by_repo":[{"repo":"chenhaoxing/KDA","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d93f408fa29e13cc35242588f586e55f5caf41dd30c3d2ada1321846e9e54d85","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}