{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:12:28Z","timestamp":1784099548905,"version":"3.55.0"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306061"],"award-info":[{"award-number":["62306061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306090"],"award-info":[{"award-number":["62306090"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171309"],"award-info":[{"award-number":["62171309"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62025604"],"award-info":[{"award-number":["62025604"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62441619"],"award-info":[{"award-number":["62441619"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Guangdong Province of China","award":["2024A1515010147"],"award-info":[{"award-number":["2024A1515010147"]}]},{"name":"Natural Science Foundation of Guangdong Province of China","award":["2514050000889"],"award-info":[{"award-number":["2514050000889"]}]},{"name":"Shenzhen Science and Technology Program","award":["CJGJZD20240729141505007"],"award-info":[{"award-number":["CJGJZD20240729141505007"]}]},{"name":"Guangdong Key Laboratory of Information Security Technology","award":["2023B1212060026"],"award-info":[{"award-number":["2023B1212060026"]}]},{"name":"Guangdong Provincial Key Laboratory","award":["2023B1212060076"],"award-info":[{"award-number":["2023B1212060076"]}]},{"name":"Guangdong Key Laboratory of Information Security Technology, Sun Yat-sen University"},{"name":"SongShan Lake HPC Center"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tpami.2025.3582389","type":"journal-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T14:22:57Z","timestamp":1750861377000},"page":"8674-8690","source":"Crossref","is-referenced-by-count":14,"title":["CAT+: Investigating and Enhancing Audio-Visual Understanding in Large Language Models"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6907-702X","authenticated-orcid":false,"given":"Qilang","family":"Ye","sequence":"first","affiliation":[{"name":"Great Bay University, Dongguan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0422-6616","authenticated-orcid":false,"given":"Zitong","family":"Yu","sequence":"additional","affiliation":[{"name":"Dongguan Key Laboratory for Intelligence and Information Technology, Great Bay University, Dongguan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0090-9604","authenticated-orcid":false,"given":"Rui","family":"Shao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9337-687X","authenticated-orcid":false,"given":"Yawen","family":"Cui","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Kowloon, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3134-0353","authenticated-orcid":false,"given":"Xiangui","family":"Kang","sequence":"additional","affiliation":[{"name":"Guangdong Key Lab of Information Security, School of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2242-6139","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0259-5732","authenticated-orcid":false,"given":"Philip","family":"Torr","sequence":"additional","affiliation":[{"name":"University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7141-708X","authenticated-orcid":false,"given":"Xiaochun","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/wacv51458.2022.00253"},{"key":"ref4","article-title":"VALOR: Vision-audio-language omni-perception pretraining model and dataset","author":"Chen","year":"2023"},{"key":"ref5","article-title":"VAST: A vision-audio-subtitle-text omni-modality foundation model and dataset","author":"Chen","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.178"},{"key":"ref7","article-title":"VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024"},{"key":"ref8","article-title":"Qwen2-audio technical report","author":"Chu","year":"2024"},{"key":"ref9","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3010650"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref14","article-title":"AV-odyssey bench: Can your multimodal LLMs really understand audio-visual information","author":"Gong","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02510"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1434"},{"key":"ref17","article-title":"LoRa: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01300"},{"key":"ref21","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020"},{"key":"ref22","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. 2019 Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Kim"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00257"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1564"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612293"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref30","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref31","article-title":"VideoChat: Chat-centric video understanding","author":"Li","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02095"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_19"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"ref40","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref41","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref42","article-title":"Macaw-LLM: Multi-modal language modeling with image, audio, video, and text integration","author":"Lyu","year":"2023"},{"key":"ref43","article-title":"Vista-LLaMA: Reliable video narrator via equal distance to visual tokens","author":"Ma","year":"2023"},{"key":"ref44","article-title":"VideoGPT: Integrating image and video encoders for enhanced video understanding","author":"Maaz","year":"2024"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref46","first-page":"2285","article-title":"Interactive learning from policy-dependent human feedback","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"MacGlashan"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"ref48","first-page":"211","article-title":"Audio captioning transformer","volume-title":"Proc. 6th Workshop Detection Classification Acoustic Scenes Events","author":"Mei"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746894"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00709"},{"key":"ref51","article-title":"From film to video: Multi-turn question answering with multi-modal context","author":"Nguyen","year":"2018"},{"key":"ref52","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19842-7_41"},{"key":"ref56","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref57","article-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2023"},{"key":"ref58","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Reid","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1437"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01283"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.463"},{"key":"ref63","article-title":"CrossCheckGPT: Universal hallucination ranking for multimodal foundation models","author":"Sun","year":"2024"},{"key":"ref64","first-page":"47198","article-title":"video-SALMONN: Speech-enhanced audio-visual large language models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n18-1074"},{"key":"ref66","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref68","article-title":"MLLM can see? Dynamic correction decoding for hallucination mitigation","author":"Wang","year":"2024"},{"key":"ref69","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s44267-024-00072-9"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref72","article-title":"PLLaVA : Parameter-free LLaVA extension from images to videos for video dense captioning","author":"Xu","year":"2024"},{"key":"ref73","article-title":"Qwen2 technical report","author":"Yang","year":"2024"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548291"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_9"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref78","first-page":"2031","article-title":"Pano-AVQA: Grounded audio-visual question answering on 360$^\\circ$\u2218 videos","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Yun"},{"key":"ref79","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Zeng"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref81","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1162\/coli.a.16"},{"key":"ref83","article-title":"ChatBridge: Bridging modalities with large language model as a language catalyst","author":"Zhao","year":"2023"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11163533\/11050020.pdf?arnumber=11050020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T13:11:26Z","timestamp":1758028286000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11050020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":83,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3582389","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}