{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T22:06:09Z","timestamp":1770933969133,"version":"3.50.1"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004835","name":"Science Foundation of Zhejiang Sci-Tech University","doi-asserted-by":"publisher","award":["25222119-Y"],"award-info":[{"award-number":["25222119-Y"]}],"id":[{"id":"10.13039\/501100004835","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcsvt.2025.3588530","type":"journal-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T17:44:27Z","timestamp":1752515067000},"page":"1433-1445","source":"Crossref","is-referenced-by-count":0,"title":["Audio-Visual LLM for Augmenting Accessibility of 360\u00b0 Video"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6733-4967","authenticated-orcid":false,"given":"Yujia","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Zhejiang Sci-Tech University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyun","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.techsoc.2020.101411"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2982142.2982171"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/VR50410.2021.00083"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/2372732215602130"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.61468\/jofdl.v20i1.255"},{"key":"ref6","volume-title":"For Hearing People Only: Answers to Some of the Most Commonly Asked Questions About the Deaf Community, Its Culture, and the \u2018Deaf Reality\u2019","author":"Moore","year":"1992"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2702123.2702393"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2013.6707758"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4324\/9780080575162"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/srep41133"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/01449290600636488"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2016.7591934"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300324"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1090785.1090797"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3517428.3544817"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1353\/aad.2012.1099"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/985921.986048"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2022.102836"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-020-01386-3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2022.102840"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300851"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413894"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445347"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10209-010-0189-5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3026042"},{"key":"ref26","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Kim"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-022-00259-2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2023-914"},{"key":"ref29","article-title":"An encoder\u2013decoder based audio captioning system with transfer and reinforcement learning","volume-title":"arXiv:2108.02752","author":"Mei","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746894"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446343"},{"key":"ref32","article-title":"SLAM-AAC: Enhancing audio captioning with paraphrasing augmentation and CLAP-refine through LLMs","author":"Chen","year":"2024","journal-title":"arXiv:2410.09503"},{"key":"ref33","first-page":"1","article-title":"Beats-based audio captioning model with instructor embedding supervision and ChatGPT mix-up","volume-title":"Proc. Conf. Detection Classification Acoust. Scenes Events, Challenge","author":"Wu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3415112"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3225549"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref37","article-title":"Audio-visual LLM for video understanding","author":"Shu","year":"2023","journal-title":"arXiv:2312.06720"},{"key":"ref38","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_21"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376758"},{"key":"ref41","first-page":"36858","article-title":"Towards versatile embodied navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300276"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376406"},{"key":"ref44","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Chen"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447215"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00278"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094781"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.71"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref51","volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality","author":"Chiang et al","year":"2023"},{"key":"ref52","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dao"},{"key":"ref53","article-title":"PandaGPT: One model to instruction-follow them all","author":"Su","year":"2023","journal-title":"arXiv:2305.16355"},{"key":"ref54","article-title":"Macaw-LLM: Multi-modal language modeling with image, audio, video, and text integration","author":"Lyu","year":"2023","journal-title":"arXiv:2306.09093"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00204"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26527"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3318220"},{"key":"ref63","article-title":"Look, listen, and answer: Overcoming biases for audio-visual question answering","author":"Ma","year":"2024","journal-title":"arXiv:2404.12020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3180592"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127489"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448050"},{"key":"ref69","volume-title":"Katna: Tool for Automating Common Vide Keyframe Extraction and Image AutoCrop Tasks","year":"2019"},{"key":"ref70","article-title":"MAViL: Masked audio-video learners","author":"Huang","year":"2022","journal-title":"arXiv:2212.08071"},{"key":"ref71","article-title":"Contrastive audio-visual masked autoencoder","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Gong"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11392768\/11079707.pdf?arnumber=11079707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:03:00Z","timestamp":1770930180000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11079707\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":71,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3588530","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}