{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:30:47Z","timestamp":1772724647352,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"UTD SPIRe"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521838","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:23:06Z","timestamp":1734981786000},"page":"2335-2346","source":"Crossref","is-referenced-by-count":15,"title":["Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9560-702X","authenticated-orcid":false,"given":"Shijian","family":"Deng","sequence":"first","affiliation":[{"name":"Department of Computer Science, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4239-8044","authenticated-orcid":false,"given":"Erin E.","family":"Kosloski","sequence":"additional","affiliation":[{"name":"School of Behavioral and Brain Sciences, The University of Texas at Dallas, Dallas, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3366-6701","authenticated-orcid":false,"given":"Siddhi","family":"Patel","sequence":"additional","affiliation":[{"name":"School of Behavioral and Brain Sciences, The University of Texas at Dallas, Dallas, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeke A.","family":"Barnett","sequence":"additional","affiliation":[{"name":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7218-6228","authenticated-orcid":false,"given":"Yiyang","family":"Nan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Brown University, Providence, RI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Kaplan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sisira","family":"Aarukapalli","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3135-6346","authenticated-orcid":false,"given":"William T.","family":"Doan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harsh","family":"Singh","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8046-2955","authenticated-orcid":false,"given":"Pamela R.","family":"Rollins","sequence":"additional","affiliation":[{"name":"School of Behavioral and Brain Sciences, The University of Texas at Dallas, Dallas, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1423-4513","authenticated-orcid":false,"given":"Yapeng","family":"Tian","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Texas at Dallas, Richardson, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Diagnostic and Statistical Manual of Mental Disorders: DSM-5-TR","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1089\/aut.2020.0014"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10803-019-03927-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/jcpp.13073"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/1362361320971107"},{"key":"ref6","article-title":"M-chat-R\/F: The modified checklist for autism in toddlers, revised with follow-up","author":"Robins","year":"2009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1192\/bjp.2022.13"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2196\/27706"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00598-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/nature12715"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2021.752274"},{"key":"ref12","article-title":"Hello GPT-4O","author":"OpenAI","year":"2024"},{"key":"ref13","first-page":"28541","article-title":"LlaVA-Med: Training a large language-and-vision assistant for biomedicine in one day","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0236939"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.438"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1089\/cyber.2020.29200.ceu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545095"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5383"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2783684"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-35215-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1186\/s13229-018-0198-4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614117"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.103"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.004"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e16763"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS58004.2023.00221"},{"key":"ref27","article-title":"Problem behaviors recognition in videos using language-assisted deep learning model for children with autism","author":"Deng","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5220\/0010839200003124"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025294"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref31","article-title":"Audiovisual slowfast networks for video recognition","author":"Xiao","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00086"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2171334"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127029"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00833"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223688"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3150469"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02194"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01018"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3324498"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00228"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_26"},{"key":"ref46","first-page":"34722","article-title":"Multi-modal grouping network for weakly-supervised audio-visual video parsing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mo","year":"2022"},{"key":"ref47","article-title":"Improving audio-visual video parsing with pseudo visual labels","author":"Zhou","year":"2023"},{"key":"ref48","first-page":"386","article-title":"Audiovisual segmentation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Zhou","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611724"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02261-x"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01524"},{"key":"ref53","article-title":"Separating invisible sounds toward universal audiovisual scene-aware sound separation","author":"Su","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_10"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.630"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref59","article-title":"Audio-visual LLM for video understanding","author":"Shu","year":"2023"},{"key":"ref60","article-title":"VideoLLaMA 2: Advancing spatial-temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024"},{"key":"ref61","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref63","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2023"},{"key":"ref64","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu","year":"2023"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3517625"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3430813"},{"key":"ref68","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang","year":"2022"},{"key":"ref69","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Dai","year":"2023"},{"key":"ref70","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref72","article-title":"The llama 3 herd of models","author":"Llama","year":"2024"},{"key":"ref73","first-page":"72842","article-title":"VAST: A vision-audio-subtitle-text omni-modality foundation model and dataset","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen","year":"2024"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094676"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10812841.pdf?arnumber=10812841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:47:54Z","timestamp":1747158474000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10812841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521838","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}