{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:20:20Z","timestamp":1778948420185,"version":"3.51.4"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Australian Government Research Training Program (AGRTP) Fee Offset Scholarship"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcsvt.2025.3588892","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T17:44:13Z","timestamp":1752601453000},"page":"12355-12368","source":"Crossref","is-referenced-by-count":6,"title":["Visual and Textual Prompts in VLLMs for Enhancing Emotion Recognition"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0392-5757","authenticated-orcid":false,"given":"Zhifeng","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computing, Australian National University (ANU), Canberra, ACT, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qixuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computing, Australian National University (ANU), Canberra, ACT, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Zhang","sequence":"additional","affiliation":[{"name":"Quriosity Pty Ltd., Melbourne, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjia","family":"Niu","sequence":"additional","affiliation":[{"name":"School of Computing, Australian National University (ANU), Canberra, ACT, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4317-660X","authenticated-orcid":false,"given":"Kaihao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computing, Australian National University (ANU), Canberra, ACT, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7001-5369","authenticated-orcid":false,"given":"Ramesh","family":"Sankaranarayana","sequence":"additional","affiliation":[{"name":"School of Computing, Australian National University (ANU), Canberra, ACT, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sabrina","family":"Caldwell","sequence":"additional","affiliation":[{"name":"School of Computing, Australian National University (ANU), Canberra, ACT, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8356-4909","authenticated-orcid":false,"given":"Tom","family":"Gedeon","sequence":"additional","affiliation":[{"name":"Human-Centric Advancements Chair in AI, Curtin University, Perth, WA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3405406"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647274"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3462433"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CSECS60003.2023.10428424"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3491098"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148707"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3104166"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2867733"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01822"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00149"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78201-5_25"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2689999"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128196"},{"key":"ref14","first-page":"24993","article-title":"Fine-grained visual prompting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang"},{"key":"ref15","first-page":"19769","article-title":"Segment everything everywhere all at once","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zou"},{"key":"ref16","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4 V","author":"Yang","year":"2023","journal-title":"arXiv:2310.11441"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01101"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.357"},{"key":"ref19","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"issue":"240","key":"ref20","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"JMLR"},{"key":"ref21","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref22","article-title":"VideoLLaMA 2: Advancing spatial\u2013temporal modeling and audio understanding in video-LLMs","author":"Cheng","year":"2024","journal-title":"arXiv:2406.07476"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261659"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3034233"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3416732"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128681"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222871"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.26599\/BDMA.2024.9020048"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112094"},{"key":"ref31","article-title":"VLLMs provide better context for emotion understanding through common sense reasoning","author":"Xenos","year":"2024","journal-title":"arXiv:2404.07078"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01821"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109780"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.12.017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111429"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2024.103749"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28034"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01083"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.257"},{"key":"ref40","first-page":"11809","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yao"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3557474"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01326"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s42761-023-00191-4"},{"key":"ref45","article-title":"Qwen2-VL: Enhancing vision-language Model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0614"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref48","volume-title":"Llava-next: A Strong Zero-shot Video Understanding Model","author":"Zhang et al","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.17671\/gazibtd.1399077"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413620"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11278843\/11080038.pdf?arnumber=11080038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T06:41:01Z","timestamp":1765262461000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11080038\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":50,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3588892","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}