{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T20:28:43Z","timestamp":1783542523707,"version":"3.55.0"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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":["62572097"],"award-info":[{"award-number":["62572097"]}],"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":["U23A20315"],"award-info":[{"award-number":["U23A20315"]}],"id":[{"id":"10.13039\/501100001809","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":[[2026,7]]},"DOI":"10.1109\/tcsvt.2026.3672052","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:00:35Z","timestamp":1773086435000},"page":"9646-9659","source":"Crossref","is-referenced-by-count":0,"title":["MATCH: Multi-Agentic Evidence Grounding for Explainable Hate Video Detection"],"prefix":"10.1109","volume":"36","author":[{"given":"Kaiju","family":"Li","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4977-1657","authenticated-orcid":false,"given":"Rongpei","family":"Hong","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0876-0497","authenticated-orcid":false,"given":"Jian","family":"Lang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8038-8150","authenticated-orcid":false,"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680663"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681595"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3474101"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3337838"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3500868.3559465"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v17i1.22209"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681521"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714534"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref11","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025","journal-title":"arXiv:2502.13923"},{"key":"ref12","first-page":"1","article-title":"LLaVA-OneVision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.685"},{"key":"ref15","article-title":"Hallucination mitigation prompts long-term video understanding","author":"Sun","year":"2024","journal-title":"arXiv:2406.11333"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref17","first-page":"2611","article-title":"The hateful memes challenge: Detecting hate speech in multimodal memes","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Kiela"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.246"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612498"},{"key":"ref20","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. (ICML)","author":"Li"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/UEMCON53757.2021.9666550"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IALP54817.2021.9675250"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI51800.2020.00104"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5254.708428"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.29172\/7c2a6982-6d72-4cd8-bba6-2fccb06a7011"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645381"},{"key":"ref28","first-page":"1","article-title":"Self-evolving multi-agent networks for software development","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref29","first-page":"1","article-title":"ImProver: Agent-based automated proof optimization","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Ahuja"},{"key":"ref30","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Bosma"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3571422"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.992"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.705"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2317887"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.269"},{"key":"ref37","first-page":"1","article-title":"ChatEval: Towards better LLM-based evaluators through multi-agent debate","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chan"},{"key":"ref38","first-page":"1","article-title":"MetaGPT: Meta programming for a multi-agent collaborative framework","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Hong"},{"key":"ref39","article-title":"Multi-agent collaboration: Harnessing the power of intelligent LLM agents","author":"Talebirad","year":"2023","journal-title":"arXiv:2306.03314"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.810"},{"key":"ref41","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref42","article-title":"PP-OCRv3: More attempts for the improvement of ultra lightweight OCR system","author":"Li","year":"2022","journal-title":"arXiv:2206.03001"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1980.1163420"},{"key":"ref45","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW65004.2024.00030"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.291"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3648145"},{"key":"ref51","article-title":"Phi-4-mini technical report: Compact yet powerful multimodal language models via mixture-of-LoRAs","author":"Abouelenin","year":"2025","journal-title":"arXiv:2503.01743"},{"key":"ref52","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv:2410.21276"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"ref54","article-title":"Qwen2.5 technical report","author":"Yang","year":"2024","journal-title":"arXiv:2412.15115"},{"key":"ref55","article-title":"GPT-5 system card","author":"Singh","year":"2025","journal-title":"arXiv:2501.06035"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645471"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/694"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.9734\/BJAST\/2015\/14975"},{"key":"ref59","article-title":"Gemma 3 technical report","author":"Team","year":"2025","journal-title":"arXiv:2503.19786"},{"issue":"86","key":"ref60","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcm.2016.02.012"},{"key":"ref62","first-page":"1","article-title":"Human simulacra: Benchmarking the personification of large language models","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Xie"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11598845\/11424606.pdf?arnumber=11424606","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T19:45:51Z","timestamp":1783539951000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11424606\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":62,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3672052","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}