{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:24:26Z","timestamp":1777890266636,"version":"3.51.4"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02035","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21917-21926","source":"Crossref","is-referenced-by-count":0,"title":["Triad: Empowering LMM-Based Anomaly Detection with Expert-Guided Region-of-Interest Tokenizer and Manufacturing Process"],"prefix":"10.1109","author":[{"given":"Yuanze","family":"Li","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology"}]},{"given":"Shihao","family":"Yuan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}]},{"given":"Haolin","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}]},{"given":"Qizhang","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}]},{"given":"Ming","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}]},{"given":"Chen","family":"Xu","sequence":"additional","affiliation":[{"name":"Pengcheng Lab,Guangzhou"}]},{"given":"Guangming","family":"Shi","sequence":"additional","affiliation":[{"name":"Pengcheng Lab,Guangzhou"}]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01578-9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_3"},{"key":"ref7","article-title":"April-gan: A zero-\/few-shot anomaly classification and segmentation method for cvpr 2023 vand workshop challenge tracks 1&2: 1st place on zero-shot ad and 4th place on few-shot ad","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-9003-6_2"},{"key":"ref9","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27963"},{"key":"ref11","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01878"},{"key":"ref13","article-title":"Mmad: The comprehensive benchmark for multimodal large language models in industrial anomaly detection","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Jiang","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01359"},{"key":"ref15","article-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref18","article-title":"Musc: Zero-shot industrial anomaly classification and segmentation with mutual scoring of the unlabeled images","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li","year":"2024"},{"key":"ref19","article-title":"Myriad: Large multimodal model by applying vision experts for industrial anomaly detection","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293772"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref22","article-title":"Llava-next: Improved reasoning, ocr, and world knowledge, 2024","author":"Liu","journal-title":"1"},{"key":"ref23","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01954"},{"key":"ref26","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov","year":"2017"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02348"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02159"},{"key":"ref31","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Customizing visual-language foundation models for multi-modal anomaly detection and reasoning","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73209-6_1"},{"key":"ref34","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref36","article-title":"Draema discriminatively trained reconstruction embedding for surface anomaly detection","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Zavrtanik","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref38","article-title":"Ferretv2: An improved baseline for referring and grounding with large language models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01580"},{"key":"ref40","article-title":"Anomalyclip: Object-agnostic prompt learning for zero-shot anomaly detection","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhou","year":"2023"},{"key":"ref41","first-page":"392","article-title":"Spot-the-difference self-supervised pretraining for anomaly detection and segmentation","volume-title":"European Conference on Computer Vision","author":"Zou","year":"2022"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446142.pdf?arnumber=11446142","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:23Z","timestamp":1777613603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446142\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02035","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}