{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T16:00:14Z","timestamp":1783440014434,"version":"3.54.6"},"reference-count":86,"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\/iccv51701.2025.02160","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23267-23278","source":"Crossref","is-referenced-by-count":3,"title":["HiMTok: Learning Hierarchical Mask Tokens for Image Segmentation with Large Multimodal Model"],"prefix":"10.1109","author":[{"given":"Tao","family":"Wang","sequence":"first","affiliation":[{"name":"Uni-Ubi"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changxu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Uni-Ubi"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Senda","family":"Chen","sequence":"additional","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wuyue","family":"Zhao","sequence":"additional","affiliation":[{"name":"Uni-Ubi"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_11"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1813"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00132"},{"key":"ref5","article-title":"Shikra: Unleashing multimodal 11 m\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2272"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_19"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01444"},{"key":"ref11","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref15","author":"Conover","year":"2023","journal-title":"Free dolly: Introducing the world\u2019s first truly open instruction-tuned 11 m"},{"key":"ref16","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref19","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.670"},{"key":"ref21","first-page":"arXiv-2402","article-title":"Allava: Harnessing gpt4v-synthesized data for a lite vision-language model","author":"Hardy Chen","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref28","article-title":"What matters when building vision-language models?","author":"Lauren\u00e7on","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref30","article-title":"Aria: An open multimodal native mixture-ofexperts model","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01789"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4187-3"},{"key":"ref39","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref41","article-title":"Orca-math: Unlocking the potential of slms in grade school math","author":"Mitra","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_17"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01335"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref46","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref48","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_16"},{"key":"ref52","first-page":"240","article-title":"Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017, Held in Conjunction with MICCAI 2017","author":"Carole","year":"2017"},{"key":"ref53","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Neural discrete representation learning","volume":"30","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref56","first-page":"23318","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref57","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":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2688"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3860"},{"key":"ref60","article-title":"Lasagna: Language-based segmentation assistant for complex queries","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","first-page":"69925","article-title":"Visionllm v2: An end-to-end generalist multimodal large language model for hundreds of visionlanguage tasks","volume":"37","author":"Wu","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref62","article-title":"Deepseek-vl2: Mixture-ofexperts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3233\/faia240541"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_6"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00254"},{"key":"ref67","article-title":"An improved baseline for reasoning segmentation with large language model","author":"Yang","year":"2023","journal-title":"CoRR"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref69","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv preprint"},{"issue":"3","key":"ref71","first-page":"5","article-title":"Scaling autoregressive models for content-rich text-to-image generation","volume":"2","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref73","article-title":"Metamath: Bootstrap your own mathematical questions for large language models","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"An image is worth 32 tokens for reconstruction and generation","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"Mammoth: Building math generalist models through hybrid instruction tuning","author":"Yue","year":"2023","journal-title":"arXiv preprint"},{"key":"ref76","article-title":"Omg-llava: Bridging image-level, object-level, pixel-level reasoning and understanding","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01349"},{"key":"ref78","first-page":"74","article-title":"Psalm: Pixelwise segmentation with large multi-modal model","volume-title":"European Conference on Computer Vision","author":"Zhang"},{"key":"ref79","article-title":"Svit: Scaling up visual instruction tuning","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.762"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00296"},{"key":"ref85","article-title":"Addressing representation collapse in vector quantized models with one linear layer","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0868"}],"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\/11444277.pdf?arnumber=11444277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:50:54Z","timestamp":1777611054000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02160","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}