{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:16Z","timestamp":1777865296097,"version":"3.51.4"},"reference-count":85,"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\/iccv51701.2025.00175","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1793-1803","source":"Crossref","is-referenced-by-count":0,"title":["Region-based Cluster Discrimination for Visual Representation Learning"],"prefix":"10.1109","author":[{"given":"Yin","family":"Xie","sequence":"first","affiliation":[{"name":"DeepGlint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaicheng","family":"Yang","sequence":"additional","affiliation":[{"name":"DeepGlint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"An","sequence":"additional","affiliation":[{"name":"DeepGlint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Wu","sequence":"additional","affiliation":[{"name":"DeepGlint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongle","family":"Zhao","sequence":"additional","affiliation":[{"name":"DeepGlint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weimo","family":"Deng","sequence":"additional","affiliation":[{"name":"DeepGlint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zimin","family":"Ran","sequence":"additional","affiliation":[{"name":"University of Technology Sydney"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yumeng","family":"Wang","sequence":"additional","affiliation":[{"name":"DeepGlint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyong","family":"Feng","sequence":"additional","affiliation":[{"name":"DeepGlint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roy","family":"Miles","sequence":"additional","affiliation":[{"name":"Huawei London Research Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ismail","family":"Elezi","sequence":"additional","affiliation":[{"name":"Huawei London Research Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiankang","family":"Deng","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00401"},{"key":"ref3","article-title":"Unicom: Universal and Compact Representation Learning for Image Retrieval","author":"An","year":"2023","journal-title":"ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_25"},{"key":"ref5","article-title":"Self-Labelling via Simultaneous Clustering and Representation Learning","author":"Asano","year":"2020","journal-title":"ICLR"},{"key":"ref6","author":"Bai","year":"2023","journal-title":"Qwen technical report"},{"key":"ref7","author":"Bai","year":"2023","journal-title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond"},{"key":"ref8","author":"Byeon","year":"2022","journal-title":"COYO-700M: Image-Text Pair Dataset"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref11","article-title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","author":"Caron","year":"2020","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01231"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref14","author":"Chen","year":"2024","journal-title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling"},{"key":"ref15","author":"Chiang","year":"2023","journal-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90 ChatGPT Quality"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2025.3618474"},{"key":"ref18","author":"Du","journal-title":"PP-OCR: A Practical Ultra Lightweight OCR System"},{"key":"ref19","volume-title":"Scalable Pre-training of Large Autoregressive Image Models","author":"El-Nouby","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00552"},{"key":"ref21","article-title":"Data Filtering Networks","author":"Fang","year":"2024","journal-title":"ICLR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00901"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.276"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2957464"},{"key":"ref26","author":"Hui","year":"2024","journal-title":"Qwen2.5-Coder Technical Report"},{"key":"ref27","author":"Ilharco","year":"2021","journal-title":"OpenCLIP"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1086"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref32","author":"Li","year":"2024","journal-title":"LLaVA- OneVision: Easy Visual Task Transfer"},{"key":"ref33","article-title":"LLaVA- NeXTInterleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","author":"Li","year":"2025","journal-title":"ICLR"},{"key":"ref34","article-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref35","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref39","author":"Liu","year":"2024","journal-title":"LLaVA- NeXT: Improved reasoning, OCR, and world knowledge"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3573023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref43","article-title":"Decoupled Weight Decay Regularization","author":"Loshchilov","year":"2018","journal-title":"ICLR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_19"},{"key":"ref48","volume-title":"DINOv2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00673"},{"key":"ref50","article-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00286"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02491"},{"key":"ref56","author":"Schuhmann","year":"2021","journal-title":"LAION400M: Open Dataset of CLIP- Filtered 400 Million ImageText Pairs"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref58","author":"Shabtay","year":"2024","journal-title":"LiveXivA Multi-Modal Live Benchmark Based on Arxiv Papers Content"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref60","author":"Sun","year":"2023","journal-title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale"},{"key":"ref61","article-title":"Intern Team","year":"2024","journal-title":"InternLM2 Technical Report"},{"key":"ref62","article-title":"LLaMA Team","year":"2023","journal-title":"LLaMA2: Open Foundation and Fine-Tuned Chat Models"},{"key":"ref63","year":"2024","journal-title":"Qwen Team. Qwen2 Technical Report"},{"key":"ref64","year":"2025","journal-title":"Qwen Team. Qwen2.5-VL Technical Report"},{"key":"ref65","article-title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","author":"Tong","year":"2024","journal-title":"NeurIPS"},{"key":"ref66","author":"Tschannen","year":"2025","journal-title":"SigLIP 2: Multilingual VisionLanguage Encoders with Improved Semantic Understanding, Localization, and Dense Features"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01355"},{"key":"ref68","author":"Wei","year":"2024","journal-title":"LaSagnA: Language-based Segmentation Assistant for Complex Queries"},{"key":"ref69","article-title":"VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks","author":"Wu","year":"2024","journal-title":"NeurIPS"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28428"},{"key":"ref71","author":"Wu","year":"2019","journal-title":"Detectron2"},{"key":"ref72","year":"2024","journal-title":"XAI.ORG. Grok-1.5 Vision Preview"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00273"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i20.35505"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_20"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref79","author":"Yuan","year":"2025","journal-title":"Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"ref82","article-title":"OMG-L LaVA: Bridging Image-level, Object-level, Pixellevel Reasoning and Understanding","author":"Zhang","year":"2024","journal-title":"NeurIPS"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref84","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2024","journal-title":"ICLR"},{"key":"ref85","article-title":"UNIT: Unifying Image and Text Recognition in One Vision Encoder","author":"Zhu","year":"2024","journal-title":"NeurIPS"}],"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\/11444527.pdf?arnumber=11444527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:12:08Z","timestamp":1777529528000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444527\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00175","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}