{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:34Z","timestamp":1777890094851,"version":"3.51.4"},"reference-count":70,"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\/iccv51701.2025.02060","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22187-22198","source":"Crossref","is-referenced-by-count":0,"title":["Mieb: Massive Image Embedding Benchmark"],"prefix":"10.1109","author":[{"given":"Chenghao","family":"Xiao","sequence":"first","affiliation":[{"name":"Durham University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Isaac","family":"Chung","sequence":"additional","affiliation":[{"name":"Zendesk"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Imene","family":"Kerboua","sequence":"additional","affiliation":[{"name":"Esker"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jamie","family":"Stirling","sequence":"additional","affiliation":[{"name":"Durham University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M\u00e1rton","family":"Kardos","sequence":"additional","affiliation":[{"name":"Aarhus University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roman","family":"Solomatin","sequence":"additional","affiliation":[{"name":"ITMO University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noura Al","family":"Moubayed","sequence":"additional","affiliation":[{"name":"Durham University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenneth","family":"Enevoldsen","sequence":"additional","affiliation":[{"name":"Aarhus University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Niklas","family":"Muennighoff","sequence":"additional","affiliation":[{"name":"Contextual AI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","journal-title":"voyage-multimodal-3: all-in-one embedding model for interleaved text, images, and screenshots"},{"key":"ref2","first-page":"32","article-title":"*SEM 2013 shared task: Semantic textual similarity","volume-title":"Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 1: Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarity","author":"Agirre"},{"key":"ref3","author":"Alain","year":"2018","journal-title":"Understanding intermediate layers using linear classifier probes"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref5","first-page":"2370","article-title":"IGLUE: A benchmark for transfer learning across modalities, tasks, and languages","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Bugliarello"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"ref7","article-title":"Bge m3-embedding: Multilingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref11","first-page":"263","article-title":"Automated multi-modality image registration based on information theory","author":"Collignon","year":"1995","journal-title":"Information processing in medical imaging"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1348246.1348248"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","article-title":"An image is worth $16 x 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1276"},{"key":"ref16","author":"Enevoldsen","year":"2025","journal-title":"Mmteb: Massive multilingual text embedding benchmark"},{"key":"ref17","author":"Faysse","year":"2024","journal-title":"Colpali: Efficient document retrieval with vision language models"},{"key":"ref18","article-title":"Datacomp: In search of the next generation of multimodal datasets","volume":"36","author":"Yitzhak Gadre","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.486"},{"key":"ref20","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2019","journal-title":"arXiv preprint"},{"issue":"2","key":"ref22","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403305"},{"key":"ref24","article-title":"Openai o1 system card","author":"Jaech","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.181"},{"key":"ref27","article-title":"Vlm2vec: Training vision-language models for massive multimodal embedding tasks","author":"Jiang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.370"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00277"},{"key":"ref30","article-title":"Jina clip: Your clip model is also your text retriever","author":"Koukounas","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref32","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proceedings of the 40th International Conference on Machine Learning. JMLR.org","author":"Li"},{"key":"ref33","article-title":"MM-EMBED: UNIVERSAL MULTIMODAL RETRIEVAL WITH MULTIMODAL LLMS","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Lin"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref37","article-title":"Retro-search: Exploring untaken paths for deeper and efficient reasoning","author":"Lu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00205"},{"key":"ref39","article-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Sgpt: Gpt sentence embeddings for semantic search","author":"Muennighoff","year":"2022","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"ref42","article-title":"Generative representational instruction tuning","author":"Muennighoff","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1025"},{"key":"ref44","article-title":"Text and code embeddings by contrastive pre-training","author":"Neelakantan","year":"2022","journal-title":"arXiv preprint"},{"key":"ref45","first-page":"1","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research Journal"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(98)00091-0"},{"key":"ref49","article-title":"Bright: A realistic and challenging benchmark for reasoning-intensive retrieval","author":"Su","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Beir: A heterogeneous benchmark for zero-shot evaluation of information retrieval models","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Thakur"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.45"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00517"},{"key":"ref54","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal llms","author":"Tong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","first-page":"22964","article-title":"What language model architecture and pretraining objective works best for zero-shot generalization?","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_23"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00265"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"ref59","article-title":"Pixel sentence representation learning","author":"Xiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Rar-b: Reasoning as retrieval benchmark","author":"Xiao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"C-pack: Packaged resources to advance general chinese embedding","author":"Xiao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Llava-o1: Let vision language models reason step-by-step","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Law of vision representation in mllms","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"The Met dataset: Instance-level recognition for artworks","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Ypsilantis"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01037"},{"key":"ref66","article-title":"When and why visionlanguage models behave like bags-of-words, and what to do about it?","volume-title":"International Conference on Learning Representations","author":"Yuksekgonul"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330739"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref69","author":"Zhang","year":"2024","journal-title":"Gme: Improving universal multimodal retrieval by multimodal 11 ms"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.175"}],"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\/11444592.pdf?arnumber=11444592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:54Z","timestamp":1777613394000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444592\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02060","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}