{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:17:28Z","timestamp":1777889848097,"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\/iccv51701.2025.01927","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"20726-20736","source":"Crossref","is-referenced-by-count":0,"title":["MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning"],"prefix":"10.1109","author":[{"given":"Mattia","family":"Segu","sequence":"first","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marta Tintore","family":"Gazulla","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqin","family":"Xian","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luc","family":"Van Gool","sequence":"additional","affiliation":[{"name":"Sofia University,INSAIT"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref2","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref3","article-title":"End-toend object detection with transformers","author":"Carion","year":"2020","journal-title":"ECCV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2699184"},{"key":"ref5","article-title":"Pix2seq: A language modeling framework for object detection","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref7","article-title":"Palm: Scaling language modeling with pathways","author":"Chowdhery","year":"2023","journal-title":"JMLR"},{"key":"ref8","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL"},{"key":"ref9","article-title":"An image is worth 16 \\times 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref11","article-title":"Unicorn: A unified contrastive learning approach for multi-view molecular representation learning","author":"Feng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref13","article-title":"Fastervit: Fast vision transformers with hierarchical attention","author":"Hatamizadeh","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_7"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref17","article-title":"Big transfer (bit): General visual and textural transfer learning","author":"Kolesnikov","year":"2019","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref19","first-page":"379","article-title":"Open images v5 text annotation and yet another mask text spotter","volume-title":"Asian Conference on Machine Learning","author":"Krylov","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01780"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref23","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","author":"Li","year":"2021","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612260"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref31","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","year":"2022"},{"key":"ref32","first-page":"10550","article-title":"Interactive segmentation as image inpainting","author":"Lu","year":"2023","journal-title":"CVPR"},{"key":"ref33","article-title":"Rt-detrv2: Improved baseline with bag-of-freebies for real-time detection transformer","author":"Lv","year":"2024","journal-title":"arXiv preprint"},{"issue":"14","key":"ref34","first-page":"1114","article-title":"Modeling context between objects for referring expression understanding","volume-title":"Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands","volume":"IV","author":"Varun","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01629-1"},{"key":"ref36","article-title":"Mobilenetv4universal models for the mobile ecosystem","author":"Qin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","author":"Radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref38","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICLR"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref40","article-title":"Grounding dino 1.5: Advance the \u201cedge\u201d of open-set object detection","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Sparse detr: Efficient end-to-end object detection with learnable sparsity","author":"Roh","year":"2021","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"234241","article-title":"U-net: Convolutional networks for biomedical image segmentation","volume-title":"International international conference on medical image computing and computer-assisted intervention","author":"Ronneberger","year":"2017"},{"key":"ref43","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Bdd100k: A large-scale diverse driving video database","volume":"511","author":"Seita","year":"2018","journal-title":"The Berkeley Artificial Intelligence Research Blog. Version"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_13"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref49","article-title":"Ov-dino: Unified open-vocabulary detection with language-aware selective fusion","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref51","first-page":"378","article-title":"Refcoco, refcoco+, and refcocog: A large-scale dataset for referring expression comprehension and generation","volume-title":"European Conference on Computer Vision","author":"Wang","year":"2022"},{"key":"ref52","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","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01060"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00363"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00363"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref57","article-title":"Universal object detection with unified visual-linguistic pre-training","author":"Yan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00529"},{"key":"ref59","article-title":"Efficient detr: improving end-to-end object detector with dense prior","author":"Yao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Glip v2: Unifying localization and vision-language understanding","author":"Zhang","year":"2022","journal-title":"NeurIPS"},{"key":"ref62","article-title":"Segment anything","author":"Zhang","year":"2023","journal-title":"CVPR"},{"key":"ref63","article-title":"Real-time transformer-based open-vocabulary detection with efficient fusion head","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00264"},{"key":"ref67","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01630"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref70","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"}],"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\/11445147.pdf?arnumber=11445147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:20:28Z","timestamp":1777612828000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445147\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01927","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}