{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:08Z","timestamp":1777865288841,"version":"3.51.4"},"reference-count":63,"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\/iccv51701.2025.02242","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24192-24202","source":"Crossref","is-referenced-by-count":0,"title":["Region-Aware Anchoring Mechanism for Efficient Referring Visual Grounding"],"prefix":"10.1109","author":[{"given":"Shuyi","family":"Ouyang","sequence":"first","affiliation":[{"name":"Zhejiang University,China"}]},{"given":"Ziwei","family":"Niu","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}]},{"given":"Hongyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}]},{"given":"Yen-Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Ritsumeikan University,Japan"}]},{"given":"Lanfen","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University,China"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Shikra: Unleashing multimodal 1lm\u2019s referential dialogue magic","author":"Chen","year":"2023"},{"key":"ref2","volume-title":"An efficient and effective transformer decoder-based framework for multi-task visual grounding","author":"Chen","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref4","volume-title":"Large model based referring camouflaged object detection","author":"Cheng","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27896"},{"key":"ref6","volume-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00179"},{"key":"ref8","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01601"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3217852"},{"key":"ref11","volume-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01525"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2911066"},{"key":"ref14","volume-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00973"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.258"},{"key":"ref19","volume-title":"Lisa: Reasoning segmentation via large language model","author":"Lai","year":"2023"},{"key":"ref20","volume-title":"Otter: A multi-modal model with in-context instruction tuning","author":"Li","year":"2023"},{"key":"ref21","first-page":"19652","article-title":"Referring transformer: A one-step approach to multi-task visual grounding","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01089"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02259"},{"key":"ref24","volume-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00205"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref28","article-title":"Vilbert: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01005"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/144"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2023.3322083"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref38","first-page":"2980","article-title":"Focal loss for dense object detection","volume-title":"proceedings of the IEEE conference on computer vision and pattern recognition","author":"Girshick","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00395"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01045"},{"key":"ref41","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":"ref42","volume-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01180"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref45","volume-title":"Hyperseg: Towards universal visual segmentation with large language model","author":"Wei","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00370"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01605"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01471"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"ref51","first-page":"4683","article-title":"A fast and accurate onestage approach to visual grounding","author":"Yang","year":"2019","journal-title":"CVPR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_30"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2291"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_5"},{"key":"ref60","volume-title":"Bubogpt: Enabling visual grounding in multi-modal 11 ms","author":"Zhao","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_35"},{"key":"ref63","volume-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"}],"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\/11444356.pdf?arnumber=11444356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:11:43Z","timestamp":1777529503000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444356\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02242","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}