{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:37:26Z","timestamp":1783183046331,"version":"3.54.6"},"reference-count":55,"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"}],"funder":[{"DOI":"10.13039\/501100014219","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["62025603"],"award-info":[{"award-number":["62025603"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2037,U22B2051,U23A20383,62176222,62176223,62176226"],"award-info":[{"award-number":["U21B2037,U22B2051,U23A20383,62176222,62176223,62176226"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2021J06003,2022J06001"],"award-info":[{"award-number":["2021J06003,2022J06001"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01843","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19816-19826","source":"Crossref","is-referenced-by-count":1,"title":["Inter2Former: Dynamic Hybrid Attention for Efficient High-Precision Interactive Segmentation"],"prefix":"10.1109","author":[{"given":"You","family":"Huang","sequence":"first","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lichao","family":"Chen","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Ji","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liujuan","family":"Cao","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengchuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongrong","family":"Ji","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00096"},{"key":"ref2","article-title":"Tsaousis","author":"Mirzaee Bafti","year":"2021","journal-title":"A crowdsourcing semi-automatic image segmentation platform for cell biology"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00982"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00136"},{"key":"ref6","author":"Dao","year":"2023","journal-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref8","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy"},{"key":"ref9","article-title":"Image compression with product quantized masked image modeling","author":"El-Nouby","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref12","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1355"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02038"},{"key":"ref19","article-title":"Hrsam: Efficiently segment anything in high-resolution images","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00544"},{"key":"ref21","article-title":"Segment anything in high quality","author":"Ke","year":"2023","journal-title":"NeurIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref23","first-page":"4015","article-title":"Segment any-thing","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Kirillov"},{"key":"ref24","article-title":"Reviving iterative training with mask guidance for interactive segmentation","author":"Konushin","year":"2021","journal-title":"arXiv: Computer Vision and Pattern Recognition"},{"key":"ref25","article-title":"Lisa: Reasoning segmentation via large language model","author":"Lai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00067"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1107\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01335"},{"key":"ref30","article-title":"Transformer-vq: Linear-time transformers via vector quantization","author":"Lingle","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02037"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_42"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00362"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00071"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918"},{"key":"ref39","article-title":"Finite scalar quantization: Vq-vae made simple","author":"Mentzer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref41","article-title":"Self-attention does not need $\\mathrm{o}\\left(\\mathrm{n}^{2}\\right)$ memory","author":"Rabe","year":"2021","journal-title":"CoRR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00865"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref44","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref46","article-title":"Order-aware interactive segmentation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01525"},{"key":"ref49","article-title":"Structured click control in transformer-based interactive segmentation","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.47"},{"key":"ref51","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Faster segment anything: Towards lightweight sam for mobile applications","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI56570.2024.10635518"},{"key":"ref54","article-title":"Image and video tokenization with binary spherical quantization","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02084"}],"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\/11445406.pdf?arnumber=11445406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:01:41Z","timestamp":1777611701000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445406\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01843","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}