{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:26:52Z","timestamp":1784737612840,"version":"3.55.0"},"reference-count":53,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376283"],"award-info":[{"award-number":["62376283"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.02253","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24309-24318","source":"Crossref","is-referenced-by-count":1,"title":["When Pixel Difference Patterns Meet ViT: PiDiViT for Few-Shot Object Detection"],"prefix":"10.1109","author":[{"given":"Hongliang","family":"Zhou","sequence":"first","affiliation":[{"name":"The College of Electronic Science and Technology, National University of Defense Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"The College of Electronic Science and Technology, National University of Defense Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Canyu","family":"Mo","sequence":"additional","affiliation":[{"name":"The College of Electronic Science and Technology, National University of Defense Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weijie","family":"Li","sequence":"additional","affiliation":[{"name":"The College of Electronic Science and Technology, National University of Defense Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Peng","sequence":"additional","affiliation":[{"name":"The College of Electronic Science and Technology, National University of Defense Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"The College of Electronic Science and Technology, National University of Defense Technology,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3519022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00876"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01207"},{"key":"ref5","first-page":"4013","article-title":"Fewshot object detection with attention-rpn and multi-relation detector","author":"Fan","year":"2020","journal-title":"CVPR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00450"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_15"},{"key":"ref8","article-title":"Openvocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02317"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00325"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19959"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00525"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref14","article-title":"One-shot object detection with co-attention and co-excitation","author":"Hsieh","year":"2019","journal-title":"NeurIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00851"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01384"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3265051"},{"key":"ref19","article-title":"Open-vocabulary object detection upon frozen vision and language models","volume-title":"ICLR","author":"Kuo","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3531988"},{"key":"ref21","article-title":"One-shot object detection without fine-tuning","author":"Li","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2012.01.001"},{"key":"ref24","article-title":"Codet: Co-occurrence guided region-word alignment for open-vocabulary object detection","author":"Ma","year":"2024","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00313"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00818"},{"key":"ref27","article-title":"One-shot instance segmentation","author":"Michaelis","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2002.1017623"},{"key":"ref29","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2448"},{"key":"ref32","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00310"},{"key":"ref34","article-title":"Bird: Learning binary and illumination robust descriptor for face recognition","author":"Su","year":"2019","journal-title":"BMVC"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00507"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3300513"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3583968"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00727"},{"key":"ref40","first-page":"9919","article-title":"Frustratingly simple few-shot object detection","author":"Wang","year":"2020","journal-title":"ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3174072"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00967"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00744"},{"key":"ref46","first-page":"32215","article-title":"Convolutions die hard: Open-vocabulary segmentation with single frozen convolutional clip","author":"Yu","year":"2023","journal-title":"NeurIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref49","article-title":"Detect every thing with few examples","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00745"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3298016"},{"key":"ref52","first-page":"16793","article-title":"Regionclip: Region-based languageimage pretraining","author":"Zhong","year":"2022","journal-title":"CVPR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"}],"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\/11445702.pdf?arnumber=11445702","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:15:25Z","timestamp":1777529725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445702\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02253","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}