{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T22:21:39Z","timestamp":1767046899463,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651474","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":3,"title":["SAMS : One-Shot Learning for the Segment Anything Model Using Similar Images"],"prefix":"10.1109","author":[{"given":"Fan","family":"Yin","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifei","family":"Wei","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"General Research Institude Ltd.,China Datang Corporation Science and Technology,Beijing,China,100040"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoyi","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of Electronic Engineering,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2019","author":"Devlin","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","key":"ref1"},{"issue":"1","key":"ref2","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"year":"2023","article-title":"GPT-4 Technical Report","key":"ref3"},{"year":"2023","author":"Touvron","article-title":"LLaMA: Open and Efficient Foundation Language Models","key":"ref4"},{"key":"ref5","first-page":"1877","article-title":"Language Models are Few-Shot Learners","volume-title":"Advances in Neural Information Processing Systems","author":"Brown","year":"2020"},{"key":"ref6","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CVPR52688.2022.01553"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref9","first-page":"12888","article-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Li"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/ICCV51070.2023.00371"},{"year":"2023","author":"Yang","article-title":"Track Anything: Segment Anything Meets Videos","key":"ref11"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/lra.2024.3366013"},{"year":"2023","author":"Liu","article-title":"Grounding DINO: Marrying DINO with Grounded PreTraining for Open-Set Object Detection","key":"ref13"},{"year":"2023","author":"Lai","article-title":"LISA: Reasoning Segmentation via Large Language Model","key":"ref14"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.33540\/2168"},{"year":"2023","author":"Ke","article-title":"Segment Anything in High Quality","key":"ref16"},{"year":"2023","author":"Zhao","article-title":"Fast Segment Anything","key":"ref17"},{"year":"2023","author":"Zhang","article-title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","key":"ref18"},{"year":"2023","author":"Zhou","article-title":"EdgeSAM: Prompt-In-the-Loop Distillation for On-Device Deployment of SAM","key":"ref19"},{"year":"2023","author":"Cen","article-title":"Segment Anything in 3D with NeRFs","key":"ref20"},{"key":"ref21","first-page":"17864","article-title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","volume-title":"Advances in Neural Information Processing Systems","author":"Cheng","year":"2021"},{"key":"ref22","first-page":"24824","article-title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","volume-title":"Advances in Neural Information Processing Systems","author":"Wei","year":"2022"},{"year":"2023","author":"Zhang","article-title":"Personalize Segment Anything Model with One Shot","key":"ref23"},{"year":"2023","author":"Liu","article-title":"Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching","key":"ref24"},{"year":"2023","author":"Hu","article-title":"Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects","key":"ref25"},{"doi-asserted-by":"publisher","key":"ref26","DOI":"10.1007\/978-3-031-20077-9_17"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICCV48922.2021.00986"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/ICCV.2019.00071"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/CVPR42600.2020.00294"},{"year":"2017","author":"Pont-Tuset","article-title":"The 2017 davis challenge on video object segmentation","key":"ref30"},{"volume-title":"CVPR","author":"Min","article-title":"Hypercorrelation squeeze for few-shot segmentation","key":"ref31"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1007\/978-3-031-19818-2_7"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/CVPR52729.2023.00660"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/iccv51070.2023.00110"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.00142","article-title":"Swem: Towards real-time video object segmentation with sequential weighted expectation19 maximization","volume-title":"CVPR","author":"Lin"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1007\/978-3-031-19815-1_37"},{"volume-title":"NIPS","author":"Yang","article-title":"Associating objects with transformers for video object segmentation","key":"ref37"},{"doi-asserted-by":"publisher","key":"ref38","DOI":"10.32604\/cmc.2022.029542"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651474.pdf?arnumber=10651474","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:49:15Z","timestamp":1725950955000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651474\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651474","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}