{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:56:20Z","timestamp":1783439780578,"version":"3.54.6"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62425603"],"award-info":[{"award-number":["62425603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005145","name":"Basic Research Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20240011"],"award-info":[{"award-number":["BK20240011"]}],"id":[{"id":"10.13039\/501100005145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005145","name":"Basic Research Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20243018"],"award-info":[{"award-number":["BK20243018"]}],"id":[{"id":"10.13039\/501100005145","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3554410","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T23:53:17Z","timestamp":1743465197000},"page":"2147-2160","source":"Crossref","is-referenced-by-count":17,"title":["Exploring Effective Factors for Improving Visual In-Context Learning"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6249-5596","authenticated-orcid":false,"given":"Yanpeng","family":"Sun","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Visual Technology Department, Baidu, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wang","sequence":"additional","affiliation":[{"name":"Visual Technology Department, Baidu, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingdong","family":"Wang","sequence":"additional","affiliation":[{"name":"Visual Technology Department, Baidu, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5341-5985","authenticated-orcid":false,"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref2","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref6","first-page":"30583","article-title":"What can transformers learn in-context? A case study of simple function classes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Garg"},{"key":"ref7","article-title":"An explanation of in-context learning as implicit Bayesian inference","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref8","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref12","first-page":"25005","article-title":"Visual prompting via image inpainting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bar"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.191"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.759"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.201"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.365"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.192"},{"key":"ref19","article-title":"Least-to-Most prompting enables complex reasoning in large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref20","first-page":"17773","article-title":"What makes good examples for visual in-context learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref22","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bao"},{"key":"ref23","first-page":"3843","article-title":"Solving quantitative reasoning problems with language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lewkowycz"},{"key":"ref24","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ouyang"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.260"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.53"},{"key":"ref27","article-title":"Using natural language prompts for machine translation","author":"Garcia","year":"2022","journal-title":"arXiv:2202.11822"},{"key":"ref28","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Devlin"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.378"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6319"},{"key":"ref31","article-title":"Self-generated in-context learning: Leveraging auto-regressive language models as a demonstration generator","author":"Kim","year":"2022","journal-title":"arXiv:2206.08082"},{"key":"ref32","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref33","first-page":"42382","article-title":"Explore in-context learning for 3D point cloud understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00236"},{"key":"ref35","first-page":"26295","article-title":"UViM: A unified modeling approach for vision with learned guiding codes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kolesnikov"},{"key":"ref36","article-title":"Pix2seq: A language modeling framework for object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Chen"},{"key":"ref37","article-title":"Unified-IO: A unified model for vision, language, and multi-modal tasks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lu"},{"key":"ref38","article-title":"Point-In-context: Understanding point cloud via in-context learning","author":"Liu","year":"2024","journal-title":"arXiv:2404.12352"},{"key":"ref39","article-title":"Spider: A unified framework for context-dependent concept segmentation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.380"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.155"},{"key":"ref46","first-page":"11027","article-title":"How do in-context examples affect compositional generalization?","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"An"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.622"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"ref49","article-title":"Benchmarking generalization via in-context instructions on 1,600+ language tasks","author":"Wang","year":"2022","journal-title":"arXiv:2204.07705"},{"key":"ref50","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref51","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref52","first-page":"156","article-title":"How does in-context learning help prompt tuning?","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"Sun"},{"key":"ref53","article-title":"In-context instruction learning","author":"Ye","year":"2023","journal-title":"arXiv:2302.14691"},{"key":"ref54","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3364056"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02224"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3282070"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3215905"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3310329"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374222"},{"key":"ref61","article-title":"Personalize segment anything model with one shot","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref62","article-title":"Explore in-context segmentation via latent diffusion models","author":"Wang","year":"2024","journal-title":"arXiv:2403.09616"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3265865"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013717"},{"key":"ref65","first-page":"37484","article-title":"Singular value fine-tuning: Few-shot segmentation requires few-parameters fine-tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00929"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00823"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.5244\/c.31.167"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00294"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref73","first-page":"6941","article-title":"Hypercorrelation squeeze for few-shot segmentation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Min"},{"key":"ref74","first-page":"21984","article-title":"Few-shot segmentation via cycle-consistent transformer","volume-title":"Proc. NIPS","volume":"34","author":"Zhang"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19800-7_41"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01128"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01126"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_7"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00789"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02264"},{"key":"ref81","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref82","first-page":"1","article-title":"DINOv2: Learning robust visual features without supervision","volume":"2024","author":"Oquab","year":"2023","journal-title":"Trans. Mach. Learn. Res. J."},{"key":"ref83","article-title":"Conditional networks for few-shot semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent. Workshop","author":"Rakelly"},{"key":"ref84","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10945944.pdf?arnumber=10945944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T08:30:31Z","timestamp":1743841831000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10945944\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3554410","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}