{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T18:28:10Z","timestamp":1761157690750,"version":"3.37.3"},"reference-count":102,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003645","name":"National Cancer Center","doi-asserted-by":"publisher","award":["NCC-2311350"],"award-info":[{"award-number":["NCC-2311350"]}],"id":[{"id":"10.13039\/501100003645","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3538617","type":"journal-article","created":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T18:43:00Z","timestamp":1738694580000},"page":"31171-31182","source":"Crossref","is-referenced-by-count":1,"title":["On Calibration of Prompt Learning Using Temperature Scaling"],"prefix":"10.1109","volume":"13","author":[{"given":"Khanh-Binh","family":"Nguyen","sequence":"first","affiliation":[{"name":"National Cancer Center, Ilsandong-gu, Research Institute, Goyang-si, Gyeonggi-do, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1261-307X","authenticated-orcid":false,"given":"Chae Jung","family":"Park","sequence":"additional","affiliation":[{"name":"National Cancer Center, Ilsandong-gu, Research Institute, Goyang-si, Gyeonggi-do, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref2","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01745"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"ref7","article-title":"Exploring diverse in-context configurations for image captioning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01441"},{"key":"ref9","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref10","article-title":"How much can CLIP benefit vision-and-language tasks?","volume-title":"arXiv:2107.06383","author":"Shen","year":"2021"},{"key":"ref11","article-title":"PaLM-E: An embodied multimodal language model","volume-title":"arXiv:2303.03378","author":"Driess","year":"2023"},{"key":"ref12","first-page":"894","article-title":"CLIPort: What and where pathways for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar"},{"key":"ref13","first-page":"13139","article-title":"Language-conditioned imitation learning for robot manipulation tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Stepputtis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"issue":"1","key":"ref15","first-page":"746","article-title":"CALIP: Zero-shot enhancement of CLIP with parameter-free attention","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"37","author":"Guo"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"},{"key":"ref17","first-page":"6216","article-title":"Data determines distributional robustness in contrastive language image pre-training (CLIP)","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fang"},{"key":"ref18","first-page":"21455","article-title":"Quality not quantity: On the interaction between dataset design and robustness of CLIP","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nguyen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref22","article-title":"Making pre-trained language models better few-shot learners","volume-title":"arXiv:2012.15723","author":"Gao","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00324"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref25","article-title":"Prefix-tuning: Optimizing continuous prompts for generation","volume-title":"arXiv:2101.00190","author":"Lisa Li","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.398"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref29","first-page":"15682","article-title":"Revisiting the calibration of modern neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Minderer"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9602"},{"key":"ref31","article-title":"Fine-grained visual classification of aircraft","volume-title":"arXiv:1306.5151","author":"Maji","year":"2013"},{"key":"ref32","first-page":"19645","article-title":"Effective adaptation in multi-task co-training for unified autonomous driving","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Liang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01934"},{"key":"ref34","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref35","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"17","author":"Grandvalet"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref37","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xie"},{"key":"ref38","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.321"},{"key":"ref40","first-page":"935","article-title":"Zero-shot learning through cross-modal transfer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Socher"},{"key":"ref41","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Frome"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.483"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.218"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_5"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.449"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"ref47","article-title":"SILC: Improving vision language pretraining with self-distillation","volume-title":"arXiv:2310.13355","author":"Ferjad Naeem","year":"2023"},{"key":"ref48","article-title":"FILIP: Fine-grained interactive language-image pre-training","volume-title":"arXiv:2111.07783","author":"Yao","year":"2021"},{"key":"ref49","article-title":"CoCa: Contrastive captioners are image-text foundation models","volume-title":"arXiv:2205.01917","author":"Yu","year":"2022"},{"key":"ref50","article-title":"Florence: A new foundation model for computer vision","volume-title":"arXiv:2111.11432","author":"Yuan","year":"2021"},{"key":"ref51","first-page":"1","article-title":"Prompt learning with optimal transport for vision-language models","volume-title":"Proc. NeurIPS","author":"Chen"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01398"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref54","article-title":"Align your prompts: Test-time prompting with distribution alignment for zero-shot generalization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Abdul Samadh"},{"key":"ref55","first-page":"14274","article-title":"Test-time prompt tuning for zero-shot generalization in vision-language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shu"},{"key":"ref56","first-page":"33781","article-title":"Bridging the gap between object and image-level representations for open-vocabulary detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Bangalath"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref58","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","volume-title":"arXiv:2303.05499","author":"Liu","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_31"},{"key":"ref62","article-title":"Language-driven semantic segmentation","volume-title":"arXiv:2201.03546","author":"Li","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3327962"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref66","first-page":"9125","article-title":"DetCLIP: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yao"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"ref69","first-page":"12569","article-title":"Prompt pre-training with twenty-thousand classes for open-vocabulary visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ren"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref82","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref83","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wang"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"article-title":"Consistency-guided prompt learning for vision-language models","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Roy","key":"ref86"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01228"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02212"},{"key":"ref89","article-title":"Cascade prompt learning for vision-language model adaptation","volume-title":"arXiv:2409.17805","author":"Wu","year":"2024"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.328"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00179"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3093883"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00954"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00283"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01466"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87196-3_18"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02288"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00936-9"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43904-9_41"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72378-0_53"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2018.02.010"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301590"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10870225.pdf?arnumber=10870225","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:40:20Z","timestamp":1740084020000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10870225\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":102,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3538617","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}