{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:46:45Z","timestamp":1776786405451,"version":"3.51.2"},"reference-count":64,"publisher":"Association for Computing Machinery (ACM)","issue":"5","funder":[{"name":"Start-up Fund for Scientific Research of Fuzhou University","award":["511530"],"award-info":[{"award-number":["511530"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U21A20472"],"award-info":[{"award-number":["U21A20472"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LMS25F020003"],"award-info":[{"award-number":["LMS25F020003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62501160"],"award-info":[{"award-number":["62501160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key Research and Development Program of China","award":["2021YFB3600503"],"award-info":[{"award-number":["2021YFB3600503"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>\n                    Source-free cross-domain few-shot learning (SF-CDFSL) aims to transfer pre-trained models to target domains with minimal samples, eliminating the need for source domain data. However, limited samples constrain visual diversity and cross-domain images lack inherent semantic context or prior knowledge, impairing the feature discriminability and generalization of large-scale pre-trained models, affecting transfer performance. To tackle these problems, this article introduces Semantic Guided Diversity Prompting (SeGDP), a method that utilizes semantic guided visual prompts to enhance input diversity. Specifically, SeGDP obtains additional diversity features by concatenating different visual prompts to each support sample, guided by randomly combined and sampled text descriptions during training. Additionally, deep prompt tuning and adapter are introduced to learn static knowledge and further enhance the model\u2019s cross-domain adaptation capability. Extensive experimental results across multiple benchmarks demonstrate that the proposed SeGDP achieves state-of-the-art (SOTA) performance under SF-CDFSL task, and rivals the performance of leading source-utilized models. Our code is available on\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/qwzlh\/TOMM_submission\">https:\/\/github.com\/qwzlh\/TOMM_submission<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1145\/3796719","type":"journal-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T16:07:58Z","timestamp":1770998878000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SeGDP: Source-free Cross-domain Few-shot Learning via Semantic Guided Diversity Prompting"],"prefix":"10.1145","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7333-6304","authenticated-orcid":false,"given":"Linhai","family":"Zhuo","sequence":"first","affiliation":[{"name":"College of Computer and Data Science, Fuzhou University, Fuzhou, China and Fujian Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6753-6569","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3881-4857","authenticated-orcid":false,"given":"Tianwen","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0412-5500","authenticated-orcid":false,"given":"Yuqian","family":"Fu","sequence":"additional","affiliation":[{"name":"INSAIT, Sofia University, Sofia, Bulgaria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00218"},{"key":"e_1_3_1_3_2","first-page":"5542","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Bose Shirsha","year":"2024","unstructured":"Shirsha Bose, Ankit Jha, Enrico Fini, Mainak Singha, Elisa Ricci, and Biplab Banerjee. 2024. Stylip: Multi-scale style-conditioned prompt learning for clip-based domain generalization. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 5542\u20135552."},{"key":"e_1_3_1_4_2","doi-asserted-by":"crossref","first-page":"109668","DOI":"10.1016\/j.patcog.2023.109668","article-title":"Knowledge driven weights estimation for large-scale few-shot image recognition","volume":"142","author":"Chen Jingjing","year":"2023","unstructured":"Jingjing Chen, Linhai Zhuo, Zhipeng Wei, Hao Zhang, Huazhu Fu, and Yu-Gang Jiang. 2023. Knowledge driven weights estimation for large-scale few-shot image recognition. Pattern Recognition 142 (2023), 109668.","journal-title":"Pattern Recognition"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01439"},{"issue":"3","key":"e_1_3_1_6_2","first-page":"211","article-title":"Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, et al. 2015. Imagenet large scale visual recognition challenge","volume":"115","unstructured":"Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, et al. 2015. Imagenet large scale visual recognition challenge. International Journal of Computer Vision 115, 3 (2015), 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475655"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547995"},{"key":"e_1_3_1_10_2","unstructured":"Yuqian Fu Yu Xie Yanwei Fu Jingjing Chen and Yu-Gang Jiang. 2022. Wave-SAN: Wavelet based style augmentation network for cross-domain few-shot learning. arXiv:2203.07656. Retrieved from https:\/\/arxiv.org\/abs\/2203.07656"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02354"},{"key":"e_1_3_1_12_2","unstructured":"Peng Gao Shijie Geng Renrui Zhang Teli Ma Rongyao Fang Yongfeng Zhang Hongsheng Li and Yu Qiao. 2021. Clip-adapter: Better vision-language models with feature adapters. arXiv:2110.04544. Retrieved from https:\/\/arxiv.org\/abs\/2110.04544"},{"key":"e_1_3_1_13_2","unstructured":"Victor Garcia and Joan Bruna. 2017. Few-shot learning with graph neural networks. arXiv:1711.04043. Retrieved from https:\/\/arxiv.org\/abs\/1711.04043"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01853"},{"key":"e_1_3_1_15_2","first-page":"124","volume-title":"Proceedings of 16th European Conference on Computer Vision (ECCV \u201920), Part XXVII","author":"Guo Yunhui","year":"2020","unstructured":"Yunhui Guo, Noel C. Codella, Leonid Karlinsky, James V. Codella, John R. Smith, Kate Saenko, Tajana Rosing, and Rogerio Feris. 2020. A broader study of cross-domain few-shot learning. In Proceedings of 16th European Conference on Computer Vision (ECCV \u201920), Part XXVII. Springer, 124\u2013141."},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00886"},{"key":"e_1_3_1_17_2","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Hu Yanxu","year":"2022","unstructured":"Yanxu Hu and Andy J. Ma. 2022. Adversarial feature augmentation for cross-domain few-shot classification. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_1_18_2","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Huang Wei","year":"2023","unstructured":"Wei Huang, Chang Chen, Yong Li, Jiacheng Li, Cheng Li, Fenglong Song, Youliang Yan, and Zhiwei Xiong. 2023. Style projected clustering for domain generalized semantic segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Gabriel Ilharco Mitchell Wortsman Ross Wightman Cade Gordon Nicholas Carlini Rohan Taori Achal Dave Vaishaal Shankar Hongseok Namkoong John Miller et al. 2021. OpenCLIP. DOI: 10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"e_1_3_1_20_2","first-page":"3584","article-title":"Dynamic distillation network for cross-domain few-shot recognition with unlabeled data","volume":"34","author":"Islam Ashraful","year":"2021","unstructured":"Ashraful Islam, Chun-Fu Richard Chen, Rameswar Panda, Leonid Karlinsky, Rogerio Feris, and Richard J. Radke. 2021. Dynamic distillation network for cross-domain few-shot recognition with unlabeled data. In Advances in Neural Information Processing Systems, Vol. 34, 3584\u20133595.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_21_2","first-page":"709","volume-title":"17th European Conference on Computer Vision (ECCV \u201922), Part XXXIII","author":"Jia Menglin","year":"2022","unstructured":"Menglin Jia, Luming Tang, Bor-Chun Chen, Claire Cardie, Serge Belongie, Bharath Hariharan, and Ser-Nam Lim. 2022. Visual prompt tuning. In Proceedings of 17th European Conference on Computer Vision (ECCV \u201922), Part XXXIII. Springer, 709\u2013727."},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00135"},{"key":"e_1_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Brian Lester Rami Al-Rfou and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv:2104.08691. Retrieved from https:\/\/arxiv.org\/abs\/2104.08691","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_1_25_2","first-page":"4260","volume-title":"Proceedings of the Asian Conference on Computer Vision","author":"Li Aodi","year":"2022","unstructured":"Aodi Li, Liansheng Zhuang, Shuo Fan, and Shafei Wang. 2022. Learning common and specific visual prompts for domain generalization. In Proceedings of the Asian Conference on Computer Vision, 4260\u20134275."},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00679"},{"key":"e_1_3_1_27_2","unstructured":"Xiang Lisa and Li Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv:2101.00190. Retrieved from https:\/\/arxiv.org\/abs\/2101.00190"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00929"},{"key":"e_1_3_1_29_2","doi-asserted-by":"crossref","first-page":"105393","DOI":"10.1016\/j.imavis.2024.105393","article-title":"Class-discriminative domain generalization for semantic segmentation","volume":"154","author":"Liao Muxin","year":"2025","unstructured":"Muxin Liao, Shishun Tian, Yuhang Zhang, Guoguang Hua, Rong You, Wenbin Zou, and Xia Li. 2025. Class-discriminative domain generalization for semantic segmentation. Image and Vision Computing 154 (2025), 105393.","journal-title":"Image and Vision Computing"},{"key":"e_1_3_1_30_2","unstructured":"Bingyu Liu Zhen Zhao Zhenpeng Li Jianan Jiang Yuhong Guo and Jieping Ye. 2020. Feature transformation ensemble model with batch spectral regularization for cross-domain few-shot classification. arXiv:2005.08463. Retrieved from https:\/\/arxiv.org\/abs\/2005.08463"},{"key":"e_1_3_1_31_2","unstructured":"Lingbo Liu Jianlong Chang Bruce X. B. Yu Liang Lin Qi Tian and Chang-Wen Chen. 2022. Prompt-matched semantic segmentation. arXiv:2208.10159. Retrieved from https:\/\/arxiv.org\/abs\/2208.10159"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Xiao Liu Kaixuan Ji Yicheng Fu Weng Lam Tam Zhengxiao Du Zhilin Yang and Jie Tang. 2021. P-tuning v2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks. arXiv:2110.07602. Retrieved from https:\/\/arxiv.org\/abs\/2110.07602","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02347"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01892"},{"key":"e_1_3_1_36_2","unstructured":"Atsuyuki Miyai Qing Yu Go Irie and Kiyoharu Aizawa. 2023. LoCoOp: Few-shot out-of-distribution detection via prompt learning. arXiv:2306.01293. Retrieved from https:\/\/arxiv.org\/abs\/2306.01293"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102949"},{"key":"e_1_3_1_38_2","doi-asserted-by":"crossref","unstructured":"Duo Peng Yinjie Lei Munawar Hayat Yulan Guo and Wen Li. 2022. Semantic-aware domain generalized segmentation. arXiv:2204.00822. Retrieved from https:\/\/arxiv.org\/abs\/2204.00822","DOI":"10.1109\/CVPR52688.2022.00262"},{"key":"e_1_3_1_39_2","unstructured":"Cheng Perng Phoo and Bharath Hariharan. 2020. Self-training for few-shot transfer across extreme task differences. arXiv:2010.07734. Retrieved from https:\/\/arxiv.org\/abs\/2010.07734"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00276"},{"issue":"3","key":"e_1_3_1_41_2","first-page":"831","article-title":"Few-shot remote sensing image scene classification","volume":"15","author":"Qiu Cheng","year":"2024","unstructured":"Cheng Qiu, Xiaoyu Zhang, Xiaochong Tong, Naiyang Guan, Xiaodong Yi, Ke Yang, Junjie Zhu, and Anzhu Yu. 2024. Few-shot remote sensing image scene classification. ISPRS Journal of Photogrammetry and Remote Sensing 15, 3 (2024), 831.","journal-title":"ISPRS Journal of Photogrammetry and Remote Sensing"},{"key":"e_1_3_1_42_2","first-page":"8748","volume-title":"International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International Conference on Machine Learning. PMLR, 8748\u20138763."},{"key":"e_1_3_1_43_2","unstructured":"Jintao Rong Hao Chen Tianxiao Chen Linlin Ou Xinyi Yu and Yifan Liu. 2023. Retrieval-enhanced visual prompt learning for few-shot classification. arXiv:2306.02243. Retrieved from https:\/\/arxiv.org\/abs\/2306.02243"},{"key":"e_1_3_1_44_2","first-page":"1","volume-title":"Proceedings of 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Song Zhao","year":"2023","unstructured":"Zhao Song, Ke Yang, Naiyang Guan, Junjie Zhu, Peng Qiao, and Qingyong Hu. 2023. VPPT: Visual pre-trained prompt tuning framework for few-shot image classification. In Proceedings of 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1\u20135."},{"key":"e_1_3_1_45_2","first-page":"7609","volume-title":"Proceedings of 2020 25th International Conference on Pattern Recognition (ICPR)","author":"Sun Jiamei","year":"2021","unstructured":"Jiamei Sun, Sebastian Lapuschkin, Wojciech Samek, Yunqing Zhao, Ngai-Man Cheung, and Alexander Binder. 2021. Explanation-guided training for cross-domain few-shot classification. In Proceedings of 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, 7609\u20137616."},{"key":"e_1_3_1_46_2","unstructured":"Ximeng Sun Ping Hu and Kate Saenko. 2022. DualCoOp: Fast adaptation to multi-label recognition with limited annotations. arXiv:2206.09541. Retrieved from https:\/\/arxiv.org\/abs\/2206.09541"},{"key":"e_1_3_1_47_2","unstructured":"Hung-Yu Tseng Hsin-Ying Lee Jia-Bin Huang and Ming-Hsuan Yang. 2020. Cross-domain few-shot classification via learned feature-wise transformation. arXiv:2001.08735. Retrieved from https:\/\/arxiv.org\/abs\/2001.08735"},{"key":"e_1_3_1_48_2","doi-asserted-by":"crossref","unstructured":"Haoqing Wang and Zhi-Hong Deng. 2021. Cross-domain few-shot classification via adversarial task augmentation. arXiv:2104.14385. Retrieved from https:\/\/arxiv.org\/abs\/2104.14385","DOI":"10.24963\/ijcai.2021\/149"},{"key":"e_1_3_1_49_2","author":"Yujia Fu","year":"2025","unstructured":"Yujia Fu, Zhiyu Dong, Tianwen Qian, Chenye Zheng, Danian Ji, Linhai Zhuo. 2025. CLIP Based Region-Aware Feature Fusion for Automated BBPS Scoring in Colonoscopy Images. arXiv:2512.20374. Retrieved from https:\/\/arxiv.org\/pdf\/2512.20374","journal-title":"Colonoscopy Images"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00620"},{"key":"e_1_3_1_51_2","first-page":"2058","article-title":"Enhancing information maximization with distance-aware contrastive learning for source-free cross-domain few-shot learning","author":"Xu Huali","year":"2024","unstructured":"Huali Xu, Li Liu, Shuaifeng Zhi, Shaojing Fu, Zhuo Su, Ming-Ming Cheng, and Yongxiang Liu. 2024. Enhancing information maximization with distance-aware contrastive learning for source-free cross-domain few-shot learning. IEEE Transactions on Image Processing 33 (2024), 2058\u20132073.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_1_52_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/180"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00324"},{"key":"e_1_3_1_54_2","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","author":"Yi Shuai","unstructured":"Shuai Yi, Yixiong Zou, Yuhua Li, and Ruixuan Li. 2025. Revisiting continuity of image tokens for cross-domain few-shot learning. In Proceedings of the 42nd International Conference on Machine Learning."},{"key":"e_1_3_1_55_2","unstructured":"Renrui Zhang Rongyao Fang Wei Zhang Peng Gao Kunchang Li Jifeng Dai Yu Qiao and Hongsheng Li. 2021. Tip-adapter: Training-free clip-adapter for better vision-language modeling. arXiv:2111.03930. Retrieved from https:\/\/arxiv.org\/abs\/2111.03930"},{"key":"e_1_3_1_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01460"},{"issue":"6","key":"e_1_3_1_57_2","first-page":"B","article-title":"Domain prompt learning for efficiently adapting clip to unseen domains","volume":"38","author":"Zhang Xin","year":"2023","unstructured":"Xin Zhang, Shixiang Shane Gu, Yutaka Matsuo, and Yusuke Iwasawa. 2023. Domain prompt learning for efficiently adapting clip to unseen domains. Transactions of the Japanese Society for Artificial Intelligence 38, 6 (2023), B\u2013MC2_1.","journal-title":"Transactions of the Japanese Society for Artificial Intelligence"},{"key":"e_1_3_1_58_2","article-title":"Dual adaptive representation alignment for cross-domain few-shot learning","author":"Zhao Yifan","year":"2023","unstructured":"Yifan Zhao, Tong Zhang, Jia Li, and Yonghong Tian. 2023. Dual adaptive representation alignment for cross-domain few-shot learning. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 10 (2023), 11720\u201311732.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_1_59_2","unstructured":"Hao Zheng Runqi Wang Jianzhuang Liu and Asako Kanezaki. 2023. Cross-level distillation and feature denoising for cross-domain few-shot classification. arXiv:2311.02392. Retrieved from https:\/\/arxiv.org\/abs\/2311.02392"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"e_1_3_1_61_2","volume-title":"Proceedings of the ACM International Conference on Multimedia (ACM MM)","author":"Zhuo Linhai","year":"2022","unstructured":"Linhai Zhuo, Yuqian Fu, Jingjing Chen, Yixin Cao, and Yu-Gang Jiang. 2022. TGDM: Target guided dynamic mixup for cross-domain few-shot learning. In Proceedings of the ACM International Conference on Multimedia (ACM MM)."},{"key":"e_1_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3673231"},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02225"},{"key":"e_1_3_1_64_2","first-page":"116332","article-title":"Attention temperature matters in vit-based cross-domain few-shot learning","volume":"37","author":"Zou Yixiong","year":"2024","unstructured":"Yixiong Zou, Ran Ma, Yuhua Li, and Ruixuan Li. 2024. Attention temperature matters in vit-based cross-domain few-shot learning. Advances in Neural Information Processing Systems, Vol. 37, 116332\u2013116354.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_1_65_2","first-page":"85523","article-title":"A closer look at the CLS token for cross-domain few-shot learning","volume":"37","author":"Zou Yixiong","year":"2024","unstructured":"Yixiong Zou, Shuai Yi, Yuhua Li, and Ruixuan Li. 2024. A closer look at the CLS token for cross-domain few-shot learning. In Advances in Neural Information Processing Systems, Vol. 37, 85523\u201385545.","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3796719","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:57:54Z","timestamp":1776783474000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3796719"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":64,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3796719"],"URL":"https:\/\/doi.org\/10.1145\/3796719","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]},"assertion":[{"value":"2025-06-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}