{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:07:07Z","timestamp":1788894427447,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":75,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370433","type":"print"},{"value":"9783032370440","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37044-0_4","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:22:20Z","timestamp":1788891740000},"page":"56-77","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Purified Multi-label Test-Time Adaptation of\u00a0Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Yiwen","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhe","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyao","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhan","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijia","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuaicheng","family":"Niu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sicheng","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jungong","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guiguang","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"4_CR1","unstructured":"Barbu, A., et al.: ObjectNet: a large-scale bias-controlled dataset for pushing the limits of object recognition models. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Bilen, H., Vedaldi, A.: Weakly supervised deep detection networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.311"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Chen, S., Duan, B., Khan, S., Khan, F.S.: Interpretable zero-shot learning with locally-aligned vision-language model (2025). https:\/\/arxiv.org\/abs\/2506.23822","DOI":"10.1109\/ICCV51701.2025.00052"},{"key":"4_CR4","doi-asserted-by":"publisher","unstructured":"Chen, T., Wang, Z., Li, G., Lin, L.: Recurrent attentional reinforcement learning for multi-label image recognition. Proc. AAAI Conf. Artif. Intell. 32(1) (2018). https:\/\/doi.org\/10.1609\/aaai.v32i1.12281","DOI":"10.1609\/aaai.v32i1.12281"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., Zhai, H., Zhang, C., Shi, X., Li, R.: Multi-cache enhanced prototype learning for test-time generalization of vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2281\u20132291 (2025)","DOI":"10.1109\/ICCV51701.2025.00220"},{"key":"4_CR6","doi-asserted-by":"publisher","unstructured":"Chua, T.S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.: NUS-WIDE: a real-world web image database from National University of Singapore. In: Proceedings of the ACM International Conference on Image and Video Retrieval, CIVR \u201909. Association for Computing Machinery, New York, NY, USA (2009). https:\/\/doi.org\/10.1145\/1646396.1646452","DOI":"10.1145\/1646396.1646452"},{"key":"4_CR7","first-page":"48009","volume":"38","author":"YS Chuang","year":"2026","unstructured":"Chuang, Y.S., et al.: Meta CLIP 2: a worldwide scaling recipe. Adv. Neural. Inf. Process. Syst. 38, 48009\u201348036 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Ding, Z., et al.: Exploring structured semantic prior for multi label recognition with incomplete labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3398\u20133407 (2023)","DOI":"10.1109\/CVPR52729.2023.00331"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Duan, S., Yang, X., Wang, N.: Multi-label prototype visual spatial search for weakly supervised semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 30241\u201330250 (2025)","DOI":"10.1109\/CVPR52734.2025.02815"},{"key":"4_CR10","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (VOC) challenge. Int. J. Comput. Vis. 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vis."},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Fan, X., et al.: Test-time retrieval-augmented adaptation for vision-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), October 2025, pp. 8810\u20138819 (2025)","DOI":"10.1109\/ICCV51701.2025.00824"},{"key":"4_CR12","doi-asserted-by":"publisher","first-page":"105171","DOI":"10.1016\/j.imavis.2024.105171","volume":"149","author":"Y Fang","year":"2024","unstructured":"Fang, Y., Sun, Q., Wang, X., Huang, T., Wang, X., Cao, Y.: EVA-02: a visual representation for neon genesis. Image Vis. Comput. 149, 105171 (2024)","journal-title":"Image Vis. Comput."},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Feng, C.M., Yu, K., Liu, Y., Khan, S., Zuo, W.: Diverse data augmentation with diffusions for effective test-time prompt tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2704\u20132714 (2023)","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"4_CR14","doi-asserted-by":"publisher","unstructured":"Gao, B.B., Zhou, H.Y.: Learning to discover multi-class attentional regions for multi-label image recognition. IEEE Trans. Image Process. 30, 5920\u20135932 (2021). https:\/\/doi.org\/10.1109\/TIP.2021.3088605","DOI":"10.1109\/TIP.2021.3088605"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Guo, Z., Dong, B., Ji, Z., Bai, J., Guo, Y., Zuo, W.: Texts as images in prompt tuning for multi-label image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2023, pp. 2808\u20132817 (2023)","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"4_CR16","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. arXiv preprint arXiv:1903.12261 (2019)"},{"issue":"5","key":"4_CR17","doi-asserted-by":"publisher","first-page":"3450","DOI":"10.1109\/TPAMI.2023.3346405","volume":"46","author":"P Hu","year":"2024","unstructured":"Hu, P., Sun, X., Sclaroff, S., Saenko, K.: DualCoOp++: fast and effective adaptation to multi-label recognition with limited annotations. IEEE Trans. Pattern Anal. Mach. Intell. 46(5), 3450\u20133462 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2023.3346405","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Huang, F., Jiang, J., Jiang, Q., Li, H., Khan, F.N., Wang, Z.: COSMIC: clique-oriented semantic multi-space integration for robust CLIP test-time adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2025, pp. 9772\u20139781 (2025)","DOI":"10.1109\/CVPR52734.2025.00913"},{"key":"4_CR19","doi-asserted-by":"publisher","first-page":"5989","DOI":"10.1109\/TIP.2025.3609185","volume":"34","author":"S Huang","year":"2025","unstructured":"Huang, S., Yan, J., Liu, B., Liu, B., Hong, R.: Dual-view alignment learning with hierarchical-prompt for class-imbalance multi-label image classification. IEEE Trans. Image Process. 34, 5989\u20136001 (2025). https:\/\/doi.org\/10.1109\/TIP.2025.3609185","journal-title":"IEEE Trans. Image Process."},{"key":"4_CR20","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, 18\u201324 July 2021, vol.\u00a0139, pp. 4904\u20134916. PMLR (2021)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Jia, J., Gao, N., He, F., Chen, X., Huang, K.: Learning disentangled attribute representations for robust pedestrian attribute recognition. Proc. AAAI Conf. Artif. Intell. 36(1), 1069\u20131077 (2022)","DOI":"10.1609\/aaai.v36i1.19991"},{"key":"4_CR22","unstructured":"Jia, J., He, F., Gao, N., Chen, X., Huang, K.: Learning disentangled label representations for multi-label classification. arXiv preprint arXiv:2212.01461 (2022)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Karmanov, A., Guan, D., Lu, S., El Saddik, A., Xing, E.: Efficient test-time adaptation of vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14162\u201314171 (2024)","DOI":"10.1109\/CVPR52733.2024.01343"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H., Maaz, M., Khan, S., Khan, F.S.: MaPLe: multi-modal prompt learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2023, pp. 19113\u201319122 (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"4_CR25","unstructured":"Koh, P.W., et al.: WILDS: a benchmark of in-the-wild distribution shifts. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, 18\u201324 July 2021, vol.\u00a0139, pp. 5637\u20135664. PMLR (2021)"},{"key":"4_CR26","unstructured":"Lee, Y., Kim, D., Kang, J., Bang, J., Song, H., Lee, J.G.: RA-TTA: retrieval-augmented test-time adaptation for vision-language models. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=V3zobHnS61"},{"key":"4_CR27","unstructured":"Li, Z., Arora, S.: An exponential learning rate schedule for deep learning. arXiv preprint arXiv:1910.07454 (2019)"},{"key":"4_CR28","doi-asserted-by":"publisher","unstructured":"Liang, Y., et al.: DAR-prompt: dynamic regulation in prompt tuning for multi-label zero-shot learning. IEEE Trans. Image Process. 34, 7697\u20137711 (2025). https:\/\/doi.org\/10.1109\/TIP.2025.3626157","DOI":"10.1109\/TIP.2025.3626157"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Liang, Y., et al.: Advancing reliable test-time adaptation of vision-language models under visual variations. In: Proceedings of the 33rd ACM International Conference on Multimedia, MM \u201925, pp. 4788\u20134797. Association for Computing Machinery, New York, NY, USA (2025)","DOI":"10.1145\/3746027.3755607"},{"key":"4_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"issue":"4","key":"4_CR31","first-page":"3513","volume":"38","author":"Y Lin","year":"2024","unstructured":"Lin, Y.: TagCLIP: a local-to-global framework to enhance open-vocabulary multi-label classification of CLIP without training. Proc. AAAI Conf. Artif. Intell. 38(4), 3513\u20133521 (2024)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"13","key":"4_CR32","doi-asserted-by":"publisher","first-page":"14106","DOI":"10.1609\/aaai.v38i13.29320","volume":"38","author":"Z Liu","year":"2024","unstructured":"Liu, Z., Sun, H., Peng, Y., Zhou, J.: DART: dual-modal adaptive online prompting and knowledge retention for test-time adaptation. Proc. AAAI Conf. Artif. Intell. 38(13), 14106\u201314114 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i13.29320","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"4_CR33","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"4_CR34","doi-asserted-by":"publisher","unstructured":"Lyu, M., et al.: Learn from the learnt: source-free active domain adaptation via contrastive sampling and visual persistence. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, pp. 228\u2013246. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73232-4_13","DOI":"10.1007\/978-3-031-73232-4_13"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Ma, L.L., Xu, S., Xie, M.K., Wang, L., Sun, D., Zhao, H.: Correlative and discriminative label grouping for multi-label visual prompt tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 25434\u201325443 (2025)","DOI":"10.1109\/CVPR52734.2025.02368"},{"key":"4_CR36","doi-asserted-by":"publisher","unstructured":"Ma, L., Xie, H., Wang, L., Fu, Y., Sun, D., Zhao, H.: Text-region matching for multi-label image recognition with missing labels. In: Proceedings of the 32nd ACM International Conference on Multimedia, MM \u201924, pp. 6133\u20136142. Association for Computing Machinery, New York, NY, USA (2024). https:\/\/doi.org\/10.1145\/3664647.3680815","DOI":"10.1145\/3664647.3680815"},{"key":"4_CR37","unstructured":"Maaten, L.v.d., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Narayan, S., Gupta, A., Khan, S., Khan, F.S., Shao, L., Shah, M.: Discriminative region-based multi-label zero-shot learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), October 2021. pp. 8731\u20138740 (2021)","DOI":"10.1109\/ICCV48922.2021.00861"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Peng, X., Bai, Q., Xia, X., Huang, Z., Saenko, K., Wang, B.: Moment matching for multi-source domain adaptation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00149"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Pratt, S., Covert, I., Liu, R., Farhadi, A.: What does a platypus look like? Generating customized prompts for zero-shot image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15691\u201315701 (2023)","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"4_CR41","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, 18\u201324 July 2021, vol.\u00a0139, pp. 8748\u20138763. PMLR (2021)"},{"key":"4_CR42","unstructured":"Rawlekar, S., Cai, Y., Wang, Y., Yang, M.H., Ahuja, N.: Efficiently disentangling CLIP for multi-object perception. arXiv preprint arXiv:2502.02977 (2025)"},{"key":"4_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1007\/978-3-030-01252-6_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"N Sarafianos","year":"2018","unstructured":"Sarafianos, N., Xu, X., Kakadiaris, I.A.: Deep imbalanced attribute classification using visual attention aggregation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 708\u2013725. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_42"},{"issue":"5","key":"4_CR44","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1109\/TBDATA.2020.3019478","volume":"8","author":"M Shi","year":"2022","unstructured":"Shi, M., Tang, Y., Zhu, X., Liu, J.: Multi-label graph convolutional network representation learning. IEEE Trans. Big Data 8(5), 1169\u20131181 (2022). https:\/\/doi.org\/10.1109\/TBDATA.2020.3019478","journal-title":"IEEE Trans. Big Data"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Shu, M., et al.: Test-time prompt tuning for zero-shot generalization in vision-language models. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol. 35, pp. 14274\u201314289. Curran Associates, Inc. (2022)","DOI":"10.52202\/068431-1038"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Sun, X., et al.: DualCoOp: fast adaptation to multi-label recognition with limited annotations. In: Oh, A. (ed.) Advances in Neural Information Processing Systems, vol. 35, pp. 30569\u201330582. Curran Associates, Inc. (2022)","DOI":"10.52202\/068431-2216"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Tan, H., et al.: Recover and match: open-vocabulary multi-label recognition through knowledge-constrained optimal transport. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2025, pp. 4650\u20134660 (2025)","DOI":"10.1109\/CVPR52734.2025.00438"},{"key":"4_CR48","unstructured":"Tschannen, M., et al.: SigLIP 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"4_CR49","doi-asserted-by":"crossref","unstructured":"Wan, F., Liu, C., Ke, W., Ji, X., Jiao, J., Ye, Q.: C-MIL: continuation multiple instance learning for weakly supervised object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00230"},{"key":"4_CR50","doi-asserted-by":"crossref","unstructured":"Wang, A., et al.: Hierarchical prompt learning using clip for multi-label classification with single positive labels. In: Proceedings of the 31st ACM International Conference on Multimedia, MM \u201923, pp. 5594\u20135604. Association for Computing Machinery, New York, NY, USA (2023)","DOI":"10.1145\/3581783.3611988"},{"key":"4_CR51","doi-asserted-by":"crossref","unstructured":"Wang, A., Chen, H., Lin, Z., Han, J., Ding, G.: LSNet: see large, focus small. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9718\u20139729 (2025)","DOI":"10.1109\/CVPR52734.2025.00908"},{"key":"4_CR52","unstructured":"Wang, D., Shelhamer, E., Liu, S., Olshausen, B., Darrell, T.: Tent: fully test-time adaptation by entropy minimization (2021). https:\/\/arxiv.org\/abs\/2006.10726"},{"key":"4_CR53","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, Y., Mao, J., Huang, Z., Huang, C., Xu, W.: CNN-RNN: a unified framework for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016 (2016)","DOI":"10.1109\/CVPR.2016.251"},{"issue":"12","key":"4_CR54","doi-asserted-by":"publisher","first-page":"5678","DOI":"10.1109\/TIP.2016.2612829","volume":"25","author":"M Wang","year":"2016","unstructured":"Wang, M., Luo, C., Hong, R., Tang, J., Feng, J.: Beyond object proposals: random crop pooling for multi-label image recognition. IEEE Trans. Image Process. 25(12), 5678\u20135688 (2016). https:\/\/doi.org\/10.1109\/TIP.2016.2612829","journal-title":"IEEE Trans. Image Process."},{"key":"4_CR55","doi-asserted-by":"crossref","unstructured":"Wang, Z., Chen, T., Li, G., Xu, R., Lin, L.: Multi-label image recognition by recurrently discovering attentional regions. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), October 2017","DOI":"10.1109\/ICCV.2017.58"},{"key":"4_CR56","unstructured":"Wu, X., Jiang, Q.Y., Yang, Y., Wu, Y.F., Chen, Q.G., Lu, J.: TAI++: text as image for multi-label image classification by co-learning transferable prompt (2024). https:\/\/arxiv.org\/abs\/2405.06926"},{"key":"4_CR57","unstructured":"Wu, X., Yu, F., Yang, Y., Chen, Q.G., Lu, J.: Multi-label test-time adaptation with bound entropy minimization. In: The Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=75PhjtbBdr"},{"key":"4_CR58","doi-asserted-by":"crossref","unstructured":"Xie, C.W., Sun, S., Xiong, X., Zheng, Y., Zhao, D., Zhou, J.: RA-CLIP: retrieval augmented contrastive language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19265\u201319274 (2023)","DOI":"10.1109\/CVPR52729.2023.01846"},{"key":"4_CR59","doi-asserted-by":"publisher","unstructured":"Xiong, Y., et al.: Pyra: parallel yielding re-activation for training-inference efficient task adaptation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, vol. 15067, pp. 455\u2013473. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72673-6_25","DOI":"10.1007\/978-3-031-72673-6_25"},{"key":"4_CR60","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Chen, H., Lin, Z., Zhao, S., Ding, G.: Confidence-based visual dispersal for few-shot unsupervised domain adaptation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11621\u201311631 (2023)","DOI":"10.1109\/ICCV51070.2023.01067"},{"key":"4_CR61","unstructured":"Xiong, Y., et al.: Neutralizing token aggregation via information augmentation for efficient test-time adaptation (2025). https:\/\/arxiv.org\/abs\/2508.03388"},{"key":"4_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/978-3-030-58589-1_39","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Ye","year":"2020","unstructured":"Ye, J., He, J., Peng, X., Wu, W., Qiao, Yu.: Attention-driven dynamic graph convolutional network for multi-label image recognition. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 649\u2013665. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_39"},{"key":"4_CR63","unstructured":"Yoon, H.S., Yoon, E., Tee, J.T.J., Hasegawa-Johnson, M., Li, Y., Yoo, C.D.: C-TPT: calibrated test-time prompt tuning for vision-language models via text feature dispersion (2024)"},{"key":"4_CR64","doi-asserted-by":"crossref","unstructured":"Zanella, M., Fuchs, C., De Vleeschouwer, C., Ben Ayed, I.: Realistic test-time adaptation of vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 25103\u201325112 (2025)","DOI":"10.1109\/CVPR52734.2025.02337"},{"key":"4_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, C., Stepputtis, S., Sycara, K.P., Xie, Y.: Dual prototype evolving for test-time generalization of vision-language models. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-1010"},{"key":"4_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, C., Xu, K., Liu, Z., Peng, Y., Zhou, J.: SCAP: transductive test-time adaptation via supportive clique-based attribute prompting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 30032\u201330041 (2025)","DOI":"10.1109\/CVPR52734.2025.02795"},{"key":"4_CR67","doi-asserted-by":"publisher","unstructured":"Zhang, J., Huang, J., Zhang, X., Shao, L., Lu, S.: Historical test-time prompt tuning for vision foundation models. In: Globerson, A., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a037, pp. 12872\u201312896. Curran Associates, Inc. (2024). https:\/\/doi.org\/10.52202\/079017-0410","DOI":"10.52202\/079017-0410"},{"key":"4_CR68","doi-asserted-by":"publisher","unstructured":"Zhang, R., et al.: Tip-Adapter: training-free adaption of clip for few-shot classification. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision, ECCV 2022. LNCS, vol. 13695. pp. 493\u2013510. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_29","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"4_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, T., Wang, J., Guo, H., Dai, T., Chen, B., Xia, S.T.: BoostAdapter: improving vision-language test-time adaptation via regional bootstrapping. In: The Thirty-eighth Annual Conference on Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-2165"},{"key":"4_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhu, W., Tang, H., Ma, Z., Zhou, K., Zhang, L.: Dual memory networks: a versatile adaptation approach for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2024, pp. 28718\u201328728 (2024)","DOI":"10.1109\/CVPR52733.2024.02713"},{"key":"4_CR71","unstructured":"Zhao, S., Wang, X., Zhu, L., Yang, Y.: Test-time adaptation with CLIP reward for zero-shot generalization in vision-language models. In: The Twelfth International Conference on Learning Representations, (2024)"},{"issue":"9","key":"4_CR72","doi-asserted-by":"publisher","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","volume":"130","author":"K Zhou","year":"2022","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Learning to prompt for vision-language models. Int. J. Comput. Vis. 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vis."},{"key":"4_CR73","doi-asserted-by":"crossref","unstructured":"Zhu, F., Li, H., Ouyang, W., Yu, N., Wang, X.: Learning spatial regularization with image-level supervisions for multi-label image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.219"},{"key":"4_CR74","doi-asserted-by":"crossref","unstructured":"Zhu, K., Wu, J.: Residual attention: a simple but effective method for multi-label recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 184\u2013193 (2021)","DOI":"10.1109\/ICCV48922.2021.00025"},{"key":"4_CR75","doi-asserted-by":"publisher","unstructured":"Zhu, X., et al.: Query-based knowledge sharing for open-vocabulary multi-label classification. ACM Trans. Multimedia Comput. Commun. Appl. 21(12) (2025). https:\/\/doi.org\/10.1145\/3762195","DOI":"10.1145\/3762195"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37044-0_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:22:34Z","timestamp":1788891754000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37044-0_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370433","9783032370440"],"references-count":75,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37044-0_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}