{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T16:45:41Z","timestamp":1777653941220,"version":"3.51.4"},"publisher-location":"Cham","reference-count":69,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729799","type":"print"},{"value":"9783031729805","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72980-5_8","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"130-148","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["CoDA: Instructive Chain-of-Domain Adaptation with\u00a0Severity-Aware Visual Prompt Tuning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5191-0380","authenticated-orcid":false,"given":"Ziyang","family":"Gong","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4830-2171","authenticated-orcid":false,"given":"Fuhao","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9391-718X","authenticated-orcid":false,"given":"Yupeng","family":"Deng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0534-852X","authenticated-orcid":false,"given":"Deblina","family":"Bhattacharjee","sequence":"additional","affiliation":[]},{"given":"Xianzheng","family":"Ma","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4415-0698","authenticated-orcid":false,"given":"Xiangwei","family":"Zhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6786-8136","authenticated-orcid":false,"given":"Zhenming","family":"Ji","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"8_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"8_CR2","unstructured":"Bahng, H., Jahanian, A., Sankaranarayanan, S., Isola, P.: Exploring visual prompts for adapting large-scale models. arXiv preprint arXiv:2203.17274 (2022)"},{"key":"8_CR3","unstructured":"Besta, M., et\u00a0al.: Graph of thoughts: solving elaborate problems with large language models. arXiv preprint arXiv:2308.09687 (2023)"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Br\u00fcggemann, D., Sakaridis, C., Truong, P., Van\u00a0Gool, L.: Refign: align and refine for adaptation of semantic segmentation to adverse conditions. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3174\u20133184 (2023)","DOI":"10.1109\/WACV56688.2023.00319"},{"issue":"4","key":"8_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Sikka, K., Cogswell, M., Ji, H., Divakaran, A.: Measuring and improving chain-of-thought reasoning in vision-language models. arXiv preprint arXiv:2309.04461 (2023)","DOI":"10.18653\/v1\/2024.naacl-long.11"},{"key":"8_CR7","unstructured":"Chen, Z., et al.: Vision transformer adapter for dense predictions. arXiv preprint arXiv:2205.08534 (2022)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133223 (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"8_CR9","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1007\/s11263-019-01182-4","volume":"128","author":"D Dai","year":"2020","unstructured":"Dai, D., Sakaridis, C., Hecker, S., Van Gool, L.: Curriculum model adaptation with synthetic and real data for semantic foggy scene understanding. Int. J. Comput. Vis. 128, 1182\u20131204 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Dai, D., Van\u00a0Gool, L.: Dark model adaptation: semantic image segmentation from daytime to nighttime. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 3819\u20133824. IEEE (2018)","DOI":"10.1109\/ITSC.2018.8569387"},{"key":"8_CR11","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers. arXiv preprint arXiv:2309.16588 (2023)"},{"key":"8_CR12","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"8_CR13","unstructured":"Elsayed, G.F., Goodfellow, I., Sohl-Dickstein, J.: Adversarial reprogramming of neural networks. arXiv preprint arXiv:1806.11146 (2018)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Fahes, M., Vu, T.H., Bursuc, A., P\u00e9rez, P., De\u00a0Charette, R.: PODA: prompt-driven zero-shot domain adaptation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18623\u201318633 (2023)","DOI":"10.1109\/ICCV51070.2023.01707"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Gan, Y., et al.: Decorate the newcomers: visual domain prompt for continual test time adaptation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 7595\u20137603 (2023)","DOI":"10.1609\/aaai.v37i6.25922"},{"key":"8_CR16","unstructured":"Gao, Y., et al.: Visual prompt tuning for test-time domain adaptation. arXiv preprint arXiv:2210.04831 (2022)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Ge, C., et al.: Domain adaptation via prompt learning. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3327962"},{"key":"8_CR18","unstructured":"Ge, J., Luo, H., Qian, S., Gan, Y., Fu, J., Zhan, S.: Chain of thought prompt tuning in vision language models. arXiv preprint arXiv:2304.07919 (2023)"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Gong, Z., et al.: Train one, generalize to all: generalizable semantic segmentation from single-scene to all adverse scenes. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2275\u20132284 (2023)","DOI":"10.1145\/3581783.3612387"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Himakunthala, V., et al.: Let\u2019s think frame by frame with VIP: a video infilling and prediction dataset for evaluating video chain-of-thought. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 204\u2013219 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.15"},{"key":"8_CR22","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Hoyer, L., Dai, D., Van\u00a0Gool, L.: DAFormer: improving network architectures and training strategies for domain-adaptive semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9924\u20139935 (2022)","DOI":"10.1109\/CVPR52688.2022.00969"},{"key":"8_CR24","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1007\/978-3-031-20056-4_22","volume-title":"ECCV 2022","author":"L Hoyer","year":"2022","unstructured":"Hoyer, L., Dai, D., Van Gool, L.: HRDA: context-aware high-resolution domain-adaptive semantic segmentation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13690, pp. 372\u2013391. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_22"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Hoyer, L., Dai, D., Wang, H., Van\u00a0Gool, L.: MIC: masked image consistency for context-enhanced domain adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11721\u201311732 (2023)","DOI":"10.1109\/CVPR52729.2023.01128"},{"key":"8_CR26","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1016\/j.neucom.2022.05.086","volume":"501","author":"J Iqbal","year":"2022","unstructured":"Iqbal, J., Hafiz, R., Ali, M.: FogAdapt: self-supervised domain adaptation for semantic segmentation of foggy images. Neurocomputing 501, 844\u2013856 (2022)","journal-title":"Neurocomputing"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Jacovi, A., et al.: A chain-of-thought is as strong as its weakest link: a benchmark for verifiers of reasoning chains. arXiv preprint arXiv:2402.00559 (2024)","DOI":"10.18653\/v1\/2024.acl-long.254"},{"key":"8_CR28","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/978-3-031-19827-4_41","volume-title":"ECCV 2022","author":"M Jia","year":"2022","unstructured":"Jia, M., et al.: Visual prompt tuning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13693, pp. 709\u2013727. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41"},{"key":"8_CR29","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/978-3-031-19833-5_7","volume-title":"ECCV 2022","author":"C Ju","year":"2022","unstructured":"Ju, C., Han, T., Zheng, K., Zhang, Y., Xie, W.: Prompting visual-language models for efficient video understanding. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13695, pp. 105\u2013124. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_7"},{"key":"8_CR30","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. In: Advances in Neural Information Processing Systems, vol. 35, pp. 22199\u201322213 (2022)"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Lee, S., Son, T., Kwak, S.: FIFO: learning fog-invariant features for foggy scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18911\u201318921 (2022)","DOI":"10.1109\/CVPR52688.2022.01834"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: Parsing all adverse scenes: severity-aware semantic segmentation with mask-enhanced cross-domain consistency. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 13483\u201313491 (2024)","DOI":"10.1609\/aaai.v38i12.29251"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Lin, G., Milan, A., Shen, C., Reid, I.: RefineNet: multi-path refinement networks for high-resolution semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1925\u20131934 (2017)","DOI":"10.1109\/CVPR.2017.549"},{"issue":"9","key":"8_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9), 1\u201335 (2023)","journal-title":"ACM Comput. Surv."},{"key":"8_CR35","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Ma, X., et al.: Both style and fog matter: cumulative domain adaptation for semantic foggy scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18922\u201318931 (2022)","DOI":"10.1109\/CVPR52688.2022.01835"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Mitra, C., Huang, B., Darrell, T., Herzig, R.: Compositional chain-of-thought prompting for large multimodal models. arXiv preprint arXiv:2311.17076 (2023)","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"8_CR38","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"8_CR40","unstructured":"Rose, D., et al.: Visual chain of thought: bridging logical gaps with multimodal infillings. arXiv preprint arXiv:2305.02317 (2023)"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Sakaridis, C., Dai, D., Gool, L.V.: Guided curriculum model adaptation and uncertainty-aware evaluation for semantic nighttime image segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7374\u20137383 (2019)","DOI":"10.1109\/ICCV.2019.00747"},{"key":"8_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/978-3-030-01261-8_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Sakaridis","year":"2018","unstructured":"Sakaridis, C., Dai, D., Hecker, S., Van Gool, L.: Model adaptation with synthetic and real data for semantic dense foggy scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 707\u2013724. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_42"},{"key":"8_CR43","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1007\/s11263-018-1072-8","volume":"126","author":"C Sakaridis","year":"2018","unstructured":"Sakaridis, C., Dai, D., Van Gool, L.: Semantic foggy scene understanding with synthetic data. Int. J. Comput. Vis. 126, 973\u2013992 (2018)","journal-title":"Int. J. Comput. Vis."},{"issue":"6","key":"8_CR44","doi-asserted-by":"publisher","first-page":"3139","DOI":"10.1109\/TPAMI.2020.3045882","volume":"44","author":"C Sakaridis","year":"2020","unstructured":"Sakaridis, C., Dai, D., Van Gool, L.: Map-guided curriculum domain adaptation and uncertainty-aware evaluation for semantic nighttime image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3139\u20133153 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Sakaridis, C., Dai, D., Van\u00a0Gool, L.: ACDC: the adverse conditions dataset with correspondences for semantic driving scene understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10765\u201310775 (2021)","DOI":"10.1109\/ICCV48922.2021.01059"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Sun, J., et al.: VPA: fully test-time visual prompt adaptation. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 5796\u20135806 (2023)","DOI":"10.1145\/3581783.3611835"},{"key":"8_CR47","unstructured":"Tarvainen, A., Valpola, H.: Mean teachers are better role models: weight-averaged consistency targets improve semi-supervised deep learning results. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H., Hung, W.C., Schulter, S., Sohn, K., Yang, M.H., Chandraker, M.: Learning to adapt structured output space for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7472\u20137481 (2018)","DOI":"10.1109\/CVPR.2018.00780"},{"key":"8_CR49","unstructured":"Uehara, K., et\u00a0al.: Advancing large multi-modal models with explicit chain-of-reasoning and visual question generation. arXiv preprint arXiv:2401.10005 (2024)"},{"key":"8_CR50","doi-asserted-by":"crossref","unstructured":"Vidit, V., Engilberge, M., Salzmann, M.: Clip the gap: a single domain generalization approach for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3219\u20133229 (2023)","DOI":"10.1109\/CVPR52729.2023.00314"},{"issue":"6","key":"8_CR51","doi-asserted-by":"publisher","first-page":"3048","DOI":"10.1109\/TPAMI.2021.3055564","volume":"44","author":"L Wang","year":"2021","unstructured":"Wang, L., Yoon, K.J.: Knowledge distillation and student-teacher learning for visual intelligence: a review and new outlooks. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3048\u20133068 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR52","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)"},{"issue":"4","key":"8_CR53","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"issue":"5","key":"8_CR54","doi-asserted-by":"publisher","first-page":"758","DOI":"10.3390\/rs16050758","volume":"16","author":"Z Wang","year":"2024","unstructured":"Wang, Z., et al.: Exploring semantic prompts in the segment anything model for domain adaptation. Remote Sens. 16(5), 758 (2024)","journal-title":"Remote Sens."},{"key":"8_CR55","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 24824\u201324837 (2022)"},{"key":"8_CR56","doi-asserted-by":"crossref","unstructured":"Wei, Z., et al.: Stronger fewer & superior: harnessing vision foundation models for domain generalized semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 28619\u201328630 (2024)","DOI":"10.1109\/CVPR52733.2024.02704"},{"key":"8_CR57","doi-asserted-by":"crossref","unstructured":"Wei, Z., Chen, L., Tu, T., Ling, P., Chen, H., Jin, Y.: Disentangle then parse: night-time semantic segmentation with illumination disentanglement. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 21593\u201321603 (2023)","DOI":"10.1109\/ICCV51070.2023.01974"},{"key":"8_CR58","doi-asserted-by":"crossref","unstructured":"Wu, X., Wu, Z., Guo, H., Ju, L., Wang, S.: DANNet: a one-stage domain adaptation network for unsupervised nighttime semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15769\u201315778 (2021)","DOI":"10.1109\/CVPR46437.2021.01551"},{"key":"8_CR59","doi-asserted-by":"crossref","unstructured":"Xiao, A., et al.: 3D semantic segmentation in the wild: learning generalized models for adverse-condition point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9382\u20139392 (2023)","DOI":"10.1109\/CVPR52729.2023.00905"},{"key":"8_CR60","doi-asserted-by":"crossref","unstructured":"Xiao, A., et al.: CAT-SAM: conditional tuning network for few-shot adaptation of segmentation anything model. arXiv preprint arXiv:2402.03631 (2024)","DOI":"10.1007\/978-3-031-73661-2_11"},{"key":"8_CR61","first-page":"9004","volume":"45","author":"B Xie","year":"2023","unstructured":"Xie, B., Li, S., Li, M., Liu, C.H., Huang, G., Wang, G.: SePiCo: semantic-guided pixel contrast for domain adaptive semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45, 9004\u20139021 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR62","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. In: Advances in Neural Information Processing Systems, vol. 34, pp. 12077\u201312090 (2021)"},{"key":"8_CR63","unstructured":"Yao, S., et al.: Tree of thoughts: deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601 (2023)"},{"key":"8_CR64","unstructured":"Yao, Y., Zhang, A., Zhang, Z., Liu, Z., Chua, T.S., Sun, M.: CPT: colorful prompt tuning for pre-trained vision-language models. arXiv preprint arXiv:2109.11797 (2021)"},{"key":"8_CR65","doi-asserted-by":"crossref","unstructured":"Yu, F., et al.: Bdd100k: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2636\u20132645 (2020)","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"8_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, J., Wang, B., Li, L., Nakashima, Y., Nagahara, H.: Instruct me more! random prompting for visual in-context learning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2597\u20132606 (2024)","DOI":"10.1109\/WACV57701.2024.00258"},{"key":"8_CR67","unstructured":"Zhang, R., et al.: Tip-adapter: training-free clip-adapter for better vision-language modeling. arXiv preprint arXiv:2111.03930 (2021)"},{"key":"8_CR68","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tu, S., Ma, X., Jiang, K., Huang, W., Wang, Z.: Rainy WCity: a real rainfall dataset with diverse conditions for semantic driving scene understanding. In: IJCAI, pp. 1743\u20131749 (2022)","DOI":"10.24963\/ijcai.2022\/243"},{"issue":"9","key":"8_CR69","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."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72980-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T10:20:45Z","timestamp":1732962045000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72980-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031729799","9783031729805"],"references-count":69,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72980-5_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"29 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}