{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:45:25Z","timestamp":1777657525682,"version":"3.51.4"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729034","type":"print"},{"value":"9783031729041","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72904-1_18","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T13:27:22Z","timestamp":1732109242000},"page":"304-320","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Open-Vocabulary RGB-Thermal Semantic Segmentation"],"prefix":"10.1007","author":[{"given":"Guoqiang","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyun","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaojing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junwei","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangjun","family":"Ou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinrong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"issue":"2","key":"18_CR1","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1037\/0033-295X.94.2.115","volume":"94","author":"I Biederman","year":"1987","unstructured":"Biederman, I.: Recognition-by-components: a theory of human image understanding. Psychol. Rev. 94(2), 115 (1987)","journal-title":"Psychol. Rev."},{"key":"18_CR2","unstructured":"Bucher, M., Vu, T.H., Cord, M., P\u00e9rez, P.: Zero-shot semantic segmentation. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"18_CR3","first-page":"16664","volume":"35","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: AdaptFormer: adapting vision transformers for scalable visual recognition. Adv. Neural. Inf. Process. Syst. 35, 16664\u201316678 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Deng, F., et al.: FEANet: feature-enhanced attention network for RGB-thermal real-time semantic segmentation. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4467\u20134473. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636084"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Ding, J., Xue, N., Xia, G.S., Dai, D.: Decoupling zero-shot semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11583\u201311592 (2022)","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Dong, S., Feng, Y., Yang, Q., Huang, Y., Liu, D., Fan, H.: Efficient multimodal semantic segmentation via dual-prompt learning. arXiv preprint arXiv:2312.00360 (2023)","DOI":"10.1109\/IROS58592.2024.10801872"},{"key":"18_CR7","unstructured":"Fu, Y., Xiang, T., Jiang, Y.G., Xue, X., Sigal, L., Gong, S.: Recent advances in zero-shot recognition. arXiv preprint arXiv:1710.04837 (2017)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Ha, Q., Watanabe, K., Karasawa, T., Ushiku, Y., Harada, T.: MFNet: towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5108\u20135115. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206396"},{"key":"18_CR9","unstructured":"Hu, E.J., et al.: LoRa: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Hwang, S., Park, J., Kim, N., Choi, Y., So\u00a0Kweon, I.: Multispectral pedestrian detection: benchmark dataset and baseline. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1037\u20131045 (2015)","DOI":"10.1109\/CVPR.2015.7298706"},{"key":"18_CR11","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"18_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/978-3-031-19827-4_41","volume-title":"Computer Vision \u2013 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":"18_CR13","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NaacL-HLT, vol.\u00a01, p.\u00a02 (2019)"},{"issue":"4","key":"18_CR14","doi-asserted-by":"publisher","first-page":"6497","DOI":"10.1109\/LRA.2021.3093652","volume":"6","author":"YH Kim","year":"2021","unstructured":"Kim, Y.H., Shin, U., Park, J., Kweon, I.S.: MS-UDA: multi-spectral unsupervised domain adaptation for thermal image semantic segmentation. IEEE Robot. Autom. Lett. 6(4), 6497\u20136504 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"18_CR15","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"18_CR17","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation. In: International Conference on Learning Representations (2022)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Liang, Y., Wakaki, R., Nobuhara, S., Nishino, K.: Multimodal material segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19800\u201319808 (2022)","DOI":"10.1109\/CVPR52688.2022.01918"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"18_CR22","unstructured":"OpenAI, R.: GPT-4 technical report. arxiv:2303.08774. View in Article 2, 13 (2023)"},{"key":"18_CR23","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"18_CR24","unstructured":"Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: ENet: a deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147 (2016)"},{"key":"18_CR25","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":"18_CR26","doi-asserted-by":"crossref","unstructured":"Shin, U., Lee, K., Kweon, I.S.: Complementary random masking for RGB-thermal semantic segmentation. arXiv preprint arXiv:2303.17386 (2023)","DOI":"10.1109\/ICRA57147.2024.10611200"},{"issue":"3","key":"18_CR27","doi-asserted-by":"publisher","first-page":"2576","DOI":"10.1109\/LRA.2019.2904733","volume":"4","author":"Y Sun","year":"2019","unstructured":"Sun, Y., Zuo, W., Liu, M.: RTFNet: RGB-thermal fusion network for semantic segmentation of urban scenes. IEEE Robot. Autom. Lett. 4(3), 2576\u20132583 (2019)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"3","key":"18_CR28","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1109\/TASE.2020.2993143","volume":"18","author":"Y Sun","year":"2020","unstructured":"Sun, Y., Zuo, W., Yun, P., Wang, H., Liu, M.: FuseSeg: semantic segmentation of urban scenes based on RGB and thermal data fusion. IEEE Trans. Autom. Sci. Eng. 18(3), 1000\u20131011 (2020)","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Valipour, M., Rezagholizadeh, M., Kobyzev, I., Ghodsi, A.: DyLorA: parameter efficient tuning of pre-trained models using dynamic search-free low-rank adaptation. arXiv preprint arXiv:2210.07558 (2022)","DOI":"10.18653\/v1\/2023.eacl-main.239"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Vertens, J., Z\u00fcrn, J., Burgard, W.: HeatNet: bridging the day-night domain gap in semantic segmentation with thermal images. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8461\u20138468. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341192"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Wang, F., Mei, J., Yuille, A.: SCLIP: rethinking self-attention for dense vision-language inference. arXiv preprint arXiv:2312.01597 (2023)","DOI":"10.1007\/978-3-031-72664-4_18"},{"key":"18_CR32","unstructured":"Wang, K., Li, C., Tu, Z., Luo, B.: Unified-modal salient object detection via adaptive prompt learning. arXiv preprint arXiv:2311.16835 (2023)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, X., Cao, Y., Wang, W., Shen, C., Huang, T.: SegGPT: segmenting everything in context. arXiv preprint arXiv:2304.03284 (2023)","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: GroupViT: semantic segmentation emerges from text supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18134\u201318144 (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2945\u20132954 (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"18_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"736","DOI":"10.1007\/978-3-031-19818-2_42","volume-title":"Computer Vision \u2013 ECCV 2022","author":"M Xu","year":"2022","unstructured":"Xu, M., et al.: A simple baseline for open-vocabulary semantic segmentation with pre-trained vision-language model. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13689, pp. 736\u2013753. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_42"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, J., Liu, H., Yang, K., Hu, X., Liu, R., Stiefelhagen, R.: CMX: Cross-modal fusion for RGB-X semantic segmentation with transformers. IEEE Trans. Intell. Transp. Syst. (2023)","DOI":"10.1109\/TITS.2023.3300537"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, K., Liu, D.: Customized segment anything model for medical image segmentation. arXiv preprint arXiv:2304.13785 (2023)","DOI":"10.2139\/ssrn.4495221"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Zhao, S., Luo, Y., Zhang, D., Huang, N., Han, J.: ABMDRNet: adaptive-weighted bi-directional modality difference reduction network for RGB-T semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2633\u20132642 (2021)","DOI":"10.1109\/CVPR46437.2021.00266"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: ICNet for real-time semantic segmentation on high-resolution images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 405\u2013420 (2018)","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, K., Yang, J., Loy, C.C., Liu, Z.: Conditional prompt learning for vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16816\u201316825 (2022)","DOI":"10.1109\/CVPR52688.2022.01631"},{"issue":"9","key":"18_CR42","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. Vision 130(9), 2337\u20132348 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, W., Dong, S., Xu, C., Qian, Y.: Edge-aware guidance fusion network for RGB\u2013thermal scene parsing. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 3571\u20133579 (2022)","DOI":"10.1609\/aaai.v36i3.20269"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, J., Lai, S., Chen, X., Wang, D., Lu, H.: Visual prompt multi-modal tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9516\u20139526 (2023)","DOI":"10.1109\/CVPR52729.2023.00918"}],"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\/978-3-031-72904-1_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,15]],"date-time":"2025-03-15T19:51:49Z","timestamp":1742068309000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72904-1_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031729034","9783031729041"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72904-1_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 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"}}]}}