{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:03:54Z","timestamp":1776114234077,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557608","type":"print"},{"value":"9789819557615","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\/978-981-95-5761-5_27","type":"book-chapter","created":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:52:45Z","timestamp":1768110765000},"page":"384-398","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["TactPav: A Vision-Language Annotated Multi-modal Dataset for\u00a0Tactile Paving Navigation"],"prefix":"10.1007","author":[{"given":"Wenqi","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youqi","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zilong","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjie","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changbo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaoqi","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"27_CR1","unstructured":"World Health Organization, et\u00a0al.: World report on vision. In: World report on vision (2019)"},{"key":"27_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122109","volume":"238","author":"X Zhang","year":"2024","unstructured":"Zhang, X., Liang, L., Zhao, S., Wang, Z.: GRFB-unet: a new multi-scale attention network with group receptive field block for tactile paving segmentation. Expert Syst. Appl. 238, 122109 (2024)","journal-title":"Expert Syst. Appl."},{"issue":"10","key":"27_CR3","doi-asserted-by":"publisher","first-page":"1661","DOI":"10.1002\/tee.24123","volume":"19","author":"T Takano","year":"2024","unstructured":"Takano, T., Nakane, T., Yu, J., Zhang, C.: Tactile paving detection and tracking using tenji10k dataset. IEEJ Trans. Electr. Electron. Eng. 19(10), 1661\u20131672 (2024)","journal-title":"IEEJ Trans. Electr. Electron. Eng."},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Chen, J., Bai, X.: Atmospheric transmission and thermal inertia induced blind road segmentation with a large-scale dataset tbrsd. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1053\u20131063 (2023)","DOI":"10.1109\/ICCV51070.2023.00103"},{"key":"27_CR5","unstructured":"Ravi, N., et\u00a0al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Gomaa, W.H., Fahmy, A.A.: A survey of text similarity approaches. Int. J. Comput. Appl. 68(13) (2013)","DOI":"10.5120\/11638-7118"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Huang, X., et al.: Segment and caption anything. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13405\u201313417 (2024)","DOI":"10.1109\/CVPR52733.2024.01273"},{"key":"27_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-030-58520-4_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Gurari","year":"2020","unstructured":"Gurari, D., Zhao, Y., Zhang, M., Bhattacharya, N.: Captioning images taken by people who are blind. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 417\u2013434. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_25"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Yu, L., Nikandrou, M., Jin, J., Rieser, V.: Quality-agnostic image captioning to safely assist people with vision impairment. arXiv preprint arXiv:2304.14623 (2023)","DOI":"10.24963\/ijcai.2023\/697"},{"key":"27_CR10","series-title":"Lecture Notes in Networks and Systems","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-031-12097-8_33","volume-title":"Advances in Computing Systems and Applications - CSA 2022","author":"K Delloul","year":"2022","unstructured":"Delloul, K., Larabi, S.: Image captioning state-of-the-art: is it enough for the guidance of visually impaired in an environment? In: Senouci, M.R., Boulahia, S.Y., Benatia, M.A. (eds.) CSA 2022. LNCS, vol. 513, pp. 385\u2013394. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-12097-8_33"},{"key":"27_CR11","unstructured":"OpenAI, Hurst, A., Lerer, A., et\u00a0al.: GPT-4o system card (2024). https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"27_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"27_CR13","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: Segformer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR14","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"27_CR15","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":"27_CR16","doi-asserted-by":"crossref","unstructured":"Choi, S., Kim, J.T., Choo, J.: Cars can\u2019t fly up in the sky: improving urban-scene segmentation via height-driven attention networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9373\u20139383 (2020)","DOI":"10.1109\/CVPR42600.2020.00939"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Jung, S., Lee, J., Gwak, D., Choi, S., Choo, J.: Standardized max logits: a simple yet effective approach for identifying unexpected road obstacles in urban-scene segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15425\u201315434 (2021)","DOI":"10.1109\/ICCV48922.2021.01514"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"27_CR19","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: Laion-5b: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR20","first-page":"16272","volume":"37","author":"HJ Kim","year":"2024","unstructured":"Kim, H.J., Sengupta, K., Kuribayashi, M., Kacorri, H., Ohn-Bar, E.: Text to blind motion. Adv. Neural. Inf. Process. Syst. 37, 16272\u201316285 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"27_CR21","doi-asserted-by":"crossref","unstructured":"Rotstein, N., Bensaid, D., Brody, S., Ganz, R., Kimmel, R.: Fusecap: leveraging large language models for enriched fused image captions. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5689\u20135700 (2024)","DOI":"10.1109\/WACV57701.2024.00559"},{"key":"27_CR22","unstructured":"Nishimura, C., Kurita, S., Seki, Y.: Text360nav: 360-degree image captioning dataset for urban pedestrians navigation. In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 15783\u201315788 (2024)"},{"key":"27_CR23","unstructured":"Hong, Y., Pan, H., Sun, W., Jia, Y.: Deep dual-resolution networks for real-time and accurate semantic segmentation of road scenes. arXiv preprint arXiv:2101.06085 (2021)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5761-5_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T05:52:47Z","timestamp":1768110767000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5761-5_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557608","9789819557615"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5761-5_27","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":"12 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}