{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T22:57:37Z","timestamp":1775516257402,"version":"3.50.1"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031250811","type":"print"},{"value":"9783031250828","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-25082-8_24","type":"book-chapter","created":{"date-parts":[[2023,2,11]],"date-time":"2023-02-11T09:12:42Z","timestamp":1676106762000},"page":"366-381","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Generating Construction Safety Observations via\u00a0CLIP-Based Image-Language Embedding"],"prefix":"10.1007","author":[{"given":"Wei Lun","family":"Tsai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jacob J.","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shang-Hsien","family":"Hsieh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,12]]},"reference":[{"key":"24_CR1","unstructured":"Alammar, J.: The illustrated gpt-2 (visualizing transformer language models) [blog post] (2019). https:\/\/jalammar.github.io\/illustrated-gpt2\/"},{"key":"24_CR2","doi-asserted-by":"publisher","unstructured":"Bang, S., Kim, H.: Context-based information generation for managing UAV-acquired data using image captioning. Autom. Constr. 112, 103116 (2020). https:\/\/doi.org\/10.1016\/j.autcon.2020.103116. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0926580519308519","DOI":"10.1016\/j.autcon.2020.103116"},{"key":"24_CR3","doi-asserted-by":"publisher","unstructured":"Chen, X., et al: Microsoft coco captions: data collection and evaluation server (2015). https:\/\/doi.org\/10.48550\/ARXIV.1504.00325. https:\/\/arxiv.org\/abs\/1504.00325","DOI":"10.48550\/ARXIV.1504.00325"},{"key":"24_CR4","doi-asserted-by":"publisher","unstructured":"Cheng, M.Y., Kusoemo, D., Gosno, R.A.: Text mining-based construction site accident classification using hybrid supervised machine learning. Autom. Constr. 118, 103265 (2020). https:\/\/doi.org\/10.1016\/j.autcon.2020.103265. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S092658051931341X","DOI":"10.1016\/j.autcon.2020.103265"},{"key":"24_CR5","doi-asserted-by":"publisher","unstructured":"Chiu, S., Li, M., Lin, Y.T., Chen, Y.N.: Salesbot: Transitioning from chit-chat to task-oriented dialogues (2022). https:\/\/doi.org\/10.48550\/ARXIV.2204.10591. https:\/\/arxiv.org\/abs\/2204.10591","DOI":"10.48550\/ARXIV.2204.10591"},{"key":"24_CR6","doi-asserted-by":"publisher","unstructured":"Conde, M.V., Turgutlu, K.: Clip-art: contrastive pre-training for fine-grained art classification. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 3951\u20133955 (2021). https:\/\/doi.org\/10.1109\/CVPRW53098.2021.00444","DOI":"10.1109\/CVPRW53098.2021.00444"},{"key":"24_CR7","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale (2020). https:\/\/doi.org\/10.48550\/ARXIV.2010.11929. https:\/\/arxiv.org\/abs\/2010.11929","DOI":"10.48550\/ARXIV.2010.11929"},{"key":"24_CR8","doi-asserted-by":"publisher","unstructured":"Du, Y., Liu, Z., Li, J., Zhao, W.X.: A survey of vision-language pre-trained models (2022). https:\/\/doi.org\/10.48550\/ARXIV.2202.10936. https:\/\/arxiv.org\/abs\/2202.10936","DOI":"10.48550\/ARXIV.2202.10936"},{"key":"24_CR9","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015). https:\/\/doi.org\/10.48550\/ARXIV.1512.03385. https:\/\/arxiv.org\/abs\/1512.03385","DOI":"10.48550\/ARXIV.1512.03385"},{"issue":"6","key":"24_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3295748","volume":"51","author":"MZ Hossain","year":"2019","unstructured":"Hossain, M.Z., Sohel, F., Shiratuddin, M.F., Laga, H.: A comprehensive survey of deep learning for image captioning. ACM Comput. Surv. 51(6), 1\u201336 (2019). https:\/\/doi.org\/10.1145\/3295748","journal-title":"ACM Comput. Surv."},{"key":"24_CR11","doi-asserted-by":"publisher","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization (2014). https:\/\/doi.org\/10.48550\/ARXIV.1412.6980. https:\/\/arxiv.org\/abs\/1412.6980","DOI":"10.48550\/ARXIV.1412.6980"},{"key":"24_CR12","unstructured":"Ministry of Labor, T.: Regulations of occupational safety and health act (2022). https:\/\/law.moj.gov.tw\/LawClass\/LawAllPara.aspx?pcode=N0060009"},{"key":"24_CR13","doi-asserted-by":"publisher","first-page":"198503","DOI":"10.1109\/ACCESS.2020.3035214","volume":"8","author":"JR Lin","year":"2020","unstructured":"Lin, J.R., Hu, Z.Z., Li, J.L., Chen, L.M.: Understanding on-site inspection of construction projects based on keyword extraction and topic modeling. IEEE Access 8, 198503\u2013198517 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3035214","journal-title":"IEEE Access"},{"key":"24_CR14","doi-asserted-by":"publisher","unstructured":"Liu, H., Wang, G., Huang, T., He, P., Skitmore, M., Luo, X.: Manifesting construction activity scenes via image captioning. Autom. Constr. 119, 103334 (2020). https:\/\/doi.org\/10.1016\/j.autcon.2020.103334. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0926580520309146","DOI":"10.1016\/j.autcon.2020.103334"},{"key":"24_CR15","doi-asserted-by":"publisher","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2017). https:\/\/doi.org\/10.48550\/ARXIV.1711.05101. https:\/\/arxiv.org\/abs\/1711.05101","DOI":"10.48550\/ARXIV.1711.05101"},{"key":"24_CR16","unstructured":"Mokady, R., Hertz, A., Bermano, A.H.: Clipcap: Clip prefix for image captioning. arXiv preprint arXiv:2111.09734 (2021)"},{"key":"24_CR17","doi-asserted-by":"publisher","unstructured":"Pal, A., Hsieh, S.H.: Deep-learning-based visual data analytics for smart construction management. Autom. Constr. 131, 103892 (2021). https:\/\/doi.org\/10.1016\/j.autcon.2021.103892. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0926580521003435","DOI":"10.1016\/j.autcon.2021.103892"},{"key":"24_CR18","unstructured":"von Platen, P.: How to generate text: using different decoding methods for language generation with transformers[blog post] (2020). https:\/\/huggingface.co\/blog\/how-to-generate"},{"issue":"3","key":"24_CR19","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1061\/(ASCE)CO.1943-7862.0000131","volume":"136","author":"MA Qady","year":"2010","unstructured":"Qady, M.A., Kandil, A.: Concept relation extraction from construction documents using natural language processing. J. Constr. Eng. Manage. 136(3), 294\u2013302 (2010). https:\/\/doi.org\/10.1061\/(ASCE)CO.1943-7862.0000131","journal-title":"J. Constr. Eng. Manage."},{"key":"24_CR20","doi-asserted-by":"publisher","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021). https:\/\/doi.org\/10.48550\/ARXIV.2103.00020. https:\/\/arxiv.org\/abs\/2103.00020","DOI":"10.48550\/ARXIV.2103.00020"},{"key":"24_CR21","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020). http:\/\/jmlr.org\/papers\/v21\/20-074.html"},{"key":"24_CR22","doi-asserted-by":"publisher","unstructured":"Tang, J., Zhao, T., Xiong, C., Liang, X., Xing, E., Hu, Z.: Target-guided open-domain conversation. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5624\u20135634. Association for Computational Linguistics, Florence, Italy (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1565. https:\/\/aclanthology.org\/P19-1565","DOI":"10.18653\/v1\/P19-1565"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. arXiv preprint arXiv:1906.05849 (2019)","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"24_CR24","doi-asserted-by":"publisher","unstructured":"Vaswani, A., et al.: Attention is all you need (2017). https:\/\/doi.org\/10.48550\/ARXIV.1706.03762. https:\/\/arxiv.org\/abs\/1706.03762","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"7","key":"24_CR25","doi-asserted-by":"publisher","first-page":"04022049","DOI":"10.1061\/(ASCE)CO.1943-7862.0002297","volume":"148","author":"B Xiao","year":"2022","unstructured":"Xiao, B., Wang, Y., Kang, S.C.: Deep learning image captioning in construction management: a feasibility study. J. Constr. Eng. Manage. 148(7), 04022049 (2022). https:\/\/doi.org\/10.1061\/(ASCE)CO.1943-7862.0002297","journal-title":"J. Constr. Eng. Manage."},{"issue":"3","key":"24_CR26","doi-asserted-by":"publisher","first-page":"04016048","DOI":"10.1061\/(ASCE)ME.1943-5479.0000495","volume":"33","author":"H Zhang","year":"2017","unstructured":"Zhang, H., Chi, S., Yang, J., Nepal, M., Moon, S.: Development of a safety inspection framework on construction sites using mobile computing. J. Manage. Eng. 33(3), 04016048 (2017). https:\/\/doi.org\/10.1061\/(ASCE)ME.1943-5479.0000495","journal-title":"J. Manage. Eng."},{"key":"24_CR27","doi-asserted-by":"publisher","unstructured":"Zhong, B., He, W., Huang, Z., Love, P.E., Tang, J., Luo, H.: A building regulation question answering system: a deep learning methodology. Adv. Eng. Inf. 46, 101195 (2020). https:\/\/doi.org\/10.1016\/j.aei.2020.101195. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1474034620301658","DOI":"10.1016\/j.aei.2020.101195"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-25082-8_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T13:06:53Z","timestamp":1709816813000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-25082-8_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031250811","9783031250828"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-25082-8_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"12 February 2023","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"From the workshops, 367 reviewed full papers have been selected for publication","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}