{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:30:20Z","timestamp":1743046220263,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031425356"},{"type":"electronic","value":"9783031425363"}],"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\/978-3-031-42536-3_15","type":"book-chapter","created":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T18:02:30Z","timestamp":1693418550000},"page":"153-162","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Indoor Scenes Video Captioning"],"prefix":"10.1007","author":[{"given":"Javier","family":"Rodr\u00edguez-Juan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Ortiz-Perez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jose","family":"Garcia-Rodriguez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Tom\u00e1s","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Grzegorz J.","family":"Nalepa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,31]]},"reference":[{"issue":"3","key":"15_CR1","doi-asserted-by":"publisher","first-page":"2827","DOI":"10.1007\/s11063-020-10231-w","volume":"51","author":"M Afif","year":"2020","unstructured":"Afif, M., Ayachi, R., Said, Y., Atri, M.: Deep learning based application for indoor scene recognition. Neural Process. Lett. 51(3), 2827\u20132837 (2020)","journal-title":"Neural Process. Lett."},{"unstructured":"Barbu, A.: Video in sentences out (2012). https:\/\/arxiv.org\/abs\/1204.2742","key":"15_CR2"},{"doi-asserted-by":"crossref","unstructured":"Deng, C., Chen, S., Chen, D., He, Y., Wu, Q.: Sketch, ground, and refine: top-down dense video captioning. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 234\u2013243 (2021)","key":"15_CR3","DOI":"10.1109\/CVPR46437.2021.00030"},{"doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez\u00a0Montenegro, J.M., Villarini, B., Angelopoulou, A., Kapetanios, E., Garcia-Rodriguez, J., Argyriou, V.: A survey of Alzheimer\u2019s disease early diagnosis methods for cognitive assessment. Sensors 20(24) (2020)","key":"15_CR4","DOI":"10.3390\/s20247292"},{"doi-asserted-by":"crossref","unstructured":"Fudholi, D.H., Nayoan, R.A.: The role of transformer-based image captioning for indoor environment visual understanding. Int. J. Comput. Digit. Syst. 12(1), 479\u2013488 (2022)","key":"15_CR5","DOI":"10.12785\/ijcds\/120138"},{"doi-asserted-by":"crossref","unstructured":"Gomez-Donoso, F.: A robotic platform for customized and interactive rehabilitation of persons with disabilities. Pattern Recogn. Lett. 99, 105\u2013113 (2017)","key":"15_CR6","DOI":"10.1016\/j.patrec.2017.05.027"},{"key":"15_CR7","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.neucom.2019.08.042","volume":"370","author":"T Jin","year":"2019","unstructured":"Jin, T., Li, Y., Zhang, Z.: Recurrent convolutional video captioning with global and local attention. Neurocomputing 370, 118\u2013127 (2019)","journal-title":"Neurocomputing"},{"doi-asserted-by":"crossref","unstructured":"Krishna, R., Hata, K., Ren, F., Fei-Fei, L., Niebles, J.C.: Dense-captioning events in videos (2017). https:\/\/arxiv.org\/abs\/1705.00754","key":"15_CR8","DOI":"10.1109\/ICCV.2017.83"},{"doi-asserted-by":"crossref","unstructured":"Li, X., Guo, D., Liu, H., Sun, F.: Robotic indoor scene captioning from streaming video. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 6109\u20136115 (2021)","key":"15_CR9","DOI":"10.1109\/ICRA48506.2021.9560904"},{"doi-asserted-by":"crossref","unstructured":"Lin, D., Kong, C., Fidler, S., Urtasun, R.: Generating multi-sentence lingual descriptions of indoor scenes (2015). https:\/\/arxiv.org\/abs\/1503.00064","key":"15_CR10","DOI":"10.5244\/C.29.93"},{"doi-asserted-by":"crossref","unstructured":"Lin, K.: SwinBERT: end-to-end transformers with sparse attention for video captioning (2022). https:\/\/arxiv.org\/abs\/2111.13196","key":"15_CR11","DOI":"10.1109\/CVPR52688.2022.01742"},{"unstructured":"Liu, Z.: Video swin transformer (2021). https:\/\/arxiv.org\/abs\/2106.13230","key":"15_CR12"},{"doi-asserted-by":"crossref","unstructured":"Pei, W., Zhang, J., Wang, X., Ke, L., Shen, X., Tai, Y.-W.: Memory-attended recurrent network for video captioning (2019). https:\/\/arxiv.org\/abs\/1905.03966","key":"15_CR13","DOI":"10.1109\/CVPR.2019.00854"},{"unstructured":"Revuelta, F.F., Chamizo, J.M.G., Garcia-Rodrguez, J., S\u00e1ez, A.H.: Representation of 2D objects with a topology preserving network. In: Quereda, J.M.I., Mic\u00f3, L. (eds.) Pattern Recognition in Information Systems, pp. 267\u2013276. ICEIS Press (2002)","key":"15_CR14"},{"doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Varol, G., Wang, X., Farhadi, A., Laptev, I., Gupta, A.: Hollywood in homes: crowdsourcing data collection for activity understanding (2016). https:\/\/arxiv.org\/abs\/1604.01753","key":"15_CR15","DOI":"10.1007\/978-3-319-46448-0_31"},{"doi-asserted-by":"crossref","unstructured":"Zamora-Hern\u00e1ndez, M.-A., Castro-Vargas, J.A., Azorin-Lopez, J., Garcia-Rodriguez, J.: Deep learning-based visual control assistant for assembly in industry 4.0. Comput. Ind. 131, 103485 (2021)","key":"15_CR16","DOI":"10.1016\/j.compind.2021.103485"},{"unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: BERTScore: evaluating text generation with BERT (2020). https:\/\/arxiv.org\/abs\/1904.09675","key":"15_CR17"},{"doi-asserted-by":"crossref","unstructured":"Zhou, L., Kalantidis, Y., Chen, X., Corso, J.J., Rohrbach, M.: Grounded video description (2019). https:\/\/arxiv.org\/abs\/1812.06587","key":"15_CR18","DOI":"10.1109\/CVPR.2019.00674"},{"doi-asserted-by":"crossref","unstructured":"Zhou, L., Zhou, Y., Corso, J.J., Socher, R., Xiong, C.: End-to-end dense video captioning with masked transformer (2018). https:\/\/arxiv.org\/abs\/1804.00819","key":"15_CR19","DOI":"10.1109\/CVPR.2018.00911"}],"container-title":["Lecture Notes in Networks and Systems","18th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2023)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-42536-3_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T18:05:19Z","timestamp":1693418719000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-42536-3_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031425356","9783031425363"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-42536-3_15","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"31 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SOCO","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Soft Computing Models in Industrial and Environmental Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salamanca","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2023","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":"icscmiea2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2023.sococonference.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}