{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T20:25:22Z","timestamp":1742934322720,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031200953"},{"type":"electronic","value":"9783031200960"}],"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\/978-3-031-20096-0_8","type":"book-chapter","created":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T15:04:11Z","timestamp":1673535851000},"page":"99-108","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Visualized Analysis of the Emerging Trends of Automated Audio Description Technology"],"prefix":"10.1007","author":[{"given":"Lingqian","family":"Zheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinrong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"8_CR1","unstructured":"WHO. World Report on Vision. Geneva: World Health Organization (2019). https:\/\/www.who.int\/publications\/i\/item\/9789241516570"},{"key":"8_CR2","unstructured":"Frazier, G.: The autobiography of Miss Jane Pitman: an all-audio adaptation of the teleplay for the blind and visually handicapped. Unpublished M.A. thesis, San Francisco State University (1975)"},{"key":"8_CR3","volume-title":"Innovation in Audio Description Research","author":"S Braun","year":"2021","unstructured":"Braun, S., Starr, K.: Innovation in Audio Description Research. Routledge, New York (2021)"},{"issue":"6","key":"8_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355390","volume":"52","author":"N Aafaq","year":"2019","unstructured":"Aafaq, N., Mian, A., Liu, W., et al.: Video description: a survey of methods, datasets, and evaluation metrics. ACM Comput. Surv. (CSUR) 52(6), 1\u201337 (2019)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"8_CR5","doi-asserted-by":"publisher","first-page":"43799","DOI":"10.1109\/ACCESS.2021.3058248","volume":"9","author":"K Khurana","year":"2021","unstructured":"Khurana, K., Deshpande, U.: Video question-answering techniques, benchmark datasets and evaluation metrics leveraging video captioning: a comprehensive survey. IEEE Access 9, 43799\u201343823 (2021)","journal-title":"IEEE Access"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., et al.: Sequence to sequence-video to text. In: The IEEE International Conference on Computer Vision 2015, pp. 4534\u20134542. IEEE, Santiago (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., et al.: Describing videos by exploiting temporal structure. In: The IEEE International Conference on Computer Vision 2015, pp. 4507\u20134515. IEEE, Santiago (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Pan, Y., Mei, T., Yao, T., et al.: Jointly modeling embedding and translation to bridge video and language. In: The IEEE Conference on Computer Vision and Pattern Recognition 2016, pp. 4594\u20134602. IEEE, Las Vegas (2016)","DOI":"10.1109\/CVPR.2016.497"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., et al.: MSR-VTT: a large video description dataset for bridging video and language. In: The IEEE Conference on Computer Vision and Pattern Recognition 2016, pp. 5288\u20135296. IEEE, Las Vegas (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., et al.: Video paragraph captioning using hierarchical recurrent neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition 2016, pp. 4584\u20134593. IEEE, Las Vegas (2016)","DOI":"10.1109\/CVPR.2016.496"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Pan, P., Xu, Z., Yang, Y., et al.: Hierarchical recurrent neural encoder for video representation with application to captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2016, pp. 1029\u20131038. IEEE, Las Vegas (2016)","DOI":"10.1109\/CVPR.2016.117"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: CIDEr: consensus-based image description evaluation. In: The IEEE Conference on Computer Vision and Pattern Recognition 2015, pp. 4566\u20134575. IEEE, Boston (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"8_CR13","doi-asserted-by":"publisher","first-page":"16639","DOI":"10.1109\/ACCESS.2018.2814075","volume":"6","author":"A Dilawari","year":"2018","unstructured":"Dilawari, A., Khan, M.U.G., Farooq, A., et al.: Natural language description of video streams using task-specific feature encoding. IEEE Access 6, 16639\u201316645 (2018)","journal-title":"IEEE Access"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., et al.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2015, pp. 3156\u20133164. IEEE, Boston (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"9","key":"8_CR15","doi-asserted-by":"publisher","first-page":"1783","DOI":"10.1109\/TPAMI.2016.2613873","volume":"39","author":"SS Husain","year":"2016","unstructured":"Husain, S.S., Bober, M.: Improving large-scale image retrieval through robust aggregation of local descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 39(9), 1783\u20131796 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Rohrbach, M., Tang, S., et al.: Generating descriptions with grounded and co-referenced people. In: The IEEE Conference on Computer Vision and Pattern Recognition 2017, pp. 4979\u20134989. IEEE, Honolulu (2017)","DOI":"10.1109\/CVPR.2017.447"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Huang, T.H., Ferraro, F., Mostafazadeh, N., et al.: Visual storytelling. In: The Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies 2016, pp. 1233\u20131239. Association for Computational Linguistics, San Diego (2016)","DOI":"10.18653\/v1\/N16-1147"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Yadav, N., Naik, D.: Generating short video description using Deep-LSTM and attention mechanism. In: International Conference for Convergence in Technology (I2CT) 2021, pp. 1\u20136. IEEE (2021)","DOI":"10.1109\/I2CT51068.2021.9417907"},{"issue":"6","key":"8_CR19","doi-asserted-by":"publisher","first-page":"2465","DOI":"10.1002\/int.22387","volume":"36","author":"YF Huang","year":"2021","unstructured":"Huang, Y.F., Shih, L.P., Tsai, C.H., et al.: Describing video scenarios using deep learning techniques. Int. J. Intell. Syst. 36(6), 2465\u20132490 (2021)","journal-title":"Int. J. Intell. Syst."},{"issue":"1","key":"8_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-022-00569-4","volume":"9","author":"D Naik","year":"2022","unstructured":"Naik, D., Jaidhar, C.D.: Semantic context driven language descriptions of videos using deep neural network. J. Big Data 9(1), 1\u201322 (2022)","journal-title":"J. Big Data"},{"issue":"1","key":"8_CR21","doi-asserted-by":"publisher","first-page":"317","DOI":"10.3390\/app12010317","volume":"12","author":"S Ahmed","year":"2021","unstructured":"Ahmed, S., Saif, A.F.M.S., Hanif, M.I., et al.: Att-BiL-SL: attention-based Bi-LSTM and sequential LSTM for describing video in the textual formation. Appl. Sci. 12(1), 317 (2021)","journal-title":"Appl. Sci."},{"key":"8_CR22","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.cviu.2017.04.013","volume":"163","author":"AA Liu","year":"2017","unstructured":"Liu, A.A., Xu, N., Wong, Y., et al.: Hierarchical & multimodal video captioning: discovering and transferring multimodal knowledge for vision to language. Comput. Vis. Image Underst. 163, 113\u2013125 (2017)","journal-title":"Comput. Vis. Image Underst."}],"container-title":["Lecture Notes in Computer Science","Machine Learning for Cyber Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20096-0_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T15:06:20Z","timestamp":1673535980000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20096-0_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031200953","9783031200960"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20096-0_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"13 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ML4CS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning for Cyber Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ml4cs2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/nsclab.org\/ml4cs2022\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}