{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:08:50Z","timestamp":1743149330355,"version":"3.40.3"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030551865"},{"type":"electronic","value":"9783030551872"}],"license":[{"start":{"date-parts":[[2020,8,25]],"date-time":"2020-08-25T00:00:00Z","timestamp":1598313600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,8,25]],"date-time":"2020-08-25T00:00:00Z","timestamp":1598313600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-55187-2_5","type":"book-chapter","created":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T23:04:00Z","timestamp":1598310240000},"page":"45-55","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Attention Mechanism Based Semantic Compositional Network for Video Captioning"],"prefix":"10.1007","author":[{"given":"Zhaoyu","family":"Dong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xian","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuqin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Cui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luo","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,8,25]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Zhong, X., Li, J., Huang, W., Xie, L.: Deep multi-label hashing for image retrieval. In: IEEE International Conference on Tools with Artificial Intelligence (ICTAI) (2019)","DOI":"10.1109\/ICTAI.2019.00-94"},{"key":"5_CR2","unstructured":"Xu, K., Ba, J., Kiros, R., Courville, A., Salakhutdinov, R., Zemel, R., Bengio, Y.: Show, attend and tell: neural image caption generation with visual attention. arXiv preprint arXiv:1502.03044 (2015)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: CVPR, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Lu, J., Xiong, C., Parikh, D., Socher, R.: Knowing when to look: adaptive attention via a visual sentinel for image captioning. arXiv preprint arXiv:1612.01887 (2016)","DOI":"10.1109\/CVPR.2017.345"},{"key":"5_CR5","unstructured":"Chen, X., Fang, H., Lin, T.-Y., Vedantam, R., Gupta, S., Dollar, P., Zitnick, C.L.: Microsoft coco captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Song, J., Guo, Z., Gao, L., Liu, W., Zhang, D., Shen, H.T.: Hierarchical LSTM with adjusted temporal attention for video captioning. arXiv:1706.01231v1 (2017)","DOI":"10.24963\/ijcai.2017\/381"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Gan, Z., Gan, C., He, X., Pu, Y., Tran, K., Gao, J., Carin, L., Deng, L.: Semantic compositional networks for visual captioning. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.127"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Rohrbach, M., Qiu, W., Titov, I., Thater, S., Pinkal, M., Schiele, B.: Translating video content to natural language descriptions. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.61"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Xu, R., Xiong, C., Chen, W., Corso, J.J.: Jointly modeling deep video and compositional text to bridge vision and language in a unified framework. In: AAAI (2015)","DOI":"10.1609\/aaai.v29i1.9512"},{"issue":"2","key":"5_CR10","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1023\/A:1020346032608","volume":"50","author":"A Kojima","year":"2002","unstructured":"Kojima, A., Tamura, T., Fukunaga, K.: Natural language description of human activities from video images based on concept hierarchy of actions. IJCV 50(2), 171\u2013184 (2002)","journal-title":"IJCV"},{"key":"5_CR11","unstructured":"Barbu, A., Bridge, A., Burchill, Z., Coroian, D., Dickinson, S., Fidler, S., Michaux, A., Mussman, S., Narayanaswamy, S., Salvi, D., et al.: Video in sentences out. In: UAI (2012)"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., Rohrbach, M., Mooney, R., Saenko, K.: Translating videos to natural language using deep recurrent neural networks. In: NAACL, pp. 1494\u20131504 (2015)","DOI":"10.3115\/v1\/N15-1173"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., Ballas, N., Pal, C., Larochelle, H., Courville, A.: Describing videos by exploiting temporal structure. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4507\u20134515 (2015)","DOI":"10.1109\/ICCV.2015.512"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional net?works. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Wu, Q., Shen, C., Liu, L., Dick, A., van den Hengel, A.: What value do explicit high level concepts have in vision to language problems? In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.29"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Fang, H., Gupta, S., Iandola, F., Srivastava, R.K., Deng, L., Doll\u00e1r, P., Gao, J., He, X., Mitchell, M., Platt, J.C., et al.: From captions to visual concepts and back. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Rohrbach, M., Donahue, J., Mooney, R., Darrell, T., Saenko, K.: Sequence to sequence-video to text. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4534\u20134542 (2015)","DOI":"10.1109\/ICCV.2015.515"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, J., Huang, Z., Yang, Y., Xu, W.: Video paragraph captioning using hierarchical recurrent neural networks. In: IEEE CVPR (2016)","DOI":"10.1109\/CVPR.2016.496"},{"key":"5_CR19","unstructured":"Xu, H., Venugopalan, S., Ramanishka, V., Rohrbach, M., Saenko, K.: A multi-scale multiple instance video description network. In: A Workshop on Closing the Loop Between Vision and Language at ICCV 2015 (2015)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Pan, Y., Mei, T., Yao, T., Li, H., Rui, Y.: Jointly modeling embedding and translation to bridge video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4594\u20134602 (2016)","DOI":"10.1109\/CVPR.2016.497"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Yang, Z., Han, Y., Wang, Z.: Catching the temporal regions-of-interest for video captioning. In: 25th ACM Multimedia, pp. 146\u2013153 (2017)","DOI":"10.1145\/3123266.3123327"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, X., Gao, K., Zhang, Y., Zhang, D., Li, J., Tian, Q.: Task-driven dynamic fusion: reducing ambiguity in video description. In: IEEE CVPR (2017)","DOI":"10.1109\/CVPR.2017.662"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, S., Zhang, W., Huang, Q.: Less is more: picking informative frames for video captioning. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01261-8_22"},{"issue":"9","key":"5_CR24","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1109\/TMM.2017.2729019","volume":"19","author":"L Gao","year":"2017","unstructured":"Gao, L., Guo, Z., Zhang, H., Xu, X., Shen, H.T.: Video captioning with attention-based LSTM and semantic consistency. IEEE Trans. Multimed. 19(9), 2045\u20132055 (2017)","journal-title":"IEEE Trans. Multimed."},{"issue":"8","key":"5_CR25","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."}],"container-title":["Advances in Intelligent Systems and Computing","Intelligent Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-55187-2_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,9]],"date-time":"2022-11-09T19:21:46Z","timestamp":1668021706000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-55187-2_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,25]]},"ISBN":["9783030551865","9783030551872"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-55187-2_5","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2020,8,25]]},"assertion":[{"value":"25 August 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IntelliSys","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Proceedings of SAI Intelligent Systems Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"London","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"intellisys2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/saiconference.com\/IntelliSys","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}