{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:24:39Z","timestamp":1743092679335,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":22,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819947607"},{"type":"electronic","value":"9789819947614"}],"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\/978-981-99-4761-4_5","type":"book-chapter","created":{"date-parts":[[2023,7,30]],"date-time":"2023-07-30T16:02:10Z","timestamp":1690732930000},"page":"51-62","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FRVidSwin:A Novel Video Captioning Model with Automatical Removal of Redundant Frames"],"prefix":"10.1007","author":[{"given":"Zehao","family":"Dong","sequence":"first","affiliation":[]},{"given":"Yuehui","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Yaou","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,31]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1109\/TPAMI.2016.2599174","volume":"39","author":"J Donahue","year":"2017","unstructured":"Donahue, J., et al.: Long-term recurrent convolutional networks for visual recognition and description. IEEE Trans. Pattern Anal. Mach. Intell. 39, 677\u2013691 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2599174","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video Swin Transformer. arXiv:2106.13230 [cs]. (2021)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"5_CR3","unstructured":"Kay, W., et al: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pp. 311\u2013318. Association for Computational Linguistics, USA (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"5_CR5","unstructured":"Banerjee, S., Lavie, A.: METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In: Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"5_CR6","unstructured":"Lin, C.-Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Zitnick, C.L., Parikh, D.: CIDEr: consensus-based image description evaluation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"5_CR8","unstructured":"Chen, D.L., Dolan, W.B.: Collecting highly parallel data for paraphrase evaluation. In: ACL, pp. 190\u2013200 (2011)"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Xu, J., Mei, T., Yao, T., Rui, Y.: MSR-VTT: a large video description dataset for bridging video and language. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5288\u20135296 (2016)","DOI":"10.1109\/CVPR.2016.571"},{"key":"5_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1007\/978-3-030-01261-8_22","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Chen","year":"2018","unstructured":"Chen, Y., Wang, S., Zhang, W., Huang, Q.: Less is more: picking informative frames for video captioning. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 367\u2013384. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_22"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Wang, B., Ma, L., Zhang, W., Liu, W.: Reconstruction network for video captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7622\u20137631 (2018)","DOI":"10.1109\/CVPR.2018.00795"},{"key":"5_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. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8347\u20138356 (2019)","DOI":"10.1109\/CVPR.2019.00854"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Zhang, J., Peng, Y.: Object-aware aggregation with bidirectional temporal graph for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8327\u20138336 (2019)","DOI":"10.1109\/CVPR.2019.00852"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Wang, B., Ma, L., Zhang, W., Jiang, W., Wang, J., Liu, W.: Controllable video captioning with pos sequence guidance based on gated fusion network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2641\u20132650 (2019)","DOI":"10.1109\/ICCV.2019.00273"},{"key":"5_CR15","doi-asserted-by":"publisher","unstructured":"Chen, S., Jiang, Y.-G.: Motion guided spatial attention for video captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8191\u20138198 (2019).https:\/\/doi.org\/10.1609\/aaai.v33i01.33018191","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Aafaq, N., Akhtar, N., Liu, W., Gilani, S.Z., Mian, A.: Spatio-temporal dynamics and semantic attribute enriched visual encoding for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12487\u201312496 (2019)","DOI":"10.1109\/CVPR.2019.01277"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Pan, B., et al.: Spatio-temporal graph for video captioning with knowledge distillation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10867\u201310876 (2020)","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Zheng, Q., Wang, C., Tao, D.: Syntax-aware action targeting for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13096\u201313105 (2020)","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Shi, Y., Yuan, C., Li, B., Wang, P., Hu, W., Zha, Z.-J.: Object relational graph with teacher-recommended learning for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13278\u201313288 (2020)","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Ryu, H., Kang, S., Kang, H., Yoo, C.D.: Semantic grouping network for video captioning. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2514\u20132522 (2021)","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Chen, S., Jiang, Y.-G.: Motion guided region message passing for video captioning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1543\u20131552 (2021)","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Ye, H., Li, G., Qi, Y., Wang, S., Huang, Q., Yang, M.-H.: Hierarchical modular network for video captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17939\u201317948 (2022)","DOI":"10.1109\/CVPR52688.2022.01741"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-4761-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T23:17:34Z","timestamp":1690931854000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-4761-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819947607","9789819947614"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-4761-4_5","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":"31 July 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2023a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2023\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}