{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:24:22Z","timestamp":1772119462793,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T00:00:00Z","timestamp":1686614400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T00:00:00Z","timestamp":1686614400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61573182"],"award-info":[{"award-number":["61573182"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073164"],"award-info":[{"award-number":["62073164"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["NS2020025"],"award-info":[{"award-number":["NS2020025"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s00530-023-01124-8","type":"journal-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T13:01:36Z","timestamp":1686661296000},"page":"2575-2589","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VMSG: a video caption network based on multimodal semantic grouping and semantic attention"],"prefix":"10.1007","volume":"29","author":[{"given":"Xin","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangchen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,13]]},"reference":[{"issue":"3","key":"1124_CR1","first-page":"2514","volume":"35","author":"H Ryu","year":"2021","unstructured":"Ryu, H., Kang, S., Kang, H., et al.: Semantic grouping network for video captioning. Proc. AAAI Conf. Artif. Intell. 35(3), 2514\u20132522 (2021)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"1124_CR2","doi-asserted-by":"crossref","unstructured":"Wang, B., Ma, L., Zhang, W., et al.: Reconstruction network for video captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 7622\u20137631. (2018)","DOI":"10.1109\/CVPR.2018.00795"},{"key":"1124_CR3","doi-asserted-by":"crossref","unstructured":"Jin, Q., Chen, J., Chen, S., et al.: Describing videos using multi-modal fusion. In: Proceedings of the 24th ACM international conference on multimedia, 1087\u20131091. (2016)","DOI":"10.1145\/2964284.2984065"},{"key":"1124_CR4","doi-asserted-by":"crossref","unstructured":"Hori, C., Hori, T., Lee T Y, et al.: Attention-based multimodal fusion for video description.In: Proceedings of the IEEE international conference on computer vision. 4193\u20134202. (2017)","DOI":"10.1109\/ICCV.2017.450"},{"key":"1124_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, S., Zhang, W., et al.: Less is more: Picking informative frames for video captioning. In: Proceedings of the European conference on computer vision (ECCV). 358\u2013373. (2018)","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"1124_CR6","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., et al.: Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision. 4489\u20134497. (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"1124_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 770\u2013778. (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1124_CR8","doi-asserted-by":"crossref","unstructured":"Hara, K., Kataoka, H., Satoh, Y.: Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet?, In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. (2018)","DOI":"10.1109\/CVPR.2018.00685"},{"issue":"12","key":"1124_CR9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0144610","volume":"10","author":"T Giannakopoulos","year":"2015","unstructured":"Giannakopoulos, T.: Pyaudioanalysis: an open-source python library for audio signal analysis[J]. PLoS ONE 10(12), e0144610 (2015)","journal-title":"PLoS ONE"},{"key":"1124_CR10","first-page":"I","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need[J]. Adv. Neural. Inf. Process. Syst. 30, I (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1124_CR11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571","author":"J Xu","year":"2016","unstructured":"Xu, J., Mei, T., Yao, T., et al.: Msr-vtt: A large video description dataset for bridging video and language. Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.571","journal-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit."},{"key":"1124_CR12","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., et al.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the Association for Computational Linguistics, 311\u2013318. (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"1124_CR13","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. 65\u201372. (2005)"},{"key":"1124_CR14","unstructured":"Rouge, LCY.: A package for automatic evaluation of summaries. In: Proceedings of Workshop on Text Summarization of ACL, Spain. (2004)"},{"key":"1124_CR15","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: Consensus-based image description evaluation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 4566\u20134575. (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"issue":"2s","key":"1124_CR16","first-page":"1","volume":"17","author":"W Ji","year":"2021","unstructured":"Ji, W., Wang, R.: A multi-instance multi-label dual learning approach for video captioning [J]. ACM Trans. Multimid. Computing Commun. Appl. 17(2s), 1\u201318 (2021)","journal-title":"ACM Trans. Multimid. Computing Commun. Appl."},{"key":"1124_CR17","doi-asserted-by":"crossref","unstructured":"Xu, N., Mao, W., Chen, G.: Multi-interactive memory network for aspect based multimodal sentiment analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence. 33(01), 371\u2013378. (2019)","DOI":"10.1609\/aaai.v33i01.3301371"},{"key":"1124_CR18","doi-asserted-by":"publisher","first-page":"1772","DOI":"10.1109\/TMM.2020.3002669","volume":"23","author":"W Xu","year":"2020","unstructured":"Xu, W., Yu, J., Miao, Z., et al.: Deep reinforcement polishing network for video captioning[J]. IEEE Trans. Multimed. 23, 1772\u20131784 (2020)","journal-title":"IEEE Trans. Multimed."},{"key":"1124_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.108332","volume":"117","author":"W Ji","year":"2022","unstructured":"Ji, W., Wang, R., Tian, Y., et al.: An attention based dual learning approach for video captioning[J]. Appl. Soft Comput. 117, 108332 (2022)","journal-title":"Appl. Soft Comput."},{"key":"1124_CR20","doi-asserted-by":"crossref","unstructured":"Yao, L., Torabi, A., Cho, K., et al.: Describing videos by exploiting temporal structure. In: Proceedings of the IEEE international conference on computer vision. 4507\u20134515. (2015)","DOI":"10.1109\/ICCV.2015.512"},{"issue":"4","key":"1124_CR21","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.3390\/s20041085","volume":"20","author":"K Zhang","year":"2020","unstructured":"Zhang, K., Li, D., Huang, J., et al.: Automated video behavior recognition of pigs using two-stream convolutional networks[J]. Sensors 20(4), 1085 (2020)","journal-title":"Sensors"},{"key":"1124_CR22","doi-asserted-by":"crossref","unstructured":"Pan, B., Cai, H., Huang, D.A., et al.: Spatio-temporal graph for video captioning with knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 10870\u201310879. (2020)","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"1124_CR23","doi-asserted-by":"crossref","unstructured":"Liu, D., Qu, X., Dong, J., et al.: Reasoning step-by-step: Temporal sentence localization in videos via deep rectification-modulation network. In: Proceedings of the 28th International Conference on Computational Linguistics. (2020)","DOI":"10.18653\/v1\/2020.coling-main.167"},{"issue":"3","key":"1124_CR24","doi-asserted-by":"publisher","first-page":"2353","DOI":"10.1007\/s11063-020-10352-2","volume":"52","author":"S Chen","year":"2020","unstructured":"Chen, S., Zhong, X., Li, L., et al.: Adaptively converting auxiliary attributes and textual embedding for video captioning based on BiLSTM [J]. Neural Process. Lett. 52(3), 2353\u20132369 (2020)","journal-title":"Neural Process. Lett."},{"key":"1124_CR25","unstructured":"Pan, Y., Xu, J., Li, Y., et al.: Pre-training for Video Captioning Challenge 2020 Summary[J]. arXiv preprint arXiv:2008.00947.(2020)"},{"key":"1124_CR26","unstructured":"Yang, B., Zou, Y., Liu, F., et al.: Non-autoregressive coarse-to-fine video captioning[J]. arXiv preprint arXiv:1911.12018.(2019)"},{"key":"1124_CR27","doi-asserted-by":"crossref","unstructured":"Zhu, M., Duan, C., Yu, C.: Video Captioning in Compressed Video[J]. arXiv preprint arXiv:2101.00359. (2021)","DOI":"10.1109\/ICIVC52351.2021.9526927"},{"issue":"1s","key":"1124_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3539225","volume":"19","author":"J Chen","year":"2023","unstructured":"Chen, J., Pan, Y., Li, Y., et al.: Retrieval augmented convolutional encoder-decoder networks for video captioning[J]. ACM Trans. Multimed. Comput. Commun. Appl. 19(1s), 1\u201324 (2023)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"issue":"2","key":"1124_CR29","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1109\/TCSVT.2021.3063423","volume":"32","author":"J Deng","year":"2021","unstructured":"Deng, J., Li, L., Zhang, B., et al.: Syntax-guided hierarchical attention network for video captioning [J]. IEEE Trans. Circuits Syst. Video Technol. 32(2), 880\u2013892 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"12","key":"1124_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2021.3132229","volume":"44","author":"F Liu","year":"2022","unstructured":"Liu, F., Wu, X., You, C., et al.: Aligning source visual and target language domains for zero-shot captioning [J]. IEEE Trans. Pattern Anal. Mach. Intell. 44(12), 1 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1124_CR31","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.916","volume":"8","author":"H Zhao","year":"2022","unstructured":"Zhao, H., Chen, Z., Guo, L., et al.: Video captioning based on vision transformer and reinforcement learning[J]. PeerJ Comput. Sci. 8, e916 (2022)","journal-title":"PeerJ Comput. Sci."},{"key":"1124_CR32","doi-asserted-by":"crossref","unstructured":"Krishnamoorthy, N., Malkarnenkar, G., Mooney, R., et al.: Generating natural-language video descriptions using text-mined knowledge. In: Twenty-Seventh AAAI Conference on Artificial Intelligence. 328\u2013337. (2013)","DOI":"10.1609\/aaai.v27i1.8679"},{"key":"1124_CR33","doi-asserted-by":"crossref","unstructured":"Venugopalan, S., Xu, H., Donahue, J., et al.: Translating videos to natural language using deep recurrent neural networks [J]. arXiv preprint arXiv:1412.4729. (2014)","DOI":"10.3115\/v1\/N15-1173"},{"key":"1124_CR34","doi-asserted-by":"crossref","unstructured":"Baraldi, L., Grana, C., Cucchiara, R.: Hierarchical boundary-aware neural encoder for video captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 1657\u20131666. (2017)","DOI":"10.1109\/CVPR.2017.339"},{"key":"1124_CR35","doi-asserted-by":"crossref","unstructured":"Guo, J., Tan, X., He, D., et al.: Non-autoregressive neural machine translation with enhanced decoder input. In: Proceedings of the AAAI conference on artificial intelligence. 33(01), 3723\u20133730. (2019)","DOI":"10.1609\/aaai.v33i01.33013723"},{"key":"1124_CR36","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1007\/s00530-018-0598-5","volume":"25","author":"N Xu","year":"2019","unstructured":"Xu, N., Liu, A.A., Nie, W., et al.: Multi-guiding long short-term memory for video captioning [J]. Multimed. Syst. 25, 663\u2013672 (2019)","journal-title":"Multimed. Syst."},{"key":"1124_CR37","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: Glove: Global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). 1532\u20131543. (2014)","DOI":"10.3115\/v1\/D14-1162"},{"issue":"22","key":"1124_CR38","doi-asserted-by":"publisher","first-page":"31793","DOI":"10.1007\/s11042-019-08011-3","volume":"78","author":"JY Lee","year":"2019","unstructured":"Lee, J.Y.: Deep multimodal embedding for video captioning[J]. Multimed. Tools Appl. 78(22), 31793\u201331805 (2019)","journal-title":"Multimed. Tools Appl."},{"key":"1124_CR39","doi-asserted-by":"crossref","unstructured":"Ramanishka, V., Das, A., Park, D.H. et al.: Multimodal video description. In: Proceedings of the 24th ACM international conference on Multimedia. 1092\u20131096. (2016)","DOI":"10.1145\/2964284.2984066"},{"key":"1124_CR40","first-page":"14200","volume":"34","author":"A Nagrani","year":"2021","unstructured":"Nagrani, A., Yang, S., Arnab, A., et al.: Attention bottlenecks for multimodal fusion [J]. Adv. Neural. Inf. Process. Syst. 34, 14200\u201314213 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1124_CR41","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 [J]. Comput. Vis. Image Underst. 163, 113\u2013125 (2017)","journal-title":"Comput. Vis. Image Underst."},{"key":"1124_CR42","doi-asserted-by":"crossref","unstructured":"Chen, S., Jiang, Y.G.: Motion guided spatial attention for video captioning. In: Proceedings of the AAAI conference on artificial intelligence. 33(01), 8191\u20138198. (2019)","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"1124_CR43","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. 8327\u20138336. (2019)","DOI":"10.1109\/CVPR.2019.00852"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01124-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-023-01124-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01124-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T09:07:42Z","timestamp":1694768862000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-023-01124-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,13]]},"references-count":43,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["1124"],"URL":"https:\/\/doi.org\/10.1007\/s00530-023-01124-8","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-1542723\/v1","asserted-by":"object"}]},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,13]]},"assertion":[{"value":"10 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Xin Yang declares that he has no conflict of interest. Xiangchen Wang declares that he has no conflict of interest. Xiaohui Ye declares that he has no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}