{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T19:24:39Z","timestamp":1767900279135,"version":"3.49.0"},"reference-count":69,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2022,1,20]],"date-time":"2022-01-20T00:00:00Z","timestamp":1642636800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,20]],"date-time":"2022-01-20T00:00:00Z","timestamp":1642636800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62062041"],"award-info":[{"award-number":["62062041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s00521-021-06733-w","type":"journal-article","created":{"date-parts":[[2022,1,20]],"date-time":"2022-01-20T00:03:46Z","timestamp":1642637026000},"page":"5959-5977","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Visual and language semantic hybrid enhancement and complementary for video description"],"prefix":"10.1007","volume":"34","author":[{"given":"Pengjie","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunlan","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenlang","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,20]]},"reference":[{"issue":"2","key":"6733_CR1","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 (2002) Natural language description of human activities from video images based on concept hierarchy of actions. Int J Comput Vis 50(2):171\u2013184","journal-title":"Int J Comput Vis"},{"key":"6733_CR2","doi-asserted-by":"crossref","unstructured":"Guadarrama S, Krishnamoorthy N, Malkarnenkar G, Venugopalan S, Mooney R, Darrell T, Kate S (2013) Youtube2text: recognizing and describing arbitrary activities using semantic hierarchies and zero-shot recognition. In: IEEE international conference on computer vision (ICCV), Sydney, Australia, Jan 2013, IEEE, pp 2712\u20132719","DOI":"10.1109\/ICCV.2013.337"},{"key":"6733_CR3","doi-asserted-by":"crossref","unstructured":"Gupta A, Srinivasan P, Shi J, Davis LS (2009) Understanding videos, constructing plots learning a visually grounded storyline model from annotated videos. In: IEEE conference on computer vision and pattern recognition (CVPR), Miami, USA, Jun 2009, IEEE, pp 2012\u20132019","DOI":"10.1109\/CVPR.2009.5206492"},{"key":"6733_CR4","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Annual conference on neural information processing systems (NIPs), Quebec, Canada, Jul 2012, MIT, pp 1097\u20131105"},{"key":"6733_CR5","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR), Banff, Canada"},{"key":"6733_CR6","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition (CVPR), Boston, USA, June 2015, IEEE, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"6733_CR7","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, USA, June 2015, IEEE, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"6733_CR8","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: Annual conference on neural information processing systems (NIPS), Montreal, Canada, Dec 2014, MIT, pp 568\u2013576"},{"key":"6733_CR9","doi-asserted-by":"crossref","unstructured":"Wang L, Qiao Y, Tang X (2015) Action recognition with trajectory-pooled deep-convolutional descriptors. In: IEEE conference on computer vision and pattern recognition (CVPR), Boston, USA, June 2015, IEEE, pp 4305\u20134314","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"6733_CR10","unstructured":"Mao J, Xu W, Yang Y, Wang J, Yuille A (2014) Deep captioning with multimodal recurrent neural networks (m-RNN). In: International conference on learning representations (ICLR), Banff, Canada, Apr 2014"},{"key":"6733_CR11","doi-asserted-by":"crossref","unstructured":"Donahue J, Hendricks LA, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In: IEEE conference on computer vision and pattern recognition (CVPR), Boston, USA, June 2015, IEEE, pp 2625\u20132634","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"6733_CR12","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S, Erhan D (2015) Show and tell: A neural image caption generator. In: IEEE conference on computer vision and pattern recognition (CVPR), Boston, USA, June 2015, IEEE, pp 3156\u20133164","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"6733_CR13","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1016\/j.neucom.2018.05.086","volume":"312","author":"P Tang","year":"2018","unstructured":"Tang P, Wang H, Kwong S (2018) Deep sequential fusion lstm network for image description. Neurocomputing 312:154\u2013164","journal-title":"Neurocomputing"},{"key":"6733_CR14","doi-asserted-by":"crossref","unstructured":"Venugopalan S, Rohrbach M, Donahue J, Mooney R, Darrell T, Saenko K (2015) Sequence to sequence$$-$$video to text. In: IEEE international conference on computer vision (ICCV), Santiago, Chile, Dec 2015, IEEE, pp 4534\u20134542","DOI":"10.1109\/ICCV.2015.515"},{"key":"6733_CR15","doi-asserted-by":"crossref","unstructured":"Pan Y, Mei T, Yao T, Li H, Rui Y (2016) Jointly modeling embedding and translation to bridge video and language. In: IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, USA, June 2016, IEEE, pp 4594\u20134602","DOI":"10.1109\/CVPR.2016.497"},{"key":"6733_CR16","doi-asserted-by":"crossref","unstructured":"Yao L, Torabi A, Cho K, Ballas N, Pal C, Larochelle H, Courville A (2015) Describing videos by exploiting temporal structure. In: IEEE international conference on computer vision (ICCV), Santiago, Chile, Dec 2015, IEEE, pp 4507\u20134515","DOI":"10.1109\/ICCV.2015.512"},{"key":"6733_CR17","doi-asserted-by":"crossref","unstructured":"Pan P, Xu Z, Yang Y, Wu F, Zhuang Y (2016) Hierarchical recurrent neural encoder for video representation with application to captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, USA, June 2016, IEEE, pp 1029\u20131038","DOI":"10.1109\/CVPR.2016.117"},{"key":"6733_CR18","doi-asserted-by":"crossref","unstructured":"Yu Y, Ko H, Choi J, Kim G (2017) End-to-end concept word detection for video captioning, retrieval, and question answering. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, USA, Jul., IEEE, pp 3261\u20133269","DOI":"10.1109\/CVPR.2017.347"},{"key":"6733_CR19","doi-asserted-by":"crossref","unstructured":"Zheng Q, Wang C, Tao D (2020) Syntax-aware action targeting for video captioning. In: In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Online (Virtual), June 2020, IEEE, pp 13096\u201313105","DOI":"10.1109\/CVPR42600.2020.01311"},{"issue":"3","key":"6733_CR20","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z et al (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"6733_CR21","unstructured":"Xu K, Ba JL, Kiros R, Cho K, Courville A, Salakhutdinov R, et al (2015) Show, attend and tell: Neural image caption generation with visual attention. In: International conference on machine learning (ICML), Lille, France, July 2015, ACM, pp 2048\u20132057"},{"issue":"11","key":"6733_CR22","doi-asserted-by":"publisher","first-page":"1875","DOI":"10.1109\/TMM.2015.2477044","volume":"17","author":"K Cho","year":"2015","unstructured":"Cho K, Courville A, Bengio Y (2015) Describing multimedia content using attention-based encoder-decoder networks. IEEE Trans Multimedia 17(11):1875\u20131886","journal-title":"IEEE Trans Multimedia"},{"issue":"7","key":"6733_CR23","doi-asserted-by":"publisher","first-page":"2631","DOI":"10.1109\/TCYB.2018.2831447","volume":"49","author":"Y Bin","year":"2019","unstructured":"Bin Y, Yang Y, Shen F, Xie N, Shen H, Li X (2019) Describing video with attention based bidirectional lstm. IEEE Trans Cyber 49(7):2631\u20132641","journal-title":"IEEE Trans Cyber"},{"issue":"9","key":"6733_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 (2017) Video captioning with attention-based lstm and semantic consistency. IEEE Trans Multimedia 19(9):2045\u20132055","journal-title":"IEEE Trans Multimedia"},{"key":"6733_CR25","doi-asserted-by":"crossref","unstructured":"Jin T, Huang S, Chen M, Li Y, Zhang Z (2020) Sbat: Video captioning with sparse boundary-aware transformer. In: International joint conference on artificial intelligence (IJCAI), Online (Virtual), Jan 2020, Morgan Kaufmann, pp 630\u2013636","DOI":"10.24963\/ijcai.2020\/88"},{"key":"6733_CR26","unstructured":"Pan Y, Li Y, Luo J, Xu J, Yao T, Mei T (2020) Auto-captions on gif: a large-scale video-sentence dataset for vision-language pre-training. arXiv:2007.02375"},{"key":"6733_CR27","doi-asserted-by":"crossref","unstructured":"Wu Q, Shen C, Liu L, Dick A, Hengel A (2016) What value do explicit high level concepts have in vision to language problems? In: IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, USA, Jun 2016, IEEE, pp 203\u2013212","DOI":"10.1109\/CVPR.2016.29"},{"key":"6733_CR28","doi-asserted-by":"crossref","unstructured":"Pan Y, Yao T, Li H, Mei T (2017) Video captioning with transferred semantic attributes. In: IEEE international conference on computer vision (ICCV), Venice, Italy, Oct 2017, IEEE, pp 984\u2013992","DOI":"10.1109\/CVPR.2017.111"},{"key":"6733_CR29","doi-asserted-by":"crossref","unstructured":"Chen Y, Wang S, Zhang W, Huang Q (2018) Less is more: picking informative frames for video captioning. In: European conference on computer vision (ECCV), Munich, Germany, Sept 2018, IEEE, pp 367\u2013384","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"6733_CR30","doi-asserted-by":"crossref","unstructured":"Wang X, Chen W, Wu J, Wang YF, Wang WY (2018) Video captioning via hierarchical reinforcement learning. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, Jun 2018, IEEE, pp 4213\u20134222","DOI":"10.1109\/CVPR.2018.00443"},{"issue":"11","key":"6733_CR31","doi-asserted-by":"publisher","first-page":"5600","DOI":"10.1109\/TIP.2018.2855422","volume":"27","author":"Y Yang","year":"2018","unstructured":"Yang Y, Zhou J, Ai J, Bin Y, Hanjalic A, Shen H (2018) Video captioning by adversarial lstm. IEEE Trans Image Process 27(11):5600\u20135611","journal-title":"IEEE Trans Image Process"},{"key":"6733_CR32","unstructured":"Chen DL, Dolan WB (2011) Collecting highly parallel data for paraphrase evaluation. In: The 49th annual meeting of the association for computational linguistics (ACL). Portland, USA, Jun 2011, ACL, pp. 190\u2013200"},{"key":"6733_CR33","doi-asserted-by":"crossref","unstructured":"Xu J, Mei T, Yao T, Rui Y (2016) MSR-VTT: A large video description dataset for bridging video and language. In: IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, USA, Jun 2016, IEEE, pp 5288\u20135296","DOI":"10.1109\/CVPR.2016.571"},{"issue":"2","key":"6733_CR34","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/BF00849074","volume":"8","author":"HH Nagel","year":"1994","unstructured":"Nagel HH (1994) A vision of xxx vision and language xxx comprises action: an example from road traffic. Artif Intell Rev 8(2):189\u2013214","journal-title":"Artif Intell Rev"},{"key":"6733_CR35","doi-asserted-by":"crossref","unstructured":"Rohrbach M, Qiu W, Titov I, Thater S, Pinkal M, Schiele B (2013) Translating video content to natural language descriptions. In: IEEE international conference on computer vision (ICCV), Sydney, Australia, Jan 2013, IEEE, , pp 433\u2013440","DOI":"10.1109\/ICCV.2013.61"},{"key":"6733_CR36","doi-asserted-by":"crossref","unstructured":"Venugopalan S, Xu H, Donahue J, Rohrbach M, Mooney R, Saenko K (2015) Translating videos to natural language using deep recurrent neural networks. In: The 2015 annual conference of the north american chapter of the ACL (NAACL), Denver, USA, May, ACL, pp 1494\u20131504","DOI":"10.3115\/v1\/N15-1173"},{"key":"6733_CR37","doi-asserted-by":"crossref","unstructured":"Venugopalan S, Hendricks LA, Mooney R, Saenko K (2016) Improving lstm-based video description with linguistic knowledge mined from text. In: Conference on empirical methods in natural language processing (EMNLP), Austin, USA, Nov 2016, ACL, pp 1961\u20131966","DOI":"10.18653\/v1\/D16-1204"},{"key":"6733_CR38","doi-asserted-by":"crossref","unstructured":"Johnson J, Karpathy A, Li FF (2016) DenseCap: Fully convolutional localization networks for dense captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, USA, Jun 2016, IEEE, pp 4565\u20134574","DOI":"10.1109\/CVPR.2016.494"},{"key":"6733_CR39","doi-asserted-by":"crossref","unstructured":"Shen Z, Li J, Su Z, Li M, Chen Y, Jiang YG, Xue X (2017) Weakly supervised dense video captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, USA, Jul 2017, IEEE, pp 1916\u20131924","DOI":"10.1109\/CVPR.2017.548"},{"key":"6733_CR40","doi-asserted-by":"crossref","unstructured":"Wang J, Jiang W, Ma L, Liu W, Xu Y (2018) Bidirectional attentive fusion with context gating for dense video captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City, USA, Jun 2018, IEEE, pp 7190\u20137198","DOI":"10.1109\/CVPR.2018.00751"},{"key":"6733_CR41","doi-asserted-by":"crossref","unstructured":"Zhou L, Zhou Y, Jason JC, Richard S, Xiong C (2018) End-to-end dense video captioning with masked transformer. In: IEEE conference on computer vision and pattern recognition (CVPR),Salt Lake City, USA, Jun 2018, IEEE, pp 8739\u20138748","DOI":"10.1109\/CVPR.2018.00911"},{"key":"6733_CR42","doi-asserted-by":"crossref","unstructured":"Krishna R, Hata K, Ren F, Li FF, Niebles JC (2017) Dense-captioning events in videos. In: IEEE international conference on computer vision (ICCV), Venice, Italy, Oct 2017, IEEE, pp 706\u2013715","DOI":"10.1109\/ICCV.2017.83"},{"key":"6733_CR43","doi-asserted-by":"crossref","unstructured":"Mun J, Yang L, Ren Z, Xu N, Han B (2019) Streamlined dense video captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Long Beach, USA, Jun 2019, IEEE, pp 6588\u20136597","DOI":"10.1109\/CVPR.2019.00675"},{"key":"6733_CR44","doi-asserted-by":"crossref","unstructured":"Zhang Z, Shi Y, Yuan C, Li B, Wang P, Hu W, Zha Z (2020) Object relational graph with teacher-recommended learning for video captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Online (Virtual), Jun 2020, IEEE, pp 13278\u201313288","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"6733_CR45","doi-asserted-by":"crossref","unstructured":"Zhang J, Peng Y (2019) Object-aware aggregation with bidirectional temporal graph for video captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Long Beach, USA, Jun 2019, IEEE, pp 8327\u20138336","DOI":"10.1109\/CVPR.2019.00852"},{"key":"6733_CR46","doi-asserted-by":"crossref","unstructured":"Zhang J, Peng Y (2019) Hierarchical vision-language alignment for video captioning. In: International conference on multimedia modeling (MMM), Thessaloniki, Greece, Jan 2019, Springer, pp 42\u201354","DOI":"10.1007\/978-3-030-05710-7_4"},{"key":"6733_CR47","doi-asserted-by":"crossref","unstructured":"Park JS, Rohrbach M, Darrell T, Rohrbach A (2019) Adversarial inference for multi-sentence video description. In: IEEE conference on computer vision and pattern recognitionlong beach, USA, Jun 2019, IEEE, pp 6598\u20136608","DOI":"10.1109\/CVPR.2019.00676"},{"key":"6733_CR48","doi-asserted-by":"crossref","unstructured":"Vedantam R, Zitnick CL, Parikh D (2015) CIDEr: Consensus-based image description evaluation. In: IEEE conference on computer vision and pattern recognition (CVPR), Boston, USA, Jun 2015, IEEE, pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"6733_CR49","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu WJ (2002) BLEU: A method for automatic evaluation of machine translation. In: Annual meeting of the association for computational linguistics (ACL), Philadelphia, USA, Jul 2002, ACL, pp 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"6733_CR50","unstructured":"Banerjee S, Lavie A (2005) METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In: Annual meeting of the association for computational linguistics workshop (ACLW), Ann Arbor, USA, Jun 2005, ACL, pp 65\u201372"},{"key":"6733_CR51","doi-asserted-by":"crossref","unstructured":"Lin CY, Och FJ (2004) Automatic evaluation of machine translation quality using longest common subsequence and skip-bigram statistics. In: Annual meeting of the association for computational linguistics (ACL), Barcelona, Spain, Jul 2004, ACL, pp 21\u201326","DOI":"10.3115\/1218955.1219032"},{"key":"6733_CR52","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: Convolutional architecture for fast feature embedding. In: ACM international conference on multimedia (ACM MM), Orlando, USA, Nov 2014, ACM, pp 675\u2013678","DOI":"10.1145\/2647868.2654889"},{"key":"6733_CR53","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollr P, Zitnick CL (2014) Microsoft coco: Common objects in context. In: European conference on computer vision (ECCV), Zurich, Switzerland, Sept 2014, Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"6733_CR54","doi-asserted-by":"crossref","unstructured":"Aafaq N, Akhtar N, Liu W, Gilani SZ, Mian A (2019) Spatio-temporal dynamics and semantic attribute enriched visual encoding for video captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Long Beach, USA, Jun 2019, IEEE, pp 12487\u201312496","DOI":"10.1109\/CVPR.2019.01277"},{"key":"6733_CR55","unstructured":"Thomason J, Venugopalan S, Guadarrama S, Saenko K, Mooney R (2014) Integrating language and vision to generate natural language descriptions of videos in the wild. In: Proceedings of international conference on computational linguistics (COLING), Dublin, Ireland, Aug 2014, ACL, pp 1218\u20131227"},{"key":"6733_CR56","doi-asserted-by":"crossref","unstructured":"Baraldi L, Costantino G, Rita C (2017) Hierarchical boundary-aware neural encoder for video captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, USA, Jul 2017, IEEE, pp 3185\u20133194","DOI":"10.1109\/CVPR.2017.339"},{"key":"6733_CR57","unstructured":"Ballas N, Yao L, Pal C, Courville A (2015) Delving deeper into convolutional networks for learning video representations. In: International conference on learning representations (ICLR), San Diego, USA, May 2015"},{"key":"6733_CR58","doi-asserted-by":"crossref","unstructured":"Yu H, Wang J, Huang Z, Yang Y, Xu W (2016) Video paragraph captioning using hierarchical recurrent neural networks. In: IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, USA, Jun 2016, IEEE, pp 4584\u20134593","DOI":"10.1109\/CVPR.2016.496"},{"key":"6733_CR59","unstructured":"Pu Y, Min MR, Gan Z, Carin L (2016) Adaptive feature abstraction for translating video to language. arXiv preprint arXiv:1611.07837"},{"issue":"5","key":"6733_CR60","first-page":"1112","volume":"42","author":"L Gao","year":"2020","unstructured":"Gao L, Li X, Song J, Shen HT (2020) Hierarchical LSTMs with adaptive attention for visual captioning. IEEE Trans Pattern Anal Mach Intell 42(5):1112\u20131131","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6733_CR61","doi-asserted-by":"crossref","unstructured":"Ramanishka V, Abir D, Huk PD, Subhashini V, Anne HL, Marcus R, Kate S (2016) Multimodal video description. In: ACM conference on multimedia conference (ACM MM), Amsterdam, Netherlands, Oct 2016 ACM, pp 1092\u20131096","DOI":"10.1145\/2964284.2984066"},{"key":"6733_CR62","doi-asserted-by":"crossref","unstructured":"Wang J, Wang W, Huang Y, Wang L, Tan T (2018) M3: Multimodal memory modelling for video captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City, USA, Jun 2018, IEEE, pp 7512\u20137520","DOI":"10.1109\/CVPR.2018.00784"},{"issue":"10","key":"6733_CR63","doi-asserted-by":"publisher","first-page":"3047","DOI":"10.1109\/TNNLS.2018.2851077","volume":"30","author":"J Song","year":"2019","unstructured":"Song J, Guo Y, Gao L, Li X, Alan H, Shen H (2019) From deterministic to generative: multimodal stochastic rnns for video captioning. IEEE Trans Neural Netw Learn Syst 30(10):3047\u20133058","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"6733_CR64","doi-asserted-by":"crossref","unstructured":"Gan Z, Gan C, He X, Pu Y, Tran K, Gao J, Carin L, Deng L (2017) Semantic compositional networks for visual captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Honolulu, USA, Jul 2017, IEEE, pp 5630\u20135639","DOI":"10.1109\/CVPR.2017.127"},{"key":"6733_CR65","doi-asserted-by":"crossref","unstructured":"Chen J, Pan Y, Li Y, Yao T, Chao H, Mei T (2019) Temporal deformable convolutional encoder-decoder networks for video captioning. In: AAAI conference on artificial intelligence (AAAI), Honolulu, USA, Jan 2019, AAAI, pp 8167\u20138174","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"6733_CR66","doi-asserted-by":"crossref","unstructured":"Wang B, Ma L, Zhang W, Liu W, Reconstruction network for video captioning. In: IEEE conference on computer vision and pattern recognition (CVPR), Salt Lake City, USA, Jun 2018, IEEE, pp 7622\u20137631","DOI":"10.1109\/CVPR.2018.00795"},{"key":"6733_CR67","doi-asserted-by":"crossref","unstructured":"Dong J, Li X, Lan W, Huo Y, Snoek CG (2016) Early embedding and late reranking for video captioning. In: ACM conference on multimedia conference (ACM MM), Amsterdam, Netherlands, Oct 2016, ACM, pp 1082\u20131086","DOI":"10.1145\/2964284.2984064"},{"key":"6733_CR68","doi-asserted-by":"crossref","unstructured":"Shetty R, Laaksonen J (2016) Frame- and segment-level features and candidate pool evaluation for video caption generation. In: ACM conference on multimedia conference (ACM MM), Amsterdam, Netherlands, Oct 2016, ACM, pp 1073\u20131076","DOI":"10.1145\/2964284.2984062"},{"key":"6733_CR69","doi-asserted-by":"crossref","unstructured":"Jin Q, Chen J, Chen S, Xiong Y, Hauptmann A (2016) Describing videos using multimodal fusion. In: ACM conference on multimedia conference (ACM MM), Amsterdam, Netherlands, Oct 2016, ACM, pp 1087\u20131091","DOI":"10.1145\/2964284.2984065"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06733-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06733-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06733-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,16]],"date-time":"2022-03-16T14:19:49Z","timestamp":1647440389000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06733-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,20]]},"references-count":69,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["6733"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06733-w","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,20]]},"assertion":[{"value":"29 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 November 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}