{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T10:38:57Z","timestamp":1784025537099,"version":"3.55.0"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2021,1,30]],"date-time":"2021-01-30T00:00:00Z","timestamp":1611964800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,30]],"date-time":"2021-01-30T00:00:00Z","timestamp":1611964800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["(Grant No. 62077009)"],"award-info":[{"award-number":["(Grant No. 62077009)"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s00521-020-05587-y","type":"journal-article","created":{"date-parts":[[2021,1,30]],"date-time":"2021-01-30T06:02:43Z","timestamp":1611986563000},"page":"8335-8354","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":61,"title":["Student Class Behavior Dataset: a video dataset for recognizing, detecting, and captioning students\u2019 behaviors in classroom scenes"],"prefix":"10.1007","volume":"33","author":[{"given":"Bo","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaijie","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lejun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanqing","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ao","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,30]]},"reference":[{"key":"5587_CR1","doi-asserted-by":"crossref","unstructured":"Wang L, Qiao Y, Tang X (2015) Action recognition with trajectory-pooled deep-convolutional descriptors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4305\u20134314","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"5587_CR2","doi-asserted-by":"crossref","unstructured":"Wang X, Girshick R, Gupta A, He K (2018) Non-local neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7794\u20137803","DOI":"10.1109\/CVPR.2018.00813"},{"key":"5587_CR3","doi-asserted-by":"crossref","unstructured":"Wang Y, Long M, Wang J, Yu PS (2017) Spatiotemporal pyramid network for video action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1529\u20131538","DOI":"10.1109\/CVPR.2017.226"},{"key":"5587_CR4","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) SSD: single shot multibox detector. In: European conference on computer vision. Springer, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"5587_CR5","doi-asserted-by":"crossref","unstructured":"Lu X, Li B, Yue Y, Li Q, Yan J (2019) Grid r-cnn. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7363\u20137372","DOI":"10.1109\/CVPR.2019.00754"},{"key":"5587_CR6","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"5587_CR7","unstructured":"Shaoqing Ren, Kaiming He,Ross Girshick,Jian Sun (2016) Faster R-CNN: towards real-time object detection with region proposal networks. In: IEEE transactions on pattern analysis and machine intelligence. arXiv:1506.01497"},{"key":"5587_CR8","doi-asserted-by":"crossref","unstructured":"Berclaz J, Fleuret F, Fua P (2006) Robust people tracking with global trajectory optimization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 744\u2013750","DOI":"10.1109\/CVPR.2006.258"},{"key":"5587_CR9","doi-asserted-by":"crossref","unstructured":"Breitenstein MD, Reichlin F, Leibe B, Koller-Meier E, Gool L (2009) Robust tracking-by-detection using a detector confidence particle filter. In: Proceedings of the IEEE international conference on computer vision, pp 1515\u20131522","DOI":"10.1109\/ICCV.2009.5459278"},{"key":"5587_CR10","unstructured":"Defferrard M, Bresson X, Vandergheynst P (2016) Convolutional neural networks on graphs with fast localized spectral filtering. In: Advances in neural information processing systems, pp 3844\u20133852"},{"key":"5587_CR11","doi-asserted-by":"crossref","unstructured":"Ma L, Lu Z, Shang L, Li H (2015) Multimodal convolutional neural networks for matching image and sentence. In: Proceedings of the IEEE international conference on computer vision, pp 2623\u20132631","DOI":"10.1109\/ICCV.2015.301"},{"issue":"1","key":"5587_CR12","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/JPROC.2015.2487976","volume":"104","author":"J Wang","year":"2016","unstructured":"Wang J, Liu W, Kumar S, Chang S (2016) Learning to hash for indexing big data: a survey. Proc IEEE 104(1):34\u201357","journal-title":"Proc IEEE"},{"key":"5587_CR13","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1109\/MMUL.2016.39","volume":"23","author":"W Liu","year":"2016","unstructured":"Liu W, Zhang T (2016) Multimedia hashing and networking. IEEE Multimed 23:75\u201379","journal-title":"IEEE Multimed"},{"key":"5587_CR14","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1016\/j.patcog.2017.03.021","volume":"75","author":"J Song","year":"2018","unstructured":"Song J, Gao L, Liu L, Zhu X, Sebe N (2018) Quantization-based hashing: a general framework for scalable image and video retrieval. Pattern Recogn 75:175\u2013187","journal-title":"Pattern Recogn"},{"issue":"4","key":"5587_CR15","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1109\/TPAMI.2017.2699960","volume":"40","author":"J Wang","year":"2018","unstructured":"Wang J, Zhang T, Song J, Sebe N, Shen H (2018) A Survey on Learning to Hash. IEEE Trans Pattern Anal Mach Intell 40(4):769\u2013790","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5587_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3579-x","author":"Z Haijun","year":"2019","unstructured":"Haijun Z, Yuzhu J, Wang H, Linlin L (2019) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-018-3579-x","journal-title":"Neural Comput Appl"},{"key":"5587_CR17","first-page":"16","volume":"3","author":"L Ma","year":"2016","unstructured":"Ma L, Lu Z, Li H (2016) Learning to answer questions from image using convolutional neural network. Assoc Adv Artif Intel 3:16","journal-title":"Assoc Adv Artif Intel"},{"key":"5587_CR18","unstructured":"Soomro K, Zamir AR, Shah MJCe (2012) UCF101: a dataset of 101 human actions classes from videos in the wild. arXiv:1212.0402"},{"key":"5587_CR19","doi-asserted-by":"crossref","unstructured":"Kuehne, H, Jhuang, H, Garrote, E, Poggio, T.A., Serre, T (2011) HMDB: a large video database for human motion recognition. In: Proceedings of the IEEE international conference on computer vision, pp 2556\u20132563","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"5587_CR20","unstructured":"Chen D, Dolan WB (2011) Collecting highly parallel data for paraphrase evaluation. In: Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies, pp 190\u2013200"},{"key":"5587_CR21","doi-asserted-by":"crossref","unstructured":"Gu C, Sun C, Ross DA, Vondrick C, Pantofaru C, Li Y, Vijayanarasimhan S, Toderici G, Ricco S, Sukthankar R (2018) Ava: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6047\u20136056","DOI":"10.1109\/CVPR.2018.00633"},{"key":"5587_CR22","doi-asserted-by":"crossref","unstructured":"Wang X, Wu J, Chen J, Li L, Wang YF, Wang WY (2019) VATEX: a large-scale, high-quality multilingual dataset for video-and-language research. In: Proceedings of the IEEE international conference on computer vision, pp 4580\u20134590","DOI":"10.1109\/ICCV.2019.00468"},{"key":"5587_CR23","doi-asserted-by":"crossref","unstructured":"Schuldt C, Laptev I, Caputo B (2004) Recognizing human actions: a local SVM approach. In: International conference on pattern recognition, pp 32\u201336","DOI":"10.1109\/ICPR.2004.1334462"},{"issue":"12","key":"5587_CR24","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.1109\/TPAMI.2007.70711","volume":"29","author":"L Gorelick","year":"2007","unstructured":"Gorelick L, Blank M, Shechtman E, Irani M, Basri R (2007) Actions as space-time shapes. IEEE Trans Pattern Anal Mach Intel 29(12):2247\u20132253","journal-title":"IEEE Trans Pattern Anal Mach Intel"},{"key":"5587_CR25","doi-asserted-by":"crossref","unstructured":"Marszalek M, Laptev I, Schmid C (2009) Actions in context. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2929\u20132936","DOI":"10.1109\/CVPRW.2009.5206557"},{"key":"5587_CR26","unstructured":"Over P, Fiscus J, Sanders G, Joy D, Qu\u00e9not G (2013) TRECVID 2013: an overview of the goals, tasks, data, evaluation mechanisms and metrics. In: TRECVID 2013 workshop participants notebook papers. http:\/\/www-nlpir.nist.gov\/projects\/tvpubs\/tv13.papers\/tv13overview.pdf. Accessed 29 Dec 2020"},{"key":"5587_CR27","unstructured":"Abu-El-Haija S, Kothari N, Lee J, Natsev P, Toderici G, Varadarajan B, Vijayanarasimhan S (2016) YouTube-8M: a large-scale video classification benchmark. arXiv:1609.08675"},{"key":"5587_CR28","doi-asserted-by":"crossref","unstructured":"Goyal R, Kahou SE, Michalski V, Materzynska J, Westphal S, Kim H, Haenel V, Fruend I, Yianilos P, Mueller-Freitag M, Hoppe F, Thurau C, Bax I, Memisevic R (2017) The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: Proceedings of the IEEE international conference on computer vision, pp 5843\u20135851","DOI":"10.1109\/ICCV.2017.622"},{"key":"5587_CR29","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1725\u20131732","DOI":"10.1109\/CVPR.2014.223"},{"key":"5587_CR30","unstructured":"Zhao H, Torralba A, Torresani L, Yan Z (2017) SLAC: a sparsely labeled dataset for action classification and localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition. arXiv:1712.09374"},{"key":"5587_CR31","unstructured":"Monfort M, Andonian A, Zhou B, Ramakrishnan K, Bargal SA, Yan T, Brown L, Fan Q, Gutfruend D, Vondrick C (2018) Moments in time dataset: one million videos for event understanding. In: IEEE transactions on pattern analysis and machine intelligence. arXiv:1801.03150"},{"key":"5587_CR32","unstructured":"Kay W, Carreira J, Simonyan K, Zhang B, Zisserman A (2017) The kinetics human action video dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition. arXiv:170506950"},{"key":"5587_CR33","doi-asserted-by":"crossref","unstructured":"Caba Heilbron F, Escorcia V, Ghanem B, Carlos Niebles J (2015) Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 961\u2013970","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"5587_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2016.10.018","volume":"155","author":"H Idrees","year":"2017","unstructured":"Idrees H, Zamir AR, Jiang Y-G, Gorban A, Laptev I, Sukthankar R, Shah M (2017) The THUMOS challenge on action recognition for videos \u201cin the wild\u201d. Comput Vis Image Underst 155:1\u201323","journal-title":"Comput Vis Image Underst"},{"key":"5587_CR35","doi-asserted-by":"crossref","unstructured":"Yeung S, Russakovsky O, Jin N, Andriluka M, Mori G, Fei-Fei L (2018) Every moment counts: dense detailed labeling of actions in complex videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 375\u2013389","DOI":"10.1007\/s11263-017-1013-y"},{"key":"5587_CR36","doi-asserted-by":"crossref","unstructured":"Sigurdsson GA, Varol G, Wang X, Farhadi A, Laptev I, Gupta (2016) A hollywood in homes: crowd sourcing data collection for activity understanding. In: European conference on computer vision. Springer, pp 510\u2013526","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"5587_CR37","unstructured":"Ke Y, Sukthankar R, Hebert M (2005) Efficient visual event detection using volumetric features. In: Proceedings of the IEEE international conference on computer vision, pp 166\u2013173"},{"key":"5587_CR38","unstructured":"Yuan J, Liu Z, Wu Y (2009) Discriminative subvolume search for efficient action detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2442\u20132449"},{"key":"5587_CR39","doi-asserted-by":"crossref","unstructured":"Rodriguez MD, Ahmed J, Shah M (2008) Action mach a spatio-temporal maximum average correlation height filter for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"5587_CR40","doi-asserted-by":"crossref","unstructured":"Jhuang H, Gall J, Zuffi S, Schmid C, Black MJ (2013) Towards understanding action recognition. In: Proceedings of the IEEE international conference on computer vision, pp 3192\u20133199","DOI":"10.1109\/ICCV.2013.396"},{"key":"5587_CR41","unstructured":"Weinzaepfel P, Martin X, Schmid C (2016) Towards weakly-supervised action localization. arXiv:1065.05197"},{"key":"5587_CR42","doi-asserted-by":"crossref","unstructured":"Mettes P, Van Gemert JC, Snoek CG (2016) Spot on: action localization from pointly-supervised proposals. In: European conference on computer vision. Springer, pp 437\u2013453","DOI":"10.1007\/978-3-319-46454-1_27"},{"key":"5587_CR43","doi-asserted-by":"crossref","unstructured":"Rohrbach M, Amin S, Andriluka M, Schiele B (2012) A database for fine grained activity detection of cooking activities. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1194\u20131201","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"5587_CR44","doi-asserted-by":"crossref","unstructured":"Das P, Xu C, Doell RF, Corso JJ (2013) A thousand frames in just a few words: lingual description of videos through latent topics and sparse object stitching. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2634\u20132641","DOI":"10.1109\/CVPR.2013.340"},{"key":"5587_CR45","doi-asserted-by":"crossref","unstructured":"Rohrbach M, Regneri M, Andriluka M, Amin S, Pinkal M, Schiele B (2012) Script data for attribute-based recognition of composite activities. In: European conference on computer vision, Springer, pp 144\u2013157","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"5587_CR46","doi-asserted-by":"crossref","unstructured":"Rohrbach A, Rohrbach M, Qiu W, Friedrich A, Pinkal M, Schiele B (2014) Coherent multi-sentence video description with variable level of detail. In: German conference on pattern recognition. Springer, pp 184\u2013195","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"5587_CR47","doi-asserted-by":"crossref","unstructured":"Zhou L, Xu C, Corso J (2018) Towards automatic learning of procedures from web instructional videos. In: Association for the advancement of artificial intelligence, pp 7590\u20137598","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"5587_CR48","doi-asserted-by":"crossref","unstructured":"Rohrbach A, Rohrbach M, Tandon N, Schiele B (2015) A dataset for movie description. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3202\u20133212","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"5587_CR49","unstructured":"Torabi A, Pal C, Larochelle H, Courville A (2015) Using descriptive video services to create a large data source for video annotation research. arXiv:1503.01070"},{"key":"5587_CR50","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: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5288\u20135296","DOI":"10.1109\/CVPR.2016.571"},{"key":"5587_CR51","doi-asserted-by":"crossref","unstructured":"Krishna R, Hata K, Ren F, Fei-Fei L, Carlos Niebles J (2017) Dense-captioning events in videos. In: Proceedings of the IEEE international conference on computer vision, pp 706\u2013715","DOI":"10.1109\/ICCV.2017.83"},{"key":"5587_CR52","doi-asserted-by":"crossref","unstructured":"Zhou L, Kalantidis Y, Chen X, Corso JJ, Rohrbach M (2019) Grounded video description. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6578\u20136587","DOI":"10.1109\/CVPR.2019.00674"},{"key":"5587_CR53","doi-asserted-by":"crossref","unstructured":"Gella S, Lewis M, Rohrbach M (2018) A dataset for telling the stories of social media videos. In: Proceedings of the 2018 conference on empirical methods in natural language processing, pp 968\u2013974","DOI":"10.18653\/v1\/D18-1117"},{"issue":"6","key":"5587_CR54","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, Gilani SZ, Shah M (2019) Video description: a survey of methods, datasets, and evaluation metrics. ACM Comput Surv 52(6):1\u201337","journal-title":"ACM Comput Surv"},{"key":"5587_CR55","doi-asserted-by":"crossref","unstructured":"Zeng K-H, Chen T-H, Niebles JC, Sun M (2016) Generation for user generated videos. In: European conference on computer vision. Springer, pp 609\u2013625","DOI":"10.1007\/978-3-319-46475-6_38"},{"key":"5587_CR56","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.image.2017.08.012","volume":"59","author":"Q Wei","year":"2017","unstructured":"Wei Q, Sun B, He J, Yu LJ (2017) BNU-LSVED 2.0: Spontaneous multimodal student affect database with multi-dimensional labels. Sig Process Image Commun 59:168\u2013181","journal-title":"Sig Process Image Commun"},{"key":"5587_CR57","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.compedu.2014.05.010","volume":"78","author":"Z Wang","year":"2014","unstructured":"Wang Z, Pan X, Miller KF, Cortina KSJC, Education (2014) Automatic classification of activities in classroom discourse. Comput Educ 78:115\u2013123","journal-title":"Comput Educ"},{"key":"5587_CR58","doi-asserted-by":"crossref","unstructured":"Sun B, Wei Q, He J, Yu L, Zhu X (2016) BNU-LSVED: a multimodal spontaneous expression database in educational environment. In: Optics and photonics for information processing X, international society for optics and photonics, p 997016","DOI":"10.1117\/12.2235892"},{"key":"5587_CR59","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL(2014) Microsoft coco: common objects in context. In: European conference on computer vision. Springer, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"5587_CR60","unstructured":"Simonyan K, Zisserman (2014) A Two-stream convolutional networks for action recognition in videos. In: Advances in neural information processing systems, pp 568\u2013576"},{"key":"5587_CR61","doi-asserted-by":"crossref","unstructured":"Ulutan O, Rallapalli S, Srivatsa M, Torres C, Manjunath B (2020) Actor conditioned attention maps for video action detection. In: The IEEE winter conference on applications of computer vision, pp 527\u2013536","DOI":"10.1109\/WACV45572.2020.9093617"},{"key":"5587_CR62","doi-asserted-by":"crossref","unstructured":"Li Y, Wang Z, Wang L, Wu G (2020) Actions as moving points. In: Proceedings of the European conference on computer vision. arXiv:2001.04608","DOI":"10.1007\/978-3-030-58517-4_5"},{"key":"5587_CR63","doi-asserted-by":"crossref","unstructured":"Yu F, Wang D, Shelhamer E, Darrell T (2018) Deep layer aggregation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2403\u20132412","DOI":"10.1109\/CVPR.2018.00255"},{"key":"5587_CR64","doi-asserted-by":"crossref","unstructured":"Gkioxari G, Malik J (2015) Finding action tubes. In: Proceedings of the IEEE international conference on computer vision, pp 759\u2013768","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"5587_CR65","doi-asserted-by":"crossref","unstructured":"Lin T, Zhao X, Su H, Wang C, Yang M (2018) Bsn: boundary sensitive network for temporal action proposal generation. In: Proceedings of the European conference on computer vision, pp 3\u201319","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"5587_CR66","doi-asserted-by":"publisher","unstructured":"Lin C, Li J, Wang Y, Tai Y, Luo D, Cui Z, Wang C, Li J, Huang F, Ji R (2020) Fast learning of temporal action proposal via dense boundary generator. In: Association for the advancement of artificial intelligence. https:\/\/doi.org\/10.22648\/ETRI.2020.J.350303","DOI":"10.22648\/ETRI.2020.J.350303"},{"key":"5587_CR67","doi-asserted-by":"crossref","unstructured":"Wang B, Ma L, Zhang W, Liu W (2018) Reconstruction network for video captioning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7622\u20137631","DOI":"10.1109\/CVPR.2018.00795"},{"key":"5587_CR68","doi-asserted-by":"crossref","unstructured":"Wang X, Wang YF, Wang WY (2018) Watch, listen, and describe: globally and locally aligned cross-modal attentions for video captioning. In Proceedings of the 2018 conference of the north american chapter of the association for computational linguistics: human language technologies, pp 795\u2013801","DOI":"10.18653\/v1\/N18-2125"},{"key":"5587_CR69","doi-asserted-by":"crossref","unstructured":"Denkowski M, Lavie (2014) A Meteor universal: language specific translation evaluation for any target language. In: Proceedings of the ninth workshop on statistical machine translation, pp 376\u2013380","DOI":"10.3115\/v1\/W14-3348"},{"key":"5587_CR70","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J (2002) BLEU: a method for automatic evaluation of machine translation. In: Proceedings of the 40th annual meeting of the association for computational linguistics, pp 311\u2013318","DOI":"10.3115\/1073083.1073135"},{"key":"5587_CR71","doi-asserted-by":"crossref","unstructured":"Vedantam R, Lawrence Zitnick C, Parikh D (2015) Cider: consensus-based image description evaluation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4566\u20134575","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"5587_CR72","unstructured":"Lin C-Y (2004) Rouge: a package for automatic evaluation of summaries. In: Text summarization branches out, pp 74\u201381"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05587-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-020-05587-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05587-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T01:21:26Z","timestamp":1670980886000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-020-05587-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,30]]},"references-count":72,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["5587"],"URL":"https:\/\/doi.org\/10.1007\/s00521-020-05587-y","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,30]]},"assertion":[{"value":"9 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2021","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 declared that they have no conflicts of interest with regard to this work. We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}