{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T23:20:49Z","timestamp":1774912849339,"version":"3.50.1"},"reference-count":129,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2021,5,15]],"date-time":"2021-05-15T00:00:00Z","timestamp":1621036800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,15]],"date-time":"2021-05-15T00:00:00Z","timestamp":1621036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"None"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s11042-021-10977-y","type":"journal-article","created":{"date-parts":[[2021,5,15]],"date-time":"2021-05-15T22:02:33Z","timestamp":1621116153000},"page":"27187-27221","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["A survey of recent work on video summarization: approaches and techniques"],"prefix":"10.1007","volume":"80","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0087-3069","authenticated-orcid":false,"given":"Vasudha","family":"Tiwari","sequence":"first","affiliation":[]},{"given":"Charul","family":"Bhatnagar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,15]]},"reference":[{"key":"10977_CR1","doi-asserted-by":"publisher","unstructured":"Ajmal M, Ashraf MH, Shakir M, Abbas Y and Shah FA (2012) Video summarization: techniques and classification. In: International Conference on Computer Vision and Graphics pp. 1\u201313. https:\/\/doi.org\/10.1007\/978-3-642-33564-8_1","DOI":"10.1007\/978-3-642-33564-8_1"},{"key":"10977_CR2","doi-asserted-by":"crossref","unstructured":"Angadi S, Naik V (2014), \u201cEntropy based fuzzy C means clustering and key frame extraction for sports video summarization\u201d, in fifth international conference on signal and image processing, pp. 271-279.","DOI":"10.1109\/ICSIP.2014.49"},{"key":"10977_CR3","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.patrec.2015.12.016","volume":"73","author":"M Apar\u00edcio","year":"2016","unstructured":"Apar\u00edcio M, Figueiredo P, Raposo F, Martins de Matos D, Ribeiro R, Marujo L (2016) Summarization of films and documentaries based on subtitles and scripts. Pattern Recogn Lett 73:7\u201312","journal-title":"Pattern Recogn Lett"},{"issue":"6","key":"10977_CR4","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1049\/iet-cvi.2018.5436","volume":"13","author":"P Atencio","year":"2019","unstructured":"Atencio P, German ST, Branch JW, Delrieux C (2019) Video summarization by deep visual and categorical diversity. IET Comput Vis 13(6):569\u2013577","journal-title":"IET Comput Vis"},{"key":"10977_CR5","doi-asserted-by":"crossref","unstructured":"Barbeiri TTDS, Goularte R (2020) Content selection criteria for news multi-video summarization based on human strategies. International Journal on Digital Libraries, 1\u201314","DOI":"10.1007\/s00799-020-00281-9"},{"issue":"6","key":"10977_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355398","volume":"52","author":"M Basavarajaiah","year":"2019","unstructured":"Basavarajaiah M, Sharma P (2019) Survey of de domain video summarization techniques. ACM Comput Surv 52(6):1\u201329","journal-title":"ACM Comput Surv"},{"key":"10977_CR7","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1016\/j.cviu.2019.02.004","volume":"181","author":"KB Baskurt","year":"2019","unstructured":"Baskurt KB, Samet R (2019) Video synopsis: a survey. Comput Vis Image Underst 181:26\u201338","journal-title":"Comput Vis Image Underst"},{"key":"10977_CR8","doi-asserted-by":"publisher","unstructured":"Cao Y et al. (2013) Recognise human activities from partially observed videos. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 2658\u20132665. doi: https:\/\/doi.org\/10.1109\/CVPR.2013.343.","DOI":"10.1109\/CVPR.2013.343"},{"key":"10977_CR9","doi-asserted-by":"publisher","unstructured":"Chang SF (2003) Content- based video summarization and adaptation for ubiquitous media access. In: 12th international conference on image analysis and processing, pp. 494-496, doi: https:\/\/doi.org\/10.1109\/ICIAP.2003.1234098.","DOI":"10.1109\/ICIAP.2003.1234098"},{"issue":"3","key":"10977_CR10","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1504\/IJCVR.2014.062936","volume":"4","author":"Y Chen","year":"2014","unstructured":"Chen Y, Zhang B (2014) Surveillance video summarization by jointly applying moving object detection and tracking. International Journal of Computational Vision and Robotics 4(3):212\u2013234","journal-title":"International Journal of Computational Vision and Robotics"},{"issue":"4","key":"10977_CR11","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/j.cag.2012.02.010","volume":"36","author":"T Chen","year":"2012","unstructured":"Chen T, Lu A, Hu SM (2012) Visual storylines: semantic visualization of movie sequence. Comput Graph 36(4):241\u2013249","journal-title":"Comput Graph"},{"key":"10977_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5244\/C.31.118","volume":"118","author":"B Chen","year":"2017","unstructured":"Chen B, Chen Y, Chen F (2017) Video to text summary: joint video summarization and captioning with recurrent neural networks. Proceedings of the British Machine Vision Conference (BMVC) 118:1\u2013118.14. https:\/\/doi.org\/10.5244\/C.31.118","journal-title":"Proceedings of the British Machine Vision Conference (BMVC)"},{"issue":"7","key":"10977_CR13","doi-asserted-by":"publisher","first-page":"1443","DOI":"10.1109\/TMM.2007.906602","volume":"9","author":"C Choudary","year":"2007","unstructured":"Choudary C, Liu T (2007) Summarization of visual content in instructional videos. IEEE Transactions on Multimedia 9(7):1443\u20131455","journal-title":"IEEE Transactions on Multimedia"},{"key":"10977_CR14","doi-asserted-by":"publisher","unstructured":"Chu WS, Song Y and Jaimes A (2015) Video co-summarization: Video summarization by visual co-occurrence. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3584\u20133592. doi:https:\/\/doi.org\/10.1109\/CVPR.2015.7298981","DOI":"10.1109\/CVPR.2015.7298981"},{"issue":"1","key":"10977_CR15","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/TMM.2011.2166951","volume":"14","author":"Y Cong","year":"2012","unstructured":"Cong Y, Yuan J, Luo J (2012) Towards scalable summarization of consumer videos via sparse dictionary selection. IEEE Transactions on Multimedia 14(1):66\u201375","journal-title":"IEEE Transactions on Multimedia"},{"key":"10977_CR16","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s12369-019-00541-y","volume":"12","author":"C Coppola","year":"2020","unstructured":"Coppola C, Cosar S, Faria DR, Belloto N (2020) Social activity recognition on continuous RGB-D video sequences. Int J Soc Robot 12:201\u2013215","journal-title":"Int J Soc Robot"},{"issue":"3","key":"10977_CR17","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1109\/TCSVT.2016.2589859","volume":"27","author":"S Cosar","year":"2017","unstructured":"Cosar S, Donatiello G, Bogorny V, Garate C, Alvares LO, Bremond F (2017) Towards abnormal trajectory and event detection in video surveillance. IEEE Transactions on Circuits and Systems for Video Technology 27(3):683\u2013695","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"6","key":"10977_CR18","doi-asserted-by":"publisher","first-page":"2704","DOI":"10.1109\/TIP.2014.2320814","volume":"23","author":"CT Dang","year":"2014","unstructured":"Dang CT, Radha H (2014) Heterogeneity image patch index and its application to consumer video summarization. IEEE Trans Image Process 23(6):2704\u20132718","journal-title":"IEEE Trans Image Process"},{"issue":"1","key":"10977_CR19","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.patrec.2010.08.004","volume":"32","author":"SEF De Aliva","year":"2011","unstructured":"De Aliva SEF et al (2011) VSUMM: a mechanism designed to produce static video summaries and a novel evaluation method. Pattern Recogn Lett 32(1):56\u201368","journal-title":"Pattern Recogn Lett"},{"key":"10977_CR20","doi-asserted-by":"publisher","unstructured":"De Silva GC, Yamasaki T and Aizawa K (2005) Evaluation of video summarization for a large number of cameras in ubiquitous home. In: proceedings of the 13th annual ACM international conference on multimedia, pp. 820-828. doi: https:\/\/doi.org\/10.1145\/1101149.1101329.","DOI":"10.1145\/1101149.1101329"},{"key":"10977_CR21","doi-asserted-by":"publisher","unstructured":"Duque D, Santos H and Cortez P (2007) Prediction of abnormal behaviors for intelligent video surveillance systems. In: IEEE Symposium on Computational Intelligence and Data Mining, pp. 362\u2013367. doi: https:\/\/doi.org\/10.1109\/CIDM.2007.368897.","DOI":"10.1109\/CIDM.2007.368897"},{"key":"10977_CR22","doi-asserted-by":"publisher","unstructured":"Evangelopoulos G, et al. (2008) Movie summarization based on audiovisual saliency detection. In: 15th IEEE international conference on image processing, pp. 2528-2531, doi: https:\/\/doi.org\/10.1109\/ICIP.2008.4712308.","DOI":"10.1109\/ICIP.2008.4712308"},{"key":"10977_CR23","doi-asserted-by":"crossref","unstructured":"Evangelopoulos G et al (n.d.) Multimodal saliency and Fusion for Movie Summarization Based on Aural, Visual and Textual Attention. IEEE Transactions on Multimedia 15(7):1553\u20131568","DOI":"10.1109\/TMM.2013.2267205"},{"issue":"12","key":"10977_CR24","doi-asserted-by":"publisher","first-page":"16995","DOI":"10.1007\/s11042-018-7083-1","volume":"78","author":"B Fakhar","year":"2019","unstructured":"Fakhar B, Kanan HR, Behrad A (2019) Event detection in soccer videos using unsupervised learning of Spatio-temporal features based on pooled spatial pyramid model. Multimed Tools Appl 78(12):16995\u201317025","journal-title":"Multimed Tools Appl"},{"key":"10977_CR25","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.jvcir.2016.12.001","volume":"42","author":"M Fei","year":"2017","unstructured":"Fei M, Jian W, Mao W (2017) Memorable and rich video summarization. J Vis Commun Image Represent 42:207\u2013217","journal-title":"J Vis Commun Image Represent"},{"issue":"7","key":"10977_CR26","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1109\/TMM.2010.2052025","volume":"12","author":"Y Fu","year":"2010","unstructured":"Fu Y, Guo Y, Zhu Y, Liu F, Song C, Zhou Z (2010) Multi-View Video Summarization. IEEE Transactions on Multimedia 12(7):717\u2013729","journal-title":"IEEE Transactions on Multimedia"},{"issue":"1","key":"10977_CR27","first-page":"65","volume":"47","author":"AM Garcia","year":"2017","unstructured":"Garcia AM, Tan C, Lim JH, Tan AH (2017) Summarization of egocentric videos: a comprehensive survey. IEEE Transactions on Human-Machine Systems 47(1):65\u201376","journal-title":"IEEE Transactions on Human-Machine Systems"},{"issue":"3","key":"10977_CR28","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1145\/1141911.1141967","volume":"25","author":"DB Goldman","year":"2006","unstructured":"Goldman DB, Curless B, Salesin D, Seitz SM (2006) Schematic storyboarding for video visualization and editing. ACM Transactions on Graphics (TOG) 25(3):862\u2013871","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"10977_CR29","unstructured":"Gong B, Chao WL, Grauman K and Sha F (2014) Diverse sequential subset selection for supervised video summarization. In advances in neural information processing systems, pp. 2069-2077."},{"issue":"4","key":"10977_CR30","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1007\/s10462-012-9341-3","volume":"42","author":"D Gowsikhaa","year":"2014","unstructured":"Gowsikhaa D, Abirami S, Baskaran R (2014) Automated human behavior analysis from surveillance videos: a survey. Artif Intell Rev 42(4):747\u2013765","journal-title":"Artif Intell Rev"},{"key":"10977_CR31","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/j.neucom.2016.03.083","volume":"208","author":"Z Guo","year":"2016","unstructured":"Guo Z, Gao L, Zhen X, Zou F, Shen F, Zheng K (2016) Spatial and temporal scoring for egocentric video summarization. Neurocomputing 208:299\u2013308","journal-title":"Neurocomputing"},{"key":"10977_CR32","doi-asserted-by":"publisher","unstructured":"Gygli M, Grabner H, Riemenschneider H and Van Gool L (2014) Creating summaries from user videos. In: European Conference on Computer Vision, pp. 505\u2013520. https:\/\/doi.org\/10.1007\/978-3-319-10584-0_33","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"10977_CR33","doi-asserted-by":"publisher","unstructured":"Gygli M, Grabner H and Van Gool L (2015) Video summarization by learning submodular mixture of objectives. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3090\u20133098. doi: https:\/\/doi.org\/10.1109\/CVPR.2015.7298928.","DOI":"10.1109\/CVPR.2015.7298928"},{"issue":"6","key":"10977_CR34","doi-asserted-by":"publisher","first-page":"155014771984527","DOI":"10.1177\/1550147719845277","volume":"15","author":"IU Haq","year":"2019","unstructured":"Haq IU, Muhammad K, Hussain T, Kwon S, Sodanil M, Baik SW, Lee MY (2019) Movie scene segmentation using object detection and set theory. International Journal of Distributed Sensor Networks 15(6):155014771984527","journal-title":"International Journal of Distributed Sensor Networks"},{"issue":"9","key":"10977_CR35","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1109\/TCSVT.2010.2057020","volume":"20","author":"L Herranz","year":"2010","unstructured":"Herranz L, Martinez JM (2010) A framework for scalable summarization of video. IEEE Transactions on Circuits and Systems for Video Technology 20(9):1265\u20131270","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10977_CR36","doi-asserted-by":"publisher","unstructured":"Hesham M, Hani B, Fouad N and Amer E (2018) Smart trailer: automatic generation of movie trailer using only subtitles. In: 2018 first international workshop on deep and representation learning (IWRDL), pp. 26-30. doi:https:\/\/doi.org\/10.1109\/IWDRL.2018.8358211.","DOI":"10.1109\/IWDRL.2018.8358211"},{"key":"10977_CR37","unstructured":"Hussein N, Gavves E and Smeulders AW (2019) VideoGraph: Recognising minutes- long human activities in videos\u201d. arXiv preprint arXiv:1905.05143."},{"key":"10977_CR38","doi-asserted-by":"publisher","unstructured":"Ide I et al. (2017) Summarization of news videos considering the consistency of auditory and visual contents. In: IEEE International Symposium on Multimedia, pp. 193\u2013199, doi: https:\/\/doi.org\/10.1109\/ISM.2017.33.","DOI":"10.1109\/ISM.2017.33"},{"issue":"4","key":"10977_CR39","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1049\/iet-ipr.2018.5589","volume":"13","author":"A Javed","year":"2019","unstructured":"Javed A, Irtaza A, Malik H, Mahmood MT, Adnan S (2019) Multimodal framework based on audio-visual features for summarization of cricket videos. IET Image Process 13(4):615\u2013622","journal-title":"IET Image Process"},{"key":"10977_CR40","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1016\/j.sigpro.2018.01.028","volume":"148","author":"Z Ji","year":"2018","unstructured":"Ji Z, Zhang Y, Pang Y, Li X (2018) Hypergraph dominant set based multi-video summarization. Signal Process 148:114\u2013123","journal-title":"Signal Process"},{"issue":"6","key":"10977_CR41","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1177\/0165551518819964","volume":"45","author":"H Ji","year":"2019","unstructured":"Ji H, Hooshyar D, Kim K, Lim H (2019) A semantic \u2013 based video scene segmentation using a deep neural network. J Inf Sci 45(6):833\u2013844","journal-title":"J Inf Sci"},{"issue":"6","key":"10977_CR42","doi-asserted-by":"publisher","first-page":"1709","DOI":"10.1109\/TCSVT.2019.2904996","volume":"30","author":"Z Ji","year":"2020","unstructured":"Ji Z, Xiong K, Pang Y, Li X (2020) Video summarization with attention-based encoder- decoder networks. IEEE Transactions on Circuits and Systems for Video Technology 30(6):1709\u20131717","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10977_CR43","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1016\/j.patrec.2020.04.011","volume":"135","author":"Z Ji","year":"2020","unstructured":"Ji Z, Zhao Y, Pang Y, Li X (2020) Cross-modal guidance based auto-encoder for multi-video summarization. Pattern Recogn Lett 135:131\u2013137. https:\/\/doi.org\/10.1016\/j.patrec.2020.04.011","journal-title":"Pattern Recogn Lett"},{"key":"10977_CR44","doi-asserted-by":"publisher","unstructured":"Jiang Y, Cui K, Peng B and Xu C (2019) Comprehensive video understanding: video summarization with content-based video recommender design. In: 2019 IEEE\/CVF international conference on computer vision workshop (ICCVW), pp. 1562-1569. doi: https:\/\/doi.org\/10.1109\/ICCVW.2019.00195.","DOI":"10.1109\/ICCVW.2019.00195"},{"key":"10977_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1646396.1646435","volume":"31","author":"H Joho","year":"2009","unstructured":"Joho H, Jose JM, Valenti R, Sebe N (2009) Exploiting facial expressions for affective video summarization. Proceedings of the ACM International Conference on Image and Video Retrieval, Article 31:1\u20138. https:\/\/doi.org\/10.1145\/1646396.1646435","journal-title":"Proceedings of the ACM International Conference on Image and Video Retrieval, Article"},{"key":"10977_CR46","doi-asserted-by":"publisher","unstructured":"Kanehira A, Van Gool L, Ushiku Y and Harada T (2018) Viewpoint \u2013 aware video summarization. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7435\u20137444. doi: https:\/\/doi.org\/10.1109\/CVPR.2018.00776.","DOI":"10.1109\/CVPR.2018.00776"},{"key":"10977_CR47","doi-asserted-by":"publisher","unstructured":"Kato K, Ide I, Deguchi D and Murase H (2014) Estimation of the representative story transition in a chronological semantic structure of news topics. In: Proceedings of International Conference on Multimedia Retrieval, pp. 487\u2013490. doi:https:\/\/doi.org\/10.1145\/2578726.2578800.","DOI":"10.1145\/2578726.2578800"},{"key":"10977_CR48","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1016\/j.procs.2015.03.209","volume":"47","author":"J Kavitha","year":"2015","unstructured":"Kavitha J, Rani PAJ (2015) Static and multi resolution feature extraction for video summarization. Procedia Computer Science 47:292\u2013300","journal-title":"Procedia Computer Science"},{"key":"10977_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11063-020-10200-3","volume":"52","author":"AA Khan","year":"2020","unstructured":"Khan AA, Shao J, Ali W, Tumrani S (2020) Content- aware summarization of broadcast sports videos: an audio-visual feature extraction approach. Neural Process Lett 52:1\u201324. https:\/\/doi.org\/10.1007\/s11063-020-10200-3","journal-title":"Neural Process Lett"},{"key":"10977_CR50","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.compeleceng.2019.106524","volume":"81","author":"G Khan","year":"2020","unstructured":"Khan G, Jabeen S, Khan MZ, Khan MUG, Iqbal R (2020) Blockchain-enabled deep semantic video-to-video summarization for IoT devices. Computers & Electrical Engineering 81:81. https:\/\/doi.org\/10.1016\/j.compeleceng.2019.106524","journal-title":"Computers & Electrical Engineering"},{"key":"10977_CR51","doi-asserted-by":"publisher","unstructured":"Khosla A, Hamid R, Lin CJ and Sundaresan N (2013) Large-scale video summarization using web-image priors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2698\u20132705. doi: https:\/\/doi.org\/10.1109\/CVPR.2013.348.","DOI":"10.1109\/CVPR.2013.348"},{"key":"10977_CR52","doi-asserted-by":"publisher","unstructured":"Khosla A, Raju AS, Torallba A and Olivia A (2015) Understanding and predicting image memorability at a large scale. In: IEEE International Conference on Computer Vision, pp. 2390\u20132398, doi: https:\/\/doi.org\/10.1109\/ICCV.2015.275.","DOI":"10.1109\/ICCV.2015.275"},{"issue":"12","key":"10977_CR53","doi-asserted-by":"publisher","first-page":"1128","DOI":"10.1109\/TCSVT.2002.806813","volume":"12","author":"C Kim","year":"2002","unstructured":"Kim C, Hwang JN (2002) Object-based video abstraction for video surveillance systems. IEEE Transactions on Circuits and Systems for Video Technology 12(12):1128\u20131138","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10977_CR54","doi-asserted-by":"publisher","unstructured":"Kim G, Sigal L and Xing EP (2014) Joint summarization of large-scale collections of web images and videos for storyline reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4225\u20134232. doi: https:\/\/doi.org\/10.1109\/CVPR.2014.538.","DOI":"10.1109\/CVPR.2014.538"},{"key":"10977_CR55","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5244\/C.22.99","volume":"99","author":"A Klaser","year":"2008","unstructured":"Klaser A, Marszalek M, Schmid C (2008) A Spatio\u2013temporal descriptor based on 3D gradients. Proceedings of British Machine Vision Conference 99:1\u201399.10. https:\/\/doi.org\/10.5244\/C.22.99","journal-title":"Proceedings of British Machine Vision Conference"},{"key":"10977_CR56","unstructured":"Kota BU, Ahmed S, Stone A, Davila K, Stelur S, Govindaraju V (2019) Summarizing Lecture Videos by Key Handwritten Content Regions. In: 2019 International conference on document analysis and recognition workshops (ICDARW) 4: 13\u201318. IEEE."},{"issue":"9","key":"10977_CR57","doi-asserted-by":"publisher","first-page":"1737","DOI":"10.1109\/TPAMI.2014.2385695","volume":"37","author":"J Kwon","year":"2015","unstructured":"Kwon J, Lee KM (2015) A unified framework for event summarization and rare event detection from multiple views. IEEE Trans Pattern Anal Mach Intell 37(9):1737\u20131750","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10977_CR58","doi-asserted-by":"publisher","unstructured":"Lai PK, Decombas M, Moutet K and Laganiere R (2016) Video summarization of surveillance cameras. In: IEEE International Conference on Advanced Video and Signal based Surveillance, pp. 286\u2013294, doi:https:\/\/doi.org\/10.1109\/AVSS.2016.7738018.","DOI":"10.1109\/AVSS.2016.7738018"},{"issue":"1","key":"10977_CR59","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s11263-014-0794-5","volume":"114","author":"YJ Lee","year":"2015","unstructured":"Lee YJ, Grauman K (2015) Predicting important objects for egocentric video summarization. Int J Comput Vis 114(1):38\u201355","journal-title":"Int J Comput Vis"},{"key":"10977_CR60","doi-asserted-by":"publisher","unstructured":"Lee YJ, Ghosh J and Grauman K (2012) Discovering important people and objects for egocentric video summarization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1346\u20131353. doi:https:\/\/doi.org\/10.1109\/CVPR.2012.6247820.","DOI":"10.1109\/CVPR.2012.6247820"},{"key":"10977_CR61","doi-asserted-by":"crossref","unstructured":"Lee S, Sung J, Yu Y and Kim G (2018) A memory network approach for story-based temporal summarization of 360 videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1410\u20131419.","DOI":"10.1109\/CVPR.2018.00153"},{"issue":"1","key":"10977_CR62","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1126004.1126005","volume":"2","author":"MS Lew","year":"2006","unstructured":"Lew MS, Sebe N, Djeraba C, Jain R (2006) Content-based multimedia information retrieval: state of the art and challenges. ACM Trans Multimed Comput Commun Appl 2(1):1\u201319","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"issue":"1","key":"10977_CR63","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/s11042-014-2287-5","volume":"75","author":"Y Li","year":"2016","unstructured":"Li Y, Merialdo B (2016) Multimedia maximal marginal relevance for multi-video summarization. Multimed Tools Appl 75(1):199\u2013220","journal-title":"Multimed Tools Appl"},{"key":"10977_CR64","doi-asserted-by":"publisher","unstructured":"Li B, Pan H and Sezan I (2003) A general framework for sports video summarization with its application to soccer. In: IEEE international conference on acoustics, speech, and signal processing, pp. III-169. doi: https:\/\/doi.org\/10.1109\/ICASSP.2003.1199134.","DOI":"10.1109\/ICASSP.2003.1199134"},{"key":"10977_CR65","doi-asserted-by":"publisher","unstructured":"Lie WN and Lai CM (2004) News video summarization based on spatial and motion feature analysis. In: Pacific-Rim Conference on Multimedia, pp. 246\u2013255. https:\/\/doi.org\/10.1007\/978-3-540-30542-2_31","DOI":"10.1007\/978-3-540-30542-2_31"},{"key":"10977_CR66","doi-asserted-by":"publisher","unstructured":"Liu T, Kender JR (2002) Rule-based semantic summarization of instructional videos. In: Proceedings of International Conference on Image Processing pp. I-I. IEEE. doi: https:\/\/doi.org\/10.1109\/ICIP.2002.1038095.","DOI":"10.1109\/ICIP.2002.1038095"},{"key":"10977_CR67","doi-asserted-by":"publisher","unstructured":"Lu Z and Grauman K (2013) Story-driven summarization for egocentric video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2714\u20132721, doi: https:\/\/doi.org\/10.1109\/CVPR.2013.350","DOI":"10.1109\/CVPR.2013.350"},{"issue":"5","key":"10977_CR68","doi-asserted-by":"publisher","first-page":"6309","DOI":"10.1007\/s11042-016-3263-z","volume":"76","author":"G Lu","year":"2017","unstructured":"Lu G, Zhou Y, Li X, Yan P (2017) Unsupervised, efficient and scalable key-frame selection for automatic summarization of surveillance videos. Multimed Tools Appl 76(5):6309\u20136331","journal-title":"Multimed Tools Appl"},{"key":"10977_CR69","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.neucom.2019.07.108","volume":"378","author":"M Ma","year":"2020","unstructured":"Ma M, Mei S, Wan S, Hou J, Wang Z, Feng DD (2020) Video summarization via block sparse dictionary selection. Neurocomputing 378:197\u2013209","journal-title":"Neurocomputing"},{"issue":"12","key":"10977_CR70","doi-asserted-by":"publisher","first-page":"5828","DOI":"10.1109\/TIP.2016.2615289","volume":"25","author":"I Mademlis","year":"2016","unstructured":"Mademlis I, Tefas A, Nikolaidis N, Pitas I (2016) Multimodal stereoscopic movie summarization conforming to narrative characteristics. IEEE Trans Image Process 25(12):5828\u20135840","journal-title":"IEEE Trans Image Process"},{"key":"10977_CR71","doi-asserted-by":"publisher","unstructured":"Mademlis I, Tefas A, Nikolaidis N and Pitas I (2017) summarization of human activity videos via low \u2013 rank approximation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1627-1631. doi: https:\/\/doi.org\/10.1109\/ICASSP.2017.7952432.","DOI":"10.1109\/ICASSP.2017.7952432"},{"key":"10977_CR72","doi-asserted-by":"publisher","unstructured":"Mahasseni B, Lam M and Todorovic S (2017) Unsupervised video summarization with adversarial LSTM networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2982\u20132991.doi: https:\/\/doi.org\/10.1109\/CVPR.2017.318.","DOI":"10.1109\/CVPR.2017.318"},{"key":"10977_CR73","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1007\/s00138-019-01007-x","volume":"30","author":"CE Matthews","year":"2019","unstructured":"Matthews CE, Kuncheva LI, Yousefi P (2019) Classification and comparison of on-line video summarization methods. Mach Vis Appl 30:507\u2013518","journal-title":"Mach Vis Appl"},{"issue":"3","key":"10977_CR74","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1016\/j.compeleceng.2012.11.020","volume":"39","author":"E Mendi","year":"2013","unstructured":"Mendi E, Clemente HB, Bayrak C (2013) Sports video summarization based on motion analysis. Computers & Electrical Engineering 39(3):790\u2013796","journal-title":"Computers & Electrical Engineering"},{"issue":"5","key":"10977_CR75","doi-asserted-by":"publisher","first-page":"2134","DOI":"10.1109\/TIP.2017.2789332","volume":"27","author":"J Meng","year":"2018","unstructured":"Meng J, Wang S, Wang H, Yuan J, Tan YP (2018) Video summarization via multiview representative selection. IEEE Trans Image Process 27(5):2134\u20132145","journal-title":"IEEE Trans Image Process"},{"issue":"2","key":"10977_CR76","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/j.jvcir.2007.04.002","volume":"19","author":"AG Money","year":"2008","unstructured":"Money AG, Agius H (2008) Video summarization: a conceptual framework and survey of the state of art. J Vis Commun Image Represent 19(2):121\u2013143","journal-title":"J Vis Commun Image Represent"},{"key":"10977_CR77","doi-asserted-by":"publisher","unstructured":"Moses TM and Balachandran K (2017) A classified study on semantic analysis of video summarization. In: 2017 international conference on algorithms, methodology, models and applications in emerging technologies (ICAMMAET), pp 1-6. doi: https:\/\/doi.org\/10.1109\/ICAMMAET.2017.8186684","DOI":"10.1109\/ICAMMAET.2017.8186684"},{"key":"10977_CR78","doi-asserted-by":"publisher","unstructured":"Niebles JC, Chen CW and Fei-Fei L (2010) Modeling temporal structure of decomposable motion segments for activity classification. In: European Conference on Computer Vision, pp. 392\u2013405, https:\/\/doi.org\/10.1007\/978-3-642-15552-9_29","DOI":"10.1007\/978-3-642-15552-9_29"},{"key":"10977_CR79","doi-asserted-by":"publisher","unstructured":"Oh S et al (2011) A large-scale benchmark dataset for event recognition in surveillance video. CVPR 2011, pp. 3153\u20133160, doi: https:\/\/doi.org\/10.1109\/CVPR.2011.5995586.","DOI":"10.1109\/CVPR.2011.5995586"},{"key":"10977_CR80","doi-asserted-by":"publisher","unstructured":"Otani M, Nakashima Y, Rahtu E and Heikkila J (2019) Rethinking the evaluation of video summaries. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp. 7588-7596. doi: https:\/\/doi.org\/10.1109\/CVPR.2019.00778.","DOI":"10.1109\/CVPR.2019.00778"},{"issue":"4","key":"10977_CR81","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1049\/iet-ipr.2012.0495","volume":"7","author":"JQ Ouyang","year":"2013","unstructured":"Ouyang JQ, Liu R (2013) Ontology reasoning scheme for constructing meaningful sports video summarization. IET Image Process 7(4):324\u2013334","journal-title":"IET Image Process"},{"issue":"9","key":"10977_CR82","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1109\/TMM.2017.2708981","volume":"19","author":"R Panda","year":"2017","unstructured":"Panda R, Roy-Chowdhury AK (2017) Multi-view surveillance video summarization via joint embedding and sparse optimization. IEEE Transactions on Multimedia 19(9):2010\u20132021","journal-title":"IEEE Transactions on Multimedia"},{"issue":"10","key":"10977_CR83","doi-asserted-by":"publisher","first-page":"4712","DOI":"10.1109\/TIP.2017.2708902","volume":"26","author":"R Panda","year":"2017","unstructured":"Panda R, Mithun NC, Roy-Chowdhury AK (2017) Diversity-aware multi-video summarization. IEEE Trans Image Process 26(10):4712\u20134724","journal-title":"IEEE Trans Image Process"},{"issue":"3","key":"10977_CR84","doi-asserted-by":"publisher","first-page":"836","DOI":"10.1109\/TCYB.2017.2657692","volume":"48","author":"R Panda","year":"2018","unstructured":"Panda R, Kuanar SK, Chowdhury AS (2018) Nystr\u00f6m approximated temporally constrained multisimilarity spectral clustering approach for movie scene detection. IEEE Transactions on Cybernetics 48(3):836\u2013847","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"1","key":"10977_CR85","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1186\/1687-6180-2013-176","volume":"2013","author":"M Paul","year":"2013","unstructured":"Paul M, Haque SM, Chakraborty S (2013) Human detection in surveillance videos and its applications- a review. EURASIP Journal on Advances in Signal processing 2013(1):176","journal-title":"EURASIP Journal on Advances in Signal processing"},{"issue":"3","key":"10977_CR86","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1109\/TMM.2011.2131638","volume":"13","author":"WT Peng","year":"2011","unstructured":"Peng WT, Chu WT, Chang CT, Chou CN, Huang WJ, Chang WY, Hung YP (2011) Editing by viewing: automatic home video summarization by viewing behaviour analysis. IEEE Transactions on Multimedia 13(3):539\u2013550","journal-title":"IEEE Transactions on Multimedia"},{"key":"10977_CR87","doi-asserted-by":"publisher","first-page":"23783","DOI":"10.1007\/s11042-019-7691-4","volume":"78","author":"MHR Pereira","year":"2019","unstructured":"Pereira MHR, Padua FLC, Dalip DH et al (2019) Multimodal approach for tension levels estimation in news videos. Multimed Tools Appl 78:23783\u201323808","journal-title":"Multimed Tools Appl"},{"key":"10977_CR88","doi-asserted-by":"publisher","unstructured":"Pirsiavash H and Ramanan D (2012) Detecting activities of daily living in first-person camera views. In: IEEE conference on computer vision and pattern recognition (CVPR), pp. 2847-2854, doi: https:\/\/doi.org\/10.1109\/CVPR.2012.6248010.","DOI":"10.1109\/CVPR.2012.6248010"},{"key":"10977_CR89","doi-asserted-by":"publisher","unstructured":"Potapov D, Douze M, Harchaoui Z and Schmid C (2014) Category-specific video summarization. In: European Conference on Computer Vision, pp. 540\u2013555. https:\/\/doi.org\/10.1007\/978-3-319-10599-4_35","DOI":"10.1007\/978-3-319-10599-4_35"},{"key":"10977_CR90","doi-asserted-by":"crossref","unstructured":"Rahman MR, Subhlok J and Shah S (2020) Visual summarization of lecture video segments for enhanced navigation. arXiv preprint arXiv:2006.02434.","DOI":"10.1109\/ISM.2020.00033"},{"issue":"3","key":"10977_CR91","doi-asserted-by":"publisher","first-page":"102190","DOI":"10.1016\/j.ipm.2019.102190","volume":"57","author":"S Rani","year":"2020","unstructured":"Rani S, Kumar M (2020) Social media video summarization using multi-visual features and Kohnen's self-organizing map. Inf Process Manag 57(3):102190","journal-title":"Inf Process Manag"},{"key":"10977_CR92","doi-asserted-by":"publisher","unstructured":"Rav-Acha A, Pritch Y and Peleg S (2006) Making a long video short: dynamic video synopsis. In: 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR\u201906), pp. 435-441. doi: https:\/\/doi.org\/10.1109\/CVPR.2006.179","DOI":"10.1109\/CVPR.2006.179"},{"key":"10977_CR93","doi-asserted-by":"publisher","unstructured":"Safdarnejad SM, Liu X, Udpa L, Andrus B, Wood J and Craven D (2015) Sports videos in the wild (SVW): a video dataset for sports analysis. In: 11th IEEE international conference and workshops on automatic face and gesture recognition, pp. 1-7, doi: https:\/\/doi.org\/10.1109\/FG.2015.7163105.","DOI":"10.1109\/FG.2015.7163105"},{"key":"10977_CR94","doi-asserted-by":"publisher","unstructured":"Sah S et al. (2017): Semantic text summarization of long videos. In: IEEE Winter Conference on Applications of Computer Vision, pp. 989\u2013997. doi: https:\/\/doi.org\/10.1109\/WACV.2017.115.","DOI":"10.1109\/WACV.2017.115"},{"key":"10977_CR95","doi-asserted-by":"publisher","first-page":"102754","DOI":"10.1016\/j.jvcir.2020.102754","volume":"67","author":"A Sasithradevi","year":"2020","unstructured":"Sasithradevi A, Roomi SMM (2020) A new pyramidal opponent color-shape model-based video shot boundary detection. J Vis Commun Image Represent 67:102754","journal-title":"J Vis Commun Image Represent"},{"key":"10977_CR96","doi-asserted-by":"publisher","unstructured":"Scovanner P, Ali S and Shah M (2007) A 3-dimensional sift descriptor and its application to action recognition. In: Proceedings of the ACM International Conference on Multimedia, pp. 357\u2013360. doi:https:\/\/doi.org\/10.1145\/1291233.1291311.","DOI":"10.1145\/1291233.1291311"},{"key":"10977_CR97","doi-asserted-by":"publisher","unstructured":"Sharghi A, Gong B and Shah M (2016) Query-focused extractive video summarization. In: European conference on computer vision, pp. 3-19. Springer. doi:https:\/\/doi.org\/10.1007\/978-3-319-46484-8_1.","DOI":"10.1007\/978-3-319-46484-8_1"},{"key":"10977_CR98","doi-asserted-by":"publisher","unstructured":"Sharghi A, Laurel JS and Gong B (2017) Query-focused video summarization: dataset, evaluation and a memory network based approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2127\u20132136. doi:https:\/\/doi.org\/10.1109\/CVPR.2017.229.","DOI":"10.1109\/CVPR.2017.229"},{"key":"10977_CR99","doi-asserted-by":"publisher","unstructured":"Song Y, Vallmitjana J, Stent A and Jaimes A (2015) TVSum: summarizing web videos using titles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5179\u20135187. doi: https:\/\/doi.org\/10.1109\/CVPR.2015.7299154","DOI":"10.1109\/CVPR.2015.7299154"},{"key":"10977_CR100","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.jvcir.2019.06.004","volume":"62","author":"MU Sreeja","year":"2019","unstructured":"Sreeja MU, Kovoor BC (2019) Towards genre-specific frameworks for video summarization: a survey. J Vis Commun Image Represent 62:340\u2013358","journal-title":"J Vis Commun Image Represent"},{"issue":"8","key":"10977_CR101","doi-asserted-by":"publisher","first-page":"2000","DOI":"10.1109\/TMM.2018.2794265","volume":"20","author":"A Tejero-de Pablos","year":"2018","unstructured":"Tejero-de Pablos A, Nakashima Y, Sato T, Yokoya N, Linna M, Rahtu E (2018) Summarization of user-generated sports video by using deep action recognition features. IEEE Transactions on Multimedia 20(8):2000\u20132011","journal-title":"IEEE Transactions on Multimedia"},{"issue":"8","key":"10977_CR102","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.1109\/TCSVT.2016.2556558","volume":"27","author":"SS Thomas","year":"2017","unstructured":"Thomas SS, Gupta S, Subramanian VK (2017) Perceptual video summarization-a new framework for video summarization. IEEE Transactions on Circuits and Systems for Video Technology 27(8):1790\u20131802","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"9","key":"10977_CR103","doi-asserted-by":"publisher","first-page":"2944","DOI":"10.1109\/TITS.2017.2769719","volume":"19","author":"SS Thomas","year":"2018","unstructured":"Thomas SS, Gupta S, Subramanian VK (2018) Event detection on roads using perceptual video summarization. IEEE Trans Intell Transp Syst 19(9):2944\u20132954","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"10","key":"10977_CR104","doi-asserted-by":"publisher","first-page":"3132","DOI":"10.1109\/TCSVT.2018.2873185","volume":"29","author":"SS Thomas","year":"2019","unstructured":"Thomas SS, Gupta S, Subramanian VK (2019) Context driven optimized perceptual video summarization and retrieval. IEEE Transactions on Circuits and Systems for Video Technology 29(10):3132\u20133145","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"1","key":"10977_CR105","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/1198302.1198305","volume":"3","author":"BT Truong","year":"2007","unstructured":"Truong BT, Venkatesh S (2007) Video abstraction: a systematic review and classification. ACM Trans Multimed Comput Commun Appl 3(1):3","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"issue":"11","key":"10977_CR106","doi-asserted-by":"publisher","first-page":"1927","DOI":"10.1109\/TCSVT.2013.2269186","volume":"23","author":"C Tsai","year":"2013","unstructured":"Tsai C, Kang LW, Lin CW, Lin W (2013) Scene based movie summarization via role-community networks. IEEE Transactions on Circuits and Systems for Video Technology 23(11):1927\u20131940","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10977_CR107","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2019\/3581419","volume":"2019","author":"I Ul Haq","year":"2019","unstructured":"Ul Haq I, Ullah A, Muhammad K, Lee MY, Baik SW (2019) Personalised movie summarization using deep CNN- assisted facial expression recognition. Complexity 2019:1\u201310. https:\/\/doi.org\/10.1155\/2019\/3581419","journal-title":"Complexity"},{"key":"10977_CR108","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.cviu.2016.10.016","volume":"156","author":"G Vaca-Castano","year":"2017","unstructured":"Vaca-Castano G, Das S, Sousa JP, Lobo ND, Shah M (2017) Improved scene identification and object detection on egocentric vision of daily activities. Comput Vis Image Underst 156:92\u2013103","journal-title":"Comput Vis Image Underst"},{"issue":"12","key":"10977_CR109","doi-asserted-by":"publisher","first-page":"2832","DOI":"10.1109\/TMM.2017.2705915","volume":"19","author":"P Varini","year":"2017","unstructured":"Varini P, Serra G, Cucchiara R (2017) Personalised egocentric video summarization of cultural tour on user preferences input. IEEE Transactions on Multimedia 19(12):2832\u20132845","journal-title":"IEEE Transactions on Multimedia"},{"key":"10977_CR110","doi-asserted-by":"publisher","unstructured":"Vasudevan AB, Gygli M, Volokitin A and Van Gool L (2017) Query-adaptive video summarization via quality aware relevance estimation. In: proceedings of the 25th ACM international conference on multimedia, pp. 582-590. https:\/\/doi.org\/10.1145\/3123266.3123297.","DOI":"10.1145\/3123266.3123297"},{"key":"10977_CR111","doi-asserted-by":"publisher","first-page":"107382","DOI":"10.1016\/j.patcog.2020.107382","volume":"107","author":"J Wu","year":"2020","unstructured":"Wu J, Zhong SH, Liu Y (2020) Dynamic graph convolutional network for multi-video summarization. Pattern Recogn 107:107382. https:\/\/doi.org\/10.1016\/j.patcog.2020.107382","journal-title":"Pattern Recogn"},{"key":"10977_CR112","doi-asserted-by":"publisher","unstructured":"Xiong B, Kim G and Sigal L (2015) Storyline representation of egocentric videos with an applications to story-based search. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4525\u20134533. doi: https:\/\/doi.org\/10.1109\/ICCV.2015.514","DOI":"10.1109\/ICCV.2015.514"},{"key":"10977_CR113","doi-asserted-by":"publisher","unstructured":"Xu J, Mukherjee L, Li Y, Warner J, Rehg JM and Singh V (2015) Gaze-enabled egocentric video summarization via constrained submodular maximization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2235\u20132244. doi: https:\/\/doi.org\/10.1109\/CVPR.2015.7298836","DOI":"10.1109\/CVPR.2015.7298836"},{"key":"10977_CR114","doi-asserted-by":"crossref","unstructured":"Yu Y, Lee S, Na J, Kang J, and Kim G (2018) A deep ranking model for spatio-temporal highlight detection from a 360 video. arXiv preprint arXiv:1801.10312.","DOI":"10.1609\/aaai.v32i1.12335"},{"key":"10977_CR115","doi-asserted-by":"publisher","unstructured":"Zhang K, Chao WL, Sha F and Grauman K (2016) Video summarization with long short-term memory. In: European Conference on Computer Vision, pp. 766\u2013782. doi: https:\/\/doi.org\/10.1007\/978-3-319-46478-7_47","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"10977_CR116","doi-asserted-by":"publisher","unstructured":"Zhang K, Chao W, Sha F and Grauman K (2016) Summary transfer: exemplar-based subset selection for video summarization. In: IEEE conference on computer vision and pattern recognition (CVPR), pp. 1059-1067, doi: https:\/\/doi.org\/10.1109\/CVPR.2016.120.","DOI":"10.1109\/CVPR.2016.120"},{"key":"10977_CR117","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/j.patcog.2015.11.018","volume":"59","author":"Y Zhang","year":"2016","unstructured":"Zhang Y, Lu H, Zhang L, Ruan X, Sakai S (2016) Video anomaly detection based on locality sensitive hashing filters. Pattern Recogn 59:302\u2013311","journal-title":"Pattern Recogn"},{"issue":"11","key":"10977_CR118","doi-asserted-by":"publisher","first-page":"5469","DOI":"10.1109\/TIP.2016.2601493","volume":"25","author":"S Zhang","year":"2016","unstructured":"Zhang S, Zhu Y, Roy Chowdhury AK (2016) Context \u2013 aware surveillance video summarization. IEEE Trans Image Process 25(11):5469\u20135478","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"10977_CR119","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1109\/TCSVT.2016.2539638","volume":"27","author":"Y Zhang","year":"2017","unstructured":"Zhang Y, Tao R, Wang Y (2017) Motion-state-adaptive video summarization via spatiotemporal analysis. IEEE Transactions on Circuits and Systems for Video Technology 27(6):1340\u20131352","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"4","key":"10977_CR120","doi-asserted-by":"publisher","first-page":"750","DOI":"10.3390\/app9040750","volume":"9","author":"Y Zhang","year":"2019","unstructured":"Zhang Y, Kampffmeyer M, Zhao X, Tan M (2019) Deep reinforcement learning for query-conditioned video summarization. Appl Sci 9(4):750","journal-title":"Appl Sci"},{"key":"10977_CR121","doi-asserted-by":"publisher","unstructured":"Zhao B and Xing EP (2014) Quasi real-time summarization for consumer videos. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2513\u20132520. doi: https:\/\/doi.org\/10.1109\/CVPR.2014.322.","DOI":"10.1109\/CVPR.2014.322"},{"key":"10977_CR122","doi-asserted-by":"publisher","unstructured":"Zhao B, Li X and Lu X (2018) HSA-RNN: hierarchical structure-adaptive RNN for video summarization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7405\u20137414. doi:https:\/\/doi.org\/10.1109\/CVPR.2018.00773.","DOI":"10.1109\/CVPR.2018.00773"},{"key":"10977_CR123","doi-asserted-by":"publisher","unstructured":"Zhong H, Shi J and Visontai M (2004) Detecting unusual activity in video. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2004), pp. II-II, doi: https:\/\/doi.org\/10.1109\/CVPR.2004.1315249.","DOI":"10.1109\/CVPR.2004.1315249"},{"key":"10977_CR124","unstructured":"Zhou B, Lapedriza A, Xiao J, Torralba A and Oliva A (2014) Learning deep features for scene recognition using places database. In Advances in neural information processing systems, pp 487\u2013495."},{"key":"10977_CR125","unstructured":"Zhou K, Qiao Y and Xiang T (2017) Deep reinforcement learning for unsupervised video summarization with diversity-representativeness reward. arXiv preprint arXiv:1801.00054."},{"key":"10977_CR126","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s00530-004-0142-7","volume":"10","author":"X Zhu","year":"2004","unstructured":"Zhu X, Wu X, Fan J, Elmagarmid AK, Aref WG (2004) Exploring video content structure for hierarchical summarization. Multimedia Systems 10:98\u2013115","journal-title":"Multimedia Systems"},{"issue":"4","key":"10977_CR127","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1109\/TMM.2005.850977","volume":"7","author":"X Zhu","year":"2005","unstructured":"Zhu X, Elmagarmid AK, Xue X, Wu L, Catlin AC (2005) InsightVideo: toward hierarchical video content Organization for Efficient Browsing, summarization and retrieval. IEEE Transactions on Multimedia 7(4):648\u2013666","journal-title":"IEEE Transactions on Multimedia"},{"key":"10977_CR128","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s11263-015-0864-3","volume":"117","author":"X Zhu","year":"2016","unstructured":"Zhu X, Loy CC, Gong S (2016) Learning from multiple sources for video summarization. Int J Comput Vis 117:247\u2013268","journal-title":"Int J Comput Vis"},{"key":"10977_CR129","doi-asserted-by":"crossref","unstructured":"Zhukov D et al. (2019) Cross-task weakly supervised learning from instructional videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3537\u20133545","DOI":"10.1109\/CVPR.2019.00365"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10977-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-10977-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-10977-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T13:34:00Z","timestamp":1672148040000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-10977-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,15]]},"references-count":129,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["10977"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-10977-y","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,15]]},"assertion":[{"value":"24 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}