{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:33:47Z","timestamp":1785422027126,"version":"3.56.0"},"reference-count":145,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2019,10,16]],"date-time":"2019-10-16T00:00:00Z","timestamp":1571184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2020,11,30]]},"abstract":"<jats:p>Video summarization is the method of extracting key frames or clips from a video to generate a synopsis of the content of the video. Generally, video is compressed before storing or transmitting it in most of the practical applications. Traditional techniques require the videos to be decoded to summarize them, which is a tedious job. Instead, compressed domain video processing can be used for summarizing videos by partially decoding them. A classification and analysis of various summarization techniques are presented in this article with special focus on compressed domain techniques along with a discussion on machine-learning-based techniques that can be applied to summarize the videos.&lt;?vsp -1.2pt?&gt;<\/jats:p>","DOI":"10.1145\/3355398","type":"journal-article","created":{"date-parts":[[2019,10,16]],"date-time":"2019-10-16T18:55:35Z","timestamp":1571252135000},"page":"1-29","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":51,"title":["Survey of Compressed Domain Video Summarization Techniques"],"prefix":"10.1145","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3042-7681","authenticated-orcid":false,"given":"Madhushree","family":"Basavarajaiah","sequence":"first","affiliation":[{"name":"Department of Computer Science 8 Engineering, Institute of Technology, Nirma University, Gujarat, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Priyanka","family":"Sharma","sequence":"additional","affiliation":[{"name":"Department of Computer Science 8 Engineering, Institute of Technology, Nirma University, Gujarat, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2019,10,16]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2011.08.007"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2012.01.009"},{"key":"e_1_2_1_3_1","volume-title":"Proceedings of IEEE International Symposium on Multimedia (ISM\u201910)","author":"Almeida Jurandy","year":"2010"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2014.05.015"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-12568-8_116"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.08.004"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-2345-z"},{"key":"e_1_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Madhushree Basavarajaiah and Priyanka Sharma. 2018. KSUMM: A compressed domain technique for video summarization using partial decoding of videos. Advanced informatics for computing research. In Communications in Computer and Information Science (ICAICR'18) Vol. 955 A. Luhach D. Singh P. A. Hsiung K. Hawari P. Lingras and P. Singh (Eds.). Springer Singapore. 241--252. DOI:https:\/\/doi.org\/10.1007\/978-981-13-3140-4_22  Madhushree Basavarajaiah and Priyanka Sharma. 2018. KSUMM: A compressed domain technique for video summarization using partial decoding of videos. Advanced informatics for computing research. In Communications in Computer and Information Science (ICAICR'18) Vol. 955 A. Luhach D. Singh P. A. Hsiung K. Hawari P. Lingras and P. Singh (Eds.). Springer Singapore. 241--252. DOI:https:\/\/doi.org\/10.1007\/978-981-13-3140-4_22","DOI":"10.1007\/978-981-13-3140-4_22"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2014.127"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2013.38"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/NCVPRIPG.2011.36"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2008.04.012"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2008.4564926"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2008.4712305"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.2009703"},{"key":"e_1_2_1_16_1","series-title":"Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering (LNICST\u201913). 1--11. DOI:https:\/\/doi.org\/10.1007\/978-3-319-03892-6_1","volume-title":"Personalized summarization of broadcasted soccer videos with adaptive fast-forwarding","author":"Chen Fan"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1290031.1290038"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2012.02.010"},{"key":"e_1_2_1_19_1","volume-title":"Proceedings of Pacific-Rim Conference on Multimedia (PCM'01)","author":"Chee"},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2166951"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2006.1621446"},{"key":"e_1_2_1_22_1","volume-title":"Proceedings of the International Conference on Document Analysis and Recognition (ICDAR\u201918)","author":"Davila Kenny","year":"2018"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3095713.3095734"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24136-9_19"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-6928-9_4"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2012.49"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0262-8856(03)00065-9"},{"key":"e_1_2_1_28_1","volume-title":"Proceedings of International Conference on Learning Representations (ICLR'16)","author":"Dundar Aysegul","year":"2016"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2013.10.005"},{"key":"e_1_2_1_30_1","first-page":"882","article-title":"Video summarization: Techniques and applications","volume":"9","author":"El Zaynab","year":"2015","journal-title":"Int. J. Comput. Inf. Eng. World Acad. Sci. Eng. Technol."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123387"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2000.859231"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2016.12.001"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052025"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1282280.1282370"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC.2006.1593230"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2011.06.008"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2014.6890642"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.03.083"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298928"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2011.5711483"},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2192917"},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2010.2057020"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2009.02.010"},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPA.2014.7041782"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2013.70"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-016-0441-4"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2002.1037977"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1646396.1646435"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2014.12.001"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2011.57"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.348"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCKE.2013.6682798"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2002.806813"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2013.08.003"},{"key":"e_1_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2385695"},{"key":"e_1_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2011.08.005"},{"key":"e_1_2_1_62_1","volume-title":"Proceedings of IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS\u201916)","author":"Lai Po Kong","year":"2016"},{"key":"e_1_2_1_63_1","first-page":"255","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"Lecun Yann","year":"1995","journal-title":"Handbook Brain Theory Neural Networks"},{"key":"e_1_2_1_64_1","volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'12)","author":"Lee Yong Jae","year":"2012"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/2530285"},{"key":"e_1_2_1_66_1","doi-asserted-by":"crossref","unstructured":"Carter De Leo and B. S. Manjunath. 2011. Multicamera video summarization from optimal reconstruction. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) (LNCS) 6468 PART 1 (2011) 94--103. DOI:https:\/\/doi.org\/10.1007\/978-3-642-22822-3_10  Carter De Leo and B. S. Manjunath. 2011. Multicamera video summarization from optimal reconstruction. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) (LNCS) 6468 PART 1 (2011) 94--103. DOI:https:\/\/doi.org\/10.1007\/978-3-642-22822-3_10","DOI":"10.1007\/978-3-642-22822-3_10"},{"key":"e_1_2_1_67_1","volume-title":"Leszczuk and Mariusz Duplaga","author":"Miko\u0142aj","year":"2011"},{"key":"e_1_2_1_68_1","doi-asserted-by":"crossref","unstructured":"Chen Li Yuxiang Xie Xidao Luan Kaichao Zhang and Liang Bai. 2015. Automatic movie summarization based on the visual-audio features. In Proceedings of the 17th IEEE International Conference on Computational Science and Engineering (CSE\u201914) Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications (IUCC\u201914) 13th International Symposium on Pervasive Systems. 1758--1761. DOI:https:\/\/doi.org\/10.1109\/CSE.2014.322  Chen Li Yuxiang Xie Xidao Luan Kaichao Zhang and Liang Bai. 2015. Automatic movie summarization based on the visual-audio features. In Proceedings of the 17th IEEE International Conference on Computational Science and Engineering (CSE\u201914) Jointly with 13th IEEE International Conference on Ubiquitous Computing and Communications (IUCC\u201914) 13th International Symposium on Pervasive Systems. 1758--1761. DOI:https:\/\/doi.org\/10.1109\/CSE.2014.322","DOI":"10.1109\/CSE.2014.322"},{"key":"e_1_2_1_69_1","doi-asserted-by":"crossref","unstructured":"Jiatong Li Ting Yao Qiang Ling and Tao Mei. 2017. Detecting shot boundary with sparse coding for video summarization. Neurocomputing 266 (2017) 66--78. DOI:https:\/\/doi.org\/10.1016\/j.neucom.2017.04.065  Jiatong Li Ting Yao Qiang Ling and Tao Mei. 2017. Detecting shot boundary with sparse coding for video summarization. Neurocomputing 266 (2017) 66--78. DOI:https:\/\/doi.org\/10.1016\/j.neucom.2017.04.065","DOI":"10.1016\/j.neucom.2017.04.065"},{"key":"e_1_2_1_70_1","volume-title":"11th International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS\u201910)","author":"Li Yingbo"},{"key":"e_1_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8297032"},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/265563.265572"},{"key":"e_1_2_1_73_1","volume-title":"10-701 Machine Learning Final Project Report: Video Summarization via Deep Convolutional Networks","author":"Lin Chen-Hsuan"},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641075"},{"key":"e_1_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.65"},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"e_1_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1109\/NGMAST.2014.20"},{"key":"e_1_2_1_78_1","volume-title":"Proceedings of the 10th ACM International Conference on Multimedia (MULTIMEDIA'02)","author":"Yf Ma Yu-Fei","year":"2002"},{"key":"e_1_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952432"},{"key":"e_1_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351002"},{"key":"e_1_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.318"},{"key":"e_1_2_1_82_1","first-page":"733","article-title":"VSCAN: An enhanced video summarization using density-based spatial clustering. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) 8156","volume":"1","author":"Mahmoud Karim M.","year":"2013","journal-title":"PART"},{"key":"e_1_2_1_83_1","volume-title":"Proceedings of IEEE International Conference on Multimedia and Expo (ICME'14)","author":"Mei Shaohui","year":"2014"},{"key":"e_1_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487268.2487269"},{"key":"e_1_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1166\/asl.2011.1892"},{"key":"e_1_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.234795"},{"key":"e_1_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553469"},{"key":"e_1_2_1_88_1","first-page":"65","article-title":"Summarization of egocentric videos: A comprehensive survey","volume":"47","author":"Del Molino Ana Garcia","year":"2017","journal-title":"IEEE Trans. Human-Mach. Syst."},{"key":"e_1_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2007.04.002"},{"key":"e_1_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33564-8_1"},{"key":"e_1_2_1_91_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40064-016-3171-8"},{"key":"e_1_2_1_92_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-016-4300-7"},{"key":"e_1_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.841694"},{"key":"e_1_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2207767"},{"key":"e_1_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853799"},{"key":"e_1_2_1_96_1","volume-title":"Proceedings of the International Workshop on TRECVID Video Summarization (TVS\u201907)","author":"Pan Chen-Ming"},{"key":"e_1_2_1_97_1","series-title":"Lecture Notes in Computer Science","volume-title":"Chowdhury","author":"Panda Rameswar","year":"2013"},{"key":"e_1_2_1_98_1","volume-title":"Proceedings of 22nd International Conference on Pattern Recognition (ICPR'14)","author":"Panda Rameswar","year":"2014"},{"key":"e_1_2_1_99_1","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP'17)","author":"Panda Rameswar","year":"2017"},{"key":"e_1_2_1_100_1","series-title":"Lecture Notes in Computer Science, 5371","volume-title":"Proceedings of Advances in Multimedia Modeling (MMM\u201909)","author":"Peng Wei-Ting"},{"key":"e_1_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2131638"},{"key":"e_1_2_1_102_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2010.09.002"},{"key":"e_1_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2317754"},{"key":"e_1_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77409-9_25"},{"key":"e_1_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"e_1_2_1_106_1","volume-title":"Proceedings of the 13th Annual ACM International Conference on Multimedia (MULTIMEDIA'05)","author":"Silva G."},{"key":"e_1_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.457"},{"key":"e_1_2_1_108_1","volume-title":"Proceedings of International Conference on Signal Processing, Communication, Computing and Networking Technologies (ICSCCN'11)","author":"Sony Aju","year":"2011"},{"key":"e_1_2_1_109_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815167"},{"key":"e_1_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30542-2_1"},{"key":"e_1_2_1_111_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSIP.2014.48"},{"key":"e_1_2_1_112_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019411"},{"key":"e_1_2_1_113_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738816"},{"key":"e_1_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.1006\/rtim.1999.0197"},{"key":"e_1_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2005.1521635"},{"key":"e_1_2_1_116_1","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208622"},{"key":"e_1_2_1_117_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2243640"},{"key":"e_1_2_1_118_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV'16)","author":"Tran Du","year":"2016"},{"key":"e_1_2_1_119_1","doi-asserted-by":"publisher","DOI":"10.1145\/1198302.1198305"},{"key":"e_1_2_1_120_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2269186"},{"key":"e_1_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-392"},{"key":"e_1_2_1_122_1","series-title":"Lecture Notes in Computer Science, Vol 8259","volume-title":"Proceedings of Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications (CIARP'13)","author":"Vinicius Marcos"},{"key":"e_1_2_1_123_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV'11)","author":"Voulodimos Athanasios S.","year":"2011"},{"key":"e_1_2_1_124_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2165531"},{"key":"e_1_2_1_125_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"e_1_2_1_126_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"e_1_2_1_127_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1047-3203(03)00019-1"},{"key":"e_1_2_1_128_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"e_1_2_1_129_1","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2016.18"},{"key":"e_1_2_1_130_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298836"},{"key":"e_1_2_1_131_1","volume-title":"Proceedings of International Conference on Multimedia Technology (ICMT\u201911)","author":"Yang Xue","year":"2011"},{"key":"e_1_2_1_132_1","volume-title":"Proceedings of IEEE Multimedia Expo (ICME'03)","author":"So Yu Jek Charlson","year":"2003"},{"key":"e_1_2_1_133_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2771247"},{"key":"e_1_2_1_134_1","doi-asserted-by":"publisher","DOI":"10.1109\/NaBIC.2011.6089409"},{"key":"e_1_2_1_135_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.120"},{"key":"e_1_2_1_136_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_47"},{"key":"e_1_2_1_137_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35725-1_35"},{"key":"e_1_2_1_138_1","doi-asserted-by":"publisher","DOI":"10.1145\/2746343"},{"key":"e_1_2_1_139_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.10.028"},{"key":"e_1_2_1_140_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00773"},{"key":"e_1_2_1_141_1","doi-asserted-by":"publisher","DOI":"10.1145\/500141.500264"},{"key":"e_1_2_1_142_1","first-page":"10281","article-title":"Learning Video-Story Composition via Recurrent Neural Network","volume":"1801","author":"Zhong Guangyu","year":"2018","journal-title":"ArXiv Preprint ArXiv"},{"key":"e_1_2_1_143_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.850977"},{"key":"e_1_2_1_144_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-004-0142-7"},{"key":"e_1_2_1_145_1","first-page":"1695","article-title":"Compressed domain video abstraction based on i-frame of HEVC coded videos Circuits Syst","volume":"38","author":"Yamghani Ali Reza","year":"2019","journal-title":"Signal Proc."}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3355398","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3355398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:34Z","timestamp":1750202614000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3355398"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,16]]},"references-count":145,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2020,11,30]]}},"alternative-id":["10.1145\/3355398"],"URL":"https:\/\/doi.org\/10.1145\/3355398","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,16]]},"assertion":[{"value":"2018-09-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-08-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-10-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}