{"id":"https://openalex.org/W2895907803","doi":"https://doi.org/10.1145/3240508.3240651","title":"Extractive Video Summarizer with Memory Augmented Neural Networks","display_name":"Extractive Video Summarizer with Memory Augmented Neural Networks","publication_year":2018,"publication_date":"2018-10-15","ids":{"openalex":"https://openalex.org/W2895907803","doi":"https://doi.org/10.1145/3240508.3240651","mag":"2895907803"},"language":"en","primary_location":{"id":"doi:10.1145/3240508.3240651","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039785210","display_name":"Litong Feng","orcid":"https://orcid.org/0000-0002-6716-3520"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Litong Feng","raw_affiliation_strings":["SenseTime Research, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114858829","display_name":"Ziyin Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyin Li","raw_affiliation_strings":["SenseTime Research, Shen Zhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Shen Zhen, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054299179","display_name":"Zhanghui Kuang","orcid":"https://orcid.org/0000-0002-9102-5152"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanghui Kuang","raw_affiliation_strings":["SenseTime Research, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057842914","display_name":"Wayne Zhang","orcid":"https://orcid.org/0000-0002-8415-1062"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhang","raw_affiliation_strings":["SenseTime Research, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research, Hong Kong, China","institution_ids":["https://openalex.org/I4210128910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210128910"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"976","last_page":"983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.9439702033996582},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8786770105361938},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6146962642669678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6015563011169434},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5919603109359741},{"id":"https://openalex.org/keywords/key-frame","display_name":"Key frame","score":0.5653324723243713},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5424384474754333},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.5396400094032288},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.4917276203632355},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4840502142906189},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.4502153992652893},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4046021103858948}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9439702033996582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8786770105361938},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6146962642669678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6015563011169434},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5919603109359741},{"id":"https://openalex.org/C2780139006","wikidata":"https://www.wikidata.org/wiki/Q1493902","display_name":"Key frame","level":3,"score":0.5653324723243713},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5424384474754333},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.5396400094032288},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.4917276203632355},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4840502142906189},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.4502153992652893},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4046021103858948},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3240508.3240651","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3240508.3240651","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1603581382","https://openalex.org/W1904325426","https://openalex.org/W1924343884","https://openalex.org/W1926243429","https://openalex.org/W1947481528","https://openalex.org/W2014328297","https://openalex.org/W2028788183","https://openalex.org/W2062903088","https://openalex.org/W2064675550","https://openalex.org/W2077802163","https://openalex.org/W2094974368","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2115857089","https://openalex.org/W2118776487","https://openalex.org/W2134577448","https://openalex.org/W2139009685","https://openalex.org/W2144577430","https://openalex.org/W2151103935","https://openalex.org/W2156303437","https://openalex.org/W2158261396","https://openalex.org/W2279098554","https://openalex.org/W2295537791","https://openalex.org/W2512435841","https://openalex.org/W2529272619","https://openalex.org/W2559655401","https://openalex.org/W2737677090","https://openalex.org/W2750526644","https://openalex.org/W2758851402","https://openalex.org/W2766630207","https://openalex.org/W2781922022","https://openalex.org/W2949888546","https://openalex.org/W2951008357","https://openalex.org/W2952276042","https://openalex.org/W2962710043","https://openalex.org/W2963220254","https://openalex.org/W2963508075","https://openalex.org/W2963890755","https://openalex.org/W2963919999","https://openalex.org/W2964094092","https://openalex.org/W4236965008"],"related_works":["https://openalex.org/W3123991145","https://openalex.org/W1574724839","https://openalex.org/W2782365651","https://openalex.org/W2622881578","https://openalex.org/W4221117092","https://openalex.org/W1803027153","https://openalex.org/W2213155192","https://openalex.org/W1623638113","https://openalex.org/W2589628610","https://openalex.org/W2096476311"],"abstract_inverted_index":{"Online":[0],"videos":[1,16],"have":[2],"been":[3],"growing":[4],"explosively":[5],"in":[6,88],"recent":[7],"years.":[8],"How":[9],"to":[10,53,124,194],"help":[11],"human":[12],"users":[13],"efficiently":[14],"browse":[15],"becomes":[17],"more":[18,20],"and":[19,68,73,171,191],"important.":[21],"Video":[22],"summarization":[23,46,90],"can":[24],"automatically":[25],"shorten":[26],"a":[27,64,85,113,148],"video":[28,41,45,82,117,131,140,149,158],"through":[29],"extracting":[30],"key-shots":[31],"from":[32,50,80],"the":[33,55,70,74,89,97,129,136,139,144,153,157,168,179],"raw":[34],"video,":[35,72],"which":[36,119],"is":[37],"helpful":[38],"for":[39],"digesting":[40],"data.":[42],"State-of-the-art":[43],"supervised":[44,94],"algorithms":[47,166],"directly":[48],"learn":[49],"manually-created":[51],"summaries":[52],"mimic":[54],"key-frame/key-shot":[56],"selection":[57],"criterion":[58],"of":[59,128,147,156],"humans.":[60],"Humans":[61],"usually":[62],"create":[63],"summary":[65],"after":[66],"viewing":[67],"understanding":[69,155],"whole":[71,130],"global":[75,154,180],"attention":[76,181],"mechanism":[77],"capturing":[78],"information":[79,127],"all":[81],"frames":[83],"plays":[84],"key":[86],"role":[87],"process.":[91],"However,":[92],"previous":[93,164],"approaches":[95],"ignored":[96],"temporal":[98],"relations":[99],"or":[100],"simply":[101,142],"modeled":[102],"local":[103],"inter-dependency":[104],"across":[105,189],"frames.":[106,159],"Motivated":[107],"by":[108],"this":[109],"observation,":[110],"we":[111,176],"proposed":[112,161],"memory":[114,123],"augmented":[115],"extractive":[116],"summarizer,":[118],"utilizes":[120],"an":[121],"external":[122,137],"record":[125],"visual":[126],"with":[132],"high":[133,192],"capacity.":[134],"With":[135],"memory,":[138],"summarizer":[141],"predicts":[143],"importance":[145],"score":[146],"shot":[150],"based":[151],"on":[152,167],"The":[160],"method":[162],"outperforms":[163],"state-of-the-art":[165],"public":[169],"SumMe":[170],"TVSum":[172],"datasets.":[173],"More":[174],"importantly,":[175],"demonstrate":[177],"that":[178],"modeling":[182],"has":[183],"two":[184],"advantages:":[185],"good":[186],"transferring":[187],"ability":[188],"datasets":[190],"robustness":[193],"noisy":[195],"videos.":[196]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}