{"id":"https://openalex.org/W2080672747","doi":"https://doi.org/10.1145/2733373.2806314","title":"Summarization-based Video Caption via Deep Neural Networks","display_name":"Summarization-based Video Caption via Deep Neural Networks","publication_year":2015,"publication_date":"2015-10-13","ids":{"openalex":"https://openalex.org/W2080672747","doi":"https://doi.org/10.1145/2733373.2806314","mag":"2080672747"},"language":"en","primary_location":{"id":"doi:10.1145/2733373.2806314","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd 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/A5100765202","display_name":"Guang Li","orcid":"https://orcid.org/0000-0001-8693-3757"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guang Li","raw_affiliation_strings":["Tianjin University, Tianjin, China","[Tianjin University, Tianjin, China.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"[Tianjin University, Tianjin, China.]","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084531586","display_name":"Shubo Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shubo Ma","raw_affiliation_strings":["Tianjin University, Tianjin, China","[Tianjin University, Tianjin, China.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"[Tianjin University, Tianjin, China.]","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031819155","display_name":"Yahong Han","orcid":"https://orcid.org/0000-0003-2768-1398"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yahong Han","raw_affiliation_strings":["Tianjin University, Tianjin, China","[Tianjin University, Tianjin, China.]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"[Tianjin University, Tianjin, China.]","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1191","last_page":"1194"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9983999729156494,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.8819625377655029},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8695061206817627},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7040122747421265},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5507161617279053},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5358216762542725},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5170834064483643},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5023739337921143},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.490864098072052},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.48239171504974365},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4504292607307434},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.41859036684036255},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36812901496887207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8819625377655029},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8695061206817627},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7040122747421265},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5507161617279053},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5358216762542725},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5170834064483643},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5023739337921143},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.490864098072052},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.48239171504974365},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4504292607307434},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.41859036684036255},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36812901496887207},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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:10.1145/2733373.2806314","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2733373.2806314","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6549115048","display_name":null,"funder_award_id":"61202166, 61472276","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1895577753","https://openalex.org/W1897761818","https://openalex.org/W1905882502","https://openalex.org/W1947481528","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2108598243","https://openalex.org/W2109586012","https://openalex.org/W2110933980","https://openalex.org/W2117539524","https://openalex.org/W2133512280","https://openalex.org/W2142900973","https://openalex.org/W2155893237","https://openalex.org/W2164290393","https://openalex.org/W2251353663","https://openalex.org/W2600463316","https://openalex.org/W2951183276","https://openalex.org/W2964241990","https://openalex.org/W3101913037"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4323520239","https://openalex.org/W4389760904","https://openalex.org/W402673672"],"abstract_inverted_index":{"Generating":[0],"appropriate":[1],"descriptions":[2,78,91],"for":[3,79,92],"visual":[4,54],"content":[5],"draws":[6],"increasing":[7],"attention":[8],"recently,":[9],"where":[10],"the":[11,18,26,86,104,109,116,130,140],"promising":[12],"progresses":[13],"were":[14],"obtained":[15],"owing":[16],"to":[17,74,84,102],"breakthroughs":[19],"in":[20,34,146],"deep":[21,46,59],"neural":[22,47],"networks.":[23,48],"Different":[24],"from":[25,125],"traditional":[27],"SVO":[28,153],"(subject,":[29],"verb,":[30],"object)":[31],"based":[32],"methods,":[33],"this":[35],"paper,":[36],"we":[37,52],"propose":[38],"a":[39,57,69,95],"novel":[40,76],"framework":[41,114],"of":[42,118,143],"video":[43,144],"caption":[44,145],"via":[45],"For":[49],"each":[50,80],"frame,":[51],"extract":[53],"features":[55],"by":[56,106,122],"fine-tuned":[58],"Convulutional":[60],"Neural":[61,71],"Networks":[62,72],"(CNN),":[63],"which":[64],"are":[65],"then":[66],"fed":[67],"into":[68],"Recurrent":[70],"(RNN)":[73],"generate":[75],"sentences":[77],"frame.":[81],"In":[82],"order":[83],"obtain":[85],"most":[87],"representative":[88],"and":[89],"high-quality":[90],"target":[93],"video,":[94],"well-devised":[96],"automatic":[97],"summarization":[98],"process":[99],"is":[100],"incorporated":[101],"reduce":[103],"noises":[105],"ranking":[107],"on":[108,129],"sentence-sequence":[110],"graph.":[111],"Moreover,":[112],"our":[113,134],"owns":[115],"merit":[117],"describing":[119],"out-of-sample":[120],"videos":[121],"transferring":[123],"knowledge":[124],"pre-captioned":[126],"images.":[127],"Experiments":[128],"benchmark":[131],"datasets":[132],"demonstrate":[133],"method":[135],"has":[136],"better":[137],"performance":[138],"than":[139],"state-of-the-art":[141],"methods":[142],"language":[147],"generation":[148],"metrics":[149],"as":[150,152],"well":[151],"accuracy.":[154]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}