{"id":"https://openalex.org/W4392902673","doi":"https://doi.org/10.1109/icassp48485.2024.10448236","title":"MTIDNet: A Multimodal Temporal Interest Detection Network for Video Summarization","display_name":"MTIDNet: A Multimodal Temporal Interest Detection Network for Video Summarization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902673","doi":"https://doi.org/10.1109/icassp48485.2024.10448236"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448236","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5058979623","display_name":"Xiaoyan Tian","orcid":"https://orcid.org/0000-0001-9278-1032"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyan Tian","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China","Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113433716","display_name":"Jin Ye","orcid":"https://orcid.org/0000-0002-9355-092X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Jin","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China","Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003363983","display_name":"Zhao Zhang","orcid":"https://orcid.org/0000-0002-9466-016X"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Zhang","raw_affiliation_strings":["Harbin Institute of Technology,School of Instrument Science and Engineering,Harbin,China","School of Instrument Science and Engineering, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Instrument Science and Engineering,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Instrument Science and Engineering, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346747","display_name":"Peng Liu","orcid":"https://orcid.org/0000-0001-6568-1335"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Liu","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China","Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100873220","display_name":"Xianglong Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xianglong Tang","raw_affiliation_strings":["Harbin Institute of Technology,Faculty of Computing,Harbin,China","Faculty of Computing, Harbin Institute of Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Faculty of Computing,Harbin,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Faculty of Computing, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058979623"],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.2408,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45607098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"34","issue":null,"first_page":"2740","last_page":"2744"},"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":0.9952999949455261,"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":0.9642000198364258,"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":0.9367637634277344},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8435252904891968},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6554818153381348},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5879689455032349},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5277486443519592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5245987176895142},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5074736475944519},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.46413061022758484},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33295905590057373},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32141467928886414}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9367637634277344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8435252904891968},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6554818153381348},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5879689455032349},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5277486443519592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5245987176895142},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5074736475944519},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.46413061022758484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33295905590057373},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32141467928886414},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10448236","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10448236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2626896578","display_name":null,"funder_award_id":"Grant Number:","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6812708429","display_name":null,"funder_award_id":"51935005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1924343884","https://openalex.org/W2529272619","https://openalex.org/W2737677090","https://openalex.org/W2788303226","https://openalex.org/W2798970487","https://openalex.org/W2902616437","https://openalex.org/W2949550202","https://openalex.org/W2962677524","https://openalex.org/W2963220254","https://openalex.org/W2963919999","https://openalex.org/W2964158702","https://openalex.org/W3037309139","https://openalex.org/W3090254005","https://openalex.org/W3094550259","https://openalex.org/W3107128832","https://openalex.org/W3108154605","https://openalex.org/W3115386295","https://openalex.org/W3203711169","https://openalex.org/W3209983272","https://openalex.org/W4246193833","https://openalex.org/W4287107550","https://openalex.org/W4297499129","https://openalex.org/W4312544061","https://openalex.org/W4372349802","https://openalex.org/W4376610929","https://openalex.org/W4379116712","https://openalex.org/W6753059133","https://openalex.org/W6780294235","https://openalex.org/W6797265648"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W2973759123","https://openalex.org/W1517524280"],"abstract_inverted_index":{"Video":[0],"summarization":[1,17],"involves":[2],"creating":[3],"a":[4,13,23,74,102],"succinct":[5],"overview":[6],"by":[7,28],"merging":[8],"the":[9,58,61,64,87,94,109,129],"valuable":[10],"parts":[11],"of":[12,25,44,60,114,131],"video.":[14],"Existing":[15],"video":[16],"methods":[18,49],"approach":[19],"this":[20],"task":[21],"as":[22],"problem":[24],"selecting":[26],"keyframes":[27],"frame-":[29],"and":[30,89,112,121,138],"shot-level":[31],"techniques":[32],"with":[33],"unimodal":[34],"or":[35],"bimodal":[36],"information.":[37],"Besides":[38],"underestimated":[39],"inter-relations":[40],"between":[41],"various":[42],"configurations":[43],"modality":[45],"embedding":[46,91],"spaces,":[47],"current":[48],"are":[50],"also":[51],"limited":[52],"in":[53,86],"their":[54],"ability":[55],"to":[56,82,107],"maintain":[57],"integrity":[59],"semantics":[62],"within":[63],"same":[65],"summary":[66],"segment.":[67],"To":[68],"address":[69],"these":[70],"issues,":[71],"we":[72,100],"propose":[73],"novel":[75],"multimodal":[76,84],"temporal":[77,103,116],"interest":[78,104],"detection":[79,105],"network":[80,106],"(MTIDNet),":[81],"learn":[83],"features":[85,123],"fine-":[88],"coarse-grained":[90],"spaces":[92],"using":[93],"mutual":[95],"cross":[96],"fusion":[97],"layer.":[98],"Furthermore,":[99],"design":[101],"predict":[108],"importance":[110],"scores":[111],"boundaries":[113],"each":[115],"segment":[117],"that":[118],"possesses":[119],"local":[120],"global":[122],"across":[124],"shots.":[125],"Experimental":[126],"results":[127],"demonstrate":[128],"effectiveness":[130],"our":[132],"MTIDNet":[133],"on":[134],"challenging":[135],"datasets":[136],"(SumMe":[137],"TVSum).":[139]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
