{"id":"https://openalex.org/W4389161308","doi":"https://doi.org/10.1109/tmm.2023.3335875","title":"VideoXum: Cross-Modal Visual and Textural Summarization of Videos","display_name":"VideoXum: Cross-Modal Visual and Textural Summarization of Videos","publication_year":2023,"publication_date":"2023-11-30","ids":{"openalex":"https://openalex.org/W4389161308","doi":"https://doi.org/10.1109/tmm.2023.3335875"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3335875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3335875","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/A5077401853","display_name":"Jingyang Lin","orcid":"https://orcid.org/0009-0000-3223-3827"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingyang Lin","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0009-0000-3223-3827","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102027020","display_name":"Hang Hua","orcid":"https://orcid.org/0000-0002-5441-5776"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Hua","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-5441-5776","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423306","display_name":"Ming Chen","orcid":"https://orcid.org/0000-0003-2603-5239"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Chen","raw_affiliation_strings":["OPPO US Research Center, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2603-5239","affiliations":[{"raw_affiliation_string":"OPPO US Research Center, Palo Alto, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100610029","display_name":"Yikang Li","orcid":"https://orcid.org/0000-0003-4666-9642"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yikang Li","raw_affiliation_strings":["OPPO US Research Center, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4666-9642","affiliations":[{"raw_affiliation_string":"OPPO US Research Center, Palo Alto, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103124223","display_name":"Jen-Hao Hsiao","orcid":"https://orcid.org/0009-0003-4542-7809"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jenhao Hsiao","raw_affiliation_strings":["OPPO US Research Center, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0009-0003-4542-7809","affiliations":[{"raw_affiliation_string":"OPPO US Research Center, Palo Alto, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067929709","display_name":"Chiuman Ho","orcid":"https://orcid.org/0000-0002-1607-6080"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chiuman Ho","raw_affiliation_strings":["OPPO US Research Center, Palo Alto, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-1607-6080","affiliations":[{"raw_affiliation_string":"OPPO US Research Center, Palo Alto, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055469774","display_name":"Jiebo Luo","orcid":"https://orcid.org/0000-0002-4516-9729"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiebo Luo","raw_affiliation_strings":["Department of Computer Science, University of Rochester, Rochester, NY, USA"],"raw_orcid":"https://orcid.org/0000-0002-4516-9729","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0418,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95473572,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"26","issue":null,"first_page":"5548","last_page":"5560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9998999834060669,"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":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9990000128746033,"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":0.993399977684021,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.9426835775375366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8896673917770386},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6094673871994019},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5715414881706238},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.5465403199195862},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5240923762321472},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5084053874015808},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.49686768651008606},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4521224796772003},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.44175273180007935},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.44086840748786926},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4357207417488098},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4219183623790741},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4194949269294739},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3359875977039337}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9426835775375366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8896673917770386},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6094673871994019},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5715414881706238},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.5465403199195862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5240923762321472},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5084053874015808},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.49686768651008606},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4521224796772003},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.44175273180007935},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.44086840748786926},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4357207417488098},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4219183623790741},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4194949269294739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3359875977039337},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3335875","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3335875","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":97,"referenced_works":["https://openalex.org/W329267344","https://openalex.org/W1586939924","https://openalex.org/W1861492603","https://openalex.org/W1924343884","https://openalex.org/W1956340063","https://openalex.org/W1979354511","https://openalex.org/W1987366351","https://openalex.org/W1991750682","https://openalex.org/W2064469569","https://openalex.org/W2101105183","https://openalex.org/W2111078031","https://openalex.org/W2255466643","https://openalex.org/W2425121537","https://openalex.org/W2529272619","https://openalex.org/W2766630207","https://openalex.org/W2781922022","https://openalex.org/W2798970487","https://openalex.org/W2893972119","https://openalex.org/W2896457183","https://openalex.org/W2897439619","https://openalex.org/W2922005172","https://openalex.org/W2922340345","https://openalex.org/W2946527862","https://openalex.org/W2952132648","https://openalex.org/W2953461088","https://openalex.org/W2962799512","https://openalex.org/W2963351113","https://openalex.org/W2963753226","https://openalex.org/W2963916161","https://openalex.org/W2963919999","https://openalex.org/W2964045651","https://openalex.org/W2967219836","https://openalex.org/W2968124245","https://openalex.org/W2970231061","https://openalex.org/W2970641574","https://openalex.org/W2979382951","https://openalex.org/W2981851019","https://openalex.org/W2988326850","https://openalex.org/W3015468748","https://openalex.org/W3027431227","https://openalex.org/W3034999214","https://openalex.org/W3043840704","https://openalex.org/W3090449556","https://openalex.org/W3105232955","https://openalex.org/W3107252718","https://openalex.org/W3126426178","https://openalex.org/W3153469116","https://openalex.org/W3157199281","https://openalex.org/W3172318343","https://openalex.org/W3173220247","https://openalex.org/W3197682865","https://openalex.org/W3208314443","https://openalex.org/W3215626407","https://openalex.org/W4225683910","https://openalex.org/W4229042118","https://openalex.org/W4285182336","https://openalex.org/W4288089799","https://openalex.org/W4312480274","https://openalex.org/W4312614039","https://openalex.org/W4312910992","https://openalex.org/W4319049530","https://openalex.org/W4320458302","https://openalex.org/W4384918448","https://openalex.org/W4394659899","https://openalex.org/W6678262379","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6726497184","https://openalex.org/W6748600614","https://openalex.org/W6757817989","https://openalex.org/W6761205521","https://openalex.org/W6762900673","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767279747","https://openalex.org/W6769627184","https://openalex.org/W6773815586","https://openalex.org/W6776048684","https://openalex.org/W6778883912","https://openalex.org/W6779101013","https://openalex.org/W6784184991","https://openalex.org/W6784333009","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6794385437","https://openalex.org/W6797265648","https://openalex.org/W6798538294","https://openalex.org/W6803872405","https://openalex.org/W6804424445","https://openalex.org/W6810334672","https://openalex.org/W6811013733","https://openalex.org/W6811072154","https://openalex.org/W6844305113","https://openalex.org/W6849307739","https://openalex.org/W6850204008","https://openalex.org/W6854866820","https://openalex.org/W6864544085"],"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],"aims":[2],"to":[3,82,100,111,157,240],"distill":[4],"the":[5,27,39,136,174,206,211,242],"most":[6],"important":[7],"information":[8],"from":[9],"a":[10,20,54,73,84,88,93,102,114,145,166,179,227],"source":[11],"video":[12,17,30,62,77,86,90,118,122,152],"into":[13,87],"either":[14],"an":[15,192,222],"abridged":[16],"clip":[18,91],"or":[19],"textual":[21,45,96],"narrative.":[22],"Existing":[23],"methods":[24,51,199],"often":[25],"treat":[26],"generation":[28],"of":[29,147,150,169,182,196,210,245],"and":[31,44,63,92,153],"text":[32,64,154],"summaries":[33,247],"as":[34,57,65,101,226],"independent":[35],"tasks,":[36],"thus":[37],"neglecting":[38],"semantic":[40,243],"correlation":[41],"between":[42],"visual":[43],"summarization.":[46,78,123],"In":[47,67,135],"other":[48],"words,":[49],"these":[50],"only":[52],"study":[53],"single":[55],"modality":[56],"output":[58],"without":[59],"considering":[60],"coherent":[61],"outputs.":[66],"this":[68,201,231],"work,":[69],"we":[70,177,190,219,235],"first":[71],"introduce":[72],"novel":[74,232],"task:":[75],"cross-modal":[76,103,121,246],"This":[79],"task":[80],"seeks":[81],"transfer":[83],"long":[85,142],"condensed":[89],"semantically":[94],"aligned":[95,151],"summary,":[97],"collectively":[98],"referred":[99],"summary.":[104],"We":[105],"then":[106],"establish":[107],"VideoXum":[108,124,139,160,239],"(X":[109],"refers":[110],"different":[112],"modalities),":[113],"new":[115],"large-scale":[116],"human-annotated":[117],"benchmark":[119],"for":[120,230,238],"is":[125,252],"reannotated":[126],"based":[127],"on":[128,200,216],"ActivityNet":[129],"Captions":[130],"with":[131,144,186],"diverse":[132],"open-domain":[133],"videos.":[134],"current":[137],"version,":[138],"provides":[140],"14K":[141],"videos,":[143],"total":[146],"140K":[148],"pairs":[149],"summaries.":[155],"Compared":[156],"existing":[158,187],"datasets,":[159],"offers":[161],"superior":[162],"scalability":[163],"while":[164],"preserving":[165],"comparable":[167],"level":[168],"annotation":[170],"quality.":[171],"To":[172],"validate":[173],"dataset's":[175],"quality,":[176],"provide":[178],"comprehensive":[180],"analysis":[181],"VideoXum,":[183],"comparing":[184],"it":[185],"datasets.":[188],"Further,":[189],"perform":[191],"extensive":[193],"empirical":[194],"evaluation":[195],"several":[197],"state-of-the-art":[198],"dataset.":[202],"Our":[203],"findings":[204],"highlight":[205],"impressive":[207],"generalization":[208],"capability":[209],"vision-language":[212],"encoder-decoder":[213],"framework":[214],"yields":[215],"VideoXum.":[217],"Particularly,":[218],"propose":[220],"VTSUM-BLIP,":[221],"end-to-end":[223],"framework,":[224],"serving":[225],"strong":[228],"baseline":[229],"benchmark.":[233],"Moreover,":[234],"adapt":[236],"CLIPScore":[237],"measure":[241],"consistency":[244],"effectively.":[248],"The":[249],"project":[250],"page":[251],"<uri":[253],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[254],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://videoxum.github.io/</uri>":[255],".":[256]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}