{"id":"https://openalex.org/W4387968041","doi":"https://doi.org/10.1145/3581783.3612087","title":"Self-supervised Video Summarization Guided by Semantic Inverse Optimal Transport","display_name":"Self-supervised Video Summarization Guided by Semantic Inverse Optimal Transport","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968041","doi":"https://doi.org/10.1145/3581783.3612087"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612087","doi":"https://doi.org/10.1145/3581783.3612087","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612087","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612087","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612087","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035931170","display_name":"Yutong Wang","orcid":"https://orcid.org/0009-0000-2225-5037","observed_orcids":["https://orcid.org/0009-0000-2225-5037"]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Wang","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-2225-5037","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035141289","display_name":"Hongteng Xu","orcid":"https://orcid.org/0000-0003-4192-5360","observed_orcids":["https://orcid.org/0000-0003-4192-5360"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongteng Xu","raw_affiliation_strings":["Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4192-5360","affiliations":[{"raw_affiliation_string":"Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101426324","display_name":"Dixin Luo","orcid":"https://orcid.org/0000-0003-1136-8903","observed_orcids":["https://orcid.org/0000-0003-1136-8903"]},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dixin Luo","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1136-8903","affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7035,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.79790649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6611","last_page":"6622"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9994999766349792,"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":0.9994999766349792,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":9.999999747378752e-05,"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/T13579","display_name":"Image and Video Stabilization","score":9.999999747378752e-05,"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/video-summarization","display_name":"video summarization","score":0.9810000061988831},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8730000257492065},{"id":"https://openalex.org/keywords/keyframe-selection","display_name":"keyframe selection","score":0.8730000257492065},{"id":"https://openalex.org/keywords/semantic-guidance","display_name":"semantic guidance","score":0.3190000057220459},{"id":"https://openalex.org/keywords/text-embeddings","display_name":"text embeddings","score":0.49799999594688416},{"id":"https://openalex.org/keywords/image-embeddings","display_name":"image embeddings","score":0.6079999804496765},{"id":"https://openalex.org/keywords/alternating-optimization","display_name":"alternating optimization","score":0.5960000157356262}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9193111658096313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.871811032295227},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6250582337379456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5568888783454895},{"id":"https://openalex.org/C2775856596","wikidata":"https://www.wikidata.org/wiki/Q25141683","display_name":"Video browsing","level":4,"score":0.4505709111690521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41592758893966675},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2534181475639343},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2464560866355896}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612087","doi":"https://doi.org/10.1145/3581783.3612087","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612087","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612087","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612087","doi":"https://doi.org/10.1145/3581783.3612087","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612087","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612087","source":{"id":"https://openalex.org/S4363608757","display_name":"ACM International Conference on Multimedia (ACM MM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6043252873","display_name":null,"funder_award_id":"62106271","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6966265784","display_name":null,"funder_award_id":"92270110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6983870997","display_name":null,"funder_award_id":"62102031","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/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"},{"id":"https://openalex.org/F4320323110","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968041.pdf","grobid_xml":"https://content.openalex.org/works/W4387968041.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W385466589","https://openalex.org/W1979354511","https://openalex.org/W1991750682","https://openalex.org/W2091038426","https://openalex.org/W2097117768","https://openalex.org/W2187089797","https://openalex.org/W2529272619","https://openalex.org/W2559655401","https://openalex.org/W2605324664","https://openalex.org/W2737677090","https://openalex.org/W2740409734","https://openalex.org/W2747329762","https://openalex.org/W2767757834","https://openalex.org/W2776277180","https://openalex.org/W2781922022","https://openalex.org/W2788303226","https://openalex.org/W2794558616","https://openalex.org/W2804828897","https://openalex.org/W2843098267","https://openalex.org/W2883429621","https://openalex.org/W2892266277","https://openalex.org/W2894030891","https://openalex.org/W2895671046","https://openalex.org/W2895758197","https://openalex.org/W2897091983","https://openalex.org/W2903758693","https://openalex.org/W2938584417","https://openalex.org/W2944414668","https://openalex.org/W2957602802","https://openalex.org/W2963220254","https://openalex.org/W2963432616","https://openalex.org/W2963919999","https://openalex.org/W2964121744","https://openalex.org/W2967219836","https://openalex.org/W2996858319","https://openalex.org/W3003344099","https://openalex.org/W3025796084","https://openalex.org/W3035242260","https://openalex.org/W3039256091","https://openalex.org/W3042359161","https://openalex.org/W3090449556","https://openalex.org/W3099156605","https://openalex.org/W3107128832","https://openalex.org/W3150815828","https://openalex.org/W3157233284","https://openalex.org/W3167308647","https://openalex.org/W3169578923","https://openalex.org/W3173181308","https://openalex.org/W3184439416","https://openalex.org/W3205822625","https://openalex.org/W4234552385","https://openalex.org/W4284674178","https://openalex.org/W4302305810","https://openalex.org/W4304080456","https://openalex.org/W4304080900","https://openalex.org/W4304084190","https://openalex.org/W4312974570","https://openalex.org/W4313038449","https://openalex.org/W4317791940","https://openalex.org/W4390871765","https://openalex.org/W4411245187"],"related_works":["https://openalex.org/W7223172100","https://openalex.org/W4386598561","https://openalex.org/W4414989803","https://openalex.org/W7204232794","https://openalex.org/W3048546257","https://openalex.org/W7160329905","https://openalex.org/W4405868458","https://openalex.org/W4414530356","https://openalex.org/W7170092724","https://openalex.org/W4361229205"],"abstract_inverted_index":{"Video":[0],"summarization":[1,33,57,82,209],"is":[2,59,214,222],"a":[3,13,23,78,184],"critical":[4],"task":[5],"in":[6,143,200],"video":[7,21,81,98,173,208],"analysis":[8],"that":[9],"aims":[10],"to":[11,63,108,133,146,182,216],"create":[12],"brief":[14],"yet":[15],"informative":[16],"summary":[17],"of":[18,25,48,55,66,87],"the":[19,45,53,64,70,85,102,105,109,144,151,156,160,165,177,193],"original":[20],"(i.e.,":[22],"set":[24],"keyframes)":[26],"while":[27],"retaining":[28],"its":[29],"primary":[30],"content.":[31],"Supervised":[32],"methods":[34,58,199],"rely":[35],"on":[36,69],"time-consuming":[37],"keyframe":[38,71,185],"labeling":[39],"and":[40,100,138,155,164,175,189,206],"thus":[41],"often":[42,60],"suffer":[43],"from":[44,97,104],"insufficiency":[46],"issue":[47],"training":[49],"data.":[50],"In":[51,73],"contrast,":[52],"performance":[54,212],"unsupervised":[56,198],"unsatisfactory":[61],"due":[62],"lack":[65],"semantically-meaningful":[67],"guidance":[68],"selection.":[72],"this":[74,135],"study,":[75],"we":[76,93,168],"propose":[77,128],"novel":[79],"self-supervised":[80],"framework":[83,195],"with":[84,113],"help":[86],"computational":[88],"optimal":[89,115,124,152],"transport":[90,116,125,153],"techniques.":[91],"Specifically,":[92],"generate":[94],"textual":[95,106,162],"descriptions":[96],"shots":[99],"learn":[101],"projection":[103],"embeddings":[107,163],"visual":[110,166],"ones":[111],"together":[112],"an":[114,122,129,140],"plan":[117,154],"between":[118,159],"them":[119],"via":[120],"solving":[121],"inverse":[123],"problem.":[126],"We":[127],"alternating":[130],"optimization":[131],"algorithm":[132,145],"solve":[134],"problem":[136],"efficiently":[137],"design":[139],"effective":[141],"mechanism":[142],"avoid":[147],"trivial":[148],"solutions.":[149],"Given":[150],"underlying":[157],"distance":[158],"projected":[161],"ones,":[167],"synthesize":[169],"pseudo-significance":[170],"scores":[171,178],"for":[172,204],"frames":[174],"leverage":[176],"as":[179],"offline":[180],"supervision":[181],"train":[183],"selector.":[186],"Without":[187],"subjective":[188],"error-prone":[190],"manual":[191],"annotations,":[192],"proposed":[194],"surpasses":[196],"previous":[197],"producing":[201],"high-quality":[202],"results":[203],"generic":[205],"instructional":[207],"tasks,":[210],"whose":[211],"even":[213],"comparable":[215],"those":[217],"supervised":[218],"competitors.":[219],"The":[220],"code":[221],"available":[223],"at":[224],"https://github.com/Dixin-s-Lab/Video-Summary-IOT.":[225]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2023-10-28T00:00:00"}
