{"id":"https://openalex.org/W4304084190","doi":"https://doi.org/10.1145/3503161.3548067","title":"Weakly-Supervised Temporal Action Alignment Driven by Unbalanced Spectral Fused Gromov-Wasserstein Distance","display_name":"Weakly-Supervised Temporal Action Alignment Driven by Unbalanced Spectral Fused Gromov-Wasserstein Distance","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304084190","doi":"https://doi.org/10.1145/3503161.3548067"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548067","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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 30th ACM International Conference on Multimedia","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/A5101426324","display_name":"Dixin Luo","orcid":"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":true,"raw_author_name":"Dixin Luo","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631530","display_name":"Yutong Wang","orcid":"https://orcid.org/0000-0003-2981-7471"},"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"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000167822","display_name":"Angxiao Yue","orcid":null},"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":"Angxiao Yue","raw_affiliation_strings":["Beijing Institute of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035141289","display_name":"Hongteng Xu","orcid":"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 Key Laboratory of Big Data Management and Analysis Methods, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Renmin University of China & Beijing Key Laboratory of Big Data Management and Analysis Methods, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101426324"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.3598,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.67317838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"728","last_page":"739"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9970999956130981,"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":0.7935611009597778},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.689771294593811},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5886750817298889},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5787362456321716},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.5637579560279846},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.522125780582428},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.46655434370040894},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43076205253601074},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.42903172969818115},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4185495376586914},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.387539803981781}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935611009597778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.689771294593811},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5886750817298889},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5787362456321716},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.5637579560279846},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.522125780582428},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46655434370040894},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43076205253601074},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.42903172969818115},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4185495376586914},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.387539803981781},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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:10.1145/3503161.3548067","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548067","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G321479996","display_name":null,"funder_award_id":"62106271, 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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1528177060","https://openalex.org/W1967664674","https://openalex.org/W2003447360","https://openalex.org/W2019660985","https://openalex.org/W2099614498","https://openalex.org/W2108710284","https://openalex.org/W2292288263","https://openalex.org/W2314362175","https://openalex.org/W2337252826","https://openalex.org/W2419501139","https://openalex.org/W2461621749","https://openalex.org/W2491875666","https://openalex.org/W2530494944","https://openalex.org/W2550143307","https://openalex.org/W2559655401","https://openalex.org/W2600081845","https://openalex.org/W2789221157","https://openalex.org/W2798345491","https://openalex.org/W2889986507","https://openalex.org/W2912083425","https://openalex.org/W2912269676","https://openalex.org/W2913954081","https://openalex.org/W2957602802","https://openalex.org/W2957775769","https://openalex.org/W2962916463","https://openalex.org/W2963017553","https://openalex.org/W2963321993","https://openalex.org/W2963398989","https://openalex.org/W2963853051","https://openalex.org/W2964045146","https://openalex.org/W2964184470","https://openalex.org/W2981689412","https://openalex.org/W2991210238","https://openalex.org/W2996858319","https://openalex.org/W3008576587","https://openalex.org/W3009622574","https://openalex.org/W3034337242","https://openalex.org/W3034687522","https://openalex.org/W3035242260","https://openalex.org/W3035557275","https://openalex.org/W3083550439","https://openalex.org/W3124314487","https://openalex.org/W3158986867","https://openalex.org/W3162773407","https://openalex.org/W3172655693","https://openalex.org/W3173698268","https://openalex.org/W3175716777","https://openalex.org/W3180463990","https://openalex.org/W3202074654","https://openalex.org/W3204670646","https://openalex.org/W4206471589","https://openalex.org/W4212841753","https://openalex.org/W4213354309","https://openalex.org/W4236965008","https://openalex.org/W6600376255","https://openalex.org/W6624914812"],"related_works":["https://openalex.org/W2943623134","https://openalex.org/W2494523064","https://openalex.org/W2215759665","https://openalex.org/W2030292806","https://openalex.org/W2960358116","https://openalex.org/W2938171715","https://openalex.org/W4287727129","https://openalex.org/W3041172967","https://openalex.org/W2749065928","https://openalex.org/W2147155098"],"abstract_inverted_index":{"Temporal":[0],"action":[1,61,215],"alignment":[2,37,62,216],"aims":[3],"at":[4,239],"segmenting":[5],"videos":[6,82],"into":[7],"clips":[8,85],"and":[9,86,116,134,145,157,182,208],"tagging":[10],"each":[11,94],"clip":[12],"with":[13,83,100],"a":[14,58,66,101,139,193],"textual":[15,88,160],"description,":[16],"which":[17,191],"is":[18,237],"an":[19],"important":[20],"task":[21],"of":[22,44,49,80,103,130,153,159,196],"video":[23,96,132],"semantic":[24],"analysis.":[25],"Most":[26],"existing":[27],"methods,":[28,217],"however,":[29],"rely":[30],"on":[31,65,186,230],"supervised":[32,227],"learning":[33,180,198,228],"to":[34,97,223],"train":[35],"their":[36],"models,":[38],"whose":[39,218],"applications":[40],"are":[41,220],"limited":[42],"because":[43],"the":[45,110,114,117,127,131,135,147,151,165,171,187],"common":[46],"insufficiency":[47],"issue":[48],"labeled":[50],"videos.":[51],"To":[52],"mitigate":[53],"this":[54],"issue,":[55],"we":[56,176],"propose":[57],"weakly-supervised":[59,121,213],"temporal":[60,214],"method":[63,91,125,207],"based":[64,185],"novel":[67],"computational":[68],"optimal":[69],"transport":[70],"technique":[71],"called":[72],"unbalanced":[73],"spectral":[74],"fused":[75],"Gromov-Wasserstein":[76],"(US-FGW)":[77],"distance.":[78],"Instead":[79],"using":[81],"known":[84],"corresponding":[87],"tags,":[89],"our":[90,124,200,206],"just":[92],"needs":[93],"training":[95],"be":[98],"associated":[99],"set":[102],"(unsorted)":[104],"texts":[105,136],"while":[106],"does":[107],"not":[108],"require":[109],"fine-grained":[111],"correspondence":[112],"between":[113,150],"frames":[115,133],"texts.":[118],"Given":[119],"such":[120],"video-text":[122],"pairs,":[123],"trains":[126],"representation":[128],"models":[129],"jointly":[137],"in":[138],"probabilistic":[140],"or":[141],"deterministic":[142],"autoencoding":[143],"architecture":[144],"penalizes":[146],"US-FGW":[148,166,189],"distance":[149,167],"distribution":[152],"visual":[154],"latent":[155,161],"codes":[156],"that":[158,205],"codes.":[162],"We":[163],"compute":[164],"efficiently":[168],"by":[169,226],"leveraging":[170],"Bregman":[172],"ADMM":[173],"algorithm.":[174],"Furthermore,":[175],"generalize":[177],"classic":[178],"contrastive":[179,197],"framework":[181],"reformulate":[183],"it":[184],"proposed":[188],"distance,":[190],"provides":[192],"new":[194],"viewpoint":[195],"for":[199],"problem.":[201],"Experimental":[202],"results":[203,219],"show":[204],"its":[209],"variants":[210],"outperform":[211],"state-of-the-art":[212],"even":[221],"comparable":[222],"those":[224],"derived":[225],"methods":[229],"some":[231],"specific":[232],"evaluation":[233],"measurements.":[234],"The":[235],"code":[236],"available":[238],"\\urlhttps://github.com/hhhh1138/Temporal-Action-Alignment-USFGW.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}