{"id":"https://openalex.org/W4379806189","doi":"https://doi.org/10.1145/3591106.3592267","title":"Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation","display_name":"Multi-Label Meta Weighting for Long-Tailed Dynamic Scene Graph Generation","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4379806189","doi":"https://doi.org/10.1145/3591106.3592267"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"proceedings-article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.10122","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101764080","display_name":"Shuo Chen","orcid":"https://orcid.org/0009-0005-6092-8104"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"funder","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shuo Chen","raw_affiliation_strings":["VIS Lab, University of Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"VIS Lab, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077690631","display_name":"Yingjun Du","orcid":"https://orcid.org/0000-0001-7537-6457"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"funder","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yingjun Du","raw_affiliation_strings":["VIS Lab, University of Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"VIS Lab, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000845063","display_name":"Pascal Mettes","orcid":"https://orcid.org/0000-0001-9275-5942"},"institutions":[],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Pascal Mettes","raw_affiliation_strings":["VIS Lab, P.S.M.Mettes@uva.nl, Netherlands"],"affiliations":[{"raw_affiliation_string":"VIS Lab, P.S.M.Mettes@uva.nl, Netherlands","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024508073","display_name":"Cees G. M. Snoek","orcid":"https://orcid.org/0000-0001-9092-1556"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"funder","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Cees G.M. Snoek","raw_affiliation_strings":["VIS Lab, University of Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"VIS Lab, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.702443,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":66,"max":77},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"47"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9989,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9971,"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/predicate","display_name":"Predicate (mathematical logic)","score":0.6994902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7039863},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.6994902},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5528799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.51713485},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49849558},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42825794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35089302},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32823098},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32284406},{"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/3591106.3592267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2306.10122","pdf_url":"https://arxiv.org/pdf/2306.10122","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"https://api.datacite.org/dois/10.48550/arxiv.2306.10122","pdf_url":null,"source":{"id":"https://openalex.org/S4393179698","display_name":"DataCite API","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I4210145204","host_organization_name":"DataCite","host_organization_lineage":["https://openalex.org/I4210145204"],"host_organization_lineage_names":["DataCite"],"type":"metadata"},"license":null,"license_id":null,"version":null}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2306.10122","pdf_url":"https://arxiv.org/pdf/2306.10122","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":["https://openalex.org/W4379806189"],"referenced_works_count":33,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2077069816","https://openalex.org/W2194775991","https://openalex.org/W2250384498","https://openalex.org/W2579549467","https://openalex.org/W2884561390","https://openalex.org/W2886970679","https://openalex.org/W3033792940","https://openalex.org/W3034679267","https://openalex.org/W3035503132","https://openalex.org/W3093028502","https://openalex.org/W3093195700","https://openalex.org/W3095707208","https://openalex.org/W3118923280","https://openalex.org/W3173181410","https://openalex.org/W3176506622","https://openalex.org/W3181556077","https://openalex.org/W3182902595","https://openalex.org/W3186621246","https://openalex.org/W3193302808","https://openalex.org/W3211107212","https://openalex.org/W4200630194","https://openalex.org/W4225868495","https://openalex.org/W4287022120","https://openalex.org/W4287116371","https://openalex.org/W4287823174","https://openalex.org/W4296262844","https://openalex.org/W4299303451","https://openalex.org/W4299670242","https://openalex.org/W4302602837","https://openalex.org/W4312561757","https://openalex.org/W4313161463","https://openalex.org/W639708223"],"related_works":["https://openalex.org/W4372260270","https://openalex.org/W4206560911","https://openalex.org/W2787352659","https://openalex.org/W2180954594","https://openalex.org/W2127804977","https://openalex.org/W2108418243","https://openalex.org/W2052835778","https://openalex.org/W2049003611","https://openalex.org/W1970611213","https://openalex.org/W164103134"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,12,23,31,71,75,96,108,117,125,149,167,192,212,217,222],"problem":[4],"of":[5,14,25,127],"scene":[6,131,153],"graph":[7,132,154],"generation":[8,133,155],"in":[9,22,42,116,134,156,221,232],"videos":[10,135],"with":[11,166],"aim":[13],"capturing":[15],"semantic":[16],"relations":[17],"between":[18,33,74,141],"subjects":[19],"and":[20,35,40,69,77,83,99,136,144,195,236],"objects":[21],"form":[24],"$\\langle$subject,":[26],"predicate,":[27],"object$\\rangle$":[28],"triplets.":[29],"Recognizing":[30],"predicate":[32,112,142,169],"subject":[34],"object":[36],"pairs":[37],"is":[38],"imbalanced":[39],"multi-label":[41,161,213],"nature,":[43],"ranging":[44],"from":[45],"ubiquitous":[46],"interactions":[47,58],"such":[48,59,65],"as":[49,60,66],"spatial":[50],"relationships":[51],"(\\eg":[52],"\\emph{in":[53],"front":[54],"of})":[55],"to":[56,95,164],"rare":[57],"\\emph{twisting}.":[61],"In":[62,120],"widely-used":[63],"benchmarks":[64,88,197],"Action":[67,193],"Genome":[68,194],"VidOR,":[70],"imbalance":[72],"ratio":[73],"most":[76,109],"least":[78],"frequent":[79],"predicates":[80,220],"reaches":[81],"3,218":[82],"3,408,":[84],"respectively,":[85],"surpassing":[86],"even":[87],"specifically":[89],"designed":[90],"for":[91,130,178,205,219,228],"long-tailed":[92,97],"recognition.":[93],"Due":[94],"distributions":[98],"label":[100,185],"co-occurrences,":[101],"recent":[102],"state-of-the-art":[103,203],"methods":[104,204],"predominantly":[105],"focus":[106],"on":[107,191],"frequently":[110],"occurring":[111],"classes,":[113,230],"ignoring":[114],"those":[115],"long":[118,223],"tail.":[119],"this":[121],"paper,":[122],"we":[123,158],"analyze":[124],"limitations":[126],"current":[128,202],"approaches":[129],"identify":[137],"a":[138,160,175],"one-to-one":[139],"correspondence":[140],"frequency":[143],"recall":[145],"performance.":[146],"To":[147],"make":[148],"step":[150],"towards":[151],"unbiased":[152],"videos,":[157],"introduce":[159],"meta-learning":[162,172],"framework":[163,173],"deal":[165],"biased":[168],"distribution.":[170],"Our":[171],"learns":[174],"meta-weight":[176,214],"network":[177,215],"each":[179,206],"training":[180],"sample":[181],"over":[182],"all":[183],"possible":[184],"losses.":[186],"We":[187],"evaluate":[188],"our":[189],"approach":[190],"VidOR":[196],"by":[198],"building":[199],"upon":[200],"two":[201],"benchmark.":[207],"The":[208],"experiments":[209],"demonstrate":[210],"that":[211],"improves":[216],"performance":[218,227,235],"tail":[224],"without":[225],"compromising":[226],"head":[229],"resulting":[231],"better":[233],"overall":[234],"favorable":[237],"generalizability.":[238],"Code:":[239],"\\url{https://github.com/shanshuo/ML-MWN}.":[240]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4379806189","counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-03-18T07:09:27.800728","created_date":"2023-06-09"}