{"id":"https://openalex.org/W4380052056","doi":"https://doi.org/10.1145/3604284","title":"Zero-shot Scene Graph Generation via Triplet Calibration and Reduction","display_name":"Zero-shot Scene Graph Generation via Triplet Calibration and Reduction","publication_year":2023,"publication_date":"2023-06-08","ids":{"openalex":"https://openalex.org/W4380052056","doi":"https://doi.org/10.1145/3604284"},"language":"en","primary_location":{"id":"doi:10.1145/3604284","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3604284","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3604284","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3604284","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001470290","display_name":"Jiankai Li","orcid":"https://orcid.org/0009-0008-8858-7980"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiankai Li","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University; and Shanghai Artificial Intelligence Laboratory, China","Shanghai Artificial Intelligence Laboratory, China"],"raw_orcid":"https://orcid.org/0009-0008-8858-7980","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University; and Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4391012619","https://openalex.org/I82880672"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100398953","display_name":"Yunhong Wang","orcid":"https://orcid.org/0000-0001-8001-2703"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhong Wang","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University; and Shanghai Artificial Intelligence Laboratory, China","Shanghai Artificial Intelligence Laboratory, China"],"raw_orcid":"https://orcid.org/0000-0001-8001-2703","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University; and Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4391012619","https://openalex.org/I82880672"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100662467","display_name":"Weixin Li","orcid":"https://orcid.org/0000-0002-5093-5635"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixin Li","raw_affiliation_strings":["State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University; and Shanghai Artificial Intelligence Laboratory, China","Shanghai Artificial Intelligence Laboratory, China"],"raw_orcid":"https://orcid.org/0000-0002-5093-5635","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University; and Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4391012619","https://openalex.org/I82880672"]},{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2911,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.48771094,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"20","issue":"1","first_page":"1","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":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":0.9987999796867371,"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":0.9922999739646912,"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/inference","display_name":"Inference","score":0.7600924968719482},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7309978008270264},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6670557260513306},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.5831490755081177},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5523651838302612},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5512701272964478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5376014113426208},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4964941143989563},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.4267643690109253},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4161233901977539},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4112378656864166},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3524061441421509},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34920430183410645},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3487088084220886},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3422917127609253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1589246392250061}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7600924968719482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7309978008270264},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6670557260513306},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.5831490755081177},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5523651838302612},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5512701272964478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5376014113426208},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4964941143989563},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4267643690109253},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4161233901977539},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4112378656864166},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3524061441421509},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34920430183410645},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3487088084220886},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3422917127609253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1589246392250061},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3604284","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3604284","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3604284","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2309.03542","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.03542","pdf_url":"https://arxiv.org/pdf/2309.03542","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":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":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/3604284","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3604284","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3604284","source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G4365890579","display_name":null,"funder_award_id":"2022ZD0161901","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G7348502280","display_name":null,"funder_award_id":"62276018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7365179782","display_name":null,"funder_award_id":"62276018, U20B2069","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7665144123","display_name":null,"funder_award_id":"U20B2069","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4380052056.pdf","grobid_xml":"https://content.openalex.org/works/W4380052056.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W1948251820","https://openalex.org/W2064675550","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2559655401","https://openalex.org/W2565639579","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2612690371","https://openalex.org/W2789177853","https://openalex.org/W2899867782","https://openalex.org/W2947385066","https://openalex.org/W2963341628","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W2964072591","https://openalex.org/W2969679616","https://openalex.org/W2992478697","https://openalex.org/W3010276570","https://openalex.org/W3016121695","https://openalex.org/W3025726122","https://openalex.org/W3033697199","https://openalex.org/W3034984754","https://openalex.org/W3035017890","https://openalex.org/W3038593179","https://openalex.org/W3048602385","https://openalex.org/W3098690786","https://openalex.org/W3101215053","https://openalex.org/W3102601130","https://openalex.org/W3107848485","https://openalex.org/W3108230874","https://openalex.org/W3109229205","https://openalex.org/W3119381934","https://openalex.org/W3121709906","https://openalex.org/W3128560592","https://openalex.org/W3142108776","https://openalex.org/W3155644662","https://openalex.org/W3162332195","https://openalex.org/W3166396011","https://openalex.org/W3174865181","https://openalex.org/W3181556077","https://openalex.org/W3198299822","https://openalex.org/W3201861986","https://openalex.org/W3205821239","https://openalex.org/W3215287157","https://openalex.org/W4200498145","https://openalex.org/W4212774754","https://openalex.org/W4213031069","https://openalex.org/W4214824212","https://openalex.org/W4214946871","https://openalex.org/W4220974559","https://openalex.org/W4225868495","https://openalex.org/W4225998785","https://openalex.org/W4283030109","https://openalex.org/W4285787895","https://openalex.org/W4288707709","https://openalex.org/W4294558607","https://openalex.org/W4303647620","https://openalex.org/W4306153300","https://openalex.org/W4312363706","https://openalex.org/W4312400874","https://openalex.org/W4312429751","https://openalex.org/W4312555984","https://openalex.org/W4312578829","https://openalex.org/W4312578903","https://openalex.org/W4312682661","https://openalex.org/W4312744661","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Scene":[0],"Graph":[1],"Generation":[2],"(SGG)":[3],"plays":[4],"a":[5,53,66,112,144],"pivotal":[6],"role":[7],"in":[8,60,87],"downstream":[9],"vision-language":[10],"tasks.":[11],"Existing":[12],"SGG":[13,177],"methods":[14],"typically":[15],"suffer":[16],"from":[17],"poor":[18],"compositional":[19,150],"generalizations":[20,151],"on":[21,28],"unseen":[22,85,95,122,134,153],"triplets.":[23],"They":[24],"are":[25],"generally":[26],"trained":[27],"incompletely":[29,88],"annotated":[30,89],"scene":[31,91,98],"graphs":[32,99],"that":[33,169],"contain":[34],"dominant":[35],"triplets":[36,44,79,86,154],"and":[37,56,80,164],"tend":[38],"to":[39,73,81,126,132,136,147],"bias":[40],"toward":[41],"these":[42],"seen":[43,107],"during":[45],"inference.":[46],"To":[47],"address":[48],"this":[49,61],"issue,":[50],"we":[51,119,142],"propose":[52,120,143],"Triplet":[54],"Calibration":[55],"Reduction":[57],"(T-CAR)":[58],"framework":[59],"article.":[62],"In":[63],"our":[64,170],"framework,":[65],"triplet":[67],"calibration":[68],"loss":[69,125],"is":[70,100,183],"first":[71],"presented":[72],"regularize":[74],"the":[75,84,94,106,128,138,149,158],"representations":[76],"of":[77,97,115,130,152],"diverse":[78],"simultaneously":[82],"excavate":[83],"training":[90],"graphs.":[92],"Moreover,":[93],"space":[96,123],"usually":[101],"several":[102],"times":[103],"larger":[104],"than":[105],"space,":[108],"since":[109],"it":[110],"contains":[111],"huge":[113],"number":[114],"unrealistic":[116],"compositions.":[117],"Thus,":[118],"an":[121],"reduction":[124],"shift":[127],"attention":[129],"excavation":[131],"reasonable":[133],"compositions":[135],"facilitate":[137],"model":[139],"training.":[140],"Finally,":[141],"contextual":[145],"encoder":[146],"improve":[148],"by":[155],"explicitly":[156],"modeling":[157],"relative":[159],"spatial":[160],"relations":[161],"between":[162],"subjects":[163],"objects.":[165],"Extensive":[166],"experiments":[167],"show":[168],"approach":[171],"achieves":[172],"consistent":[173],"improvements":[174],"for":[175],"zero-shot":[176],"over":[178],"state-of-the-art":[179],"methods.":[180],"The":[181],"code":[182],"available":[184],"at":[185],"https://github.com/jkli1998/T-CAR":[186],".":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}