{"id":"https://openalex.org/W4388579765","doi":"https://doi.org/10.1109/tip.2023.3330304","title":"Toward a Unified Transformer-Based Framework for Scene Graph Generation and Human-Object Interaction Detection","display_name":"Toward a Unified Transformer-Based Framework for Scene Graph Generation and Human-Object Interaction Detection","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4388579765","doi":"https://doi.org/10.1109/tip.2023.3330304","pmid":"https://pubmed.ncbi.nlm.nih.gov/37948145"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2023.3330304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3330304","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100761497","display_name":"Tao He","orcid":"https://orcid.org/0000-0001-8676-7429"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Tao He","raw_affiliation_strings":["Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, China","Department of Data Science and AI, Faculty of Information Technology, Monash University, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8676-7429","affiliations":[{"raw_affiliation_string":"Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]},{"raw_affiliation_string":"Department of Data Science and AI, Faculty of Information Technology, Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066645546","display_name":"Lianli Gao","orcid":"https://orcid.org/0000-0002-2522-6394"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lianli Gao","raw_affiliation_strings":["Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2522-6394","affiliations":[{"raw_affiliation_string":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036987388","display_name":"Jingkuan Song","orcid":"https://orcid.org/0000-0002-2549-8322"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingkuan Song","raw_affiliation_strings":["Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-2549-8322","affiliations":[{"raw_affiliation_string":"Center for Future Media, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017943466","display_name":"Yuan-Fang Li","orcid":"https://orcid.org/0000-0003-4651-2821"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yuan-Fang Li","raw_affiliation_strings":["Department of Data Science and AI, Faculty of Information Technology, Monash University, Melbourne, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4651-2821","affiliations":[{"raw_affiliation_string":"Department of Data Science and AI, Faculty of Information Technology, Monash University, Melbourne, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4891,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84960362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"6274","last_page":"6288"},"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9983999729156494,"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":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.750532865524292},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6541190147399902},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.62388676404953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5718111991882324},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.565738320350647},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5175842046737671},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4696943759918213},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4367818236351013},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42505744099617004},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.4196242690086365},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3049566149711609},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2297547161579132}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750532865524292},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6541190147399902},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.62388676404953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5718111991882324},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.565738320350647},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5175842046737671},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4696943759918213},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4367818236351013},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42505744099617004},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.4196242690086365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3049566149711609},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2297547161579132},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014796","descriptor_name":"Visual Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014796","descriptor_name":"Visual Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014796","descriptor_name":"Visual Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021641","descriptor_name":"Recognition, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2023.3330304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2023.3330304","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:37948145","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37948145","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6966311521","display_name":null,"funder_award_id":"62306064","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":67,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1551928752","https://openalex.org/W2194775991","https://openalex.org/W2222512263","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2607855566","https://openalex.org/W2884822772","https://openalex.org/W2888096830","https://openalex.org/W2888814092","https://openalex.org/W2913340405","https://openalex.org/W2937297214","https://openalex.org/W2962785943","https://openalex.org/W2962844592","https://openalex.org/W2962933664","https://openalex.org/W2963097937","https://openalex.org/W2963150697","https://openalex.org/W2963453233","https://openalex.org/W2963498646","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W2964225075","https://openalex.org/W2990599624","https://openalex.org/W3014641072","https://openalex.org/W3034638741","https://openalex.org/W3034934229","https://openalex.org/W3034951775","https://openalex.org/W3035017890","https://openalex.org/W3035047011","https://openalex.org/W3035598501","https://openalex.org/W3096609285","https://openalex.org/W3102452576","https://openalex.org/W3106121867","https://openalex.org/W3106988096","https://openalex.org/W3107081247","https://openalex.org/W3109813419","https://openalex.org/W3132455321","https://openalex.org/W3151099711","https://openalex.org/W3168279596","https://openalex.org/W3168488421","https://openalex.org/W3171169846","https://openalex.org/W3173181410","https://openalex.org/W3174164794","https://openalex.org/W3174480456","https://openalex.org/W3181556077","https://openalex.org/W3195860412","https://openalex.org/W3201861986","https://openalex.org/W3204397973","https://openalex.org/W3216551675","https://openalex.org/W4312343844","https://openalex.org/W4312407537","https://openalex.org/W4312563197","https://openalex.org/W4312960102","https://openalex.org/W4366352717","https://openalex.org/W4385245566","https://openalex.org/W6632922691","https://openalex.org/W6739930931","https://openalex.org/W6754152559","https://openalex.org/W6761438616","https://openalex.org/W6785527955","https://openalex.org/W6791353385","https://openalex.org/W6799822930","https://openalex.org/W6810269325","https://openalex.org/W6811394763"],"related_works":["https://openalex.org/W4231704780","https://openalex.org/W2083794993","https://openalex.org/W352609212","https://openalex.org/W1511772879","https://openalex.org/W4379115841","https://openalex.org/W4200340037","https://openalex.org/W4206178588","https://openalex.org/W4287635093","https://openalex.org/W3094491777","https://openalex.org/W3214715529"],"abstract_inverted_index":{"Scene":[0],"graph":[1],"generation":[2],"(SGG)":[3],"and":[4,17,22,26,61,131,181,221],"human-object":[5,71,99,159],"interaction":[6],"(HOI)":[7],"detection":[8],"are":[9],"two":[10,87,120],"important":[11],"visual":[12,55,149],"tasks":[13,33,128,223,233],"aiming":[14],"at":[15],"localising":[16],"recognising":[18],"relationships":[19,56],"between":[20,24,85],"objects,":[21,27],"interactions":[23,160],"humans":[25],"respectively.":[28],"Prevailing":[29],"works":[30],"treat":[31],"these":[32],"as":[34,94],"distinct":[35],"tasks,":[36,88],"leading":[37],"to":[38,45,76,124,157,193,206,235],"the":[39,52,68,86,114,127,163,184],"development":[40],"of":[41,54,70,103,129,148,170,187],"task-specific":[42],"models":[43],"tailored":[44],"individual":[46],"datasets.":[47],"However,":[48],"we":[49,105,135,152,211],"posit":[50],"that":[51,65,213],"presence":[53],"can":[57,92],"furnish":[58],"crucial":[59],"contextual":[60],"intricate":[62],"relational":[63],"cues":[64],"significantly":[66],"augment":[67],"inference":[69],"interactions.":[72,100],"This":[73],"motivates":[74],"us":[75],"think":[77],"if":[78],"there":[79],"is":[80],"a":[81,95,108,137,146],"natural":[82],"intrinsic":[83],"relationship":[84],"where":[89],"scene":[90],"graphs":[91],"serve":[93],"source":[96],"for":[97,231],"inferring":[98],"In":[101],"light":[102],"this,":[104],"introduce":[106],"SG2HOI+,":[107],"unified":[109],"one-step":[110],"model":[111,190],"based":[112,161],"on":[113,162,218],"Transformer":[115,139],"architecture.":[116],"Our":[117],"approach":[118,200],"employs":[119],"interactive":[121],"hierarchical":[122],"Transformers":[123],"seamlessly":[125],"unify":[126],"SGG":[130,196,220],"HOI":[132,208,222],"detection.":[133],"Concretely,":[134],"initiate":[136],"relation":[138,143,165],"tasked":[140],"with":[141],"generating":[142],"triples":[144],"from":[145],"suite":[147],"features.":[150],"Subsequently,":[151],"employ":[153],"another":[154],"transformer-based":[155],"decoder":[156],"predict":[158],"generated":[164],"triples.":[166],"A":[167],"comprehensive":[168],"series":[169],"experiments":[171],"conducted":[172],"across":[173],"established":[174],"benchmark":[175],"datasets":[176],"including":[177],"Visual":[178],"Genome,":[179],"V-COCO,":[180],"HICO-DET":[182],"demonstrates":[183],"compelling":[185],"performance":[186,203],"our":[188,199,214],"SG2HOI+":[189,215],"in":[191,224],"comparison":[192],"prevalent":[194],"one-stage":[195],"models.":[197],"Remarkably,":[198],"achieves":[201],"competitive":[202],"when":[204],"compared":[205,234],"state-of-the-art":[207],"methods.":[209],"Additionally,":[210],"observe":[212],"jointly":[216],"trained":[217],"both":[219,232],"an":[225],"end-to-end":[226],"manner":[227],"yields":[228],"substantial":[229],"improvements":[230],"individualized":[236],"training":[237],"paradigms.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}