{"id":"https://openalex.org/W3133684245","doi":"https://doi.org/10.1109/tmm.2021.3062543","title":"Align R-CNN: A Pairwise Head Network for Visual Relationship Detection","display_name":"Align R-CNN: A Pairwise Head Network for Visual Relationship Detection","publication_year":2021,"publication_date":"2021-02-26","ids":{"openalex":"https://openalex.org/W3133684245","doi":"https://doi.org/10.1109/tmm.2021.3062543","mag":"3133684245"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2021.3062543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3062543","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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/A5017130020","display_name":"Mitra Tajrobehkar","orcid":"https://orcid.org/0000-0002-5914-7440"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mitra Tajrobehkar","raw_affiliation_strings":["SCSE, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-5914-7440","affiliations":[{"raw_affiliation_string":"SCSE, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044120384","display_name":"Kaihua Tang","orcid":"https://orcid.org/0000-0002-1008-7053"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kaihua Tang","raw_affiliation_strings":["SCSE, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-1008-7053","affiliations":[{"raw_affiliation_string":"SCSE, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["SCSE, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7374-8739","affiliations":[{"raw_affiliation_string":"SCSE, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077258552","display_name":"Joo\u2010Hwee Lim","orcid":"https://orcid.org/0000-0002-4103-3824"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Joo-Hwee Lim","raw_affiliation_strings":["Institute for Infocomm Research, A*Star, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4103-3824","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*Star, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.848,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.74283153,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":null,"first_page":"1266","last_page":"1276"},"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":0.9994000196456909,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9969000220298767,"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/concatenation","display_name":"Concatenation (mathematics)","score":0.8466790914535522},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7511801719665527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7083292007446289},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6422510147094727},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5476412773132324},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.4820574223995209},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42345455288887024},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37772291898727417},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3201114535331726},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10993212461471558},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.098303884267807}],"concepts":[{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.8466790914535522},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7511801719665527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7083292007446289},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6422510147094727},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5476412773132324},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.4820574223995209},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42345455288887024},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37772291898727417},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3201114535331726},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10993212461471558},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.098303884267807},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2021.3062543","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2021.3062543","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2077069816","https://openalex.org/W2105482032","https://openalex.org/W2250378130","https://openalex.org/W2277195237","https://openalex.org/W2479423890","https://openalex.org/W2481240925","https://openalex.org/W2549139847","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2579549467","https://openalex.org/W2591644541","https://openalex.org/W2605736949","https://openalex.org/W2607855566","https://openalex.org/W2739107216","https://openalex.org/W2740962769","https://openalex.org/W2754191212","https://openalex.org/W2795378892","https://openalex.org/W2799029629","https://openalex.org/W2806070179","https://openalex.org/W2810482788","https://openalex.org/W2883170015","https://openalex.org/W2886970679","https://openalex.org/W2887029921","https://openalex.org/W2890531016","https://openalex.org/W2913618459","https://openalex.org/W2950096400","https://openalex.org/W2955988340","https://openalex.org/W2962764817","https://openalex.org/W2962779575","https://openalex.org/W2962785943","https://openalex.org/W2962964995","https://openalex.org/W2963091558","https://openalex.org/W2963101956","https://openalex.org/W2963514444","https://openalex.org/W2963536419","https://openalex.org/W2963649796","https://openalex.org/W2963871344","https://openalex.org/W2963902384","https://openalex.org/W2963938081","https://openalex.org/W2963980128","https://openalex.org/W2964094751","https://openalex.org/W2971974407","https://openalex.org/W2976818183","https://openalex.org/W2981967134","https://openalex.org/W2987327987","https://openalex.org/W2990356824","https://openalex.org/W2992195701","https://openalex.org/W3026441479","https://openalex.org/W3035017890","https://openalex.org/W3108864070","https://openalex.org/W6676647902","https://openalex.org/W6739901393","https://openalex.org/W6739930931","https://openalex.org/W6748581942","https://openalex.org/W6754554023","https://openalex.org/W6759081955","https://openalex.org/W6766545348"],"related_works":["https://openalex.org/W2373577936","https://openalex.org/W4221148444","https://openalex.org/W4387678054","https://openalex.org/W2389596151","https://openalex.org/W3095575180","https://openalex.org/W4306784355","https://openalex.org/W2169308097","https://openalex.org/W2965546495","https://openalex.org/W2784004155","https://openalex.org/W4377864795"],"abstract_inverted_index":{"Scene":[0,25],"graphs":[1],"connect":[2],"individual":[3],"objects":[4],"with":[5,141],"visual":[6,68],"relationships.":[7],"They":[8],"serve":[9],"as":[10],"a":[11,108,129],"comprehensive":[12],"scene":[13],"representation":[14],"for":[15,67,92,112],"downstream":[16],"multimodal":[17],"tasks.":[18],"However,":[19],"by":[20,40,45],"exploring":[21],"recent":[22,35],"progress":[23],"in":[24,63],"Graph":[26],"Generation":[27],"(SGG),":[28],"we":[29,106,127],"find":[30],"that":[31,136,152],"the":[32,41,58,79,145,153,161,169],"performance":[33],"of":[34],"works":[36],"is":[37],"highly":[38],"limited":[39],"pairwise":[42,50,65,75],"relationship":[43,69],"modeling":[44],"naive":[46,73,162],"feature":[47,76,115,163],"concatenation.":[48,116],"Such":[49],"features":[51,66],"lack":[52],"sufficient":[53],"object":[54,60,93,114],"interaction":[55],"due":[56],"to":[57,82],"mis-aligned":[59],"parts,":[61],"resulting":[62],"non-discriminative":[64],"prediction.":[70],"For":[71],"example,":[72],"concatenated":[74],"usually":[77],"make":[78],"model":[80],"fail":[81],"discriminate":[83],"between":[84],"<monospace":[85,89,95,99],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[86,90,96,100,122,156],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">riding</monospace>":[87],"and":[88,98,165],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">feeding</monospace>":[91],"pair":[94],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">person</monospace>":[97],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">horse</monospace>":[101],".":[102,125],"To":[103],"this":[104],"end,":[105],"design":[107],"meta-architecture\u2014":[109],"learning-to-align":[110],"\u2014":[111],"dynamic":[113],"We":[117],"call":[118],"our":[119],"model:":[120],"<bold":[121,155],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Align":[123,157],"R-CNN</b>":[124,158],"Specifically,":[126],"introduce":[128],"novel":[130],"attention-based":[131],"multiple":[132],"region":[133],"alignment":[134],"module":[135],"can":[137,159],"be":[138],"jointly":[139],"optimized":[140],"SGG.":[142],"Experiments":[143],"on":[144],"large-scale":[146],"SGG":[147,171],"benchmark":[148],"Visual":[149],"Genome":[150],"show":[151],"proposed":[154],"replace":[160],"concatenation":[164],"thus":[166],"boost":[167],"all":[168],"existing":[170],"methods.":[172]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}