{"id":"https://openalex.org/W4387968447","doi":"https://doi.org/10.1145/3581783.3611889","title":"Improving Scene Graph Generation with Superpixel-Based Interaction Learning","display_name":"Improving Scene Graph Generation with Superpixel-Based Interaction Learning","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968447","doi":"https://doi.org/10.1145/3581783.3611889"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611889","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611889","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611889","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611889","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100319492","display_name":"Jingyi Wang","orcid":"https://orcid.org/0000-0001-7832-8848"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingyi Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440826","display_name":"Can Zhang","orcid":"https://orcid.org/0000-0001-9530-5218"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Zhang","raw_affiliation_strings":["Tencent Media Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tencent Media Lab, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101890579","display_name":"Jinfa Huang","orcid":"https://orcid.org/0000-0002-0081-4106"},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinfa Huang","raw_affiliation_strings":["University of Rochester, Rochester, NY, USA"],"affiliations":[{"raw_affiliation_string":"University of Rochester, Rochester, NY, USA","institution_ids":["https://openalex.org/I5388228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029172080","display_name":"Botao Ren","orcid":"https://orcid.org/0009-0001-1646-9183"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Botao Ren","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102011846","display_name":"Zhidong Deng","orcid":"https://orcid.org/0000-0001-9970-1023"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhidong Deng","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100319492"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.8343,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7555167,"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":"1809","last_page":"1820"},"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":0.992900013923645,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9908999800682068,"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":0.8182910680770874},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.533926248550415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5158237814903259},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5075289011001587},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48699861764907837},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4728938639163971},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46337762475013733},{"id":"https://openalex.org/keywords/plug-in","display_name":"Plug-in","score":0.456863135099411},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.4426475763320923},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.27004632353782654}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8182910680770874},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.533926248550415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5158237814903259},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5075289011001587},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48699861764907837},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4728938639163971},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46337762475013733},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.456863135099411},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4426475763320923},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27004632353782654},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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:10.1145/3581783.3611889","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611889","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611889","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3611889","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3611889","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3611889","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3529638414","display_name":"Systematics and  Zoogeography of Chelodesmoid Diplopoda","funder_award_id":"6217613","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4700434351","display_name":null,"funder_award_id":"2019GQG0002","funder_id":"https://openalex.org/F4320322392","funder_display_name":"Tsinghua University"},{"id":"https://openalex.org/G5541826327","display_name":null,"funder_award_id":"62176134","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387968447.pdf","grobid_xml":"https://content.openalex.org/works/W4387968447.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2104125540","https://openalex.org/W2118246710","https://openalex.org/W2277195237","https://openalex.org/W2549139847","https://openalex.org/W2591644541","https://openalex.org/W2810482788","https://openalex.org/W2962785943","https://openalex.org/W2962858109","https://openalex.org/W2963514444","https://openalex.org/W2963649796","https://openalex.org/W2963938081","https://openalex.org/W2981860940","https://openalex.org/W2992478697","https://openalex.org/W2997514790","https://openalex.org/W3034538190","https://openalex.org/W3035017890","https://openalex.org/W3035241330","https://openalex.org/W3041297595","https://openalex.org/W3092668800","https://openalex.org/W3099715001","https://openalex.org/W3105916048","https://openalex.org/W3124408609","https://openalex.org/W3173181410","https://openalex.org/W3181556077","https://openalex.org/W3183295755","https://openalex.org/W3205051885","https://openalex.org/W3205398323","https://openalex.org/W3205822151","https://openalex.org/W3206617243","https://openalex.org/W3209102402","https://openalex.org/W3215287157","https://openalex.org/W4200498145","https://openalex.org/W4225868495","https://openalex.org/W4226396876","https://openalex.org/W4288083516","https://openalex.org/W4304080485","https://openalex.org/W4304080820","https://openalex.org/W4304092470","https://openalex.org/W4309804076","https://openalex.org/W4312275869","https://openalex.org/W4312590184","https://openalex.org/W4378805076","https://openalex.org/W4386066401","https://openalex.org/W4386071640","https://openalex.org/W4386071767","https://openalex.org/W4386072171","https://openalex.org/W4386075638","https://openalex.org/W4386075801","https://openalex.org/W4386075828","https://openalex.org/W4386075932","https://openalex.org/W4386075933","https://openalex.org/W4386076265"],"related_works":["https://openalex.org/W47352601","https://openalex.org/W2981957539","https://openalex.org/W4287378204","https://openalex.org/W2545422590","https://openalex.org/W4240705470","https://openalex.org/W2945311252","https://openalex.org/W631546281","https://openalex.org/W4206501676","https://openalex.org/W88292646","https://openalex.org/W2266220644"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,25,86,181],"Scene":[3],"Graph":[4],"Generation":[5],"(SGG)":[6],"typically":[7],"model":[8,79],"the":[9,28,43,46,53,72,83,107,117,149,167,175,202],"relationships":[10],"among":[11,116],"entities":[12,124],"utilizing":[13],"box-level":[14,154,179,215],"features":[15],"from":[16],"pre-defined":[17],"detectors.":[18],"We":[19,110],"argue":[20],"that":[21,142],"an":[22,126,189],"overlooked":[23],"problem":[24],"SGG":[26],"is":[27],"coarse-grained":[29,69],"interactions":[30,70,81,115,122],"between":[31,123],"boxes,":[32],"which":[33,208],"inadequately":[34],"capture":[35],"contextual":[36],"semantics":[37],"for":[38,201],"relationship":[39],"modeling,":[40],"practically":[41],"limiting":[42],"development":[44],"of":[45,97,106,177,192,199],"field.":[47],"In":[48,185],"this":[49],"paper,":[50],"we":[51,90],"take":[52],"initiative":[54],"to":[55,67,78,119,173,197],"explore":[56,111],"and":[57,99,113,137,156],"propose":[58],"a":[59,92,95,182],"generic":[60],"paradigm":[61],"termed":[62],"Superpixel-based":[63],"Interaction":[64],"Learning":[65],"(SIL)":[66],"remedy":[68],"at":[71,82,125,148],"box":[73],"level.":[74],"It":[75],"allows":[76],"us":[77],"fine-grained":[80,121,146],"superpixel":[84,150],"level":[85,151],"SGG.":[87],"Specifically,":[88],"(i)":[89],"treat":[91],"scene":[93],"as":[94],"set":[96],"points":[98],"cluster":[100],"them":[101],"into":[102,212],"superpixels":[103,118],"representing":[104],"sub-regions":[105],"scene.":[108],"(ii)":[109],"intra-entity":[112],"cross-entity":[114],"enrich":[120],"earlier":[127],"stage.":[128],"Extensive":[129],"experiments":[130],"on":[131,205],"two":[132],"challenging":[133],"benchmarks":[134],"(Visual":[135],"Genome":[136],"Open":[138],"Image":[139],"V6)":[140],"prove":[141],"our":[143],"SIL":[144,187],"enables":[145],"interaction":[147],"above":[152],"previous":[153,159],"methods,":[155],"significantly":[157],"outperforms":[158],"state-of-the-art":[160],"methods":[161],"across":[162],"all":[163],"metrics.":[164],"More":[165],"encouragingly,":[166],"proposed":[168],"method":[169],"can":[170],"be":[171],"applied":[172],"boost":[174],"performance":[176],"existing":[178,214],"approaches":[180],"plug-and-play":[183],"fashion.":[184],"particular,":[186],"brings":[188],"average":[190],"improvement":[191],"2.0%":[193],"mR":[194],"(even":[195],"up":[196],"3.4%)":[198],"baselines":[200],"PredCls":[203],"task":[204],"Visual":[206],"Genome,":[207],"facilitates":[209],"its":[210],"integration":[211],"any":[213],"method.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}