{"id":"https://openalex.org/W7164513596","doi":"https://doi.org/10.1007/s11760-026-05439-7","title":"ZeroRel: Multimodal Transformer-Guided Zero-Shot Relationship Retrieval for Generalized Scene Graph Generation","display_name":"ZeroRel: Multimodal Transformer-Guided Zero-Shot Relationship Retrieval for Generalized Scene Graph Generation","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7164513596","doi":"https://doi.org/10.1007/s11760-026-05439-7"},"language":"en","primary_location":{"id":"doi:10.1007/s11760-026-05439-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11760-026-05439-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11760-026-05439-7.pdf","source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11760-026-05439-7.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102945426","display_name":"Muhammad Junaid Khan","orcid":"https://orcid.org/0000-0002-5912-0504"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Junaid Khan","raw_affiliation_strings":["Department of Electrical Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108583808","display_name":"Adil Masood Siddiqui","orcid":null},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Adil Masood Siddiqui","raw_affiliation_strings":["Department of Electrical Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007208401","display_name":"Maryam Rasool","orcid":"https://orcid.org/0000-0002-7939-0421"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Maryam Rasool","raw_affiliation_strings":["Department of Electrical Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101424805","display_name":"Hussain Ali","orcid":"https://orcid.org/0000-0002-5234-8469"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Hussain Ali","raw_affiliation_strings":["Department of Electrical Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045807996","display_name":"Umar Ghafoor","orcid":"https://orcid.org/0000-0002-1661-4061"},"institutions":[{"id":"https://openalex.org/I929597975","display_name":"National University of Sciences and Technology","ror":"https://ror.org/03w2j5y17","country_code":"PK","type":"education","lineage":["https://openalex.org/I929597975"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Umar Ghafoor","raw_affiliation_strings":["Department of Electrical Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad, Pakistan","institution_ids":["https://openalex.org/I929597975"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123219571","display_name":"Jaleed Khan","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]},{"id":"https://openalex.org/I4210146410","display_name":"Science Oxford","ror":"https://ror.org/04j8yhy50","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I4210146410"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jaleed Khan","raw_affiliation_strings":["Medical Sciences Division, University of Oxford, Oxfordshire, OX3 9DU, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medical Sciences Division, University of Oxford, Oxfordshire, OX3 9DU, United Kingdom","institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5123219571"],"corresponding_institution_ids":["https://openalex.org/I40120149","https://openalex.org/I4210146410"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75629578,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"20","issue":"7","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9799000024795532,"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":0.9799000024795532,"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":0.004600000102072954,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.004600000102072954,"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/embedding","display_name":"Embedding","score":0.6740999817848206},{"id":"https://openalex.org/keywords/scene-graph","display_name":"Scene graph","score":0.6301000118255615},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6146000027656555},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.5702999830245972},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5376999974250793},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5340999960899353},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5271000266075134},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.42989999055862427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247999906539917},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6740999817848206},{"id":"https://openalex.org/C179372163","wikidata":"https://www.wikidata.org/wiki/Q1406181","display_name":"Scene graph","level":3,"score":0.6301000118255615},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6146000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5895000100135803},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.5702999830245972},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5376999974250793},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5340999960899353},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.42989999055862427},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40369999408721924},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3449000120162964},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C75564084","wikidata":"https://www.wikidata.org/wiki/Q5597085","display_name":"Graph embedding","level":3,"score":0.31139999628067017},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.30869999527931213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29019999504089355},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2824000120162964},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.26669999957084656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11760-026-05439-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11760-026-05439-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11760-026-05439-7.pdf","source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11760-026-05439-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11760-026-05439-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11760-026-05439-7.pdf","source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.44385668635368347,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7164513596.pdf","grobid_xml":"https://content.openalex.org/works/W7164513596.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2277195237","https://openalex.org/W2561529111","https://openalex.org/W2565639579","https://openalex.org/W2950096400","https://openalex.org/W2962785943","https://openalex.org/W2963518342","https://openalex.org/W2963536419","https://openalex.org/W2963938081","https://openalex.org/W3034679267","https://openalex.org/W3035017890","https://openalex.org/W3107848485","https://openalex.org/W3108864070","https://openalex.org/W3109507892","https://openalex.org/W3165066581","https://openalex.org/W3176825161","https://openalex.org/W3202514640","https://openalex.org/W3203581965","https://openalex.org/W4200498145","https://openalex.org/W4220974559","https://openalex.org/W4285208802","https://openalex.org/W4288045581","https://openalex.org/W4293733630","https://openalex.org/W4312862807","https://openalex.org/W4390190073","https://openalex.org/W4392230073","https://openalex.org/W4396889120","https://openalex.org/W4402715983","https://openalex.org/W4402727824","https://openalex.org/W4402754270","https://openalex.org/W4403791539","https://openalex.org/W4404792503","https://openalex.org/W4407825796","https://openalex.org/W4409263066","https://openalex.org/W4411651461","https://openalex.org/W4412944868","https://openalex.org/W4413157161","https://openalex.org/W4415795196"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Scene":[1],"Graph":[2,213],"Generation":[3],"(SGG)":[4],"aims":[5],"to":[6,39,191],"represent":[7],"an":[8],"image\u2019s":[9],"objects":[10,70],"and":[11,32,71,77,104,120,130,139,144,180,203,238],"their":[12],"pairwise":[13],"relationships":[14,113,240],"in":[15,36,169],"a":[16,46,90,99,106,208],"structured":[17,231],"graph":[18,108],"for":[19,49],"downstream":[20],"visual":[21,60,227],"reasoning.":[22],"However,":[23],"conventional":[24],"SGG":[25],"models":[26,205],"struggle":[27],"with":[28,62,98,215,230],"long-tail":[29],"predicate":[30,101],"distributions":[31],"closed-world":[33],"vocabularies,":[34],"resulting":[35],"poor":[37],"generalization":[38],"rare":[40,185,237],"or":[41],"unseen":[42,239],"relationships.":[43],"We":[44],"propose":[45],"neurosymbolic":[47],"framework":[48],"zero-shot":[50,143,150,167],"relationship":[51],"retrieval":[52,93,110,229,233],"that":[53,94,111,207,225],"addresses":[54],"these":[55,124],"challenges":[56],"by":[57],"integrating":[58],"deep":[59],"features":[61],"external":[63],"commonsense":[64,116],"knowledge.":[65],"Our":[66],"model":[67,188],"first":[68],"detects":[69],"refines":[72],"them":[73],"via":[74],"positional":[75],"overlap":[76],"semantic":[78],"similarity.":[79],"It":[80],"then":[81],"retrieves":[82],"candidate":[83],"predicates":[84],"through":[85],"two":[86],"complementary":[87],"channels:":[88],"(1)":[89],"visual-textual":[91],"prototype":[92,228],"aligns":[95],"subject-object":[96],"representations":[97],"broad":[100],"embedding":[102,204],"space,":[103],"(2)":[105],"knowledge":[107,201,232],"constrained":[109],"ranks":[112],"using":[114],"heterogeneous":[115,209],"graphs.":[117],"A":[118],"calibration":[119],"late-fusion":[121],"module":[122],"combines":[123],"channels,":[125],"balancing":[126],"confidence":[127],"between":[128],"head":[129],"tail":[131],"classes.":[132],"Evaluations":[133],"on":[134,163,184,200,245],"the":[135,153,164,219],"Visual":[136],"Genome":[137],"(VG)":[138],"GQA":[140,192],"benchmarks":[141],"under":[142],"open-vocabulary":[145],"settings":[146],"show":[147,206],"strong":[148],"strict":[149],"performance.":[151,221],"On":[152],"reported":[154],"VG":[155],"split,":[156],"ZeroRel":[157],"reaches":[158],"zR@100":[159],"=":[160],"37.1%,":[161],"improving":[162],"strongest":[165],"prior":[166],"baseline":[168],"our":[170],"comparison":[171],"table":[172],"(KnowZRel,":[173],"35.7%)":[174],"while":[175],"maintaining":[176],"competitive":[177],"overall":[178],"recall":[179,183],"improved":[181],"mean":[182],"predicates.":[186,247],"The":[187],"also":[189],"generalizes":[190],"without":[193,241],"retraining,":[194],"demonstrating":[195],"robust":[196],"cross-dataset":[197],"transfer.":[198],"Ablations":[199],"sources":[202],"Common":[210],"Sense":[211],"Knowledge":[212],"(CSKG)":[214],"ComplEx":[216],"embeddings":[217],"yields":[218],"best":[220],"These":[222],"results":[223],"indicate":[224],"combining":[226],"improves":[234],"coverage":[235],"of":[236],"sacrificing":[242],"scene-graph":[243],"quality":[244],"frequent":[246]},"counts_by_year":[],"updated_date":"2026-06-14T06:11:07.267592","created_date":"2026-06-13T00:00:00"}