{"id":"https://openalex.org/W4414920990","doi":"https://doi.org/10.1109/iccv51701.2025.01515","title":"ART: Adaptive Relation Tuning for Generalized Relation Prediction","display_name":"ART: Adaptive Relation Tuning for Generalized Relation Prediction","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414920990","doi":"https://doi.org/10.1109/iccv51701.2025.01515"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.23543","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011721474","display_name":"Gopika Sudhakaran","orcid":"https://orcid.org/0009-0007-3721-5602"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Gopika Sudhakaran","raw_affiliation_strings":["TU,Department of Computer Science,Darmstadt,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU,Department of Computer Science,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063339544","display_name":"Hikaru Shindo","orcid":"https://orcid.org/0000-0001-7129-6118"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hikaru Shindo","raw_affiliation_strings":["TU,Department of Computer Science,Darmstadt,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU,Department of Computer Science,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017166414","display_name":"Patrick Schramowski","orcid":"https://orcid.org/0000-0003-1231-7120"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Patrick Schramowski","raw_affiliation_strings":["TU,Department of Computer Science,Darmstadt,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU,Department of Computer Science,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079476861","display_name":"Simone Schaub-Meyer","orcid":"https://orcid.org/0000-0001-8644-1074"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simone Schaub-Meyer","raw_affiliation_strings":["TU,Department of Computer Science,Darmstadt,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU,Department of Computer Science,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037636074","display_name":"Kristian Kersting","orcid":"https://orcid.org/0000-0002-2873-9152"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kristian Kersting","raw_affiliation_strings":["TU,Department of Computer Science,Darmstadt,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU,Department of Computer Science,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039746777","display_name":"S. Roth","orcid":"https://orcid.org/0000-0003-3616-2223"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technische Universit\u00e4t Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Roth","raw_affiliation_strings":["TU,Department of Computer Science,Darmstadt,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU,Department of Computer Science,Darmstadt,Germany","institution_ids":["https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5011721474"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13641451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16323","last_page":"16332"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9527999758720398,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9527999758720398,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9391999840736389,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9283000230789185,"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/relation","display_name":"Relation (database)","score":0.8219000101089478},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.555899977684021},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45579999685287476},{"id":"https://openalex.org/keywords/predicate","display_name":"Predicate (mathematical logic)","score":0.41449999809265137},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.36500000953674316},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.30820000171661377}],"concepts":[{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.8219000101089478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769999861717224},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.555899977684021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5476999878883362},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C140146324","wikidata":"https://www.wikidata.org/wiki/Q1144319","display_name":"Predicate (mathematical logic)","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.30820000171661377},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C65180967","wikidata":"https://www.wikidata.org/wiki/Q130901","display_name":"Binary relation","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01515","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01515","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.23543","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.23543","pdf_url":"https://arxiv.org/pdf/2507.23543","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},{"id":"doi:10.48550/arxiv.2507.23543","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.23543","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.23543","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.23543","pdf_url":"https://arxiv.org/pdf/2507.23543","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"relation":[1,21,129,170],"detection":[2,22],"(VRD)":[3],"is":[4],"the":[5,9,28,114,128,137,140,186],"task":[6],"of":[7,156],"identifying":[8],"relationships":[10],"between":[11,142],"objects":[12],"in":[13,175],"a":[14,65,147,172],"scene.":[15],"VRD":[16,89,99,177],"models":[17,44],"trained":[18],"solely":[19],"on":[20,30,72,118,127,146],"data":[23],"struggle":[24],"to":[25,41,116],"generalize":[26],"beyond":[27],"relations":[29,120,188],"which":[31],"they":[32],"are":[33,134],"trained.":[34],"While":[35],"prompt":[36],"tuning":[37,63,92,104],"has":[38],"been":[39],"used":[40],"adapt":[42],"vision-language":[43],"(VLMs)":[45],"for":[46,88,189],"VRD,":[47],"it":[48],"uses":[49],"handcrafted":[50],"prompts":[51],"and":[52,93,106,136,150,166],"struggles":[53],"with":[54],"novel":[55],"or":[56],"complex":[57,191],"relations.":[58],"We":[59,76,144,179],"argue":[60],"that":[61,85],"instruction":[62,91,103],"offers":[64],"more":[66],"effective":[67],"solution":[68],"by":[69,184],"fine-tuning":[70],"VLMs":[71,87],"diverse":[73],"instructional":[74],"data.":[75],"thus":[77],"introduce":[78],"ART,":[79],"an":[80,102,108],"Adaptive":[81],"Relation":[82],"Tuning":[83],"framework":[84],"adapts":[86],"through":[90],"strategic":[94],"instance":[95],"selection.":[96],"By":[97],"converting":[98],"datasets":[100,155],"into":[101],"format":[105],"employing":[107],"adaptive":[109],"sampling":[110],"algorithm,":[111],"ART":[112],"directs":[113],"VLM":[115],"focus":[117,126],"informative":[119],"while":[121],"maintaining":[122],"generalizability.":[123],"Specifically,":[124],"we":[125],"classification,":[130],"where":[131],"subject-object":[132],"boxes":[133],"given":[135],"model":[138],"predicts":[139],"predicate":[141],"them.":[143],"tune":[145],"held-in":[148],"set":[149],"evaluate":[151],"across":[152],"multiple":[153],"held-out":[154],"varying":[157],"complexity.":[158],"Our":[159],"approach":[160],"strongly":[161],"improves":[162],"over":[163],"its":[164],"baselines":[165],"can":[167],"infer":[168],"unseen":[169],"concepts,":[171],"capability":[173],"absent":[174],"mainstream":[176],"methods.":[178],"demonstrate":[180],"ART's":[181],"practical":[182],"value":[183],"using":[185],"predicted":[187],"segmenting":[190],"scenes.":[192]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-10T00:00:00"}