{"id":"https://openalex.org/W4386566430","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.196","title":"CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension","display_name":"CK-Transformer: Commonsense Knowledge Enhanced Transformers for Referring Expression Comprehension","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4386566430","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.196"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-eacl.196","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.196","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-eacl.196","pdf_url":"https://aclanthology.org/2023.findings-eacl.196.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.findings-eacl.196.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100410697","display_name":"Zhi Zhang","orcid":"https://orcid.org/0000-0002-7742-2135","observed_orcids":["https://orcid.org/0000-0002-7742-2135"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Zhi Zhang","raw_affiliation_strings":["ILLC, University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ILLC, University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083950817","display_name":"Helen Yannakoudakis","orcid":"https://orcid.org/0000-0002-4429-7729","observed_orcids":["https://orcid.org/0000-0002-4429-7729"]},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Helen Yannakoudakis","raw_affiliation_strings":["Dept. of Informatics, King's College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Informatics, King's College London","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026486701","display_name":"Xiantong Zhen","orcid":"https://orcid.org/0000-0001-5213-0462","observed_orcids":["https://orcid.org/0000-0001-5213-0462"]},"institutions":[{"id":"https://openalex.org/I4210135459","display_name":"United Imaging Healthcare (China)","ror":"https://ror.org/03qqw3m37","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210135459"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiantong Zhen","raw_affiliation_strings":["United Imaging"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"United Imaging","institution_ids":["https://openalex.org/I4210135459"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016184654","display_name":"Ekaterina Shutova","orcid":"https://orcid.org/0009-0003-6664-4474","observed_orcids":["https://orcid.org/0009-0003-6664-4474"]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ekaterina Shutova","raw_affiliation_strings":["ILLC, University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ILLC, University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2638,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.5794836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2586","last_page":"2596"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":9.999999747378752e-05,"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/referring-expression-comprehension","display_name":"referring expression comprehension","score":0.9800000190734863},{"id":"https://openalex.org/keywords/commonsense-knowledge","display_name":"commonsense knowledge","score":0.972000002861023},{"id":"https://openalex.org/keywords/multimodal-reasoning","display_name":"multimodal reasoning","score":0.5519999861717224},{"id":"https://openalex.org/keywords/image-localization","display_name":"image localization","score":0.4970000088214874},{"id":"https://openalex.org/keywords/object-representation","display_name":"object representation","score":0.6290000081062317},{"id":"https://openalex.org/keywords/natural-language-description-of-images","display_name":"natural language description of images","score":0.4749999940395355}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.79156094789505},{"id":"https://openalex.org/C30542707","wikidata":"https://www.wikidata.org/wiki/Q1603203","display_name":"Commonsense knowledge","level":3,"score":0.7854151725769043},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.7751432061195374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096139192581177},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.6921760439872742},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415838360786438},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5236886739730835},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.4142783284187317},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.1819702386856079},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12010085582733154},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09422221779823303},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06723865866661072},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2023.findings-eacl.196","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.196","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-eacl.196","pdf_url":"https://aclanthology.org/2023.findings-eacl.196.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:dare.uva.nl:openaire/b8b43607-b6d9-485f-96b8-9d9417775ec5","doi":null,"is_oa":true,"landing_page_url":"https://handle.uba.uva.nl/personal/pure/en/publications/cktransformer-commonsense-knowledge-enhanced-transformers-for-referring-expression-comprehension(b8b43607-b6d9-485f-96b8-9d9417775ec5).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400088","display_name":"UvA-DARE (University of Amsterdam)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I887064364","host_organization_name":"University of Amsterdam","host_organization_lineage":["https://openalex.org/I887064364"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:arXiv.org:2302.09027","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.09027","pdf_url":"https://arxiv.org/pdf/2302.09027","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2302.09027","doi":"https://doi.org/10.48550/arxiv.2302.09027","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2302.09027","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-eacl.196","doi":"https://doi.org/10.18653/v1/2023.findings-eacl.196","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2023.findings-eacl.196","pdf_url":"https://aclanthology.org/2023.findings-eacl.196.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EACL 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386566430.pdf","grobid_xml":"https://content.openalex.org/works/W4386566430.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W2109586012","https://openalex.org/W2153579005","https://openalex.org/W2251512949","https://openalex.org/W2277195237","https://openalex.org/W2489434015","https://openalex.org/W2525778437","https://openalex.org/W2558535589","https://openalex.org/W2561529111","https://openalex.org/W2561715562","https://openalex.org/W2571175805","https://openalex.org/W2740432174","https://openalex.org/W2745461083","https://openalex.org/W2886641317","https://openalex.org/W2896457183","https://openalex.org/W2904910963","https://openalex.org/W2908510526","https://openalex.org/W2955014993","https://openalex.org/W2962764817","https://openalex.org/W2963109634","https://openalex.org/W2963735856","https://openalex.org/W2964345792","https://openalex.org/W2968124245","https://openalex.org/W2969862959","https://openalex.org/W2969876226","https://openalex.org/W2970231061","https://openalex.org/W3090449556","https://openalex.org/W3093355642","https://openalex.org/W3197394194"],"related_works":["https://openalex.org/W3093355642","https://openalex.org/W4317495590","https://openalex.org/W4385893917","https://openalex.org/W3112077297","https://openalex.org/W4405175881","https://openalex.org/W2964345792","https://openalex.org/W4285594363","https://openalex.org/W7164939447","https://openalex.org/W2583360688","https://openalex.org/W4294069567"],"abstract_inverted_index":{"The":[0],"task":[1,43,96],"of":[2,72,79,97,109,116,123],"multimodal":[3],"referring":[4,35],"expression":[5,36],"comprehension":[6,37],"(REC),":[7],"aiming":[8],"at":[9],"localizing":[10],"an":[11,75,113],"image":[12],"region":[13],"described":[14],"by":[15,85],"a":[16,42,55,106],"natural":[17],"language":[18],"expression,":[19],"has":[20],"recently":[21],"received":[22],"increasing":[23],"attention":[24],"within":[25],"the":[26,70,80,86,95,102,110,120,124],"research":[27],"comminity.In":[28],"this":[29],"paper,":[30],"we":[31],"specifically":[32],"focus":[33],"on":[34,91],"with":[38,112],"commonsense":[39,67],"knowledge":[40,68],"(KB-Ref),":[41],"which":[44,64],"typically":[45],"requires":[46],"reasoning":[47],"beyond":[48],"spatial,":[49],"visual":[50],"or":[51],"semantic":[52],"information.We":[53],"propose":[54],"novel":[56],"framework":[57],"for":[58,94],"Commonsense":[59],"Knowledge":[60],"Enhanced":[61],"Transformers":[62],"(CK-Transformer)":[63],"effectively":[65],"integrates":[66],"into":[69],"representations":[71],"objects":[73,82],"in":[74],"image,":[76],"facilitating":[77],"identification":[78],"target":[81],"referred":[83],"to":[84],"expressions.We":[87],"conduct":[88],"extensive":[89],"experiments":[90],"several":[92],"benchmarks":[93],"KB-Ref.Our":[98],"results":[99],"show":[100],"that":[101],"proposed":[103],"CK-Transformer":[104],"achieves":[105],"new":[107],"state":[108,122],"art,":[111],"absolute":[114],"improvement":[115],"3.14%":[117],"accuracy":[118],"over":[119],"existing":[121],"art":[125],"1":[126],".":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-09-10T00:00:00"}