{"id":"https://openalex.org/W3200873909","doi":"https://doi.org/10.1609/aaai.v36i10.21285","title":"Cross-Modal Coherence for Text-to-Image Retrieval","display_name":"Cross-Modal Coherence for Text-to-Image Retrieval","publication_year":2022,"publication_date":"2022-06-28","ids":{"openalex":"https://openalex.org/W3200873909","doi":"https://doi.org/10.1609/aaai.v36i10.21285","mag":"3200873909"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i10.21285","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/21285/21034","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/21285/21034","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025559955","display_name":"Malihe Alikhani","orcid":"https://orcid.org/0000-0002-1315-2228"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Malihe Alikhani","raw_affiliation_strings":["University of Pittsburgh"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015319661","display_name":"Fangda Han","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Fangda Han","raw_affiliation_strings":["Rutgers University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038035093","display_name":"Hareesh Ravi","orcid":"https://orcid.org/0000-0002-3237-1899"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Hareesh Ravi","raw_affiliation_strings":["Rutgers University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069589954","display_name":"Mubbasir Kapadia","orcid":"https://orcid.org/0000-0002-3501-0028"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mubbasir Kapadia","raw_affiliation_strings":["Rutgers University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020368096","display_name":"Vladimir Pavlovi\u0107","orcid":"https://orcid.org/0000-0003-3979-1236"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Vladimir Pavlovic","raw_affiliation_strings":["Rutgers University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086088412","display_name":"Matthew Stone","orcid":"https://orcid.org/0000-0003-3629-2941"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Matthew Stone","raw_affiliation_strings":["Rutgers University"],"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.513,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.681005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":83,"max":85},"biblio":{"volume":"36","issue":"10","first_page":"10427","last_page":"10435"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9999,"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":0.9999,"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":0.9983,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9967,"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/margin","display_name":"Margin (machine learning)","score":0.5002401},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.42187953}],"concepts":[{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.8338161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7571202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.57592696},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5474988},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.50363463},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.5002401},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43794957},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.42187953},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37274197},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35572025},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32144463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20755002},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11036575},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i10.21285","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/21285/21034","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2109.11047","pdf_url":"https://arxiv.org/pdf/2109.11047","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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v36i10.21285","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/21285/21034","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":34,"referenced_works":["https://openalex.org/W1514535095","https://openalex.org/W1574440611","https://openalex.org/W1605174196","https://openalex.org/W168564468","https://openalex.org/W1861492603","https://openalex.org/W1985944917","https://openalex.org/W1995258346","https://openalex.org/W2100751297","https://openalex.org/W2123024445","https://openalex.org/W2143432970","https://openalex.org/W2150421899","https://openalex.org/W2194775991","https://openalex.org/W2598634450","https://openalex.org/W2737041163","https://openalex.org/W2799185021","https://openalex.org/W2886641317","https://openalex.org/W2890399523","https://openalex.org/W2897152025","https://openalex.org/W2942348619","https://openalex.org/W2963403868","https://openalex.org/W2964121744","https://openalex.org/W2966715458","https://openalex.org/W2970608575","https://openalex.org/W2970971581","https://openalex.org/W2982260276","https://openalex.org/W3009381623","https://openalex.org/W3035532688","https://openalex.org/W3082436432","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3203309275","https://openalex.org/W4241595053","https://openalex.org/W4288373474","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2993674027","https://openalex.org/W2775347418","https://openalex.org/W2772917594","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W2161229648","https://openalex.org/W2130228941","https://openalex.org/W2036807459","https://openalex.org/W1969923398","https://openalex.org/W1891287906"],"abstract_inverted_index":{"Common":[0],"image-text":[1],"joint":[2,43],"understanding":[3,44],"techniques":[4],"presume":[5],"that":[6,62,88,113],"images":[7,23,71,89],"and":[8,24,33,117,129],"the":[9,39,92,111,118],"associated":[10],"text":[11,25,76,128],"can":[12,26,69],"universally":[13],"be":[14,27],"characterized":[15],"by":[16,91,102],"a":[17,51,99,103],"single":[18],"implicit":[19],"model.":[20],"However,":[21],"co-occurring":[22],"related":[28],"in":[29,123,127],"qualitatively":[30],"different":[31,114],"ways,":[32],"explicitly":[34],"modeling":[35],"it":[36],"could":[37],"improve":[38],"performance":[40],"of":[41,120],"current":[42],"models.":[45,81],"In":[46],"this":[47],"paper,":[48],"we":[49],"train":[50],"Cross-Modal":[52],"Coherence":[53],"Model":[54],"for":[55],"text-to-image":[56],"retrieval":[57],"task.":[58],"Our":[59,106],"analysis":[60],"shows":[61],"models":[63],"trained":[64],"with":[65,74],"image\u2013text":[66],"coherence":[67,121],"relations":[68,122],"retrieve":[70],"originally":[72],"paired":[73],"target":[75],"more":[77],"often":[78],"than":[79],"coherence-agnostic":[80,100],"We":[82],"also":[83],"show":[84],"via":[85],"human":[86],"evaluation":[87],"retrieved":[90],"proposed":[93],"coherence-aware":[94],"model":[95],"are":[96],"preferred":[97],"over":[98],"baseline":[101],"huge":[104],"margin.":[105],"findings":[107],"provide":[108],"insights":[109],"into":[110],"ways":[112],"modalities":[115],"communicate":[116],"role":[119],"capturing":[124],"commonsense":[125],"inferences":[126],"imagery.":[130]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3200873909","counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2024-12-08T17:07:55.812257","created_date":"2021-09-27"}