{"id":"https://openalex.org/W2950162424","doi":"https://doi.org/10.1145/3323873.3325043","title":"Improving What Cross-Modal Retrieval Models Learn through Object-Oriented Inter- and Intra-Modal Attention Networks","display_name":"Improving What Cross-Modal Retrieval Models Learn through Object-Oriented Inter- and Intra-Modal Attention Networks","publication_year":2019,"publication_date":"2019-06-05","ids":{"openalex":"https://openalex.org/W2950162424","doi":"https://doi.org/10.1145/3323873.3325043","mag":"2950162424"},"language":"en","primary_location":{"id":"doi:10.1145/3323873.3325043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3323873.3325043","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3323873.3325043","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 on International Conference on Multimedia Retrieval","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/10.1145/3323873.3325043","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063149046","display_name":"Po-Yao Huang","orcid":"https://orcid.org/0000-0002-3319-5145"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Po-Yao Huang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060908309","display_name":"Vaibhav","orcid":"https://orcid.org/0009-0000-0815-6972"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaibhav","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107836252","display_name":"Alexander G. Hauptmann","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander G. Hauptmann","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063149046"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":1.6355,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.87242429,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"244","last_page":"252"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"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":0.9944999814033508,"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/computer-science","display_name":"Computer science","score":0.8372548818588257},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7872612476348877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6006761789321899},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.586772620677948},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.583435595035553},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5178528428077698},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4680580496788025},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4245792627334595},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.308025985956192}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8372548818588257},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7872612476348877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6006761789321899},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.586772620677948},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.583435595035553},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5178528428077698},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4680580496788025},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4245792627334595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.308025985956192},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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":[{"id":"doi:10.1145/3323873.3325043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3323873.3325043","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3323873.3325043","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:figshare.com:article/27592338","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Improving_What_Cross-Modal_Retrieval_Models_Learn_through_Object-Oriented_Inter-_and_Intra-Modal_Attention_Networks/27592338","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3323873.3325043","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3323873.3325043","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3323873.3325043","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 on International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4723519231","display_name":null,"funder_award_id":"60NANB17D156","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"},{"id":"https://openalex.org/G740863221","display_name":null,"funder_award_id":"FA8750-18-2-0018","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320306111","display_name":"U.S. Department of Commerce","ror":"https://ror.org/04chq2495"},{"id":"https://openalex.org/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"},{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"},{"id":"https://openalex.org/F4320333452","display_name":"Interior Business Center","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2950162424.pdf","grobid_xml":"https://content.openalex.org/works/W2950162424.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W68733909","https://openalex.org/W1527575280","https://openalex.org/W1533861849","https://openalex.org/W1686810756","https://openalex.org/W1832693441","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W1916445035","https://openalex.org/W1949478088","https://openalex.org/W1957706851","https://openalex.org/W2053946370","https://openalex.org/W2064675550","https://openalex.org/W2112912048","https://openalex.org/W2133564696","https://openalex.org/W2147238549","https://openalex.org/W2153579005","https://openalex.org/W2157331557","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2296283641","https://openalex.org/W2546696630","https://openalex.org/W2552579943","https://openalex.org/W2606473278","https://openalex.org/W2618530766","https://openalex.org/W2626778328","https://openalex.org/W2745461083","https://openalex.org/W2768454054","https://openalex.org/W2778940641","https://openalex.org/W2803125506","https://openalex.org/W2808084195","https://openalex.org/W2953106684","https://openalex.org/W2962964995","https://openalex.org/W2963040148","https://openalex.org/W2963389687","https://openalex.org/W2963467339","https://openalex.org/W2963499204","https://openalex.org/W2963969878","https://openalex.org/W2964236337","https://openalex.org/W3000226596","https://openalex.org/W6600225990"],"related_works":["https://openalex.org/W3125011624","https://openalex.org/W1508631387","https://openalex.org/W2081900870","https://openalex.org/W2370917603","https://openalex.org/W2017776670","https://openalex.org/W2952760143","https://openalex.org/W2347897961","https://openalex.org/W2979236518","https://openalex.org/W2358318464","https://openalex.org/W2340870721"],"abstract_inverted_index":{"Although":[0],"significant":[1],"progress":[2],"has":[3],"been":[4],"made":[5],"for":[6,60,110],"cross-modal":[7,61,81,111],"retrieval":[8,35,68,159],"models":[9,18,36],"in":[10,53,156],"recent":[11],"years,":[12],"few":[13],"have":[14],"explored":[15],"what":[16,22],"those":[17],"truly":[19],"learn":[20],"and":[21,43,50,74,79,102,150,165],"makes":[23],"one":[24],"model":[25,94],"superior":[26],"to":[27,106,129],"another.":[28],"Start":[29],"by":[30,87,145],"training":[31],"two":[32],"state-of-the-art":[33],"text-to-image":[34,158],"with":[37,100,153],"adversarial":[38],"text":[39],"inputs,":[40],"we":[41,90,115],"investigate":[42],"quantify":[44],"the":[45,55,67,76,83,137,141,157,162,166],"importance":[46],"of":[47],"syntactic":[48],"structure":[49],"lexical":[51],"information":[52],"learning":[54],"joint":[56],"visual-semantic":[57],"embedding":[58],"space":[59],"retrieval.":[62,112],"The":[63],"results":[64],"show":[65,135],"that":[66,136],"power":[69],"mainly":[70],"comes":[71],"from":[72],"localizing":[73],"connecting":[75],"visual":[77],"objects":[78],"their":[80],"counter-parts,":[82],"textual":[84],"phrases.":[85],"Inspired":[86],"this":[88],"observation,":[89],"propose":[91],"a":[92,117,146],"novel":[93],"which":[95,122],"employs":[96],"object-oriented":[97],"encoders":[98],"along":[99],"inter-":[101],"intra-modal":[103,125,131],"attention":[104],"networks":[105],"improve":[107],"inter-modal":[108],"dependencies":[109],"In":[113],"addition,":[114],"develop":[116],"new":[118],"multimodal":[119],"structure-preserving":[120],"objective":[121],"additionally":[123],"emphasizes":[124],"hard":[126],"negative":[127],"examples":[128],"promote":[130],"discrepancies.":[132],"Extensive":[133],"experiments":[134],"proposed":[138],"approach":[139],"outperforms":[140],"existing":[142],"best":[143],"method":[144],"large":[147],"margin":[148],"(16.4%":[149],"6.7%":[151],"relatively":[152],"[email":[154],"protected]":[155],"task":[160],"on":[161],"Flickr30K":[163],"dataset":[164,168],"MS-COCO":[167],"respectively).":[169]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}