{"id":"https://openalex.org/W4352981326","doi":"https://doi.org/10.1109/iscmi56532.2022.10068471","title":"Hybrid Joint Embedding with Intra-Modality Loss for Image-Text Matching","display_name":"Hybrid Joint Embedding with Intra-Modality Loss for Image-Text Matching","publication_year":2022,"publication_date":"2022-11-26","ids":{"openalex":"https://openalex.org/W4352981326","doi":"https://doi.org/10.1109/iscmi56532.2022.10068471"},"language":"en","primary_location":{"id":"doi:10.1109/iscmi56532.2022.10068471","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscmi56532.2022.10068471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090875870","display_name":"Doaa B. Ebaid","orcid":"https://orcid.org/0000-0002-7035-8441"},"institutions":[{"id":"https://openalex.org/I107613613","display_name":"Information Technology Institute","ror":"https://ror.org/04ynw2g14","country_code":"EG","type":"facility","lineage":["https://openalex.org/I107613613"]},{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Doaa B. Ebaid","raw_affiliation_strings":["Institute of Graduate Studies and Research, Alexandria University,Department of Information Technology,Alexandria,Egypt","Department of Information Technology, Institute of Graduate Studies and Research, Alexandria University, Alexandria, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Graduate Studies and Research, Alexandria University,Department of Information Technology,Alexandria,Egypt","institution_ids":["https://openalex.org/I84524832"]},{"raw_affiliation_string":"Department of Information Technology, Institute of Graduate Studies and Research, Alexandria University, Alexandria, Egypt","institution_ids":["https://openalex.org/I84524832","https://openalex.org/I107613613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068565541","display_name":"Adel A. El-Zoghabi","orcid":"https://orcid.org/0009-0009-5256-5568"},"institutions":[{"id":"https://openalex.org/I107613613","display_name":"Information Technology Institute","ror":"https://ror.org/04ynw2g14","country_code":"EG","type":"facility","lineage":["https://openalex.org/I107613613"]},{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Adel A. El-Zoghabi","raw_affiliation_strings":["Institute of Graduate Studies and Research, Alexandria University,Department of Information Technology,Alexandria,Egypt","Department of Information Technology, Institute of Graduate Studies and Research, Alexandria University, Alexandria, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Graduate Studies and Research, Alexandria University,Department of Information Technology,Alexandria,Egypt","institution_ids":["https://openalex.org/I84524832"]},{"raw_affiliation_string":"Department of Information Technology, Institute of Graduate Studies and Research, Alexandria University, Alexandria, Egypt","institution_ids":["https://openalex.org/I84524832","https://openalex.org/I107613613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041801663","display_name":"Magda M. Madbouly","orcid":"https://orcid.org/0000-0002-9854-4609"},"institutions":[{"id":"https://openalex.org/I107613613","display_name":"Information Technology Institute","ror":"https://ror.org/04ynw2g14","country_code":"EG","type":"facility","lineage":["https://openalex.org/I107613613"]},{"id":"https://openalex.org/I84524832","display_name":"Alexandria University","ror":"https://ror.org/00mzz1w90","country_code":"EG","type":"education","lineage":["https://openalex.org/I84524832"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Magda M. Madbouly","raw_affiliation_strings":["Institute of Graduate Studies and Research, Alexandria University,Department of Information Technology,Alexandria,Egypt","Department of Information Technology, Institute of Graduate Studies and Research, Alexandria University, Alexandria, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Graduate Studies and Research, Alexandria University,Department of Information Technology,Alexandria,Egypt","institution_ids":["https://openalex.org/I84524832"]},{"raw_affiliation_string":"Department of Information Technology, Institute of Graduate Studies and Research, Alexandria University, Alexandria, Egypt","institution_ids":["https://openalex.org/I84524832","https://openalex.org/I107613613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16086172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"26","issue":null,"first_page":"178","last_page":"182"},"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/T10028","display_name":"Topic Modeling","score":0.9934999942779541,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.991100013256073,"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/embedding","display_name":"Embedding","score":0.7989811897277832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7076714634895325},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.70008784532547},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.677685022354126},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6368424296379089},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6124470829963684},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6107454895973206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5986524820327759},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5209997296333313},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5018749237060547},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4771396815776825},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.44405949115753174},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4163863956928253},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33718734979629517},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32364141941070557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2180044949054718}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7989811897277832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7076714634895325},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.70008784532547},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.677685022354126},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6368424296379089},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6124470829963684},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6107454895973206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5986524820327759},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5209997296333313},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5018749237060547},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4771396815776825},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.44405949115753174},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4163863956928253},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33718734979629517},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32364141941070557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2180044949054718},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscmi56532.2022.10068471","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iscmi56532.2022.10068471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 9th International Conference on Soft Computing & Machine Intelligence (ISCMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1905882502","https://openalex.org/W1949478088","https://openalex.org/W2064675550","https://openalex.org/W2123024445","https://openalex.org/W2149557440","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2560835477","https://openalex.org/W2747329762","https://openalex.org/W2798280084","https://openalex.org/W2894786240","https://openalex.org/W2912500072","https://openalex.org/W2962964995","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W2997403743","https://openalex.org/W3108373531","https://openalex.org/W3118694826","https://openalex.org/W3147954272","https://openalex.org/W3186617021","https://openalex.org/W4213348104","https://openalex.org/W4220689946","https://openalex.org/W4293363567","https://openalex.org/W6676647902","https://openalex.org/W6678470764","https://openalex.org/W6685183736","https://openalex.org/W6747225742"],"related_works":["https://openalex.org/W2385859805","https://openalex.org/W2081900870","https://openalex.org/W2530972254","https://openalex.org/W2374013449","https://openalex.org/W73545470","https://openalex.org/W2188500270","https://openalex.org/W2303858293","https://openalex.org/W2183306018","https://openalex.org/W2549990292","https://openalex.org/W2345479200"],"abstract_inverted_index":{"Image-text(caption)":[0],"matching":[1,172],"has":[2],"become":[3],"a":[4,27,77,108,168],"regular":[5],"evaluation":[6],"of":[7,21,97],"joint-embedding":[8],"models":[9],"that":[10,54,80,113,126,138],"combine":[11],"vision":[12],"and":[13,32,123],"language.":[14],"This":[15],"task":[16],"comprises":[17],"ranking":[18,33],"the":[19,69,73,82,85,88,94,101,147,158],"data":[20],"one":[22],"modality":[23,79],"(images)":[24],"based":[25,119,127],"on":[26,120,128,157,161],"Text":[28],"query":[29,40],"(Image":[30],"Retrieval),":[31],"texts":[34],"by":[35],"relevance":[36],"for":[37],"an":[38,141],"image":[39],"(Text":[41],"Retrieval).":[42],"The":[43,164],"current":[44],"joint":[45,110],"embedding":[46,56,111,148,155],"approaches":[47],"use":[48],"symmetric":[49,121],"similarity":[50,75],"measurement,":[51],"due":[52],"to":[53,64,131,137,145],"order":[55,124],"is":[57],"not":[58],"taken":[59],"in":[60,66,76,87,100,171],"consideration.":[61],"In":[62,91,103,135],"addition":[63,136],"that,":[65],"image-text":[67,133],"matching,":[68],"used":[70],"losses":[71],"ignore":[72],"intra":[74,98,142],"certain":[78],"explores":[81],"relation":[83],"between":[84,115],"candidates":[86],"same":[89],"modality.":[90],"spite":[92],"of,":[93],"important":[95],"role":[96],"information":[99],"embedding.":[102],"this":[104],"paper,":[105],"we":[106,139],"proposed":[107,165],"hybrid":[109],"approach":[112,156],"combines":[114],"distance":[116,122,130],"preserving":[117,125],"which":[118],"asymmetric":[129],"improve":[132],"matching.":[134],"propose":[140],"loss":[143,166],"function":[144],"enrich":[146],"with":[149],"intra-modality":[150],"information.":[151],"We":[152],"evaluate":[153],"our":[154],"baseline":[159],"model":[160],"Flickr30K":[162],"dataset.":[163],"shows":[167],"significant":[169],"enhancement":[170],"task.":[173]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}