{"id":"https://openalex.org/W4409311340","doi":"https://doi.org/10.1109/crc63701.2024.10949885","title":"Implicit Fine-Grained Alignment for Cross-Modal Retrieval","display_name":"Implicit Fine-Grained Alignment for Cross-Modal Retrieval","publication_year":2024,"publication_date":"2024-11-21","ids":{"openalex":"https://openalex.org/W4409311340","doi":"https://doi.org/10.1109/crc63701.2024.10949885"},"language":"en","primary_location":{"id":"doi:10.1109/crc63701.2024.10949885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/crc63701.2024.10949885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 9th International Conference on Control, Robotics and Cybernetics (CRC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100387660","display_name":"Hui Liu","orcid":"https://orcid.org/0000-0003-2948-8217"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Liu","raw_affiliation_strings":["University of Electronic Science and Technology of China, Avic Chengdu Aircraft Design and Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Avic Chengdu Aircraft Design and Research Institute","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084710341","display_name":"Xiaoping Chen","orcid":"https://orcid.org/0000-0001-8992-9286"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao-ping Chen","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038538654","display_name":"Rui Hong","orcid":"https://orcid.org/0000-0002-7627-4628"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Hong","raw_affiliation_strings":["University of Electronic Science and Technology of China, Avic Chengdu Aircraft Design and Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Avic Chengdu Aircraft Design and Research Institute","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735883","display_name":"Yan Zhou","orcid":"https://orcid.org/0000-0002-3213-8229"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhou","raw_affiliation_strings":["University of Electronic Science and Technology of China, Avic Chengdu Aircraft Design and Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Avic Chengdu Aircraft Design and Research Institute","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113142444","display_name":"Tian-cai Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian-cai Wan","raw_affiliation_strings":["Avic Chengdu Aircraft Design and Research Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Avic Chengdu Aircraft Design and Research Institute","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109691701","display_name":"Tai-li Bai","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tai-li Bai","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"66","last_page":"70"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9897000193595886,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9897000193595886,"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":0.9718999862670898,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9291999936103821,"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/modal","display_name":"Modal","score":0.7328600287437439},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7153356671333313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5055112838745117},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3774803876876831},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33608973026275635},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05760473012924194}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7328600287437439},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7153356671333313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5055112838745117},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3774803876876831},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33608973026275635},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05760473012924194},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/crc63701.2024.10949885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/crc63701.2024.10949885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 9th International Conference on Control, Robotics and Cybernetics (CRC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2185175083","https://openalex.org/W2975813532","https://openalex.org/W3118694826","https://openalex.org/W4206546481","https://openalex.org/W4214819138","https://openalex.org/W4285138127","https://openalex.org/W4323338501"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Cross-modal":[0],"retrieval":[1,31,163],"has":[2],"always":[3],"been":[4],"one":[5],"of":[6,16,151],"the":[7,14,19,58,66,102,127,132,149,171],"essential":[8],"tasks":[9],"in":[10,57,71,84,126],"multimodal":[11],"learning,":[12],"with":[13],"aim":[15],"searching":[17],"for":[18],"most":[20],"relevant":[21],"cross-modal":[22,153],"samples":[23,50,56],"based":[24],"on":[25,159],"a":[26,35,88,112],"given":[27],"query.":[28],"Taking":[29],"image-text":[30,162],"as":[32],"an":[33,95],"example,":[34],"direct":[36],"and":[37,52,86,123,140,167,174],"efficient":[38],"approach":[39,130],"is":[40],"to":[41,47,116,144,169,177],"use":[42],"visual":[43],"semantic":[44],"embedding":[45],"technology":[46],"bring":[48],"positive":[49],"closer":[51],"push":[53],"away":[54],"negative":[55],"shared":[59],"subspace.":[60],"However,":[61],"these":[62],"methods":[63],"often":[64],"overlook":[65],"potential":[67,81],"implicit":[68,109],"alignment":[69,82,110,119,154],"relationships":[70,83],"text.":[72,128],"In":[73],"this":[74,152],"letter,":[75],"we":[76,156],"enhance":[77],"representation":[78],"by":[79,137],"revisiting":[80],"text":[85],"propose":[87],"new":[89],"method":[90],"called":[91],"IACR":[92,173],"that":[93],"exploits":[94],"Implicit":[96],"Alignment":[97],"Module":[98],"(IAM),":[99],"thereby":[100],"capturing":[101],"fine-grained":[103,118,138],"local":[104,142],"associations.":[105],"Specifically,":[106],"IAM":[107],"captures":[108],"through":[111],"multi-head":[113],"attention":[114],"mechanism":[115],"establish":[117],"between":[120],"image":[121],"representations":[122],"partial":[124],"words":[125],"This":[129],"avoids":[131],"additional":[133],"reasoning":[134],"costs":[135],"caused":[136],"modeling":[139],"maintains":[141],"correlation":[143],"improve":[145],"performance.":[146],"To":[147],"verify":[148,178],"superiority":[150],"paradigm,":[155],"conduct":[157],"experiments":[158],"two":[160],"large-scale":[161],"datasets,":[164],"i.e.,":[165],"Flickr30K":[166],"MS-COCO,":[168],"evaluate":[170],"proposed":[172],"provide":[175],"analysis":[176],"its":[179],"effectiveness.":[180]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}