{"id":"https://openalex.org/W4414170127","doi":"https://doi.org/10.1109/avss65446.2025.11149975","title":"Active Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples","display_name":"Active Learning for Finely-Categorized Image-Text Retrieval by Selecting Hard Negative Unpaired Samples","publication_year":2025,"publication_date":"2025-08-11","ids":{"openalex":"https://openalex.org/W4414170127","doi":"https://doi.org/10.1109/avss65446.2025.11149975"},"language":"en","primary_location":{"id":"doi:10.1109/avss65446.2025.11149975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss65446.2025.11149975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)","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/A5103014669","display_name":"Dae Ung Jo","orcid":"https://orcid.org/0000-0002-8883-8400"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dae Ung Jo","raw_affiliation_strings":["Kyungpook National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kyungpook National University","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049457843","display_name":"Kyuewang Lee","orcid":"https://orcid.org/0000-0002-4481-8395"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyuewang Lee","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071670581","display_name":"Jaeho Chung","orcid":"https://orcid.org/0009-0008-2332-117X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaeho Chung","raw_affiliation_strings":["Seoul National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7655,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.74932687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5936999917030334},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.5461999773979187},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5037999749183655},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4999000132083893},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4163999855518341},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41130000352859497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6873999834060669},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.682699978351593},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5936999917030334},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5461999773979187},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4999000132083893},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44620001316070557},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4163999855518341},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3395000100135803},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2703000009059906}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/avss65446.2025.11149975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/avss65446.2025.11149975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Advanced Visual and Signal-Based Systems (AVSS)","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":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1583837637","https://openalex.org/W1905882502","https://openalex.org/W1995875735","https://openalex.org/W2007972815","https://openalex.org/W2031489346","https://openalex.org/W2066852389","https://openalex.org/W2100799972","https://openalex.org/W2106277773","https://openalex.org/W2129156852","https://openalex.org/W2185175083","https://openalex.org/W2616652378","https://openalex.org/W2745461083","https://openalex.org/W2774267535","https://openalex.org/W2774918944","https://openalex.org/W2948367246","https://openalex.org/W2952122856","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2980704105","https://openalex.org/W2984303785","https://openalex.org/W2986514296","https://openalex.org/W2988823324","https://openalex.org/W2994818707","https://openalex.org/W3035454331","https://openalex.org/W3179192172","https://openalex.org/W4206648492"],"related_works":[],"abstract_inverted_index":{"Securing":[0],"a":[1,75,145],"sufficient":[2],"amount":[3],"of":[4,69,117,158],"paired":[5,18,41,112],"data":[6,19,42],"is":[7,20,72,122],"important":[8],"to":[9,58,110,123,149],"train":[10],"an":[11,32,91],"image-text":[12,48,83],"retrieval":[13,76],"(ITR)":[14],"model,":[15],"but":[16],"collecting":[17],"very":[21],"expensive.":[22],"To":[23,140],"address":[24],"this":[25,28,86,141],"issue,":[26],"in":[27,62],"paper,":[29],"we":[30,88,143],"propose":[31],"active":[33,92],"learning":[34,93],"algorithm":[35,121],"for":[36,135],"ITR":[37,65],"that":[38,47,129],"can":[39,78,130],"collect":[40],"cost-efficiently.":[43],"Previous":[44],"studies":[45],"assume":[46],"pairs":[49],"are":[50,56,100],"given":[51,101],"and":[52,102,164],"their":[53],"category":[54,70],"labels":[55],"asked":[57],"the":[59,63,67,103,118,156,159],"annotator.":[60],"However,":[61],"recent":[64],"studies,":[66],"importance":[68],"label":[71],"decreased":[73],"since":[74],"model":[77],"be":[79,131],"trained":[80],"with":[81],"only":[82],"pairs.":[84],"For":[85],"reason,":[87],"set":[89],"up":[90],"scenario":[94],"where":[95],"unpaired":[96,125],"images":[97,126],"(or":[98,108,127,138],"texts)":[99,128],"annotator":[104],"provides":[105],"corresponding":[106],"texts":[107,137],"images)":[109],"make":[111],"data.":[113],"The":[114],"key":[115],"idea":[116],"proposed":[119,160],"AL":[120],"select":[124],"hard":[132,151],"negative":[133,152],"samples":[134],"existing":[136],"images).":[139],"end,":[142],"introduce":[144],"novel":[146],"scoring":[147],"function":[148],"choose":[150],"samples.":[153],"We":[154],"validate":[155],"effectiveness":[157],"method":[161],"on":[162],"Flickr30K":[163],"MS-COCO":[165],"datasets.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}