{"id":"https://openalex.org/W7202299183","doi":"https://doi.org/10.48550/arxiv.2608.10524","title":"Rethinking Text-Based Image Retrieval in Specific Domain","display_name":"Rethinking Text-Based Image Retrieval in Specific Domain","publication_year":2026,"publication_date":"2026-08-11","ids":{"openalex":"https://openalex.org/W7202299183","doi":"https://doi.org/10.48550/arxiv.2608.10524"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.10524","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10524","pdf_url":"https://arxiv.org/pdf/2608.10524","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.10524","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146971387","display_name":"Jingyang Tan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan, Jingyang","raw_affiliation_strings":["Department of Electronic and Communication Engineering , Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic and Communication Engineering , Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122329626","display_name":"Sheng Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Sheng","raw_affiliation_strings":["School of Data Science , Fudan University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science , Fudan University ,","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069046107","display_name":"Yuanpeng Chen","orcid":"https://orcid.org/0009-0007-2015-7813","observed_orcids":["https://orcid.org/0009-0007-2015-7813","https://orcid.org/0009-0004-0417-7353"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yuanpeng","raw_affiliation_strings":["Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139151321","display_name":"Jian Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jian","raw_affiliation_strings":["School of Data Science , Fudan University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Data Science , Fudan University ,","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083972141","display_name":"Nianjin Ye","orcid":"https://orcid.org/0000-0002-7459-2390","observed_orcids":["https://orcid.org/0000-0002-7459-2390"]},"institutions":[{"id":"https://openalex.org/I4210155932","display_name":"Changhong (China)","ror":"https://ror.org/04tttpd30","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye, Nianjin","raw_affiliation_strings":["Changhong Intelligent Robot ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changhong Intelligent Robot ,","institution_ids":["https://openalex.org/I4210155932"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146984699","display_name":"Chen Xing","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210155932","display_name":"Changhong (China)","ror":"https://ror.org/04tttpd30","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xing, Chen","raw_affiliation_strings":["Changhong Intelligent Robot ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changhong Intelligent Robot ,","institution_ids":["https://openalex.org/I4210155932"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090123285","display_name":"Lanpeng Jia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210155932","display_name":"Changhong (China)","ror":"https://ror.org/04tttpd30","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210155932"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia, Lanpeng","raw_affiliation_strings":["Changhong Intelligent Robot ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changhong Intelligent Robot ,","institution_ids":["https://openalex.org/I4210155932"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7484999895095825,"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":0.7484999895095825,"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":0.14110000431537628,"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":0.08889999985694885,"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/text-based-image-retrieval","display_name":"text-based image retrieval","score":0.9990000128746033},{"id":"https://openalex.org/keywords/domain-specific-retrieval","display_name":"domain-specific retrieval","score":0.781000018119812},{"id":"https://openalex.org/keywords/surveillance-images","display_name":"surveillance images","score":0.8399999737739563},{"id":"https://openalex.org/keywords/benchmark-design","display_name":"benchmark design","score":0.675000011920929},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.8119999766349792},{"id":"https://openalex.org/keywords/false-negative-results","display_name":"false-negative results","score":0.7179999947547913},{"id":"https://openalex.org/keywords/semantic-compression","display_name":"semantic compression","score":0.8320000171661377},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.7940000295639038},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7210000157356262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7833999991416931},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6967999935150146},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.6607000231742859},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4763999879360199},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4724999964237213},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4675000011920929},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33239999413490295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33160001039505005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.3118000030517578},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.10524","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10524","pdf_url":"https://arxiv.org/pdf/2608.10524","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.10524","doi":"https://doi.org/10.48550/arxiv.2608.10524","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.10524","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.10524","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.10524","pdf_url":"https://arxiv.org/pdf/2608.10524","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202299183.pdf","grobid_xml":"https://content.openalex.org/works/W7202299183.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2964211610","https://openalex.org/W3184033217","https://openalex.org/W4303648003","https://openalex.org/W4366208220","https://openalex.org/W4407815020","https://openalex.org/W4415272877","https://openalex.org/W4415276238","https://openalex.org/W4415537304","https://openalex.org/W4415797829","https://openalex.org/W4415923593","https://openalex.org/W4416780398","https://openalex.org/W6891889405","https://openalex.org/W6910554155","https://openalex.org/W7120003758","https://openalex.org/W7143496489"],"related_works":["https://openalex.org/W4403791994","https://openalex.org/W7167685819","https://openalex.org/W7135018741","https://openalex.org/W4416962945","https://openalex.org/W4381327576","https://openalex.org/W4411146885","https://openalex.org/W7079766446","https://openalex.org/W4402980375","https://openalex.org/W4405032599","https://openalex.org/W4366851068"],"abstract_inverted_index":{"Driven":[0],"by":[1],"the":[2,111,126],"rapid":[3],"advancement":[4],"of":[5,171],"vision-language":[6],"representation":[7],"learning,":[8],"Text-based":[9,70],"Image":[10,71],"Retrieval":[11,72],"(TBIR)":[12],"has":[13],"made":[14],"notable":[15],"progress.":[16],"However,":[17],"existing":[18],"benchmarks":[19],"are":[20],"predominantly":[21],"constructed":[22],"on":[23,174],"an":[24,167],"exclusive":[25],"single-match":[26],"assumption":[27,38],"between":[28],"query":[29,53],"and":[30,119,144],"images.":[31,60],"While":[32],"effective":[33],"in":[34,45,102,135],"general":[35],"scenarios,":[36],"this":[37,63,77],"fails":[39],"to":[40,56,113,131,149,193],"reflect":[41],"practical":[42],"system":[43],"performance":[44],"specific":[46,103,136],"domains":[47,104],"(e.g.,":[48],"surveillance),":[49],"where":[50],"a":[51,67,85,151],"single":[52],"often":[54],"corresponds":[55],"multiple":[57],"relevant":[58],"candidate":[59],"To":[61],"address":[62,132],"limitation,":[64],"we":[65,79,96],"design":[66],"Domain-Specific":[68],"Multi-Match":[69,82],"(DSMM-TBIR)":[73],"data":[74],"engine.":[75],"Leveraging":[76],"engine,":[78],"construct":[80],"Security":[81],"TBIR":[83,156],"(SecMM-TBIR),":[84],"benchmark":[86,189],"comprising":[87],"50k":[88],"surveillance":[89],"images":[90],"with":[91],"200":[92],"comprehensive":[93],"queries.":[94],"Furthermore,":[95],"observe":[97],"that":[98,164],"vanilla":[99],"contrastive":[100,179],"learning":[101],"suffers":[105],"from":[106],"severe":[107],"false":[108],"negatives,":[109],"forcing":[110],"model":[112],"push":[114],"apart":[115],"semantically":[116],"similar":[117],"pairs":[118],"thus":[120],"degrading":[121],"retrieval":[122],"performance.":[123,186],"We":[124],"propose":[125],"Semantic-Aware":[127,140],"Fine-Tuning":[128],"(SAFT)":[129],"framework":[130],"semantic":[133],"compression":[134],"domains,":[137],"which":[138],"incorporates":[139],"Soft-Label":[141],"Supervision":[142],"(SASS)":[143],"Intra-modal":[145],"Structural":[146],"Distillation":[147],"(ISD)":[148],"establish":[150],"promising":[152],"paradigm":[153],"for":[154],"domain-specific":[155],"tasks.":[157],"Experiments":[158],"across":[159],"diverse":[160],"CLIP-like":[161],"models":[162],"demonstrate":[163],"SAFT":[165],"yields":[166],"average":[168],"mAP@20":[169],"gain":[170],"7.8":[172],"points":[173],"SecMM-TBIR":[175],"over":[176],"standard":[177],"image-text":[178],"(ITC)":[180],"fine-tuning,":[181],"while":[182],"also":[183],"improving":[184],"general-domain":[185],"The":[187],"entire":[188],"will":[190],"be":[191],"released":[192],"facilitate":[194],"further":[195],"research.":[196]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-13T00:00:00"}