{"id":"https://openalex.org/W7126021603","doi":"https://doi.org/10.1109/icfsp67350.2025.11353752","title":"An Efficient and Lightweight Way of Instance Level Image Retrieval: Chain Retrieval with Visual Transformers","display_name":"An Efficient and Lightweight Way of Instance Level Image Retrieval: Chain Retrieval with Visual Transformers","publication_year":2025,"publication_date":"2025-09-10","ids":{"openalex":"https://openalex.org/W7126021603","doi":"https://doi.org/10.1109/icfsp67350.2025.11353752"},"language":null,"primary_location":{"id":"doi:10.1109/icfsp67350.2025.11353752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfsp67350.2025.11353752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Frontiers of Signal Processing (ICFSP)","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/A5111196390","display_name":"Yagmur Aktas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ya\u011fmur \u00c7i\u011fdem Akta\u015f","raw_affiliation_strings":["Basque Research and Technology Alliance (BRTA),Vicomtech Foundation,Donostia-San Sebastián,Spain,20009"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basque Research and Technology Alliance (BRTA),Vicomtech Foundation,Donostia-San Sebastián,Spain,20009","institution_ids":["https://openalex.org/I4210092551"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113468059","display_name":"Jorge Garc\u00eda Casta\u00f1o","orcid":null},"institutions":[{"id":"https://openalex.org/I4210092551","display_name":"Vicomtech","ror":"https://ror.org/0023sah13","country_code":"ES","type":"facility","lineage":["https://openalex.org/I4210092551"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jorge Garc\u00eda Casta\u00f1o","raw_affiliation_strings":["Basque Research and Technology Alliance (BRTA),Vicomtech Foundation,Donostia-San Sebastián,Spain,20009"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basque Research and Technology Alliance (BRTA),Vicomtech Foundation,Donostia-San Sebastián,Spain,20009","institution_ids":["https://openalex.org/I4210092551"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210092551"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61249245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"43"},"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":0.8551999926567078,"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":0.8551999926567078,"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":0.09160000085830688,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.020500000566244125,"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/image-retrieval","display_name":"Image retrieval","score":0.626800000667572},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5317999720573425},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4417000114917755},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.42100000381469727},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41909998655319214},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4081000089645386},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.37720000743865967},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.3521000146865845},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.32260000705718994}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840999960899353},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.626800000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5879999995231628},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5317999720573425},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.42100000381469727},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.37720000743865967},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35830000042915344},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3521000146865845},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3352999985218048},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2775999903678894},{"id":"https://openalex.org/C2779597229","wikidata":"https://www.wikidata.org/wiki/Q17146505","display_name":"Similarity learning","level":3,"score":0.2761000096797943},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.2639999985694885},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icfsp67350.2025.11353752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icfsp67350.2025.11353752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 10th International Conference on Frontiers of Signal Processing (ICFSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5727630257606506,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2005750530","https://openalex.org/W2503462743","https://openalex.org/W2549858646","https://openalex.org/W2951019013","https://openalex.org/W3110536152","https://openalex.org/W4386071700","https://openalex.org/W4390873539"],"related_works":[],"abstract_inverted_index":{"Instance-Level":[0],"image":[1],"retrieval":[2,73,113,138,178],"(ILIR)":[3],"requires":[4],"fine-grained":[5],"discrimination":[6],"to":[7,52,90,104,115],"identify":[8],"all":[9],"images":[10,103],"depicting":[11],"the":[12,77,91,99,102,127,143,173,222],"same":[13],"object":[14],"or":[15,26,165,203],"scene":[16],"as":[17,60,84,86],"a":[18,64,96,135,161,177,188,229],"query,":[19],"regardless":[20],"of":[21,101,123],"variations":[22],"in":[23,176],"viewpoint,":[24],"scale,":[25],"background.":[27],"While":[28],"recent":[29],"methods":[30,214],"based":[31],"on":[32,43,167,194,215],"convolutional":[33],"and":[34,46,119,180,199,218,227],"transformer":[35],"architectures":[36],"have":[37],"achieved":[38],"high":[39],"accuracy,":[40],"most":[41],"rely":[42,166],"supervised":[44,78,225],"training":[45,202],"dataset-specific":[47],"tuning,":[48],"limiting":[49],"their":[50],"generalization":[51],"real-world,":[53],"open-set":[54],"scenarios.":[55],"Pretrained":[56],"Vision":[57],"Transformers":[58],"such":[59],"CLIP":[61,196],"[1]":[62,197],"offer":[63],"promising":[65],"zero-shot":[66,137,212],"alternative,":[67],"but":[68],"current":[69],"approaches":[70],"for":[71,81,98,111,233],"image-to-image":[72,213],"yet":[74],"far":[75],"from":[76,149],"method\u2019s":[79],"performances":[80],"benchmark":[82,219],"datasets,":[83,220],"well":[85],"they":[87],"focus":[88],"only":[89],"ranking":[92],"task,":[93],"not":[94,159],"offering":[95,228],"solution":[97,232],"amount":[100,122],"retrieve,":[105],"which":[106],"is":[107],"an":[108],"important":[109],"point":[110],"real-world":[112],"task":[114],"prevent":[116],"false":[117],"retrievals":[118],"obtaining":[120],"unnecessary":[121],"retrieved":[124,151],"data":[125],"at":[126],"end.In":[128],"this":[129],"paper,":[130],"we":[131],"propose":[132],"Chain":[133,205],"Retrieve,":[134],"fully":[136],"framework":[139],"that":[140],"iteratively":[141],"refines":[142],"query":[144,174],"embedding":[145],"by":[146],"integrating":[147],"information":[148],"top-k":[150],"images.":[152],"Unlike":[153],"existing":[154,211],"methods,":[155],"our":[156],"approach":[157],"does":[158],"assume":[160],"fixed":[162],"result":[163],"count":[164],"handcrafted":[168],"thresholds.":[169],"Instead,":[170],"it":[171],"expands":[172],"representation":[175],"loop":[179],"stops":[181],"automatically":[182],"when":[183],"similarity":[184],"scores":[185],"fall":[186],"below":[187],"fixed,":[189],"interpretable":[190],"threshold.":[191],"Built":[192],"entirely":[193],"pre-trained":[195],"ViTs":[198],"requiring":[200],"no":[201],"fine-tuning,":[204],"Retrieve":[206],"achieves":[207],"superior":[208],"performance":[209],"over":[210],"both":[216],"custom":[217],"narrowing":[221],"gap":[223],"with":[224],"models":[226],"scalable,":[230],"plug-and-play":[231],"ILIR.":[234]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-30T00:00:00"}