{"id":"https://openalex.org/W7160326203","doi":"https://doi.org/10.1109/wacv61042.2026.00147","title":"ITSELF: Attention Guided Fine-Grained Alignment for Vision\u2013Language Retrieval","display_name":"ITSELF: Attention Guided Fine-Grained Alignment for Vision\u2013Language Retrieval","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160326203","doi":"https://doi.org/10.1109/wacv61042.2026.00147"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","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/A5031473482","display_name":"Tien-Huy Nguyen","orcid":"https://orcid.org/0009-0000-0196-6083"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien-Huy Nguyen","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114223978","display_name":"Huu-Loc Tran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huu-Loc Tran","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135307459","display_name":"Thanh Duc Ngo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thanh Duc Ngo","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"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":0.69316347,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1448","last_page":"1458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9542999863624573,"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":0.9542999863624573,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.008700000122189522,"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":0.005499999970197678,"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/feature","display_name":"Feature (linguistics)","score":0.3154999911785126},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.24869999289512634},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2312999963760376},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.22949999570846558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6184999942779541},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045999884605408},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2969000041484833},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.24869999289512634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.23960000276565552},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2312999963760376},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.22949999570846558},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.22830000519752502},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2282000035047531}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.46779248118400574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W2946794439","https://openalex.org/W2962858109","https://openalex.org/W2963449390","https://openalex.org/W3035422918","https://openalex.org/W3095440956","https://openalex.org/W3175888430","https://openalex.org/W3176196997","https://openalex.org/W3189221782","https://openalex.org/W3206868111","https://openalex.org/W4225159440","https://openalex.org/W4283818632","https://openalex.org/W4304087170","https://openalex.org/W4312998013","https://openalex.org/W4321231469","https://openalex.org/W4385764787","https://openalex.org/W4386065462","https://openalex.org/W4386758381","https://openalex.org/W4387969466","https://openalex.org/W4388145471","https://openalex.org/W4390190636","https://openalex.org/W4390874394","https://openalex.org/W4392172801","https://openalex.org/W4392903070","https://openalex.org/W4393148792","https://openalex.org/W4393154149","https://openalex.org/W4393158672","https://openalex.org/W4393158793","https://openalex.org/W4402702979","https://openalex.org/W4402753821","https://openalex.org/W4402753981","https://openalex.org/W4402754293","https://openalex.org/W4403760443","https://openalex.org/W4403780841","https://openalex.org/W4408220440","https://openalex.org/W4409367909","https://openalex.org/W4409917583","https://openalex.org/W4410540215","https://openalex.org/W4410636489","https://openalex.org/W4412013308","https://openalex.org/W4414198362","https://openalex.org/W4414198468","https://openalex.org/W4414198960","https://openalex.org/W4415797829","https://openalex.org/W7131117529"],"related_works":[],"abstract_inverted_index":{"Vision":[0],"Language":[1],"Models":[2],"(VLMs)":[3],"have":[4],"rapidly":[5],"advanced":[6],"and":[7,25,46,75,111,129,144,149,185,192],"show":[8,182],"strong":[9,186],"promise":[10],"for":[11,86,135],"text-based":[12],"person":[13],"search":[14],"(TBPS),":[15],"a":[16],"task":[17],"that":[18,63],"requires":[19],"capturing":[20],"fine-grained":[21,119],"relationships":[22],"between":[23],"images":[24],"text":[26],"to":[27,43,76,161],"distinguish":[28],"individuals.":[29],"Previous":[30],"methods":[31],"address":[32],"these":[33,78],"challenges":[34],"through":[35],"local":[36,88,113],"alignment,":[37],"yet":[38],"they":[39],"are":[40],"often":[41],"prone":[42],"shortcut":[44],"learning":[45,118],"spurious":[47],"correlations,":[48],"yielding":[49],"misalignment.":[50],"Moreover,":[51],"injecting":[52],"prior":[53,199],"knowledge":[54],"can":[55],"distort":[56],"intra-modality":[57],"structure.":[58],"Motivated":[59],"by":[60],"our":[61,195],"finding":[62],"encoder":[64],"attention":[65,103,141],"surfaces":[66],"spatially":[67],"precise":[68],"evidence":[69],"from":[70,159],"the":[71,100,126,156,190],"earliest":[72],"training":[73],"epochs,":[74],"alleviate":[77],"issues,":[79],"we":[80,131],"introduce":[81,132],"ITSELF,":[82],"an":[83,105],"attention-guided":[84],"framework":[85],"implicit":[87],"alignment.":[89],"At":[90],"its":[91],"core,":[92],"Guided":[93],"Representation":[94],"with":[95],"Attentive":[96,106],"Bank":[97,107],"(GRAB)":[98],"converts":[99],"model\u2019s":[101],"own":[102],"into":[104],"of":[108,194],"high-saliency":[109],"tokens":[110],"applies":[112],"objectives":[114],"on":[115,171,176],"this":[116],"bank,":[117],"correspondences":[120],"without":[121,197],"extra":[122],"supervision.":[123,200],"To":[124],"make":[125],"selection":[127],"reliable":[128],"non-redundant,":[130],"Multi-Layer":[133],"Attention":[134],"Robust":[136],"Selection":[137],"(MARS),":[138],"which":[139,154],"aggregates":[140],"across":[142],"layers":[143],"performs":[145],"diversity-aware":[146],"top-k":[147],"selection;":[148],"Adaptive":[150],"Token":[151],"Scheduler":[152],"(ATS),":[153],"schedules":[155],"retention":[157],"budget":[158],"coarse":[160],"fine":[162],"over":[163],"training,":[164],"preserving":[165],"context":[166],"early":[167],"while":[168],"progressively":[169],"focusing":[170],"discriminative":[172],"details.":[173],"Extensive":[174],"experiments":[175],"three":[177],"widely":[178],"used":[179],"TBPS":[180],"benchmarks":[181],"state-of-the-art":[183],"performance":[184],"cross-dataset":[187],"generalization,":[188],"confirming":[189],"effectiveness":[191],"robustness":[193],"approach":[196],"additional":[198],"Our":[201],"project":[202],"is":[203],"publicly":[204],"available":[205],"at":[206],"https://trhuuloc.github.io/itself":[207]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-06T00:00:00"}