{"id":"https://openalex.org/W7127144919","doi":"https://doi.org/10.1109/tip.2026.3658218","title":"Bidirectional Cross-Modal Collaborative Alignment via Semantic-Guided Visual Embeddings for Partially Relevant Video Retrieval","display_name":"Bidirectional Cross-Modal Collaborative Alignment via Semantic-Guided Visual Embeddings for Partially Relevant Video Retrieval","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7127144919","doi":"https://doi.org/10.1109/tip.2026.3658218","pmid":"https://pubmed.ncbi.nlm.nih.gov/41628038"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3658218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3658218","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huafeng Li","orcid":"https://orcid.org/0000-0003-2462-6174"},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huafeng Li","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0003-2462-6174","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124766161","display_name":"Jialong Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialong Zhao","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0009-0007-0086-6946","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124807658","display_name":"Yafei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I10660446","display_name":"Kunming University of Science and Technology","ror":"https://ror.org/00xyeez13","country_code":"CN","type":"education","lineage":["https://openalex.org/I10660446"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafei Zhang","raw_affiliation_strings":["Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"],"raw_orcid":"https://orcid.org/0000-0003-2347-5642","affiliations":[{"raw_affiliation_string":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China","institution_ids":["https://openalex.org/I10660446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017617923","display_name":"Jie Wen","orcid":"https://orcid.org/0000-0001-9554-2379"},"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":"Jie Wen","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9554-2379","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen Campus, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.10932734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"1423","last_page":"1435"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9760000109672546,"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":0.9760000109672546,"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":0.013899999670684338,"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/T11439","display_name":"Video Analysis and Summarization","score":0.0019000000320374966,"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/semantics","display_name":"Semantics (computer science)","score":0.6234999895095825},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5144000053405762},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46799999475479126},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.46050000190734863},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.43309998512268066},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.42080000042915344},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.41749998927116394},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41620001196861267},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.3993000090122223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8475000262260437},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6234999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5967000126838684},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5726000070571899},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46050000190734863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4415000081062317},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.42080000042915344},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.41749998927116394},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38670000433921814},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.3637999892234802},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.33500000834465027},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3658218","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3658218","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Image Processing","raw_type":"journal-article"},{"id":"pmid:41628038","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41628038","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6814356446266174}],"awards":[{"id":"https://openalex.org/G1439643001","display_name":null,"funder_award_id":"202401AS070640","funder_id":"https://openalex.org/F4320330387","funder_display_name":"Foundation for Fundamental Research of China"},{"id":"https://openalex.org/G6545507832","display_name":null,"funder_award_id":"62276120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6961297351","display_name":null,"funder_award_id":"202301AV070004","funder_id":"https://openalex.org/F4320330387","funder_display_name":"Foundation for Fundamental Research of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330387","display_name":"Foundation for Fundamental Research of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2142838865","https://openalex.org/W2194775991","https://openalex.org/W2250539671","https://openalex.org/W2963524571","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2965373594","https://openalex.org/W3035524453","https://openalex.org/W3104862079","https://openalex.org/W3130796238","https://openalex.org/W3155721152","https://openalex.org/W3200217958","https://openalex.org/W4211053420","https://openalex.org/W4285606530","https://openalex.org/W4293567872","https://openalex.org/W4312661097","https://openalex.org/W4321614506","https://openalex.org/W4324291273","https://openalex.org/W4386072365","https://openalex.org/W4386076289","https://openalex.org/W4386076600","https://openalex.org/W4386076615","https://openalex.org/W4386159024","https://openalex.org/W4390872366","https://openalex.org/W4390872434","https://openalex.org/W4390872529","https://openalex.org/W4390873165","https://openalex.org/W4390889802","https://openalex.org/W4393148201","https://openalex.org/W4402704596","https://openalex.org/W4402716394","https://openalex.org/W4402777374","https://openalex.org/W4403936202","https://openalex.org/W4407252565","https://openalex.org/W4409370048","https://openalex.org/W4409986095","https://openalex.org/W4412536423","https://openalex.org/W4413155274","https://openalex.org/W4415799009","https://openalex.org/W4416214650"],"related_works":[],"abstract_inverted_index":{"Partially":[0],"Relevant":[1],"Video":[2],"Retrieval":[3],"(PRVR)":[4],"aims":[5],"to":[6,23,82,89,153,175],"retrieve":[7],"videos":[8],"that":[9,57,79,157,224],"match":[10],"a":[11,52,69,105],"given":[12],"textual":[13,63,83,94,114,182,190,194],"query":[14],"only":[15],"partially.":[16],"This":[17],"task":[18],"is":[19,32,236],"inherently":[20],"challenging":[21],"due":[22],"the":[24,36,66,74,86,121,125,136,168,172,180,189,204,210,234],"modality":[25,211],"gap":[26],"between":[27,40],"text":[28],"and":[29,43,62,113],"video,":[30],"which":[31,109],"further":[33,208],"exacerbated":[34],"by":[35,196],"partial":[37,219],"semantic":[38,117,220],"correspondence":[39,221],"linguistic":[41],"descriptions":[42],"visual":[44,61,67,77,91,112,129,138,159,166,173,200],"content.":[45],"To":[46,99],"address":[47],"these":[48,164],"challenges,":[49],"we":[50,103,192],"propose":[51],"bidirectional":[53],"cross-modal":[54,149,186],"alignment":[55,178],"mechanism":[56],"collaboratively":[58],"optimizes":[59],"both":[60],"modalities.":[64],"In":[65,188],"modality,":[68,191],"major":[70],"difficulty":[71],"lies":[72],"in":[73],"absence":[75],"of":[76,233],"cues":[78],"directly":[80],"correspond":[81],"semantics,":[84],"limiting":[85],"model's":[87],"ability":[88],"align":[90],"representations":[92,174,195],"with":[93,116,146,179],"meanings":[95],"under":[96,218],"unsupervised":[97],"conditions.":[98],"overcome":[100],"this":[101,132],"issue,":[102],"construct":[104],"semantic-visual":[106],"association":[107,206],"library,":[108,207],"stores":[110],"paired":[111],"features":[115,201],"annotations.":[118],"During":[119],"training,":[120],"model":[122,169],"dynamically":[123],"retrieves":[124],"most":[126],"semantically":[127,198],"similar":[128],"samples":[130],"from":[131,203],"library":[133],"based":[134],"on":[135,215],"current":[137],"feature":[139],"vector.":[140],"These":[141],"retrieved":[142],"samples,":[143],"preliminarily":[144],"associated":[145],"semantics":[147],"via":[148],"matching,":[150],"are":[151],"used":[152],"form":[154],"dynamic":[155],"anchors":[156],"guide":[158],"representation":[160],"learning.":[161],"By":[162],"leveraging":[163],"enriched":[165],"features,":[167],"progressively":[170],"refines":[171],"achieve":[176],"better":[177],"corresponding":[181],"inputs,":[183],"thereby":[184],"enhancing":[185],"consistency.":[187],"enhance":[193],"integrating":[197],"aligned":[199],"selected":[202],"same":[205],"narrowing":[209],"gap.":[212],"Extensive":[213],"experiments":[214],"benchmark":[216],"datasets":[217],"scenarios":[222],"demonstrate":[223],"our":[225],"method":[226],"achieves":[227],"state-of-the-art":[228],"performance.":[229],"The":[230],"source":[231],"code":[232],"paper":[235],"available":[237],"at":[238],"https://github.com/cyanlll/BOA.":[239]},"counts_by_year":[],"updated_date":"2026-02-12T06:13:03.167441","created_date":"2026-02-03T00:00:00"}