{"id":"https://openalex.org/W4386766892","doi":"https://doi.org/10.1109/tmm.2023.3316077","title":"Feature First: Advancing Image-Text Retrieval Through Improved Visual Features","display_name":"Feature First: Advancing Image-Text Retrieval Through Improved Visual Features","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386766892","doi":"https://doi.org/10.1109/tmm.2023.3316077"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3316077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3316077","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-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/A5083360832","display_name":"Dongqing Wu","orcid":"https://orcid.org/0000-0003-0749-4050"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongqing Wu","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0003-0749-4050","affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088848549","display_name":"Huihui Li","orcid":"https://orcid.org/0000-0001-8675-3449"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huihui Li","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0001-8675-3449","affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065332512","display_name":"Cang Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cang Gu","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0000-0003-4427-3652","affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338949","display_name":"Hang Liu","orcid":"https://orcid.org/0000-0002-3408-3807"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Liu","raw_affiliation_strings":["School of Cybersecurity, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012537659","display_name":"Cuili Xu","orcid":"https://orcid.org/0009-0009-1048-9384"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cuili Xu","raw_affiliation_strings":["School of Cybersecurity, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0009-0009-1048-9384","affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070664582","display_name":"Xinyuan Hou","orcid":"https://orcid.org/0000-0002-9249-7928"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinxuan Hou","raw_affiliation_strings":["School of Cybersecurity, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":"https://orcid.org/0009-0000-3344-6664","affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100344286","display_name":"Lei Guo","orcid":"https://orcid.org/0000-0003-0728-896X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Guo","raw_affiliation_strings":["School of Automation, Northwestern Polytechnical University, Xi&#x0027;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Northwestern Polytechnical University, Xi&#x0027;an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.7855,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.69334768,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"26","issue":null,"first_page":"3827","last_page":"3841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9988999962806702,"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":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8919491767883301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6393027305603027},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.5404748320579529},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5387704372406006},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.505305826663971},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4877110421657562},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.4653632938861847},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.46444159746170044},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.4499668478965759},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.43900197744369507},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43351346254348755},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4206193685531616},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4192034602165222},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38187310099601746},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.33162370324134827},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.25745540857315063}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8919491767883301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6393027305603027},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.5404748320579529},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5387704372406006},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.505305826663971},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4877110421657562},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.4653632938861847},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.46444159746170044},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.4499668478965759},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.43900197744369507},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43351346254348755},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4206193685531616},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4192034602165222},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38187310099601746},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33162370324134827},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25745540857315063},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3316077","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3316077","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.75,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2117539524","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2745461083","https://openalex.org/W2774267535","https://openalex.org/W2778100917","https://openalex.org/W2896457183","https://openalex.org/W2900953995","https://openalex.org/W2962964995","https://openalex.org/W2963882743","https://openalex.org/W2964015378","https://openalex.org/W2964120214","https://openalex.org/W2968374502","https://openalex.org/W2981448908","https://openalex.org/W2981586349","https://openalex.org/W2988823324","https://openalex.org/W2990571534","https://openalex.org/W2994818707","https://openalex.org/W2997525715","https://openalex.org/W2998715470","https://openalex.org/W3028151507","https://openalex.org/W3034305926","https://openalex.org/W3035160838","https://openalex.org/W3035454331","https://openalex.org/W3035497460","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3047381720","https://openalex.org/W3092820619","https://openalex.org/W3094172275","https://openalex.org/W3094502228","https://openalex.org/W3100260313","https://openalex.org/W3106925514","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3138516171","https://openalex.org/W3153232703","https://openalex.org/W3155152110","https://openalex.org/W3155230099","https://openalex.org/W3174377922","https://openalex.org/W3175888430","https://openalex.org/W3189718596","https://openalex.org/W3190055600","https://openalex.org/W3197809352","https://openalex.org/W3198064418","https://openalex.org/W3206477365","https://openalex.org/W4200631806","https://openalex.org/W4206314411","https://openalex.org/W4210894218","https://openalex.org/W4213348104","https://openalex.org/W4283394402","https://openalex.org/W4283812943","https://openalex.org/W4297733535","https://openalex.org/W4304092345","https://openalex.org/W4312761738","https://openalex.org/W4319299832","https://openalex.org/W4321199648","https://openalex.org/W4377710209","https://openalex.org/W4385572090","https://openalex.org/W6631516269","https://openalex.org/W6676647902","https://openalex.org/W6678470764","https://openalex.org/W6726873649","https://openalex.org/W6747225742","https://openalex.org/W6789753369","https://openalex.org/W6791353385","https://openalex.org/W6798805250","https://openalex.org/W6804198819","https://openalex.org/W6850255523"],"related_works":["https://openalex.org/W2063218608","https://openalex.org/W4386105885","https://openalex.org/W2184288218","https://openalex.org/W2947282851","https://openalex.org/W2374066281","https://openalex.org/W4387423606","https://openalex.org/W2071180033","https://openalex.org/W2036058638","https://openalex.org/W2528082075","https://openalex.org/W2122803910"],"abstract_inverted_index":{"Current":[0],"image-text":[1,52],"retrieval":[2,17,53],"methods":[3],"mainly":[4],"utilize":[5],"region":[6,29,83],"features":[7,50,120,146,163],"that":[8,133,172],"provide":[9],"object-level":[10,122],"information":[11,136],"to":[12,72,98,111,139,157],"represent":[13],"images,":[14],"making":[15,116],"the":[16,87,100,106,117,180],"results":[18],"more":[19,74,166],"accurate":[20],"and":[21,42,60,76,108,123,184],"interpretable.":[22],"However,":[23],"there":[24],"are":[25,86],"several":[26],"issues":[27],"with":[28,147],"features,":[30],"such":[31],"as":[32,137],"lack":[33],"of":[34,39,44],"rich":[35],"contextual":[36],"information,":[37,115],"loss":[38],"object":[40],"details":[41],"risk":[43],"detection":[45],"redundancy.":[46],"The":[47],"ideal":[48],"visual":[49,69,78,119,130,145,162],"in":[51,164],"should":[54],"have":[55],"three":[56],"characteristics:":[57],"object-level,":[58],"semantically-rich,":[59],"language-aligned.":[61],"To":[62],"this":[63],"end,":[64],"we":[65,91,126,151],"propose":[66],"a":[67,94,128,153,165],"novel":[68],"representation":[70],"framework":[71],"capture":[73],"comprehensive":[75],"powerful":[77],"features.":[79],"Specifically,":[80],"since":[81],"these":[82,160],"feature":[84,89],"disadvantages":[85],"grid":[88],"advantages,":[90],"first":[92],"build":[93],"two-step":[95],"interaction":[96],"model":[97,175],"explore":[99],"complex":[101],"relationship":[102],"between":[103],"them":[104],"from":[105],"spatial":[107],"semantic":[109],"perspectives":[110],"integrate":[112],"their":[113],"complementary":[114],"fused":[118],"both":[121],"semantic-rich.":[124],"Then,":[125],"design":[127],"text-integrated":[129],"embedding":[131],"module":[132,156],"utilizes":[134],"textual":[135],"guidance":[138],"filter":[140],"redundant":[141],"regions,":[142],"further":[143],"endowing":[144],"language-aligned":[148],"capabilities.":[149],"Finally,":[150],"develop":[152],"multi-attention":[154],"pooling":[155],"better":[158],"aggregate":[159],"enhanced":[161],"fine-grained":[167],"manner.":[168],"Extensive":[169],"experiments":[170],"demonstrate":[171],"our":[173],"proposed":[174],"achieves":[176],"state-of-the-art":[177],"performance":[178],"on":[179],"benchmark":[181],"datasets":[182],"Flickr30K":[183],"MS-COCO.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}
