{"id":"https://openalex.org/W4304092345","doi":"https://doi.org/10.1145/3503161.3548223","title":"Improving Fusion of Region Features and Grid Features via Two-Step Interaction for Image-Text Retrieval","display_name":"Improving Fusion of Region Features and Grid Features via Two-Step Interaction for Image-Text Retrieval","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304092345","doi":"https://doi.org/10.1145/3503161.3548223"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548223","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548223","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/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":true,"raw_author_name":"Dongqing Wu","raw_affiliation_strings":["Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338278","display_name":"Huihui Li","orcid":"https://orcid.org/0000-0003-1302-0580"},"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":["Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042976220","display_name":"Cang Gu","orcid":"https://orcid.org/0000-0003-4427-3652"},"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":["Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","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":["Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100338895","display_name":"Hang Liu","orcid":"https://orcid.org/0000-0001-7948-4236"},"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":["Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083360832"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.5397,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.75188935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5055","last_page":"5064"},"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":0.9997000098228455,"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":0.9973000288009644,"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":0.827126145362854},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.7032710909843445},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6637176871299744},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5483390688896179},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5303871035575867},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.5115929245948792},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.49375709891319275},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4563981890678406},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4128412902355194},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4060801863670349},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3580127954483032},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.14206025004386902}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.827126145362854},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.7032710909843445},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6637176871299744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5483390688896179},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5303871035575867},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.5115929245948792},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.49375709891319275},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4563981890678406},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4128412902355194},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4060801863670349},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3580127954483032},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.14206025004386902},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3548223","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548223","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1947481528","https://openalex.org/W2117539524","https://openalex.org/W2185175083","https://openalex.org/W2194775991","https://openalex.org/W2549139847","https://openalex.org/W2745461083","https://openalex.org/W2778100917","https://openalex.org/W2900953995","https://openalex.org/W2962964995","https://openalex.org/W2964120214","https://openalex.org/W2979304729","https://openalex.org/W2981448908","https://openalex.org/W2981586349","https://openalex.org/W2982078236","https://openalex.org/W2988823324","https://openalex.org/W2990571534","https://openalex.org/W2994818707","https://openalex.org/W2996478685","https://openalex.org/W2997525715","https://openalex.org/W2998215884","https://openalex.org/W3033697199","https://openalex.org/W3034305926","https://openalex.org/W3035454331","https://openalex.org/W3035497460","https://openalex.org/W3035552787","https://openalex.org/W3035588244","https://openalex.org/W3035605030","https://openalex.org/W3092820619","https://openalex.org/W3094172275","https://openalex.org/W3106925514","https://openalex.org/W3110042533","https://openalex.org/W3118694826","https://openalex.org/W3153232703","https://openalex.org/W3154688463","https://openalex.org/W3155230099","https://openalex.org/W3167939936","https://openalex.org/W3169179648","https://openalex.org/W3174377922","https://openalex.org/W3175888430","https://openalex.org/W3189718596","https://openalex.org/W3197809352","https://openalex.org/W3198064418","https://openalex.org/W3206477365","https://openalex.org/W3207608362","https://openalex.org/W4210894218","https://openalex.org/W4213348104","https://openalex.org/W6600140277"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W3015684221"],"abstract_inverted_index":{"In":[0,64,135,184],"recent":[1],"years,":[2],"region":[3,41,56,75,111,153,179,197],"features":[4,42,57,76,79,112,115,154,180,198],"extracted":[5],"from":[6],"object":[7],"detection":[8],"networks":[9],"have":[10],"been":[11],"widely":[12],"used":[13],"in":[14,37,49,96],"the":[15,40,45,50,59,74,97,123,126,129,136,149,175,195,217,221],"image-text":[16,93,224],"retrieval":[17,225],"task.":[18],"However,":[19],"they":[20],"lack":[21],"rich":[22],"background":[23],"and":[24,77,113,155,158,181,199,210,219],"contextual":[25],"information,":[26],"which":[27,72,146],"makes":[28],"it":[29],"difficult":[30],"to":[31,192,226],"match":[32],"words":[33],"describing":[34],"global":[35],"concepts":[36],"sentences.":[38],"Meanwhile,":[39],"also":[43],"lose":[44],"details":[46],"of":[47,55,61,164,178,223],"objects":[48],"image.":[51],"Fortunately,":[52],"these":[53,167],"disadvantages":[54],"are":[58,116],"advantages":[60,177],"grid":[62,78,114,156,182,200],"features.":[63,165,183,201],"this":[65],"paper,":[66],"we":[67,139,186],"propose":[68,140,187],"a":[69,81,87,100,141,188,227],"novel":[70],"framework,":[71],"fuses":[73,161],"through":[80],"two-step":[82],"interaction":[83],"strategy,":[84],"thus":[85],"extracting":[86],"more":[88],"comprehensive":[89],"image":[90],"representation":[91],"for":[92],"retrieval.":[94],"Concretely,":[95],"first":[98],"step,":[99,138],"joint":[101,127],"graph":[102,119],"with":[103],"spatial":[104],"information":[105,130],"constraints":[106],"is":[107],"constructed,":[108],"where":[109],"all":[110],"represented":[117],"as":[118],"nodes.":[120],"By":[121],"modeling":[122],"relationships":[124],"using":[125],"graph,":[128],"can":[131,172],"be":[132],"passed":[133],"edge-wise.":[134],"second":[137],"Cross-attention":[142],"Gated":[143],"Fusion":[144],"module,":[145],"further":[147],"explores":[148],"complex":[150],"interactions":[151],"between":[152],"features,":[157],"then":[159],"adaptively":[160],"different":[162],"types":[163],"With":[166],"two":[168,205],"steps,":[169],"our":[170,214],"model":[171,215],"fully":[173],"realize":[174],"complementary":[176],"addition,":[185],"Multi-Attention":[189],"Pooling":[190],"module":[191],"better":[193],"aggregate":[194],"fused":[196],"Extensive":[202],"experiments":[203],"on":[204],"public":[206],"datasets,":[207],"including":[208],"Flickr30K":[209],"MS-COCO,":[211],"demonstrate":[212],"that":[213],"achieves":[216],"state-of-the-art":[218],"pushes":[220],"performance":[222],"new":[228],"height.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}