{"id":"https://openalex.org/W4317514677","doi":"https://doi.org/10.1109/ccis57298.2022.10016352","title":"Multimodal Co-Attention Mechanism for One-stage Visual Grounding","display_name":"Multimodal Co-Attention Mechanism for One-stage Visual Grounding","publication_year":2022,"publication_date":"2022-11-26","ids":{"openalex":"https://openalex.org/W4317514677","doi":"https://doi.org/10.1109/ccis57298.2022.10016352"},"language":"en","primary_location":{"id":"doi:10.1109/ccis57298.2022.10016352","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ccis57298.2022.10016352","pdf_url":null,"source":{"id":"https://openalex.org/S4363608348","display_name":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","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":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","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/A5101490809","display_name":"Zhihan Yu","orcid":"https://orcid.org/0009-0000-6411-9420"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihan Yu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068753064","display_name":"Mingcong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingcong Lu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China,100876"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068728736","display_name":"Ruifan Li","orcid":"https://orcid.org/0000-0002-3543-6272"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruifan Li","raw_affiliation_strings":["Beijing University of Posts and Telecommunications,Beijing,China,100876","Engineering Research Center of Information Networks, Ministry of Education, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications,Beijing,China,100876","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Engineering Research Center of Information Networks, Ministry of Education, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101490809"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.1799,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54627121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"288","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.9976999759674072,"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":0.8102445602416992},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.7176955938339233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6197558641433716},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.555040717124939},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5528016686439514},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5174163579940796},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.50387042760849},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.49048396944999695},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48191121220588684},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.47074469923973083},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.45285680890083313},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43800613284111023},{"id":"https://openalex.org/keywords/fusion-mechanism","display_name":"Fusion mechanism","score":0.4123767018318176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3916488289833069},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32557040452957153},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.26596778631210327},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.26308509707450867},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08813455700874329},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08212032914161682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8102445602416992},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.7176955938339233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6197558641433716},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.555040717124939},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5528016686439514},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5174163579940796},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.50387042760849},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.49048396944999695},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48191121220588684},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.47074469923973083},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45285680890083313},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43800613284111023},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.4123767018318176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3916488289833069},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32557040452957153},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.26596778631210327},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.26308509707450867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08813455700874329},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08212032914161682},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C103038307","wikidata":"https://www.wikidata.org/wiki/Q6556360","display_name":"Lipid bilayer fusion","level":3,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccis57298.2022.10016352","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ccis57298.2022.10016352","pdf_url":null,"source":{"id":"https://openalex.org/S4363608348","display_name":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","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":"2022 IEEE 8th International Conference on Cloud Computing and Intelligent Systems (CCIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1964073652","https://openalex.org/W2489434015","https://openalex.org/W2565639579","https://openalex.org/W2779827764","https://openalex.org/W2905571389","https://openalex.org/W2962764817","https://openalex.org/W2963109634","https://openalex.org/W2964345792","https://openalex.org/W2966683369","https://openalex.org/W2987734933","https://openalex.org/W3034772468","https://openalex.org/W3159619744","https://openalex.org/W4205685122","https://openalex.org/W4214490042","https://openalex.org/W4293518031"],"related_works":["https://openalex.org/W2016461833","https://openalex.org/W2382607599","https://openalex.org/W3197541072","https://openalex.org/W3104335588","https://openalex.org/W4322727030","https://openalex.org/W3120027188","https://openalex.org/W3131127372","https://openalex.org/W32212251","https://openalex.org/W1996616201","https://openalex.org/W4317514677"],"abstract_inverted_index":{"Visual":[0],"grounding":[1,38,118],"aims":[2],"to":[3,85,95,107],"locate":[4],"a":[5,9,14,30,35,50,139],"specific":[6],"region":[7],"in":[8,29,142],"given":[10],"image":[11],"guided":[12],"by":[13,67],"natural":[15],"language":[16],"query.":[17],"It":[18],"relies":[19],"on":[20,41,120],"the":[21,47,68,87,97,100,110,147],"alignment":[22],"of":[23,61,99,149],"visual":[24,37,150],"information":[25,89],"and":[26,54,80,129],"text":[27],"semantics":[28],"fine-grained":[31],"fashion.":[32],"We":[33,115],"propose":[34],"one-stage":[36],"model":[39,119],"based":[40],"cross-modal":[42],"feature":[43,91,144],"fusion,":[44],"which":[45],"regards":[46],"task":[48,148],"as":[49,76],"coordinate":[51],"regression":[52],"problem":[53],"implement":[55],"an":[56],"end-to-end":[57],"optimization.":[58],"The":[59],"coordinates":[60],"bounding":[62],"box":[63],"are":[64,82],"directly":[65],"predicted":[66],"fusion":[69,73,101,145],"features,":[70,102],"but":[71],"previous":[72],"methods":[74],"such":[75],"element-wise":[77],"product,":[78],"summation,":[79],"concatenation":[81],"too":[83],"simple":[84],"combine":[86],"deep":[88],"within":[90],"vectors.":[92],"In":[93],"order":[94],"improve":[96],"quality":[98],"we":[103],"incorporate":[104],"co-attention":[105,136],"mechanism":[106,137],"deeply":[108],"transform":[109],"representations":[111],"from":[112],"two":[113],"modalities.":[114],"evaluate":[116],"our":[117],"publicly":[121],"available":[122],"datasets,":[123],"including":[124],"Flickr30k":[125],"Entities,":[126],"RefCOCO,":[127],"RefCOCO+":[128],"RefCOCOg.":[130],"Quantitative":[131],"evaluation":[132],"results":[133],"show":[134],"that":[135],"plays":[138],"positive":[140],"role":[141],"multi-modal":[143],"for":[146],"grounding.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}
