{"id":"https://openalex.org/W3168680617","doi":"https://doi.org/10.1109/icme51207.2021.9428380","title":"Auxiliary Bi-Level Graph Representation for Cross-Modal Image-Text Retrieval","display_name":"Auxiliary Bi-Level Graph Representation for Cross-Modal Image-Text Retrieval","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3168680617","doi":"https://doi.org/10.1109/icme51207.2021.9428380","mag":"3168680617"},"language":"en","primary_location":{"id":"doi:10.1109/icme51207.2021.9428380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5064738683","display_name":"Xian Zhong","orcid":"https://orcid.org/0000-0002-5242-0467"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xian Zhong","raw_affiliation_strings":["Wuhan University of Technology,School of Computer Science and Technology","School of Computer Science and Technology, Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,School of Computer Science and Technology","institution_ids":["https://openalex.org/I196699116"]},{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024393567","display_name":"Zhengwei Yang","orcid":"https://orcid.org/0000-0002-8190-1438"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengwei Yang","raw_affiliation_strings":["Wuhan University of Technology,School of Computer Science and Technology","School of Computer Science and Technology, Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,School of Computer Science and Technology","institution_ids":["https://openalex.org/I196699116"]},{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008999954","display_name":"Mang Ye","orcid":"https://orcid.org/0000-0003-3989-7655"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mang Ye","raw_affiliation_strings":["Wuhan University,School of Computer Science","School of Computer Science, Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Computer Science","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"School of Computer Science, Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949151","display_name":"Wenxin Huang","orcid":"https://orcid.org/0000-0001-8683-7327"},"institutions":[{"id":"https://openalex.org/I75900474","display_name":"Hubei University","ror":"https://ror.org/03a60m280","country_code":"CN","type":"education","lineage":["https://openalex.org/I75900474"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenxin Huang","raw_affiliation_strings":["Hubei University,School of Computer Science and Information Engineering","School of Computer Science and Information Engineering, Hubei University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hubei University,School of Computer Science and Information Engineering","institution_ids":["https://openalex.org/I75900474"]},{"raw_affiliation_string":"School of Computer Science and Information Engineering, Hubei University","institution_ids":["https://openalex.org/I75900474"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062853168","display_name":"Jingling Yuan","orcid":"https://orcid.org/0000-0001-7924-8620"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingling Yuan","raw_affiliation_strings":["Wuhan University of Technology,School of Computer Science and Technology","School of Computer Science and Technology, Wuhan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University of Technology,School of Computer Science and Technology","institution_ids":["https://openalex.org/I196699116"]},{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051264473","display_name":"Chia\u2010Wen Lin","orcid":"https://orcid.org/0000-0002-9097-2318"},"institutions":[{"id":"https://openalex.org/I25846049","display_name":"National Tsing Hua University","ror":"https://ror.org/00zdnkx70","country_code":"TW","type":"education","lineage":["https://openalex.org/I25846049"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Wen Lin","raw_affiliation_strings":["National Tsing Hua University,Department of Electrical Engineering","Department of Electrical Engineering, National Tsing Hua University","Institute of Communications Engineering, National Tsing Hua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Tsing Hua University,Department of Electrical Engineering","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Department of Electrical Engineering, National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]},{"raw_affiliation_string":"Institute of Communications Engineering, National Tsing Hua University","institution_ids":["https://openalex.org/I25846049"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9991999864578247,"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":0.9940999746322632,"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":0.7943622469902039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5754023194313049},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5600287318229675},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5120440125465393},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.5015003681182861},{"id":"https://openalex.org/keywords/visual-word","display_name":"Visual Word","score":0.47796201705932617},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45979592204093933},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.4495491087436676},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.44443878531455994},{"id":"https://openalex.org/keywords/semantic-gap","display_name":"Semantic gap","score":0.4384259283542633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43494805693626404},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4024912118911743},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.3955903649330139},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2679115831851959},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.19106677174568176}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943622469902039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5754023194313049},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5600287318229675},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5120440125465393},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.5015003681182861},{"id":"https://openalex.org/C189391414","wikidata":"https://www.wikidata.org/wiki/Q7936579","display_name":"Visual Word","level":4,"score":0.47796201705932617},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45979592204093933},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.4495491087436676},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.44443878531455994},{"id":"https://openalex.org/C86034646","wikidata":"https://www.wikidata.org/wiki/Q474311","display_name":"Semantic gap","level":4,"score":0.4384259283542633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43494805693626404},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4024912118911743},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.3955903649330139},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2679115831851959},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.19106677174568176},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/icme51207.2021.9428380","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme51207.2021.9428380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W2077069816","https://openalex.org/W2250539671","https://openalex.org/W2277195237","https://openalex.org/W2506483933","https://openalex.org/W2750608840","https://openalex.org/W2752345995","https://openalex.org/W2774267535","https://openalex.org/W2890531016","https://openalex.org/W2896457183","https://openalex.org/W2905169750","https://openalex.org/W2962964995","https://openalex.org/W2963536419","https://openalex.org/W2964015378","https://openalex.org/W2982078236","https://openalex.org/W2996941455","https://openalex.org/W2998792609","https://openalex.org/W3010277541","https://openalex.org/W3015982325","https://openalex.org/W3033697199","https://openalex.org/W3035043893","https://openalex.org/W3035212740","https://openalex.org/W3035552787","https://openalex.org/W3047363187","https://openalex.org/W6639102338","https://openalex.org/W6725318829","https://openalex.org/W6726873649","https://openalex.org/W6747225742","https://openalex.org/W6749537441","https://openalex.org/W6754778999","https://openalex.org/W6755207826","https://openalex.org/W6771967508","https://openalex.org/W6781629741"],"related_works":["https://openalex.org/W2002918846","https://openalex.org/W1987073347","https://openalex.org/W2120663665","https://openalex.org/W2373526234","https://openalex.org/W2756529358","https://openalex.org/W1546688958","https://openalex.org/W2037415180","https://openalex.org/W3194728774","https://openalex.org/W2046589280","https://openalex.org/W1926504679"],"abstract_inverted_index":{"Image-text":[0],"retrieval":[1,158],"is":[2,23],"one":[3],"of":[4,17,41,84,152],"the":[5,15,35,39,59,64,81,85,98,107,131,150],"most":[6],"common":[7,103],"tasks":[8],"in":[9,101],"multimodal":[10],"retrieval.":[11],"It":[12,27],"suffers":[13],"from":[14],"problem":[16],"information":[18,61,65,100],"imbalance":[19],"between":[20,109,133],"modalities,":[21],"which":[22,126],"so-called":[24],"modality":[25,71],"gap.":[26],"remains":[28],"challenging":[29],"because":[30],"prior":[31],"methods":[32],"cannot":[33],"bridge":[34],"gap":[36],"reasonably.":[37,138],"With":[38],"help":[40],"scene":[42],"graph,":[43],"we":[44,88],"start":[45],"by":[46,75],"designing":[47],"an":[48],"auxiliary":[49],"bi-level":[50],"graph":[51,78,91],"representation":[52,117],"(ABGR)":[53],"pipeline":[54],"that":[55,79],"can":[56,123],"fully":[57],"mine":[58],"potential":[60],"and":[62,121,135,147],"reduce":[63],"redundancy.":[66],"By":[67],"doing":[68],"so,":[69],"each":[70],"will":[72],"be":[73,124],"represented":[74],"lexical":[76,110],"word":[77],"carries":[80],"main":[82],"content":[83],"information.":[86],"Specifically,":[87],"design":[89],"a":[90,102,113,115],"feature":[92],"enhancement":[93],"(GFE)":[94],"module":[95],"to":[96,129],"embed":[97],"graph-structured":[99],"subspace":[104],"while":[105],"exploring":[106],"relationship":[108],"words.":[111],"As":[112],"result,":[114],"better":[116],"for":[118,156],"both":[119],"image":[120],"text":[122],"obtained,":[125],"helps":[127],"us":[128],"evaluate":[130],"similarity":[132],"images":[134],"texts":[136],"more":[137],"Experimental":[139],"results":[140],"conducted":[141],"on":[142],"two":[143],"benchmark":[144],"datasets":[145],"Flickr30K":[146],"MS-COCO":[148],"demonstrate":[149],"effectiveness":[151],"our":[153],"proposed":[154],"model":[155],"cross-modal":[157],"task.":[159]},"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}