{"id":"https://openalex.org/W4367146219","doi":"https://doi.org/10.1109/icmre56789.2023.10106583","title":"Similarity Contrastive Capsule Transformation for Image-Text Matching","display_name":"Similarity Contrastive Capsule Transformation for Image-Text Matching","publication_year":2023,"publication_date":"2023-02-10","ids":{"openalex":"https://openalex.org/W4367146219","doi":"https://doi.org/10.1109/icmre56789.2023.10106583"},"language":"en","primary_location":{"id":"doi:10.1109/icmre56789.2023.10106583","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmre56789.2023.10106583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 9th International Conference on Mechatronics and Robotics Engineering (ICMRE)","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/A5100392856","display_name":"Bin Zhang","orcid":"https://orcid.org/0000-0002-6286-6227"},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhang","raw_affiliation_strings":["State Grid Digital Technology Holding Co., Ltd/State Grid Xiongan Financial Technology Group Co., Ltd,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","Technology Research Institute (Artificial Intelligence Laboratory), State Grid Digital Technology Holding Co., Ltd/State Grid Xiongan Financial Technology Group Co., Ltd, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Digital Technology Holding Co., Ltd/State Grid Xiongan Financial Technology Group Co., Ltd,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","institution_ids":["https://openalex.org/I17442442"]},{"raw_affiliation_string":"Technology Research Institute (Artificial Intelligence Laboratory), State Grid Digital Technology Holding Co., Ltd/State Grid Xiongan Financial Technology Group Co., Ltd, Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101185090","display_name":"Ximin Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I17442442","display_name":"State Grid Corporation of China (China)","ror":"https://ror.org/05twwhs70","country_code":"CN","type":"company","lineage":["https://openalex.org/I17442442"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ximin Sun","raw_affiliation_strings":["State Grid Digital Technology Holding Co., Ltd/State Grid Xiongan Financial Technology Group Co., Ltd,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","Technology Research Institute (Artificial Intelligence Laboratory), State Grid Digital Technology Holding Co., Ltd/State Grid Xiongan Financial Technology Group Co., Ltd, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Grid Digital Technology Holding Co., Ltd/State Grid Xiongan Financial Technology Group Co., Ltd,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","institution_ids":["https://openalex.org/I17442442"]},{"raw_affiliation_string":"Technology Research Institute (Artificial Intelligence Laboratory), State Grid Digital Technology Holding Co., Ltd/State Grid Xiongan Financial Technology Group Co., Ltd, Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452149","display_name":"Xiaoming Li","orcid":"https://orcid.org/0000-0003-3844-9308"},"institutions":[{"id":"https://openalex.org/I4210094970","display_name":"Energy Research Institute","ror":"https://ror.org/00ndnb620","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094970","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Li","raw_affiliation_strings":["STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","Technology Research Institute (Artificial Intelligence Laboratory), STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","institution_ids":["https://openalex.org/I4210094970"]},{"raw_affiliation_string":"Technology Research Institute (Artificial Intelligence Laboratory), STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD, Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328272","display_name":"Shuai Wang","orcid":"https://orcid.org/0000-0002-1595-3619"},"institutions":[{"id":"https://openalex.org/I4210094970","display_name":"Energy Research Institute","ror":"https://ror.org/00ndnb620","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094970","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Wang","raw_affiliation_strings":["STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","Technology Research Institute (Artificial Intelligence Laboratory), STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","institution_ids":["https://openalex.org/I4210094970"]},{"raw_affiliation_string":"Technology Research Institute (Artificial Intelligence Laboratory), STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD, Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100326831","display_name":"Dan Liu","orcid":"https://orcid.org/0000-0002-2198-3910"},"institutions":[{"id":"https://openalex.org/I4210094970","display_name":"Energy Research Institute","ror":"https://ror.org/00ndnb620","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094970","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Liu","raw_affiliation_strings":["STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","Technology Research Institute (Artificial Intelligence Laboratory), STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","institution_ids":["https://openalex.org/I4210094970"]},{"raw_affiliation_string":"Technology Research Institute (Artificial Intelligence Laboratory), STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD, Tianjin, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002084063","display_name":"Jiangkai Jia","orcid":"https://orcid.org/0009-0006-1231-8974"},"institutions":[{"id":"https://openalex.org/I4210094970","display_name":"Energy Research Institute","ror":"https://ror.org/00ndnb620","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094970","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangkai Jia","raw_affiliation_strings":["STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","Technology Research Institute (Artificial Intelligence Laboratory), STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD,Technology Research Institute (Artificial Intelligence Laboratory),Tianjin,China","institution_ids":["https://openalex.org/I4210094970"]},{"raw_affiliation_string":"Technology Research Institute (Artificial Intelligence Laboratory), STATE GRID ECOMMERCE TECHNOLOGY CO.,LTD, Tianjin, China","institution_ids":[]}]}],"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":0.03358416,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":null,"first_page":"84","last_page":"85"},"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":0.998199999332428,"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":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.7257251143455505},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7213277816772461},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5458389520645142},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5280025005340576},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5075150728225708},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4677541255950928},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4658210277557373},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4463460147380829},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4424033463001251},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.43285173177719116},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4265047013759613},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.4233323037624359},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.42047619819641113},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1701170802116394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257251143455505},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7213277816772461},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5458389520645142},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5280025005340576},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5075150728225708},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4677541255950928},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4658210277557373},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4463460147380829},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4424033463001251},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.43285173177719116},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4265047013759613},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4233323037624359},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.42047619819641113},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1701170802116394},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icmre56789.2023.10106583","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icmre56789.2023.10106583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 9th International Conference on Mechatronics and Robotics Engineering (ICMRE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W854541894","https://openalex.org/W1527575280","https://openalex.org/W1773149199","https://openalex.org/W1811254738","https://openalex.org/W1861492603","https://openalex.org/W1905882502","https://openalex.org/W2112912048","https://openalex.org/W2131774270","https://openalex.org/W2277195237","https://openalex.org/W2546696630","https://openalex.org/W2606473278","https://openalex.org/W2745461083","https://openalex.org/W2774267535","https://openalex.org/W2778100917","https://openalex.org/W2785994986","https://openalex.org/W2797472209","https://openalex.org/W2803218650","https://openalex.org/W2894786240","https://openalex.org/W2896442399","https://openalex.org/W2914306086","https://openalex.org/W2956018683","https://openalex.org/W2962964995","https://openalex.org/W2963389687","https://openalex.org/W2963467339","https://openalex.org/W2963703618","https://openalex.org/W2963966654","https://openalex.org/W2964120214","https://openalex.org/W2964228567","https://openalex.org/W2985951359","https://openalex.org/W2988823324","https://openalex.org/W2990571534","https://openalex.org/W3007731621","https://openalex.org/W3034804856","https://openalex.org/W3035454331","https://openalex.org/W3035605030","https://openalex.org/W3118694826","https://openalex.org/W3159131359","https://openalex.org/W4295238618","https://openalex.org/W4297805688","https://openalex.org/W4313178921","https://openalex.org/W6623517193","https://openalex.org/W6631516269","https://openalex.org/W6638742206","https://openalex.org/W6639102338","https://openalex.org/W6676647902","https://openalex.org/W6743446608","https://openalex.org/W6747225742","https://openalex.org/W6748053814","https://openalex.org/W6750207810","https://openalex.org/W6751339499","https://openalex.org/W6751575020","https://openalex.org/W6751741970","https://openalex.org/W6767651371","https://openalex.org/W6787902397"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2054685365","https://openalex.org/W2988126442","https://openalex.org/W2272354214","https://openalex.org/W2252959236","https://openalex.org/W2044769131","https://openalex.org/W2359293891"],"abstract_inverted_index":{"Image-text":[0],"matching":[1],"plays":[2],"a":[3,14,61,101],"critical":[4],"role":[5],"in":[6],"bridging":[7],"the":[8,41,49,71,85],"vision":[9],"and":[10,31,38,54,91,112],"language,":[11],"which":[12,114],"attracts":[13],"lot":[15],"of":[16,105],"attention.":[17],"Most":[18],"prior":[19],"works":[20],"are":[21],"devoted":[22],"to":[23,47,69,83],"making":[24],"progress":[25],"through":[26,80],"global":[27],"alignment":[28,35],"between":[29,36,52,87],"image":[30,53],"text":[32],"or":[33],"local":[34],"words":[37],"regions.":[39],"However,":[40],"scalar-based":[42],"score":[43,89,93],"is":[44],"not":[45],"sufficient":[46],"infer":[48,70],"complex":[50],"relationship":[51,86],"text.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,78],"propose":[60],"novel":[62],"Similarity":[63],"Contrastive":[64],"Capsule":[65],"Transformation":[66],"(SCCT)":[67],"network":[68,82],"image-text":[72],"similarity":[73],"with":[74,100],"capsule":[75,81],"clustering.":[76],"Specifically,":[77],"can":[79],"encode":[84],"word-region":[88],"vector":[90],"phrase-region":[92],"vector,":[94],"then":[95],"get":[96],"more":[97],"accurate":[98],"predictions":[99],"dynamically":[102],"changing":[103],"number":[104],"capsules.":[106],"We":[107],"conduct":[108],"experiments":[109],"on":[110],"Flickr30K":[111],"MSCOCO,":[113],"shows":[115],"our":[116],"superiority":[117],"over":[118],"state-of-the-arts":[119],"methods.":[120]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
