{"id":"https://openalex.org/W4392159253","doi":"https://doi.org/10.1109/globecom54140.2023.10436782","title":"IMG2InChI: Extracting Molecular Big Data from Chemical Images Using Transformer Models","display_name":"IMG2InChI: Extracting Molecular Big Data from Chemical Images Using Transformer Models","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4392159253","doi":"https://doi.org/10.1109/globecom54140.2023.10436782"},"language":"en","primary_location":{"id":"doi:10.1109/globecom54140.2023.10436782","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/globecom54140.2023.10436782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2023 - 2023 IEEE Global Communications Conference","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/A5064729482","display_name":"Zhenyu Wu","orcid":"https://orcid.org/0000-0002-7183-6943"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyu Wu","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, School of Internet of Things,Nanjing,China","Nanjing University of Posts and Telecommunications, School of Internet of Things, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, School of Internet of Things,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, School of Internet of Things, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062475345","display_name":"Zhenyuan Zhang","orcid":"https://orcid.org/0000-0003-3356-0111"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhenyuan Zhang","raw_affiliation_strings":["Boston University, Metropolitan College,Boston,United States","Boston University, Metropolitan College, Boston, United States"],"affiliations":[{"raw_affiliation_string":"Boston University, Metropolitan College,Boston,United States","institution_ids":["https://openalex.org/I111088046"]},{"raw_affiliation_string":"Boston University, Metropolitan College, Boston, United States","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102621894","display_name":"Zhiyang Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyang Ding","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications, School of Internet of Thing,Nanjing,China","Nanjing University of Posts and Telecommunications, School of Internet of Thing, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, School of Internet of Thing,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications, School of Internet of Thing, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076776322","display_name":"Joel J. P. C. Rodrigues","orcid":"https://orcid.org/0000-0001-8657-3800"},"institutions":[{"id":"https://openalex.org/I4210162190","display_name":"China University of Petroleum, East China","ror":"https://ror.org/05gbn2817","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210162190"]},{"id":"https://openalex.org/I4210120471","display_name":"Instituto de Telecomunica\u00e7\u00f5es","ror":"https://ror.org/02ht4fk33","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I4210120471"]}],"countries":["CN","PT"],"is_corresponding":false,"raw_author_name":"Joel J. P. C. Rodrigues","raw_affiliation_strings":["Instituto de Telecomunicações,Covilhã,Portugal","China University of Petroleum (East China), College of Computer Science and Technology, Qingdao, China"],"affiliations":[{"raw_affiliation_string":"Instituto de Telecomunicações,Covilhã,Portugal","institution_ids":["https://openalex.org/I4210120471"]},{"raw_affiliation_string":"China University of Petroleum (East China), College of Computer Science and Technology, Qingdao, China","institution_ids":["https://openalex.org/I4210162190"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064729482"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13891898,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"308","last_page":"313"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.9589999914169312,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9440000057220459,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6397984623908997},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5294311046600342},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.512647807598114},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4487794041633606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4301905930042267},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35287725925445557},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2718944549560547},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.11043936014175415},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10952809453010559},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10605376958847046},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.08691519498825073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6397984623908997},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5294311046600342},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.512647807598114},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4487794041633606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4301905930042267},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35287725925445557},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2718944549560547},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.11043936014175415},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10952809453010559},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10605376958847046},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.08691519498825073}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom54140.2023.10436782","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/globecom54140.2023.10436782","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2023 - 2023 IEEE Global Communications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1895577753","https://openalex.org/W1966456689","https://openalex.org/W2119289922","https://openalex.org/W2130942839","https://openalex.org/W2524455268","https://openalex.org/W2738029666","https://openalex.org/W2756953478","https://openalex.org/W2883583109","https://openalex.org/W2884430236","https://openalex.org/W2963734039","https://openalex.org/W2964153283","https://openalex.org/W2990818246","https://openalex.org/W3007750971","https://openalex.org/W3034971973","https://openalex.org/W3094502228","https://openalex.org/W3097598035","https://openalex.org/W3102138045","https://openalex.org/W3103383152","https://openalex.org/W3107503524","https://openalex.org/W3124149278","https://openalex.org/W3133696297","https://openalex.org/W3159124846","https://openalex.org/W3159789740","https://openalex.org/W3198473709","https://openalex.org/W4206029367","https://openalex.org/W4297730588","https://openalex.org/W4385245566","https://openalex.org/W6679436768","https://openalex.org/W6739419154","https://openalex.org/W6789705400","https://openalex.org/W6790690058","https://openalex.org/W6794728252","https://openalex.org/W6801670973"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W2910064364","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Machine":[0],"learning":[1,121],"methods":[2,123],"are":[3,101],"extensively":[4],"used":[5,88],"to":[6,51,89],"develop":[7],"new":[8],"drugs":[9],"and":[10,12,68,73,126,179],"materials,":[11],"molecular":[13,39,53,71,78,92,99,170],"big":[14,40],"data":[15,54,134],"plays":[16],"a":[17,83,173],"vital":[18],"role":[19],"in":[20,29,152,172],"this":[21,81],"process.":[22],"A":[23],"large":[24],"amount":[25],"of":[26,38,65,70,76,143,156],"chemical":[27,180],"molecules":[28],"documents":[30],"should":[31,61],"be":[32,62,147],"well":[33],"utilized":[34],"for":[35],"the":[36,58,66,74,97,115,133,141,144,154,160,165],"construction":[37],"data.":[41],"Although":[42],"optical":[43],"character":[44],"recognition":[45,59],"technology":[46],"has":[47],"been":[48],"widely":[49],"applied":[50],"extract":[52,91,169],"from":[55,94],"scanned":[56,77],"images,":[57],"accuracy":[60],"improved":[63],"because":[64],"complexity":[67],"sparsity":[69],"structure":[72],"fuzziness":[75],"images.":[79,95],"In":[80],"paper,":[82],"novel":[84],"Transformer-based":[85],"model":[86,145],"is":[87,137,150],"automatically":[90],"features":[93,100,171],"Furthermore,":[96],"extracted":[98],"translated":[102],"into":[103],"InChI":[104],"descriptors":[105],"by":[106],"another":[107],"Transformer":[108],"model.":[109],"The":[110],"experimental":[111],"results":[112,161],"suggest":[113],"that":[114,140,164],"proposed":[116,166],"method":[117,167],"outperforms":[118],"other":[119],"deep":[120],"based":[122],"including":[124],"ResNet":[125],"LSTM":[127],"(Long":[128],"Short":[129],"Term":[130],"Memory).":[131],"Moreover,":[132],"extraction":[135],"process":[136],"visualized":[138],"so":[139],"interpretability":[142],"could":[146,168],"guaranteed.":[148],"This":[149],"significant":[151],"understanding":[153],"mechanism":[155],"molecule":[157],"representation.":[158],"Meanwhile,":[159],"also":[162],"demonstrate":[163],"fine":[174],"granularity,":[175],"such":[176],"as":[177],"atoms":[178],"bonds.":[181]},"counts_by_year":[],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}