{"id":"https://openalex.org/W4404570676","doi":"https://doi.org/10.1109/iccv51701.2025.02274","title":"MolParser: End-to-End Visual Recognition of Molecule Structures in the Wild","display_name":"MolParser: End-to-End Visual Recognition of Molecule Structures in the Wild","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4404570676","doi":"https://doi.org/10.1109/iccv51701.2025.02274"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.02274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.11098","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010754242","display_name":"Xi Fang","orcid":"https://orcid.org/0000-0002-3783-2041"},"institutions":[{"id":"https://openalex.org/I4210144013","display_name":"SP Technology (South Korea)","ror":"https://ror.org/051mxsx19","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210144013"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Xi Fang","raw_affiliation_strings":["DP Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DP Technology","institution_ids":["https://openalex.org/I4210144013"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101695084","display_name":"Jiankun Wang","orcid":"https://orcid.org/0000-0001-8973-020X"},"institutions":[{"id":"https://openalex.org/I4210144013","display_name":"SP Technology (South Korea)","ror":"https://ror.org/051mxsx19","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210144013"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jiankun Wang","raw_affiliation_strings":["DP Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DP Technology","institution_ids":["https://openalex.org/I4210144013"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102245433","display_name":"Xiaochen Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144013","display_name":"SP Technology (South Korea)","ror":"https://ror.org/051mxsx19","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210144013"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Xiaochen Cai","raw_affiliation_strings":["DP Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DP Technology","institution_ids":["https://openalex.org/I4210144013"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043492733","display_name":"S C Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144013","display_name":"SP Technology (South Korea)","ror":"https://ror.org/051mxsx19","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210144013"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shangqian Che","raw_affiliation_strings":["DP Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DP Technology","institution_ids":["https://openalex.org/I4210144013"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106406220","display_name":"Shuwen Yang","orcid":"https://orcid.org/0009-0003-5517-4024"},"institutions":[{"id":"https://openalex.org/I4210144013","display_name":"SP Technology (South Korea)","ror":"https://ror.org/051mxsx19","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210144013"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shuwen Yang","raw_affiliation_strings":["DP Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DP Technology","institution_ids":["https://openalex.org/I4210144013"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoyi Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144013","display_name":"SP Technology (South Korea)","ror":"https://ror.org/051mxsx19","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210144013"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Haoyi Tao","raw_affiliation_strings":["DP Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DP Technology","institution_ids":["https://openalex.org/I4210144013"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Nan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144013","display_name":"SP Technology (South Korea)","ror":"https://ror.org/051mxsx19","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210144013"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nan Wang","raw_affiliation_strings":["DP Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DP Technology","institution_ids":["https://openalex.org/I4210144013"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lin Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144013","display_name":"SP Technology (South Korea)","ror":"https://ror.org/051mxsx19","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210144013"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Lin Yao","raw_affiliation_strings":["DP Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DP Technology","institution_ids":["https://openalex.org/I4210144013"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030506407","display_name":"Linfeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210144013","display_name":"SP Technology (South Korea)","ror":"https://ror.org/051mxsx19","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210144013"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Linfeng Zhang","raw_affiliation_strings":["DP Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DP Technology","institution_ids":["https://openalex.org/I4210144013"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061200287","display_name":"Guolin Ke","orcid":"https://orcid.org/0000-0002-1227-7221"},"institutions":[{"id":"https://openalex.org/I4210144013","display_name":"SP Technology (South Korea)","ror":"https://ror.org/051mxsx19","country_code":"KR","type":"company","lineage":["https://openalex.org/I4210144013"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Guolin Ke","raw_affiliation_strings":["DP Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DP Technology","institution_ids":["https://openalex.org/I4210144013"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210144013"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"24528","last_page":"24538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.8802000284194946,"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"}},"topics":[{"id":"https://openalex.org/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.8802000284194946,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.5371978878974915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3512856364250183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2257983386516571}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5371978878974915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3512856364250183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2257983386516571}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.02274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.02274","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2411.11098","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.11098","pdf_url":"https://arxiv.org/pdf/2411.11098","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.11098","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.11098","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.11098","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.11098","pdf_url":"https://arxiv.org/pdf/2411.11098","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404570676.pdf","grobid_xml":"https://content.openalex.org/works/W4404570676.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"In":[0],"recent":[1],"decades,":[2],"chemistry":[3],"publications":[4],"and":[5,26,40,72,96,159,184],"patents":[6,158],"have":[7],"increased":[8],"rapidly.":[9],"A":[10],"significant":[11],"portion":[12],"of":[13,30,45,50,56,78,140],"key":[14],"information":[15],"is":[16,49,198],"embedded":[17],"in":[18,34,60,66,201],"molecular":[19,67,129,170],"structure":[20,82],"figures,":[21],"complicating":[22],"large-scale":[23],"literature":[24],"searches":[25],"limiting":[27],"the":[28,54,76,126,163],"application":[29],"large":[31,138],"language":[32],"models":[33],"fields":[35],"such":[36],"as":[37],"biology,":[38],"chemistry,":[39],"pharmaceuticals.":[41],"The":[42,196],"automatic":[43],"extraction":[44],"precise":[46],"chemical":[47,81,99],"structures":[48,59,100],"critical":[51],"importance.":[52],"However,":[53],"presence":[55],"numerous":[57],"Markush":[58,106],"real-world":[61,102],"documents,":[62,103],"along":[63],"with":[64,190],"variations":[65],"image":[68,130,171],"quality,":[69],"drawing":[70],"styles,":[71],"noise,":[73],"significantly":[74,181],"limits":[75],"performance":[77],"existing":[79],"optical":[80],"recognition":[83],"(OCSR)":[84],"methods.":[85],"We":[86,108,166],"present":[87],"MolParser,":[88,174],"a":[89,110,137,176],"novel":[90],"end-to-end":[91,169],"OCSR":[92],"method":[93],"that":[94],"efficiently":[95],"accurately":[97],"recognizes":[98],"from":[101,156],"including":[104],"difficult":[105],"structure.":[107],"use":[109],"extended":[111],"SMILES":[112],"encoding":[113],"rule":[114],"to":[115,132,148],"annotate":[116],"our":[117,133],"training":[118,164],"dataset.":[119],"Under":[120],"this":[121],"rule,":[122],"we":[123,143],"build":[124],"MolParser-7M,":[125],"largest":[127],"annotated":[128],"dataset":[131,197],"knowledge.":[134],"While":[135],"utilizing":[136],"amount":[139],"synthetic":[141],"data,":[142,152],"employed":[144],"active":[145],"learning":[146,178],"methods":[147,186],"incorporate":[149],"substantial":[150],"in-the-wild":[151],"specifically":[153],"samples":[154],"cropped":[155],"real":[157],"scientific":[160],"literature,":[161],"into":[162],"process.":[165],"trained":[167],"an":[168],"captioning":[172],"model,":[173],"using":[175],"curriculum":[177],"approach.":[179],"MolParser":[180],"outperforms":[182],"classical":[183],"learning-based":[185],"across":[187],"most":[188],"scenarios,":[189],"potential":[191],"for":[192],"broader":[193],"downstream":[194],"applications.":[195],"publicly":[199],"available":[200],"huggingface.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
