{"id":"https://openalex.org/W4413156398","doi":"https://doi.org/10.1109/cvpr52734.2025.01352","title":"MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures","display_name":"MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413156398","doi":"https://doi.org/10.1109/cvpr52734.2025.01352"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.01352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.16096","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005557687","display_name":"Lucas Morin","orcid":"https://orcid.org/0000-0002-5829-5118"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lucas Morin","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037624425","display_name":"Val\u00e9ry Weber","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Val\u00e9ry Weber","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088090169","display_name":"Ahmed Nassar","orcid":"https://orcid.org/0000-0001-8047-0069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ahmed Nassar","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000851812","display_name":"Gerhard Ingmar Meijer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gerhard Ingmar Meijer","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105530582","display_name":"Luc Van Gool","orcid":null},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Luc Van Gool","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074728263","display_name":"Yawei Li","orcid":"https://orcid.org/0000-0003-0065-4824"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Yawei Li","raw_affiliation_strings":["ETH Zurich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ETH Zurich","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024778597","display_name":"Peter Staar","orcid":"https://orcid.org/0000-0002-8088-0823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Staar","raw_affiliation_strings":["IBM Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5005557687"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0724,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88401817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"14505","last_page":"14515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9973999857902527,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9973999857902527,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9922999739646912,"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"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9789000153541565,"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":0.757134199142456},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6092878580093384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5749551057815552},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4106748104095459},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0991620123386383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.757134199142456},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6092878580093384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5749551057815552},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4106748104095459},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0991620123386383},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cvpr52734.2025.01352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.01352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.16096","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16096","pdf_url":"https://arxiv.org/pdf/2503.16096","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.16096","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16096","pdf_url":"https://arxiv.org/pdf/2503.16096","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1508604947","https://openalex.org/W1975147762","https://openalex.org/W2013896592","https://openalex.org/W2021662118","https://openalex.org/W2026800167","https://openalex.org/W2031671513","https://openalex.org/W2032330078","https://openalex.org/W2051810242","https://openalex.org/W2060576972","https://openalex.org/W2136794542","https://openalex.org/W2523785361","https://openalex.org/W2622236128","https://openalex.org/W2800079696","https://openalex.org/W2899070097","https://openalex.org/W2970374239","https://openalex.org/W3013318641","https://openalex.org/W3130247384","https://openalex.org/W4206029367","https://openalex.org/W4285982393","https://openalex.org/W4288089799","https://openalex.org/W4304013646","https://openalex.org/W4306640168","https://openalex.org/W4312233877","https://openalex.org/W4353112191","https://openalex.org/W4366551372","https://openalex.org/W4386001223","https://openalex.org/W4386065837","https://openalex.org/W4388819251","https://openalex.org/W4389519972","https://openalex.org/W4390872067","https://openalex.org/W4392931906","https://openalex.org/W4393161306","https://openalex.org/W4394740965","https://openalex.org/W4400177400","https://openalex.org/W4400876815","https://openalex.org/W4401256332","https://openalex.org/W4402778052","https://openalex.org/W4402950921","https://openalex.org/W4402955109","https://openalex.org/W4404782234","https://openalex.org/W4405546127","https://openalex.org/W4408196005","https://openalex.org/W4411112899"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"The":[0],"automated":[1],"analysis":[2],"of":[3,50,119,135,151,163],"chemical":[4,25,51],"literature":[5],"holds":[6],"promise":[7],"to":[8,65,112,167],"accelerate":[9],"discovery":[10],"in":[11,46,83,187],"fields":[12],"such":[13],"as":[14],"material":[15],"science":[16],"and":[17,27,55,91,98,110,183,193],"drug":[18],"development.":[19],"In":[20,70],"particular,":[21],"search":[22],"capabilities":[23],"for":[24,39,79],"structures":[26,29,52,60,82],"Markush":[28,59,81,121,153,165],"(chemical":[30],"structure":[31,122],"templates)":[32],"within":[33],"patent":[34],"documents":[35],"are":[36,108,195],"valuable,":[37],"e.g.,":[38],"prior-art":[40],"search.":[41],"Advancements":[42],"have":[43],"been":[44],"made":[45],"the":[47,58,120,133,159],"automatic":[48],"extraction":[49],"from":[53],"text":[54],"images,":[56],"yet":[57],"remain":[61],"largely":[62],"unexplored":[63],"due":[64],"their":[66],"complex":[67],"multi-modal":[68],"nature.":[69],"this":[71,171],"work,":[72],"we":[73,139,156],"present":[74,157],"MarkushGrapher,":[75],"a":[76,95,115,125,141,148],"multimodal":[77],"approach":[78,179],"recognizing":[80],"documents.":[84],"Our":[85],"method":[86],"jointly":[87],"encodes":[88],"text,":[89],"image,":[90],"layout":[92],"information":[93],"through":[94],"Vision-Text-Layout":[96],"encoder":[97],"an":[99],"Optical":[100],"Chemical":[101],"Structure":[102],"Recognition":[103],"vision":[104],"encoder.":[105],"These":[106],"representations":[107],"merged":[109],"used":[111],"autoregressively":[113],"generate":[114],"sequential":[116],"graph":[117],"representation":[118],"along":[123],"with":[124],"table":[126],"defining":[127],"its":[128],"variable":[129],"groups.":[130],"To":[131],"overcome":[132],"lack":[134],"real-world":[136,164],"training":[137],"data,":[138],"propose":[140],"synthetic":[142],"data":[143],"generation":[144],"pipeline":[145],"that":[146,177],"produces":[147],"wide":[149],"range":[150],"realistic":[152],"structures.":[154],"Additionally,":[155],"M2S,":[158],"first":[160],"annotated":[161],"benchmark":[162],"structures,":[166],"advance":[168],"research":[169],"on":[170],"challenging":[172],"task.":[173],"Extensive":[174],"experiments":[175],"demonstrate":[176],"our":[178],"outperforms":[180],"state-of-the-art":[181],"chemistry-specific":[182],"general-purpose":[184],"vision-language":[185],"models":[186],"most":[188],"evaluation":[189],"settings.":[190],"Code,":[191],"models,":[192],"datasets":[194],"available<sup":[196],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}