{"id":"https://openalex.org/W4304015090","doi":"https://doi.org/10.1145/3503161.3548424","title":"A Tree-Based Structure-Aware Transformer Decoder for Image-To-Markup Generation","display_name":"A Tree-Based Structure-Aware Transformer Decoder for Image-To-Markup Generation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304015090","doi":"https://doi.org/10.1145/3503161.3548424"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3548424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548424","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","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/A5086460511","display_name":"Shuhan Zhong","orcid":"https://orcid.org/0000-0003-4037-4288"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shuhan Zhong","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042276200","display_name":"Sizhe Song","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sizhe Song","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029470286","display_name":"Guanyao Li","orcid":"https://orcid.org/0000-0002-3950-9360"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I4210126705","display_name":"Guangzhou Urban Planning Survey & Design Institute","ror":"https://ror.org/02crg7060","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210126705"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Guanyao Li","raw_affiliation_strings":["The Hong Kong University of Science and Technology & Guangzhou Urban Planning and Design Survey Research Institute, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology & Guangzhou Urban Planning and Design Survey Research Institute, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I4210126705","https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003418485","display_name":"S.-H. Gary Chan","orcid":"https://orcid.org/0000-0003-4207-764X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"S.-H. Gary Chan","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9438,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.83246965,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5751","last_page":"5760"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980000257492065,"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":0.9980000257492065,"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/T10028","display_name":"Topic Modeling","score":0.9865999817848206,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9855999946594238,"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/markup-language","display_name":"Markup language","score":0.873977780342102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8364745378494263},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6227479577064514},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.5233439803123474},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5114694833755493},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5048940777778625},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.491970032453537},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4603443443775177},{"id":"https://openalex.org/keywords/bit-array","display_name":"Bit array","score":0.4283202886581421},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3574613034725189},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3351706266403198},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.3015749454498291},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.19748389720916748},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1190786063671112}],"concepts":[{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.873977780342102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8364745378494263},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6227479577064514},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.5233439803123474},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5114694833755493},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5048940777778625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.491970032453537},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4603443443775177},{"id":"https://openalex.org/C150807984","wikidata":"https://www.wikidata.org/wiki/Q1992074","display_name":"Bit array","level":3,"score":0.4283202886581421},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3574613034725189},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3351706266403198},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3015749454498291},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.19748389720916748},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1190786063671112},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3503161.3548424","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3503161.3548424","pdf_url":null,"source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-125216","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2022&rft.spage=&rft.aulast=Zhong&rft.aufirst=Shuhan&rft.atitle=Tree-Based+Structure-Aware+Transformer+Decoder+for+Image-To-Markup+Generation&rft.title=Proceedings+of+the+30th+ACM+International+Conference+on+Multimedia+%28ACM+MM+2022%29","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1810641085","https://openalex.org/W1975147762","https://openalex.org/W1978799108","https://openalex.org/W1981451828","https://openalex.org/W1998768285","https://openalex.org/W2612690371","https://openalex.org/W2623860192","https://openalex.org/W2794908093","https://openalex.org/W2889404673","https://openalex.org/W2962724148","https://openalex.org/W2971351900","https://openalex.org/W2997386764","https://openalex.org/W2997847174","https://openalex.org/W3002575754","https://openalex.org/W3092396754","https://openalex.org/W3096609285","https://openalex.org/W3099452997","https://openalex.org/W3104652292","https://openalex.org/W3172275282","https://openalex.org/W3201853323","https://openalex.org/W3206430998","https://openalex.org/W4212774754","https://openalex.org/W6600018615"],"related_works":["https://openalex.org/W2372453241","https://openalex.org/W2371387875","https://openalex.org/W2531660186","https://openalex.org/W1987871343","https://openalex.org/W2064670891","https://openalex.org/W1508699539","https://openalex.org/W2025988984","https://openalex.org/W2013559555","https://openalex.org/W2030846031","https://openalex.org/W4387591332"],"abstract_inverted_index":{"Image-to-markup":[0],"generation":[1,158],"aims":[2],"at":[3],"translating":[4],"an":[5,145],"image":[6],"into":[7],"markup":[8,72,176],"(structured":[9],"language)":[10],"that":[11,106],"represents":[12],"both":[13],"the":[14,17,22,34,38,45,66,70,84,112,122,133,150,166,170,174],"contents":[15],"and":[16,89,137,160,191],"structural":[18,48,123,171],"semantics":[19],"corresponding":[20],"to":[21,32,63,81,102,119,164,185,193],"image.":[23],"Recent":[24],"encoder-decoder":[25],"based":[26],"approaches":[27],"typically":[28],"employ":[29],"string":[30,35],"decoders":[31],"model":[33,79,154],"representation":[36,68],"of":[37,69,152],"target":[39,71,134,175],"markup,":[40],"which":[41],"cannot":[42],"effectively":[43],"capture":[44],"rich":[46],"embedded":[47],"information.":[49,124],"In":[50],"this":[51],"paper,":[52],"we":[53,96],"propose":[54],"TSDNet,":[55],"a":[56,74,98],"novel":[57,99],"Tree-based":[58],"Structure-aware":[59],"Transformer":[60],"Decoder":[61],"NETwork":[62],"directly":[64,109],"generate":[65],"tree":[67,114,135],"in":[73,116,144,173,187,195],"structure-aware":[75],"manner.":[76],"Specifically,":[77],"our":[78,103,153],"learns":[80],"sequentially":[82],"predict":[83],"node":[85,90],"attributes,":[86,88],"edge":[87],"connectivities":[91],"by":[92,183],"multi-task":[93],"learning.":[94],"Meanwhile,":[95],"introduce":[97],"tree-structured":[100],"attention":[101],"decoder":[104],"such":[105],"it":[107],"can":[108,138],"operate":[110],"on":[111,128,132,155],"partial":[113],"generated":[115],"each":[117],"step":[118],"fully":[120],"exploit":[121],"TSDNet":[125],"doesn't":[126],"rely":[127],"any":[129],"prior":[130],"assumptions":[131],"structure,":[136],"be":[139],"jointly":[140],"optimized":[141],"with":[142,177],"encoders":[143],"end-to-end":[146],"fashion.":[147],"We":[148],"evaluate":[149],"performance":[151],"public":[156],"image-to-markup":[157],"datasets,":[159],"demonstrate":[161],"its":[162],"ability":[163],"learn":[165],"complicated":[167],"correlation":[168],"from":[169],"information":[172],"significant":[178],"improvement":[179],"over":[180],"state-of-the-art":[181],"methods":[182],"up":[184,192],"5.6%":[186],"mathematical":[188],"expression":[189],"recognition":[190],"35.34%":[194],"chemical":[196],"formula":[197],"recognition.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}