{"id":"https://openalex.org/W4415539868","doi":"https://doi.org/10.1145/3746027.3755101","title":"G2LFormer: Global-to-Local Query Enhancement for Robust Table Structure Recognition","display_name":"G2LFormer: Global-to-Local Query Enhancement for Robust Table Structure Recognition","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539868","doi":"https://doi.org/10.1145/3746027.3755101"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd 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/A5055332880","display_name":"Huaqian Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haosheng Cai","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078014585","display_name":"Yang Xue","orcid":"https://orcid.org/0000-0002-1947-4957"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Xue","raw_affiliation_strings":["South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055332880"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29872741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"305","last_page":"314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9891999959945679,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9836000204086304,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/minimum-bounding-box","display_name":"Minimum bounding box","score":0.640999972820282},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5430999994277954},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.5220999717712402},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.48500001430511475},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.48260000348091125},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4339999854564667},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.41609999537467957},{"id":"https://openalex.org/keywords/sargable","display_name":"Sargable","score":0.3695000112056732},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36390000581741333}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733299970626831},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.640999972820282},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5430999994277954},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49239999055862427},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.48500001430511475},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4339999854564667},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.41609999537467957},{"id":"https://openalex.org/C192939062","wikidata":"https://www.wikidata.org/wiki/Q104840822","display_name":"Sargable","level":4,"score":0.3695000112056732},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36719998717308044},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C24028149","wikidata":"https://www.wikidata.org/wiki/Q7094056","display_name":"Online aggregation","level":5,"score":0.36070001125335693},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.34700000286102295},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C118689300","wikidata":"https://www.wikidata.org/wiki/Q7978614","display_name":"Web query classification","level":4,"score":0.28600001335144043},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.27549999952316284},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26080000400543213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755101","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3755101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5652283461","display_name":null,"funder_award_id":"grant no.61771199","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2962766617","https://openalex.org/W2963677766","https://openalex.org/W3003496674","https://openalex.org/W3003514020","https://openalex.org/W3003953860","https://openalex.org/W3118722740","https://openalex.org/W3120043490","https://openalex.org/W3180751782","https://openalex.org/W3207083256","https://openalex.org/W3217518891","https://openalex.org/W4214693170","https://openalex.org/W4225829029","https://openalex.org/W4226189435","https://openalex.org/W4304013646","https://openalex.org/W4304098321","https://openalex.org/W4321615127","https://openalex.org/W4387969511","https://openalex.org/W4389179984","https://openalex.org/W4390886488","https://openalex.org/W4404781552"],"related_works":[],"abstract_inverted_index":{"Table":[0],"structure":[1,31],"recognition":[2],"(TSR),":[3],"the":[4,35,92,148],"task":[5],"of":[6,151],"extracting":[7],"logical":[8,36],"and":[9,48,54,87,97,126,162],"physical":[10,30],"structures":[11],"from":[12,45],"table":[13],"images,":[14],"is":[15],"critical":[16],"for":[17,129],"document":[18],"understanding.":[19],"Current":[20],"end-to-end":[21],"image-to-text":[22],"methods":[23],"typically":[24],"employ":[25],"a":[26,65,71,79,104,110],"top-down":[27],"strategy":[28],"where":[29],"prediction":[32,99],"depends":[33],"on":[34,137],"decoder's":[37],"output":[38],"sequence.":[39],"However,":[40],"this":[41,60],"process":[42],"often":[43],"suffers":[44],"training":[46],"instability":[47],"misalignment":[49],"between":[50],"predicted":[51],"bounding":[52,132],"boxes":[53],"ground-truth":[55],"cell":[56,121],"positions.":[57],"To":[58],"address":[59],"issue,":[61],"we":[62,102],"propose":[63],"G2LFormer,":[64],"novel":[66],"transformer-based":[67],"framework":[68],"that":[69,108],"employs":[70],"''Global-to-Local''":[72],"query":[73,94,117],"enhancement":[74],"strategy.":[75],"Specifically,":[76],"G2LFormer":[77],"introduces":[78],"Vision-guided":[80],"Query":[81],"Enhancer":[82],"to":[83,114],"integrate":[84],"both":[85],"textual":[86],"visual":[88],"modalities,":[89],"significantly":[90],"improving":[91],"overall":[93],"representation":[95],"capability":[96],"boosting":[98],"accuracy.":[100],"Additionally,":[101],"design":[103],"Multi-scale":[105],"Manhattan":[106],"Vision-guider":[107],"leverages":[109],"spatial":[111],"attenuation":[112],"matrix":[113],"guide":[115],"each":[116,152],"towards":[118],"its":[119],"corresponding":[120],"location,":[122],"effectively":[123],"balancing":[124],"local":[125],"global":[127],"information":[128],"more":[130],"precise":[131],"box":[133],"generation.":[134],"Extensive":[135],"experiments":[136],"benchmark":[138],"datasets":[139],"demonstrate":[140],"G2LFormer's":[141],"superior":[142],"performance,":[143],"while":[144],"ablation":[145],"studies":[146],"confirming":[147],"significant":[149],"contribution":[150],"proposed":[153],"module":[154],"in":[155],"achieving":[156],"state-of-the-art":[157],"results.":[158],"The":[159],"source":[160],"code":[161],"model":[163],"have":[164],"been":[165],"released":[166],"at:":[167],"https://github.com/Hzbupahaozi/G2LFormer.":[168]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-25T00:00:00"}