{"id":"https://openalex.org/W4408403226","doi":"https://doi.org/10.1145/3677389.3702534","title":"Fine-Grained, Accurate Data Generation and Multimodal Layout Analysis for Academic Papers","display_name":"Fine-Grained, Accurate Data Generation and Multimodal Layout Analysis for Academic Papers","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4408403226","doi":"https://doi.org/10.1145/3677389.3702534"},"language":"en","primary_location":{"id":"doi:10.1145/3677389.3702534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677389.3702534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"},"type":"conference-paper","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/A5086812879","display_name":"Dehao Ying","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dehao Ying","raw_affiliation_strings":["School of Information Management, Wuhan University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0009-0005-2180-4184","affiliations":[{"raw_affiliation_string":"School of Information Management, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051738938","display_name":"Fengchang Yu","orcid":"https://orcid.org/0000-0002-6503-4688"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fengchang Yu","raw_affiliation_strings":["School of Information Management, Wuhan University, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0002-6503-4688","affiliations":[{"raw_affiliation_string":"School of Information Management, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100670005","display_name":"Haihua Chen","orcid":"https://orcid.org/0000-0002-7088-9752"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haihua Chen","raw_affiliation_strings":["Department of Information Science, University of North Texas, Denton, Texas, USA"],"raw_orcid":"https://orcid.org/0000-0002-7088-9752","affiliations":[{"raw_affiliation_string":"Department of Information Science, University of North Texas, Denton, Texas, USA","institution_ids":["https://openalex.org/I123534392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113599845","display_name":"Wei Lu","orcid":"https://orcid.org/0000-0002-0929-7416"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Lu","raw_affiliation_strings":["School of Information Management, Wuhan university, Wuhan, Hubei, China"],"raw_orcid":"https://orcid.org/0000-0002-0929-7416","affiliations":[{"raw_affiliation_string":"School of Information Management, Wuhan university, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9843999743461609,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9843999743461609,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9817000031471252,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.973800003528595,"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":0.7234814167022705},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.38554275035858154},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3220350742340088}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7234814167022705},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.38554275035858154},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3220350742340088}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3677389.3702534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3677389.3702534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM/IEEE Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2135164809","https://openalex.org/W2151765755","https://openalex.org/W2565639579","https://openalex.org/W2768926640","https://openalex.org/W2786480153","https://openalex.org/W2787480186","https://openalex.org/W2798826627","https://openalex.org/W2963150697","https://openalex.org/W2964241181","https://openalex.org/W2964346820","https://openalex.org/W3003711898","https://openalex.org/W3104637907","https://openalex.org/W3105988348","https://openalex.org/W3113753692","https://openalex.org/W3176664887","https://openalex.org/W3176851559","https://openalex.org/W3200280307","https://openalex.org/W3201871940","https://openalex.org/W3214042621","https://openalex.org/W4221167941","https://openalex.org/W4304013646","https://openalex.org/W4304014014","https://openalex.org/W4390872501"],"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/W4396696052"],"abstract_inverted_index":{"Layout":[0],"analysis":[1,150,177],"of":[2,24,63,139,178,203],"academic":[3,132,147,180],"papers":[4,116,133,181],"aims":[5],"to":[6,93,121,135,183,193,214],"identify":[7],"various":[8],"components":[9,130],"within":[10,66],"unstructured":[11],"papers,":[12,112],"benefiting":[13],"researchers":[14],"in":[15,57,97,131,174],"quickly":[16],"locating":[17],"and":[18,32,48,82,100,108,129,134,157,209],"extracting":[19],"critical":[20],"information.":[21],"The":[22,187],"effectiveness":[23,202],"this":[25],"process":[26],"depends":[27],"heavily":[28],"on":[29],"the":[30,60,67,123,201,207,215],"datasets":[31,39],"models":[33,52],"used":[34],"for":[35,79],"training.":[36],"However,":[37],"existing":[38,184],"often":[40],"have":[41],"issues":[42],"with":[43,117,166],"annotation":[44],"accuracy,":[45],"granularity,":[46],"scale,":[47],"acquisition":[49],"cost.":[50],"Current":[51],"treat":[53],"each":[54],"document":[55],"image":[56],"isolation,":[58],"ignoring":[59],"position":[61,155],"information":[62,156],"a":[64,77,145,197],"page":[65,127,154],"entire":[68],"paper.":[69],"To":[70],"address":[71],"these":[72],"challenges,":[73],"we":[74,142],"propose":[75],"DLAgen,":[76],"method":[78],"rapidly,":[80],"accurately,":[81],"cost-effectively":[83],"generating":[84],"fine-grained":[85,175],"annotated":[86],"paper":[87,148],"datasets.":[88],"DLAgen":[89,170],"uses":[90],"context-free":[91],"grammar":[92],"generate":[94],"textual":[95,140],"content":[96],"LaTeX":[98],"format,":[99],"incorporates":[101],"visual":[102],"content,":[103],"such":[104],"as":[105],"images,":[106],"tables,":[107],"formulas,":[109],"from":[110,191],"real":[111,179],"thus":[113],"creating":[114],"synthetic":[115],"accurate":[118],"annotations.":[119],"Concurrently,":[120],"leverage":[122],"high":[124],"correlation":[125],"between":[126],"numbers":[128],"make":[136],"better":[137],"use":[138],"information,":[141],"introduce":[143],"MDT,":[144],"multimodal":[146],"layout":[149,176],"model":[151,208],"that":[152,163],"utilizes":[153],"correctly":[158],"ordered":[159],"text.":[160],"Experiments":[161],"show":[162],"MDT":[164],"trained":[165],"data":[167],"generated":[168],"by":[169],"achieves":[171],"higher":[172],"accuracy":[173],"compared":[182],"state-of-the-art":[185],"models.":[186],"mAP":[188],"is":[189,196],"improved":[190],"85.13":[192],"88.61,":[194],"which":[195],"4.09%":[198],"enhancement,":[199],"validating":[200],"our":[204],"approach.":[205],"Both":[206],"dataset":[210],"will":[211],"be":[212],"released":[213],"public.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}