{"id":"https://openalex.org/W4312779768","doi":"https://doi.org/10.1145/3558100.3563851","title":"A cascaded approach for page-object detection in scientific papers","display_name":"A cascaded approach for page-object detection in scientific papers","publication_year":2022,"publication_date":"2022-09-20","ids":{"openalex":"https://openalex.org/W4312779768","doi":"https://doi.org/10.1145/3558100.3563851"},"language":"en","primary_location":{"id":"doi:10.1145/3558100.3563851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3558100.3563851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM Symposium on Document Engineering","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/A5085406783","display_name":"Erika Spiteri Bailey","orcid":null},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":true,"raw_author_name":"Erika Spiteri Bailey","raw_affiliation_strings":["University of Malta, Malta"],"affiliations":[{"raw_affiliation_string":"University of Malta, Malta","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064364631","display_name":"Alexandra Bonnici","orcid":"https://orcid.org/0000-0002-6580-3424"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"Alexandra Bonnici","raw_affiliation_strings":["University of Malta, Malta"],"affiliations":[{"raw_affiliation_string":"University of Malta, Malta","institution_ids":["https://openalex.org/I197854408"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051576459","display_name":"Stefania Cristina","orcid":"https://orcid.org/0000-0003-4617-7998"},"institutions":[{"id":"https://openalex.org/I197854408","display_name":"University of Malta","ror":"https://ror.org/03a62bv60","country_code":"MT","type":"education","lineage":["https://openalex.org/I197854408"]}],"countries":["MT"],"is_corresponding":false,"raw_author_name":"Stefania Cristina","raw_affiliation_strings":["University of Malta, Malta"],"affiliations":[{"raw_affiliation_string":"University of Malta, Malta","institution_ids":["https://openalex.org/I197854408"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085406783"],"corresponding_institution_ids":["https://openalex.org/I197854408"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13166477,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T10028","display_name":"Topic Modeling","score":0.9807000160217285,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9778000116348267,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.7458035945892334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7262828350067139},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6758408546447754},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6442757844924927},{"id":"https://openalex.org/keywords/bounding-overwatch","display_name":"Bounding overwatch","score":0.6063473224639893},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.5470850467681885},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5345966219902039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.476832777261734},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4537534713745117},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3586239218711853},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3520503640174866},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3397260308265686},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33604949712753296},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3142017722129822},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09479901194572449}],"concepts":[{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.7458035945892334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7262828350067139},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6758408546447754},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6442757844924927},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.6063473224639893},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.5470850467681885},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5345966219902039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.476832777261734},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4537534713745117},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3586239218711853},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3520503640174866},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3397260308265686},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33604949712753296},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3142017722129822},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09479901194572449},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3558100.3563851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3558100.3563851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM Symposium on Document Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1981453410","https://openalex.org/W2137998699","https://openalex.org/W2444353601","https://openalex.org/W2614454874","https://openalex.org/W2752903006","https://openalex.org/W3026561280","https://openalex.org/W3088382477","https://openalex.org/W3115558689","https://openalex.org/W3178925974","https://openalex.org/W4249809465"],"related_works":["https://openalex.org/W2365264209","https://openalex.org/W962203960","https://openalex.org/W2026999166","https://openalex.org/W3166204570","https://openalex.org/W3121246613","https://openalex.org/W1599954583","https://openalex.org/W1996802783","https://openalex.org/W4321784794","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"In":[0,58],"recent":[1],"years,":[2],"Page":[3],"Object":[4],"Detection":[5],"(POD)":[6],"has":[7],"become":[8],"a":[9,17,32,85,94,101,117],"popular":[10],"document":[11,149],"understanding":[12],"task,":[13],"proving":[14],"to":[15,37,71,147,180],"be":[16],"non-trivial":[18],"task":[19],"given":[20],"the":[21,42,44,63,97,141,148,155,181,184],"potential":[22],"complexity":[23],"of":[24,28,66,88,122,172],"documents.":[25],"The":[26],"rise":[27],"neural":[29],"networks":[30],"facilitated":[31],"more":[33],"general":[34],"learning":[35],"approach":[36],"this":[38,59,164],"task.":[39],"However,":[40],"in":[41,140,151],"literature,":[43],"different":[45],"objects":[46],"such":[47],"as":[48],"formulae,":[49,76,78],"or":[50],"figures":[51],"among":[52,96],"others,":[53],"are":[54],"generally":[55],"considered":[56,188],"individually.":[57],"paper,":[60],"we":[61,92,167],"describe":[62],"joint":[64],"localisation":[65,103],"six":[67,128],"object":[68,90,129,185],"classes":[69,98,186],"relevant":[70],"scientific":[72],"papers,":[73],"namely":[74],"isolated":[75],"embedded":[77],"figures,":[79,158],"tables,":[80,159],"variables":[81,160],"and":[82,99,161],"references.":[83,162],"Through":[84],"qualitative":[86],"analysis":[87],"these":[89,152],"classes,":[91,176],"note":[93],"hierarchy":[95],"propose":[100],"new":[102,118],"approach,":[104],"using":[105],"two,":[106],"cascaded":[107],"You":[108],"Only":[109],"Look":[110],"Once":[111],"(YOLO)":[112],"networks.":[113],"We":[114],"also":[115],"present":[116],"data":[119,132,138,153,165],"set":[120,133],"consisting":[121],"labelled":[123],"bounding":[124],"boxes":[125],"for":[126,143,157,183,190],"all":[127,175],"classes.":[130],"This":[131],"combines":[134],"two":[135],"commonly":[136],"used":[137],"sets":[139,154],"literature":[142],"formulae":[144],"localisation,":[145],"adding":[146],"images":[150],"labels":[156],"Using":[163],"set,":[166],"achieve":[168],"an":[169],"average":[170],"F1-score":[171],"0.755":[173],"across":[174],"which":[177],"is":[178],"comparable":[179],"state-of-the-art":[182],"when":[187],"individually":[189],"localisation.":[191]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}