{"id":"https://openalex.org/W2970668492","doi":"https://doi.org/10.1109/icip.2019.8803529","title":"Wacnet: Word Segmentation Guided Characters Aggregation Net for Scene Text Spotting With Arbitrary Shapes","display_name":"Wacnet: Word Segmentation Guided Characters Aggregation Net for Scene Text Spotting With Arbitrary Shapes","publication_year":2019,"publication_date":"2019-08-26","ids":{"openalex":"https://openalex.org/W2970668492","doi":"https://doi.org/10.1109/icip.2019.8803529","mag":"2970668492"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2019.8803529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8803529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","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/A5101682899","display_name":"Yuting Gao","orcid":"https://orcid.org/0000-0002-4329-4091"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Gao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103055957","display_name":"Zheng Huang","orcid":"https://orcid.org/0009-0003-2994-8030"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Huang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067772383","display_name":"Yuchen Dai","orcid":"https://orcid.org/0000-0002-9710-9031"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Dai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437924","display_name":"Kai Chen","orcid":"https://orcid.org/0000-0001-6384-0355"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709308","display_name":"Jie Guo","orcid":"https://orcid.org/0000-0003-0032-9116"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Guo","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088072972","display_name":"Weidong Qiu","orcid":"https://orcid.org/0000-0001-6428-1655"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Qiu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3382","last_page":"3386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.996399998664856,"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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.8480696678161621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8196201324462891},{"id":"https://openalex.org/keywords/subnetwork","display_name":"Subnetwork","score":0.7833616733551025},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7014007568359375},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6953911781311035},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6315146088600159},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6310437917709351},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.568727433681488},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5334093570709229},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5273381471633911},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.5137590169906616},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4462079107761383},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.32142651081085205},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08582207560539246}],"concepts":[{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.8480696678161621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8196201324462891},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.7833616733551025},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7014007568359375},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6953911781311035},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6315146088600159},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6310437917709351},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.568727433681488},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5334093570709229},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5273381471633911},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.5137590169906616},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4462079107761383},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.32142651081085205},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08582207560539246},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip.2019.8803529","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8803529","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4300000071525574}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1998042868","https://openalex.org/W2008806374","https://openalex.org/W2056518953","https://openalex.org/W2194775991","https://openalex.org/W2343052201","https://openalex.org/W2519818067","https://openalex.org/W2550687635","https://openalex.org/W2565639579","https://openalex.org/W2605076167","https://openalex.org/W2605982830","https://openalex.org/W2613718673","https://openalex.org/W2766895242","https://openalex.org/W2777652944","https://openalex.org/W2784050770","https://openalex.org/W2810028092","https://openalex.org/W2875814315","https://openalex.org/W2962773189","https://openalex.org/W2962986948","https://openalex.org/W2963150697","https://openalex.org/W2963187132","https://openalex.org/W2963299604","https://openalex.org/W2964018263","https://openalex.org/W3102695566","https://openalex.org/W6620707391","https://openalex.org/W6729791593"],"related_works":["https://openalex.org/W2028814537","https://openalex.org/W1979387045","https://openalex.org/W4230966950","https://openalex.org/W209905266","https://openalex.org/W2393940967","https://openalex.org/W2418075562","https://openalex.org/W2385598138","https://openalex.org/W2346578824","https://openalex.org/W2366925922","https://openalex.org/W2159591557"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"an":[5],"end-to-end":[6],"trainable":[7],"framework":[8,22,61],"for":[9],"scene":[10],"text":[11,16],"spotting":[12],"which":[13,32],"can":[14],"handle":[15],"with":[17,107],"arbitrary":[18,108],"shapes.":[19],"The":[20,59],"proposed":[21,118],"is":[23],"called":[24],"Word":[25],"Segmentation":[26],"Guided":[27],"Characters":[28],"Aggregation":[29],"Net":[30],"(WAC-Net),":[31],"consists":[33],"of":[34,116],"a":[35],"shared":[36],"convolutional":[37],"backbone":[38],"and":[39,50,56,68,110],"two":[40,78,105],"task-specific":[41],"subnetworks.":[42],"One":[43],"subnetwork":[44],"does":[45,53],"word-level":[46],"instance-aware":[47],"segmentation":[48,99],"(WSN)":[49],"the":[51,87,111,114,117],"other":[52],"char-level":[54],"detection":[55],"recognition":[57],"(CDRN).":[58],"entire":[60],"segments":[62],"each":[63,70],"word":[64,97],"instance":[65,98],"while":[66],"detects":[67],"recognizes":[69],"character":[71],"in":[72],"one":[73],"single":[74],"forward":[75],"pass.":[76],"These":[77],"subnetworks":[79],"are":[80,91,102],"jointly":[81],"trained":[82],"by":[83,96],"multi-task":[84],"learning.":[85],"At":[86],"inference":[88],"stage,":[89],"characters":[90],"aggregated":[92],"into":[93],"words":[94],"guided":[95],"results.":[100],"Experiments":[101],"conducted":[103],"on":[104],"datasets":[106],"shapes,":[109],"results":[112],"demonstrate":[113],"effectiveness":[115],"method.":[119]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}