{"id":"https://openalex.org/W4206184212","doi":"https://doi.org/10.1109/smc52423.2021.9658799","title":"Temporally-aware Convolutional Block Attention Module for Video Text Detection","display_name":"Temporally-aware Convolutional Block Attention Module for Video Text Detection","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4206184212","doi":"https://doi.org/10.1109/smc52423.2021.9658799"},"language":"en","primary_location":{"id":"doi:10.1109/smc52423.2021.9658799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658799","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5051026262","display_name":"Masato Fujitake","orcid":"https://orcid.org/0000-0001-7702-499X"},"institutions":[{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Fujitake","raw_affiliation_strings":["The Graduate University for Advanced Studies, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Graduate University for Advanced Studies, Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063272445","display_name":"Hongpeng Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongpeng Ge","raw_affiliation_strings":["Fast Accounting, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fast Accounting, Tokyo, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4595,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76131805,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"220","last_page":"225"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9991000294685364,"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":0.9970999956130981,"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":0.8715366125106812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6799924969673157},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6529282927513123},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6511616706848145},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6258068680763245},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.6020359992980957},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5733604431152344},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4708808362483978},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43961554765701294},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4234203100204468},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.26538342237472534}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8715366125106812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6799924969673157},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6529282927513123},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6511616706848145},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6258068680763245},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.6020359992980957},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5733604431152344},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4708808362483978},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43961554765701294},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4234203100204468},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.26538342237472534},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc52423.2021.9658799","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658799","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":38,"referenced_works":["https://openalex.org/W1924770834","https://openalex.org/W1995052126","https://openalex.org/W2008806374","https://openalex.org/W2104946622","https://openalex.org/W2117539524","https://openalex.org/W2144554289","https://openalex.org/W2343052201","https://openalex.org/W2522182470","https://openalex.org/W2549139847","https://openalex.org/W2572373566","https://openalex.org/W2596297229","https://openalex.org/W2605982830","https://openalex.org/W2752782242","https://openalex.org/W2786502936","https://openalex.org/W2808206204","https://openalex.org/W2884585870","https://openalex.org/W2891048813","https://openalex.org/W2963149042","https://openalex.org/W2963163009","https://openalex.org/W2964018263","https://openalex.org/W2965615148","https://openalex.org/W2982049215","https://openalex.org/W2990524584","https://openalex.org/W2997924499","https://openalex.org/W3003938330","https://openalex.org/W3015261361","https://openalex.org/W3089933987","https://openalex.org/W3106963860","https://openalex.org/W4295246343","https://openalex.org/W4295312788","https://openalex.org/W6640212811","https://openalex.org/W6675965468","https://openalex.org/W6685670348","https://openalex.org/W6691603626","https://openalex.org/W6731801012","https://openalex.org/W6753412334","https://openalex.org/W6766978945","https://openalex.org/W6786618570"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W4293226380","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W2239445980","https://openalex.org/W2080152487","https://openalex.org/W3083152911","https://openalex.org/W3022347918"],"abstract_inverted_index":{"Scene":[0],"text":[1,111],"in":[2,13,40,45],"video":[3,16,91,112],"carries":[4],"rich":[5],"semantic":[6],"information":[7],"that":[8,121],"is":[9],"of":[10,90],"great":[11],"value":[12],"various":[14],"content-based":[15],"applications.":[17],"Existing":[18],"methods":[19,124],"have":[20,32],"been":[21],"proposed":[22,123],"to":[23,38,43,78,129],"improve":[24],"accuracy,":[25],"such":[26],"as":[27],"combining":[28],"tracking;":[29],"however,":[30],"many":[31],"complex":[33,153],"structures":[34],"and":[35,52,118],"are":[36],"difficult":[37],"execute":[39],"real-time.":[41],"Therefore,":[42],"run":[44,141],"real-time,":[46],"this":[47],"paper":[48],"proposes":[49],"a":[50,66],"simple":[51],"practical":[53],"feature":[54,76,82],"refinement":[55],"module,":[56],"named":[57],"Temporally-aware":[58],"Convolutional":[59],"Block":[60],"Attention":[61],"Module":[62],"(TCBAM),":[63],"based":[64],"on":[65,108,148],"novel":[67],"self-attention":[68],"recurrent":[69],"neural":[70],"network.":[71],"The":[72],"model":[73],"exploits":[74],"still-image-based":[75],"maps":[77,83],"refine":[79],"temporal":[80],"constant":[81],"for":[84],"better":[85,94],"capturing":[86],"widely":[87],"varied":[88],"appearances":[89],"text.":[92],"For":[93],"generalization,":[95],"we":[96],"also":[97],"provide":[98],"the":[99,109,122,126,130],"flow-based":[100],"data":[101],"augmentation":[102],"method":[103,137],"with":[104,138,145],"artificial":[105],"data.":[106],"Explements":[107],"scene":[110],"datasets":[113],"including":[114],"ICDAR2013":[115],"Video,":[116],"Minetto,":[117],"RoadText-1K":[119],"demonstrate":[120],"perform":[125],"competitive":[127],"accuracy":[128],"state-of-the-art":[131],"models":[132],"within":[133],"real-time":[134],"running.":[135],"Our":[136],"ResNext-50":[139],"can":[140],"at":[142],"17":[143],"FPS":[144],"73.11":[146],"F-score":[147],"ICDAR":[149],"2013":[150],"Video":[151],"without":[152],"tracking":[154],"methods.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}