{"id":"https://openalex.org/W4408353397","doi":"https://doi.org/10.1109/icassp49660.2025.10888044","title":"Col-OLHTR: A Novel Framework for Multimodal Online Handwritten Text Recognition","display_name":"Col-OLHTR: A Novel Framework for Multimodal Online Handwritten Text Recognition","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353397","doi":"https://doi.org/10.1109/icassp49660.2025.10888044"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5056564532","display_name":"Chenyu Liu","orcid":"https://orcid.org/0009-0004-2954-8958"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyu Liu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050645517","display_name":"Jinshui Hu","orcid":"https://orcid.org/0009-0001-3017-973X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinshui Hu","raw_affiliation_strings":["iFLYTEK Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059859891","display_name":"Baocai Yin","orcid":"https://orcid.org/0000-0002-4164-6647"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baocai Yin","raw_affiliation_strings":["iFLYTEK Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076812698","display_name":"Jia Pan","orcid":"https://orcid.org/0000-0001-9003-2054"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia Pan","raw_affiliation_strings":["iFLYTEK Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085519273","display_name":"Bing Yin","orcid":"https://orcid.org/0000-0002-5890-0031"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bing Yin","raw_affiliation_strings":["iFLYTEK Research,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"iFLYTEK Research,Hefei,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066595711","display_name":"Jun Du","orcid":"https://orcid.org/0000-0002-2387-0389"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Du","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100349220","display_name":"Qingfeng Liu","orcid":"https://orcid.org/0000-0001-8857-6677"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingfeng Liu","raw_affiliation_strings":["University of Science and Technology of China,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","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"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","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/T12707","display_name":"Vehicle License Plate Recognition","score":0.9811000227928162,"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"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.964900016784668,"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":0.7972540855407715},{"id":"https://openalex.org/keywords/text-recognition","display_name":"Text recognition","score":0.7055146098136902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48392611742019653},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4827817976474762},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39876192808151245},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3624317944049835},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1417810320854187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972540855407715},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.7055146098136902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48392611742019653},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4827817976474762},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39876192808151245},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3624317944049835},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1417810320854187}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888044","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888044","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1978964824","https://openalex.org/W2064237425","https://openalex.org/W2122585011","https://openalex.org/W2123119958","https://openalex.org/W2127141656","https://openalex.org/W2152550252","https://openalex.org/W2153873029","https://openalex.org/W2156338447","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2396666837","https://openalex.org/W2530921800","https://openalex.org/W2576349048","https://openalex.org/W2578485521","https://openalex.org/W2609112450","https://openalex.org/W2787087445","https://openalex.org/W2963150697","https://openalex.org/W2963260202","https://openalex.org/W2970720335","https://openalex.org/W2972810968","https://openalex.org/W2987258871","https://openalex.org/W2989354280","https://openalex.org/W3004194266","https://openalex.org/W3004690717","https://openalex.org/W3087417110","https://openalex.org/W3146797348","https://openalex.org/W3193386897","https://openalex.org/W3196547859","https://openalex.org/W3198848843","https://openalex.org/W4210337376","https://openalex.org/W4296902001","https://openalex.org/W4385245566","https://openalex.org/W4388979610","https://openalex.org/W4392903552","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6679434410"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4312825515","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Online":[0],"Handwritten":[1],"Text":[2],"Recognition":[3],"(OLHTR)":[4],"has":[5],"gained":[6],"considerable":[7],"attention":[8],"for":[9,157],"its":[10],"diverse":[11],"range":[12],"of":[13,114,203],"applications.":[14],"Current":[15],"approaches":[16,46],"usually":[17],"treat":[18],"OLHTR":[19,96,191],"as":[20],"a":[21,27,38,93,108,115,118],"sequence":[22],"recognition":[23,42],"task,":[24],"employing":[25],"either":[26,56],"single":[28,51],"trajectory":[29,116],"or":[30,33,40,59],"image":[31],"encoder,":[32,117],"multi-stream":[34,75],"encoders,":[35,76],"combined":[36],"with":[37],"CTC":[39],"attention-based":[41,125],"decoder.":[43,126],"However,":[44],"these":[45],"face":[47],"several":[48,190],"drawbacks:":[49],"1)":[50],"encoders":[52],"typically":[53],"focus":[54],"on":[55,189],"local":[57],"trajectories":[58],"visual":[60],"regions,":[61],"lacking":[62],"the":[63,162,169,177,180,194,199],"ability":[64],"to":[65,132,154],"dynamically":[66],"capture":[67],"relevant":[68],"global":[69],"features":[70,103,136,139],"in":[71],"challenging":[72],"cases;":[73],"2)":[74],"while":[77,106,182],"more":[78],"comprehensive,":[79],"suffer":[80],"from":[81],"complex":[82],"structures":[83],"and":[84,123,140,167,174,201],"increased":[85],"inference":[86,110],"costs.":[87],"To":[88],"tackle":[89],"this,":[90],"we":[91],"propose":[92],"Collaborative":[94],"learning-based":[95],"framework,":[97],"called":[98],"Col-OLHTR,":[99],"that":[100],"learns":[101],"multimodal":[102],"during":[104],"training":[105],"maintaining":[107],"single-stream":[109],"process.":[111],"Col-OLHTR":[112],"consists":[113],"Point-to-Spatial":[119],"Alignment":[120],"(P2SA)":[121],"module,":[122],"an":[124,147],"The":[127],"P2SA":[128,158,170],"module":[129,171],"is":[130,151,172],"designed":[131],"learn":[133],"image-level":[134],"spatial":[135],"through":[137],"trajectory-encoded":[138],"2D":[141],"rotary":[142],"position":[143],"embeddings.":[144],"During":[145],"training,":[146],"additional":[148],"image-stream":[149],"encoder-decoder":[150],"collaboratively":[152],"trained":[153],"provide":[155],"supervision":[156],"features.":[159],"At":[160],"inference,":[161],"extra":[163],"streams":[164],"are":[165],"discarded,":[166],"only":[168],"used":[173],"merged":[175],"before":[176],"decoder,":[178],"simplifying":[179],"process":[181],"preserving":[183],"high":[184],"performance.":[185],"Extensive":[186],"experimental":[187],"results":[188],"benchmarks":[192],"demonstrate":[193],"state-of-the-art":[195],"(SOTA)":[196],"performance,":[197],"proving":[198],"effectiveness":[200],"robustness":[202],"our":[204],"design.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}