{"id":"https://openalex.org/W4408353439","doi":"https://doi.org/10.1109/icassp49660.2025.10889372","title":"Conditional Convolutions for End-to-End Single-Stage Video Text Detection","display_name":"Conditional Convolutions for End-to-End Single-Stage Video Text Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353439","doi":"https://doi.org/10.1109/icassp49660.2025.10889372"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889372","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":null,"display_name":"Xiaoge Song","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoge Song","raw_affiliation_strings":["Nanjing University,Department of Computer Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Department of Computer Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071986082","display_name":"Danhuai Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Danhuai Zhao","raw_affiliation_strings":["China Mobile Zijin Innovation Institute,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Zijin Innovation Institute,Nanjing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060852587","display_name":"W. J. Zhu","orcid":"https://orcid.org/0000-0003-2618-0436"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhu","raw_affiliation_strings":["China Mobile Zijin Innovation Institute,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Zijin Innovation Institute,Nanjing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049183561","display_name":"Zheng Kang","orcid":"https://orcid.org/0000-0002-1351-7311"},"institutions":[{"id":"https://openalex.org/I180662265","display_name":"China Mobile (China)","ror":"https://ror.org/05gftfe97","country_code":"CN","type":"company","lineage":["https://openalex.org/I180662265"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Zheng","raw_affiliation_strings":["China Mobile Zijin Innovation Institute,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Mobile Zijin Innovation Institute,Nanjing,China","institution_ids":["https://openalex.org/I180662265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083605614","display_name":"Tong Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I36399199","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62","country_code":"CN","type":"education","lineage":["https://openalex.org/I36399199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Lu","raw_affiliation_strings":["Nanjing University,Department of Computer Science and Technology,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University,Department of Computer Science and Technology,Nanjing,China","institution_ids":["https://openalex.org/I36399199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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":0.9988999962806702,"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":0.9988999962806702,"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":0.9926000237464905,"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":0.9714999794960022,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7509804964065552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.711245059967041},{"id":"https://openalex.org/keywords/single-stage","display_name":"Single stage","score":0.4204801619052887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2980741858482361},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08799716830253601}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7509804964065552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711245059967041},{"id":"https://openalex.org/C3020376581","wikidata":"https://www.wikidata.org/wiki/Q16866784","display_name":"Single stage","level":2,"score":0.4204801619052887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2980741858482361},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08799716830253601},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889372","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":24,"referenced_works":["https://openalex.org/W1569095176","https://openalex.org/W1901129140","https://openalex.org/W1995052126","https://openalex.org/W1998981432","https://openalex.org/W2008806374","https://openalex.org/W2104946622","https://openalex.org/W2142159465","https://openalex.org/W2144554289","https://openalex.org/W2159072271","https://openalex.org/W2194775991","https://openalex.org/W2565639579","https://openalex.org/W2596297229","https://openalex.org/W2786463147","https://openalex.org/W2786502936","https://openalex.org/W2808206204","https://openalex.org/W2891048813","https://openalex.org/W2963351448","https://openalex.org/W2982121298","https://openalex.org/W2982770724","https://openalex.org/W3106546328","https://openalex.org/W3120080989","https://openalex.org/W6731801012","https://openalex.org/W6766978945","https://openalex.org/W6767312599"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2151749779","https://openalex.org/W3179968364","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109"],"abstract_inverted_index":{"We":[0],"propose":[1,61],"a":[2,99,125,139],"simple":[3],"yet":[4],"effective":[5],"single-stage":[6,30,140],"video":[7,31,36,94,177],"text":[8,32,37,41,45,50,64,100,110,120,147,167,178],"detection":[9,33,38,46,51,65,121,133,168],"framework,":[10],"termed":[11],"CVTD":[12],"(Conditional":[13],"convolutions":[14],"for":[15,145],"Video":[16],"Text":[17,132],"Detection),":[18],"which,":[19],"to":[20,43,62,87,107,118,165],"the":[21,27,90,143,181],"best":[22],"of":[23,74,93,162,183,188],"our":[24,184],"knowledge,":[25],"is":[26,105,113],"first":[28],"end-to-end":[29],"framework.Most":[34],"existing":[35],"methods":[39],"adopt":[40],"tracking":[42,53,67,78,123,135,148],"enhance":[44],"performance,":[47],"but":[48],"treat":[49],"and":[52,66,104,115,122,134,170,191],"as":[54],"two":[55,129],"separate":[56],"tasks.":[57],"In":[58],"contrast,":[59],"we":[60,80],"solve":[63],"in":[68,124,138,186],"an":[69,76],"end-to-end,":[70],"unified":[71],"way.":[72],"Instead":[73],"using":[75],"additional":[77,146],"module,":[79],"employ":[81],"dynamic":[82],"instance-aware":[83],"conditional":[84],"convolution":[85],"(CondConv)":[86],"implicitly":[88],"model":[89],"temporal":[91,159],"variation":[92],"text.":[95],"Each":[96],"CondConv":[97,152],"represents":[98],"instance":[101],"over":[102],"time":[103],"responsible":[106],"predict":[108],"corresponding":[109],"mask.":[111],"It":[112],"propagated":[114],"updated":[116],"frame-by-frame":[117],"perform":[119],"seamless":[126],"manner.CVTD":[127],"enjoys":[128],"advantages:":[130],"(1)":[131],"are":[136],"integrated":[137],"network,":[141],"eliminating":[142],"need":[144],"process.":[149],"(2)":[150],"The":[151],"transferred":[153],"across":[154],"frames":[155],"can":[156],"compactly":[157],"encodes":[158],"context":[160],"features":[161],"text,":[163],"leading":[164],"enhanced":[166],"performance":[169],"real-time":[171],"inference":[172],"speed.":[173],"Experiments":[174],"on":[175],"multiple":[176],"benchmarks":[179],"demonstrate":[180],"superiority":[182],"method":[185],"terms":[187],"both":[189],"accuracy":[190],"efficiency.":[192]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}