{"id":"https://openalex.org/W4282012165","doi":"https://doi.org/10.48550/arxiv.2206.02343","title":"Contrastive Graph Multimodal Model for Text Classification in Videos","display_name":"Contrastive Graph Multimodal Model for Text Classification in Videos","publication_year":2022,"publication_date":"2022-06-06","ids":{"openalex":"https://openalex.org/W4282012165","doi":"https://doi.org/10.48550/arxiv.2206.02343"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2206.02343","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.02343","pdf_url":"https://arxiv.org/pdf/2206.02343","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2206.02343","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100346587","display_name":"Ye Liu","orcid":"https://orcid.org/0000-0003-3436-7620","observed_orcids":["https://orcid.org/0000-0003-3436-7620"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029212095","display_name":"Changchong Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Changchong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100443769","display_name":"Lin Chen","orcid":"https://orcid.org/0000-0002-8367-3651","observed_orcids":["https://orcid.org/0000-0002-8367-3651"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100567807","display_name":"Di Yin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Di","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041413561","display_name":"Bo Ren","orcid":"https://orcid.org/0000-0002-0481-5069","observed_orcids":["https://orcid.org/0000-0002-0481-5069"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9628999829292297,"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":0.9628999829292297,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0284000001847744,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.001500000013038516,"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/video-text-recognition","display_name":"video text recognition","score":0.8410000205039978},{"id":"https://openalex.org/keywords/multimodal-fusion","display_name":"multimodal fusion","score":0.9240000247955322},{"id":"https://openalex.org/keywords/contrastive-learning","display_name":"contrastive learning","score":0.9559999704360962},{"id":"https://openalex.org/keywords/layout-information","display_name":"layout information","score":0.5400000214576721},{"id":"https://openalex.org/keywords/unlabeled-video","display_name":"unlabeled video","score":0.640999972820282},{"id":"https://openalex.org/keywords/video-news","display_name":"news video","score":0.6800000071525574},{"id":"https://openalex.org/keywords/video-indexing","display_name":"video indexing","score":0.7609999775886536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8461325168609619},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6563171744346619},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.573309600353241},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5307165384292603},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5127919316291809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.504890501499176},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49519744515419006},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.46584805846214294},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.45586681365966797},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4531250298023224},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4509614408016205},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.44068387150764465},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4258512258529663},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.22714874148368835},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2206.02343","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.02343","pdf_url":"https://arxiv.org/pdf/2206.02343","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2206.02343","doi":"https://doi.org/10.48550/arxiv.2206.02343","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2206.02343","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2206.02343","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2206.02343","pdf_url":"https://arxiv.org/pdf/2206.02343","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4410474426","https://openalex.org/W4401542310","https://openalex.org/W4323051585","https://openalex.org/W2389996138","https://openalex.org/W4387968404","https://openalex.org/W4414020414","https://openalex.org/W4239892253","https://openalex.org/W2069816967","https://openalex.org/W4324291273","https://openalex.org/W4386908242"],"abstract_inverted_index":{"The":[0],"extraction":[1],"of":[2,15,41,63,93,110,191],"text":[3,24,28,42,65,95,179],"information":[4,100],"in":[5,20,33],"videos":[6],"serves":[7],"as":[8,76],"a":[9,128,160],"critical":[10],"step":[11,62],"towards":[12],"semantic":[13],"understanding":[14],"videos.":[16,156],"It":[17],"usually":[18],"involved":[19],"two":[21],"steps:":[22],"(1)":[23],"recognition":[25,43,180],"and":[26,79,121,176,181],"(2)":[27],"classification.":[29],"To":[30],"localize":[31],"texts":[32,112],"videos,":[34],"we":[35,84,126,158],"can":[36],"resort":[37],"to":[38,50,72,88,101,133,147,174],"large":[39],"numbers":[40],"methods":[44],"based":[45],"on":[46,59,186],"OCR":[47],"technology.":[48],"However,":[49],"our":[51,192],"knowledge,":[52],"there":[53],"is":[54,145,172],"no":[55],"existing":[56],"work":[57],"focused":[58],"the":[60,70,86,104,166,189],"second":[61],"video":[64,77,94,111,178],"classification,":[66],"which":[67,171],"will":[68],"limit":[69],"guidance":[71],"downstream":[73],"tasks":[74],"such":[75],"indexing":[78],"browsing.":[80],"In":[81,124],"this":[82,90],"paper,":[83],"are":[85],"first":[87],"address":[89],"new":[91,161],"task":[92],"classification":[96,182],"by":[97,137],"fusing":[98],"multimodal":[99],"deal":[102],"with":[103,116],"challenging":[105],"scenario":[106],"where":[107],"different":[108],"types":[109],"may":[113],"be":[114],"confused":[115],"various":[117],"colors,":[118],"unknown":[119],"fonts":[120],"complex":[122],"layouts.":[123],"addition,":[125],"tailor":[127],"specific":[129],"module":[130],"called":[131,169],"CorrelationNet":[132],"reinforce":[134],"feature":[135],"representation":[136],"explicitly":[138],"extracting":[139],"layout":[140],"information.":[141],"Furthermore,":[142],"contrastive":[143],"learning":[144],"utilized":[146],"explore":[148],"inherent":[149],"connections":[150],"between":[151],"samples":[152],"using":[153],"plentiful":[154],"unlabeled":[155],"Finally,":[157],"construct":[159],"well-defined":[162],"industrial":[163],"dataset":[164],"from":[165],"news":[167],"domain,":[168],"TI-News,":[170],"dedicated":[173],"building":[175],"evaluating":[177],"applications.":[183],"Extensive":[184],"experiments":[185],"TI-News":[187],"demonstrate":[188],"effectiveness":[190],"method.":[193]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2022-06-13T00:00:00"}