{"id":"https://openalex.org/W4402980592","doi":"https://doi.org/10.1109/icme57554.2024.10688220","title":"VTR: Bidirectional Video-Textual Transmission Rail for CLIP-based Video Recognition","display_name":"VTR: Bidirectional Video-Textual Transmission Rail for CLIP-based Video Recognition","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402980592","doi":"https://doi.org/10.1109/icme57554.2024.10688220"},"language":"en","primary_location":{"id":"doi:10.1109/icme57554.2024.10688220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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/A5078677858","display_name":"Shaoqi Yu","orcid":"https://orcid.org/0000-0002-2764-6843"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoqi Yu","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100349887","display_name":"Lili Chen","orcid":"https://orcid.org/0000-0002-0066-5649"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lili Chen","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100403843","display_name":"Xiaolin Zhang","orcid":"https://orcid.org/0009-0000-1244-4360"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolin Zhang","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035418350","display_name":"Jiamao Li","orcid":"https://orcid.org/0000-0002-7478-4544"},"institutions":[{"id":"https://openalex.org/I4210147322","display_name":"Shanghai Institute of Microsystem and Information Technology","ror":"https://ror.org/04nytyj38","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210147322"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiamao Li","raw_affiliation_strings":["Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Shanghai Institute of Microsystem and Information Technology,Shanghai,China","institution_ids":["https://openalex.org/I4210147322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2187,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51034054,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9627000093460083,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9627000093460083,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9510999917984009,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9473000168800354,"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":0.7519783973693848},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.5049291253089905},{"id":"https://openalex.org/keywords/video-capture","display_name":"Video capture","score":0.4999573230743408},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3591207265853882},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3424145579338074},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.33480310440063477},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3323516845703125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3213183879852295},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1995994746685028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519783973693848},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.5049291253089905},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.4999573230743408},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3591207265853882},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3424145579338074},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.33480310440063477},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3323516845703125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3213183879852295},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1995994746685028}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme57554.2024.10688220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme57554.2024.10688220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","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":18,"referenced_works":["https://openalex.org/W2126579184","https://openalex.org/W2625366777","https://openalex.org/W2904378456","https://openalex.org/W3035254087","https://openalex.org/W3126721948","https://openalex.org/W4214612132","https://openalex.org/W4214746887","https://openalex.org/W4312310776","https://openalex.org/W4312480274","https://openalex.org/W4312558481","https://openalex.org/W4312560592","https://openalex.org/W4312614039","https://openalex.org/W4312769131","https://openalex.org/W4385245566","https://openalex.org/W4386065852","https://openalex.org/W4386071547","https://openalex.org/W4386076424","https://openalex.org/W4402727584"],"related_works":["https://openalex.org/W2136310606","https://openalex.org/W2386993521","https://openalex.org/W2350362445","https://openalex.org/W2363676404","https://openalex.org/W2365286546","https://openalex.org/W2384551958","https://openalex.org/W40875350","https://openalex.org/W2391059704","https://openalex.org/W1000953433","https://openalex.org/W2364871915"],"abstract_inverted_index":{"There":[0],"are":[1,50],"two":[2],"key":[3],"issues":[4],"when":[5],"transferring":[6],"vision-language":[7],"model":[8],"like":[9],"CLIP":[10],"for":[11],"video":[12,108,127],"recognition:":[13],"bidirectional":[14,36,57],"video-textual":[15],"transmission":[16,37],"and":[17,41,93,114,125],"temporal":[18,42,70,80,95],"modeling.":[19],"To":[20],"address":[21],"the":[22,56,74,88],"issues,":[23],"we":[24,72],"propose":[25],"a":[26,79],"novel":[27],"framework":[28],"named":[29],"Video-Textual":[30],"Transmission":[31],"Rail":[32,47],"(VTR)":[33],"which":[34],"enables":[35],"of":[38,59,90],"visual-textual":[39],"representations":[40],"modeling":[43,81,96],"concurrently.":[44],"Specifically,":[45],"Message":[46],"(MR)":[48],"tokens":[49],"proposed":[51],"within":[52,83],"VTR":[53,86,118],"to":[54,101],"realize":[55],"transfer":[58],"not":[60],"only":[61],"high-level":[62],"visual-language":[63],"knowledge":[64],"but":[65],"also":[66],"low-level":[67],"knowledge.":[68],"For":[69],"modeling,":[71],"introduce":[73],"Temporal":[75],"Elite":[76],"(TE)":[77],"-":[78],"module":[82],"VTR,":[84],"providing":[85],"with":[87],"capability":[89],"both":[91],"short-":[92],"long-range":[94],"under":[97],"textual":[98],"supervision":[99],"thanks":[100],"MR":[102],"tokens.":[103],"Extensive":[104],"experiments":[105],"on":[106],"popular":[107],"datasets":[109],"(i.e.,":[110],"Kinetics-400,":[111],"Something-Something-v2,":[112],"UCF-101":[113],"HMDB-51)":[115],"demonstrate":[116],"that":[117],"achieves":[119],"state-of-the-art":[120],"performance":[121],"in":[122],"fully-supervised,":[123],"zero-shot":[124],"few-shot":[126],"recognition.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
