{"id":"https://openalex.org/W7105661487","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227554","title":"GCL-Vid: Efficient Video Foundation Model via Generative and Contrastive Encoding with LLMs","display_name":"GCL-Vid: Efficient Video Foundation Model via Generative and Contrastive Encoding with LLMs","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W7105661487","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227554"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":null,"display_name":"Wanjing Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wanjing Xie","raw_affiliation_strings":["Central South University,School of Computer Science and Engineering,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Central South University,School of Computer Science and Engineering,Changsha,China","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":null,"display_name":"Lingyan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyan Zhang","raw_affiliation_strings":["Central South University,School of Computer Science and Engineering,Changsha,China"],"affiliations":[{"raw_affiliation_string":"Central South University,School of Computer Science and Engineering,Changsha,China","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57745603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.30970001220703125,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.30970001220703125,"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":0.2587999999523163,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.10189999639987946,"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/generative-grammar","display_name":"Generative grammar","score":0.7587000131607056},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5468999743461609},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5080999732017517},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4925000071525574},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4268999993801117},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.41940000653266907},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.3971000015735626},{"id":"https://openalex.org/keywords/generative-design","display_name":"Generative Design","score":0.38260000944137573}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7587000131607056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7121000289916992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5672000050544739},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4925000071525574},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4268999993801117},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.41940000653266907},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3901999890804291},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.38260000944137573},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3725000023841858},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3292999863624573},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5964313745498657,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2126579184","https://openalex.org/W2747141180","https://openalex.org/W2963091558","https://openalex.org/W2963155035","https://openalex.org/W2981851019","https://openalex.org/W2990152177","https://openalex.org/W2990503944","https://openalex.org/W3126721948","https://openalex.org/W3170837227","https://openalex.org/W3191973673","https://openalex.org/W3196393026","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W4214612132","https://openalex.org/W4312614039","https://openalex.org/W4313156423","https://openalex.org/W4386076504","https://openalex.org/W4390874458","https://openalex.org/W4390874610","https://openalex.org/W4402703046","https://openalex.org/W4402727142","https://openalex.org/W4402754178","https://openalex.org/W4403887646","https://openalex.org/W4404724811"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"video":[1,39,67,93],"recognition":[2],"methods":[3],"have":[4],"predominantly":[5],"relied":[6],"on":[7,124,153,159,162,165,169],"linear":[8],"probing":[9],"or":[10],"contrastive":[11,46,63,139],"learning,":[12],"which":[13,121],"require":[14],"large":[15,50],"amounts":[16],"of":[17,107,113],"pretraining":[18],"data":[19],"and":[20,45,62,73,95,127,138,167],"limit":[21],"the":[22,55,82,85,89,92,96,100,129,146],"model\u2019s":[23,101],"transferability":[24],"to":[25,65,103,143],"various":[26],"downstream":[27,108],"tasks.":[28,109],"To":[29],"address":[30],"these":[31],"limitations,":[32],"we":[33],"introduce":[34],"GCL-Vid,":[35],"a":[36,104],"two-stage":[37],"general-purpose":[38],"foundation":[40],"model":[41],"that":[42],"integrates":[43],"generative":[44,61,137],"self-supervised":[47],"learning":[48,140],"with":[49,141],"language":[51],"models":[52,64],"(LLMs).":[53],"In":[54,81],"first":[56],"stage,":[57,84],"GCL-Vid":[58,114,149],"employs":[59],"frozen":[60,125],"enhance":[66],"encoding,":[68],"capturing":[69],"both":[70],"global":[71],"structures":[72],"fine-grained":[74],"details":[75],"while":[76],"significantly":[77],"reducing":[78],"training":[79,119],"costs.":[80],"second":[83],"Q-Former":[86],"module":[87],"bridges":[88],"gap":[90],"between":[91],"encoder":[94],"LLM":[97],"encoder,":[98],"improving":[99],"adaptability":[102],"wide":[105],"range":[106],"The":[110],"core":[111],"innovation":[112],"lies":[115],"in":[116],"its":[117],"efficient":[118],"strategy,":[120],"primarily":[122],"relies":[123],"parameters":[126],"eliminates":[128],"need":[130],"for":[131],"additional":[132,175],"data.":[133,176],"This":[134],"design":[135],"unifies":[136],"alignment":[142],"LLMs":[144],"via":[145],"Q-Former.":[147],"Notably,":[148],"achieves":[150],"state-of-the-art":[151],"performance":[152],"several":[154],"benchmark":[155],"datasets,":[156],"including":[157],"88.2%":[158],"Kinetics-400,":[160],"92.1%":[161],"HMDB-51,":[163],"99.7%":[164],"UCF-101,":[166],"99.8%":[168],"YUP++,":[170],"all":[171],"without":[172],"requiring":[173],"any":[174]},"counts_by_year":[],"updated_date":"2025-11-15T23:13:30.683059","created_date":"2025-11-14T00:00:00"}