{"id":"https://openalex.org/W4386597126","doi":"https://doi.org/10.1109/icip49359.2023.10223123","title":"A Global-Local Contrastive Learning Framework for Video Captioning","display_name":"A Global-Local Contrastive Learning Framework for Video Captioning","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386597126","doi":"https://doi.org/10.1109/icip49359.2023.10223123"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10223123","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10223123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","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/A5101307313","display_name":"Qunyue Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qunyue Huang","raw_affiliation_strings":["Chongqing University,College of Computer Science,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University,College of Computer Science,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046520540","display_name":"Bin Fang","orcid":"https://orcid.org/0000-0003-1955-6626"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Fang","raw_affiliation_strings":["Chongqing University,College of Computer Science,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University,College of Computer Science,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081756234","display_name":"Xi Ai","orcid":"https://orcid.org/0000-0002-4241-3837"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Ai","raw_affiliation_strings":["Chongqing University,College of Computer Science,Chongqing,China","College of Computer Science, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chongqing University,College of Computer Science,Chongqing,China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I158842170"],"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":"2410","last_page":"2414"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":0.9968000054359436,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9944999814033508,"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/modalities","display_name":"Modalities","score":0.8438036441802979},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7677347660064697},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.696184515953064},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5795609951019287},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5569352507591248},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5287520289421082},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.523455798625946},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5027847290039062},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47479739785194397},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4619264006614685},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.42824041843414307},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40366214513778687},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.13629740476608276},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07975542545318604}],"concepts":[{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.8438036441802979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677347660064697},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.696184515953064},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5795609951019287},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5569352507591248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5287520289421082},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.523455798625946},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5027847290039062},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47479739785194397},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4619264006614685},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.42824041843414307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40366214513778687},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.13629740476608276},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07975542545318604},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10223123","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icip49359.2023.10223123","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1607035479","https://openalex.org/W1956340063","https://openalex.org/W2101105183","https://openalex.org/W2154652894","https://openalex.org/W2425121537","https://openalex.org/W2741951152","https://openalex.org/W2905145027","https://openalex.org/W2948358897","https://openalex.org/W2951390634","https://openalex.org/W2953461088","https://openalex.org/W2962990649","https://openalex.org/W2978017171","https://openalex.org/W2984862483","https://openalex.org/W3034221024","https://openalex.org/W3035392611","https://openalex.org/W3090886579","https://openalex.org/W3093309253","https://openalex.org/W3134875898","https://openalex.org/W3176425931","https://openalex.org/W3195284414","https://openalex.org/W3217340782","https://openalex.org/W4213152894","https://openalex.org/W4285600262","https://openalex.org/W4286488082","https://openalex.org/W4308235822","https://openalex.org/W4312463400","https://openalex.org/W4312560592","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6682631176","https://openalex.org/W6684090549","https://openalex.org/W6758859460","https://openalex.org/W6768851824"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W4289422896"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,30],"global-local":[4,31],"contrastive":[5,27,52],"learning":[6,53],"framework":[7],"is":[8,33,54,82,113],"proposed":[9,34,111],"to":[10,35,56,84,115],"leverage":[11],"global":[12,48,96],"contextual":[13,40,49,97],"information":[14,41,98],"from":[15,42,99],"different":[16,43,87,100],"modalities":[17],"and":[18,73],"then":[19],"effectively":[20,85],"fuse":[21,86],"them":[22],"with":[23],"the":[24,38,47,58,62,68,74,91,116],"supervision":[25],"of":[26],"learning.":[28],"First,":[29],"encoder":[32,81],"sufficiently":[36],"explore":[37],"salient":[39],"modalities,":[44,64,88],"which":[45,65],"generates":[46],"information.":[50],"Second,":[51],"used":[55],"minimize":[57],"semantic":[59],"distance":[60],"between":[61,71],"paired":[63],"can":[66],"improve":[67],"content":[69],"matching":[70],"videos":[72],"predicted":[75],"captions.":[76],"Finally,":[77],"an":[78],"attention-based":[79],"multimodal":[80,92],"presented":[83],"thereby":[89],"generating":[90],"representations":[93],"that":[94,109],"include":[95],"modalities.":[101],"Extensive":[102],"experimental":[103],"results":[104],"on":[105],"benchmark":[106],"datasets":[107],"indicate":[108],"our":[110],"method":[112],"superior":[114],"state-of-the-art":[117],"approaches.":[118]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}