{"id":"https://openalex.org/W4390479162","doi":"https://doi.org/10.1145/3595916.3626413","title":"Learning a Contextualized Multimodal Embedding for Zero-shot Cooking Video Caption Generation","display_name":"Learning a Contextualized Multimodal Embedding for Zero-shot Cooking Video Caption Generation","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390479162","doi":"https://doi.org/10.1145/3595916.3626413"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626413","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626413","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626413","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626413","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100403214","display_name":"Lin Wang","orcid":"https://orcid.org/0000-0002-9944-5151"},"institutions":[{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"lin wang","raw_affiliation_strings":["USTC, ??"],"affiliations":[{"raw_affiliation_string":"USTC, ??","institution_ids":["https://openalex.org/I91090688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102814256","display_name":"Hongyi Zhang","orcid":"https://orcid.org/0000-0002-2060-3832"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyi Zhang","raw_affiliation_strings":["Huawei, CN"],"affiliations":[{"raw_affiliation_string":"Huawei, CN","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100742230","display_name":"Xingfu Wang","orcid":"https://orcid.org/0000-0002-1301-3535"},"institutions":[{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"xingfu wang","raw_affiliation_strings":["USTC, ??"],"affiliations":[{"raw_affiliation_string":"USTC, ??","institution_ids":["https://openalex.org/I91090688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100735350","display_name":"Yan Xiong","orcid":"https://orcid.org/0000-0001-6347-8747"},"institutions":[{"id":"https://openalex.org/I91090688","display_name":"University of Science and Technology Chittagong","ror":"https://ror.org/00w9tx359","country_code":"BD","type":"education","lineage":["https://openalex.org/I91090688"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"yan xiong","raw_affiliation_strings":["ustc, ??"],"affiliations":[{"raw_affiliation_string":"ustc, ??","institution_ids":["https://openalex.org/I91090688"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100403214"],"corresponding_institution_ids":["https://openalex.org/I91090688"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18223029,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.7147091031074524},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.6719805002212524},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6469957828521729},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.5355498790740967},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3626067638397217},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3608589470386505},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.33973950147628784},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.10384467244148254},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06060135364532471}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.7147091031074524},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6719805002212524},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6469957828521729},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5355498790740967},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3626067638397217},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3608589470386505},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.33973950147628784},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.10384467244148254},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06060135364532471},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595916.3626413","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626413","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626413","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626413","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626413","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626413","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390479162.pdf","grobid_xml":"https://content.openalex.org/works/W4390479162.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2111078031","https://openalex.org/W2737041163","https://openalex.org/W2890399523","https://openalex.org/W2957775769","https://openalex.org/W2964094654","https://openalex.org/W2981851019","https://openalex.org/W2982335217","https://openalex.org/W3105441977","https://openalex.org/W3153469116","https://openalex.org/W3174572181","https://openalex.org/W3200873909","https://openalex.org/W3203711169","https://openalex.org/W3208474254","https://openalex.org/W4226217255","https://openalex.org/W4285242218","https://openalex.org/W4285601291","https://openalex.org/W4287889346","https://openalex.org/W4312325116","https://openalex.org/W4312384316","https://openalex.org/W4312885609","https://openalex.org/W4312938727","https://openalex.org/W4313038449","https://openalex.org/W4319300722","https://openalex.org/W4386066129","https://openalex.org/W4386066385","https://openalex.org/W4386075849"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"CookingCLIP,":[3],"which":[4],"introduces":[5],"the":[6,14,18,29,37,43,48,63,68,109,112],"latest":[7],"CLIP":[8,31],"(Contrastive":[9],"Language-Image":[10],"Pre-training)":[11],"embedding":[12,32,72],"from":[13,42,62],"general":[15],"domain":[16,20],"into":[17],"specific":[19],"of":[21,70,83,91,111],"cooking":[22,38,101],"understanding,":[23],"and":[24,106],"makes":[25],"two":[26,99],"adaption":[27],"upon":[28],"original":[30],"for":[33],"better":[34],"customization":[35],"to":[36,56,73],"understanding":[39],"problems:":[40],"1)":[41],"upstream":[44],"perspective,":[45,65],"we":[46,66],"extend":[47],"static":[49],"multi-modal":[50],"CLIPembedding":[51],"with":[52],"a":[53],"temporal":[54],"dimension,":[55],"facilitate":[57],"context-aware":[58],"semantic":[59],"understanding;":[60],"2)":[61],"downstream":[64],"introduce":[67],"concept":[69],"zero-shot":[71],"sequence-to-sequence":[74],"dense":[75],"prediction":[76],"domains,":[77],"facilitating":[78],"CLIPbeing":[79],"not":[80],"only":[81],"capable":[82,90],"telling":[84,92],"\u201cWhich\u201d":[85],"(cross-modal":[86],"recognition),":[87],"but":[88],"also":[89],"\u201cWhen\u201d":[93],"(cross-context":[94],"localization).":[95],"Experiments":[96],"conducted":[97],"on":[98],"challenging":[100],"caption":[102],"generation":[103],"benchmarks,":[104],"YouCook":[105],"CrossTask,":[107],"demonstrate":[108],"effectiveness":[110],"proposed":[113],"embedding.":[114]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
