{"id":"https://openalex.org/W4408100771","doi":"https://doi.org/10.1109/acai63924.2024.10899553","title":"ConDVC: Bridging Visual and Semantic Spaces with Key Semantics for Video Understanding","display_name":"ConDVC: Bridging Visual and Semantic Spaces with Key Semantics for Video Understanding","publication_year":2024,"publication_date":"2024-12-20","ids":{"openalex":"https://openalex.org/W4408100771","doi":"https://doi.org/10.1109/acai63924.2024.10899553"},"language":"en","primary_location":{"id":"doi:10.1109/acai63924.2024.10899553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acai63924.2024.10899553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th International Conference on Algorithms, Computing and Artificial Intelligence (ACAI)","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/A5101503314","display_name":"Jian-Xiong Wang","orcid":"https://orcid.org/0000-0002-8398-5591"},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianxiong Wang","raw_affiliation_strings":["School of Artificial Intelligence, South China Normal University,Foshan,China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, South China Normal University,Foshan,China","institution_ids":["https://openalex.org/I187400657"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070173803","display_name":"Jing Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I187400657","display_name":"South China Normal University","ror":"https://ror.org/01kq0pv72","country_code":"CN","type":"education","lineage":["https://openalex.org/I187400657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Xiao","raw_affiliation_strings":["School of Computer Science, South China Normal University,Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, South China Normal University,Guangzhou,China","institution_ids":["https://openalex.org/I187400657"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101503314"],"corresponding_institution_ids":["https://openalex.org/I187400657"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29020487,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9441999793052673,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9441999793052673,"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":0.9243000149726868,"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":0.9241999983787537,"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/bridging","display_name":"Bridging (networking)","score":0.9024121761322021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7856327295303345},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.646346390247345},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5774080753326416},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35121023654937744},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1599586308002472},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.05826124548912048}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.9024121761322021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7856327295303345},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.646346390247345},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5774080753326416},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35121023654937744},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1599586308002472},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.05826124548912048}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acai63924.2024.10899553","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acai63924.2024.10899553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th International Conference on Algorithms, Computing and Artificial Intelligence (ACAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214"],"abstract_inverted_index":{"Dense":[0,58],"video":[1,8,35],"captioning":[2],"task":[3],"aims":[4],"to":[5,24,86,140],"understand":[6],"unsegmented":[7],"content":[9,36],"for":[10,96,119,165],"accurate":[11],"event":[12,108,123],"localization":[13,124],"and":[14,37,72,79,90,125,150],"captioning.":[15],"Recent":[16],"studies":[17],"have":[18],"focused":[19],"on":[20,147],"leveraging":[21],"inter-task":[22],"relationships":[23],"address":[25],"this":[26],"task.":[27],"However,":[28],"the":[29,107,131,148,155],"complexity":[30],"of":[31,135,157],"cross-modal":[32],"learning":[33],"between":[34],"captions,":[38],"particularly":[39],"without":[40,162],"prior":[41,117,132],"knowledge":[42,133],"guidance,":[43],"presents":[44],"significant":[45],"challenges":[46],"in":[47],"jointly":[48],"handling":[49],"these":[50,92,101],"two":[51],"tasks.":[52],"This":[53,111],"paper":[54],"introduces":[55],"a":[56,75],"Concept-Guided":[57],"Video":[59],"Captioning":[60],"framework":[61],"(ConDVC)":[62],"that":[63],"uses":[64],"concepts,":[65],"i.e.,":[66],"key":[67],"elements":[68],"such":[69],"as":[70,74,103],"objects":[71],"actions,":[73],"bridge":[76],"linking":[77],"visual":[78],"semantic":[80,104],"spaces.":[81],"By":[82],"employing":[83],"video-to-text":[84],"retrieval":[85],"gather":[87],"textual":[88],"features":[89,95],"integrating":[91],"with":[93],"multimodal":[94],"concept":[97],"detection,":[98],"we":[99],"utilize":[100],"concepts":[102],"guides":[105],"during":[106],"matching":[109],"process.":[110],"approach":[112],"not":[113],"only":[114],"provides":[115],"additional":[116],"information":[118],"optimizing":[120],"both":[121],"subtasks,":[122],"caption":[126],"generation,":[127],"but":[128],"also":[129],"leverages":[130],"capabilities":[134],"pretrained":[136],"models":[137],"like":[138],"CLIP":[139],"enhance":[141],"overall":[142],"model":[143],"performance.":[144],"Extensive":[145],"experiments":[146],"YouCook2":[149],"ActivityNet":[151],"Captions":[152],"datasets":[153],"demonstrate":[154],"superiority":[156],"ConDVC":[158],"against":[159],"state-of-the-art":[160],"methods":[161],"extra":[163],"data":[164],"pretraining.":[166]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
