{"id":"https://openalex.org/W4386590413","doi":"https://doi.org/10.1109/icip49359.2023.10222286","title":"Video Question Answering Using Clip-Guided Visual-Text Attention","display_name":"Video Question Answering Using Clip-Guided Visual-Text Attention","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386590413","doi":"https://doi.org/10.1109/icip49359.2023.10222286"},"language":"en","primary_location":{"id":"doi:10.1109/icip49359.2023.10222286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222286","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":"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/A5102750930","display_name":"Shuhong Ye","orcid":"https://orcid.org/0000-0003-2581-1777"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhong Ye","raw_affiliation_strings":["University of Nottingham,School of Computer Science,Ningbo,China","School of Computer Science, University of Nottingham, Ningbo, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nottingham,School of Computer Science,Ningbo,China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"School of Computer Science, University of Nottingham, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077199392","display_name":"Weikai Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weikai Kong","raw_affiliation_strings":["University of Nottingham,School of Computer Science,Ningbo,China","School of Computer Science, University of Nottingham, Ningbo, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nottingham,School of Computer Science,Ningbo,China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"School of Computer Science, University of Nottingham, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102979546","display_name":"Chenglin Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglin Yao","raw_affiliation_strings":["University of Nottingham,School of Computer Science,Ningbo,China","School of Computer Science, University of Nottingham, Ningbo, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nottingham,School of Computer Science,Ningbo,China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"School of Computer Science, University of Nottingham, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033219457","display_name":"Jianfeng Ren","orcid":"https://orcid.org/0000-0003-4619-6590"},"institutions":[{"id":"https://openalex.org/I13591777","display_name":"University of Nottingham Ningbo China","ror":"https://ror.org/03y4dt428","country_code":"CN","type":"education","lineage":["https://openalex.org/I13591777","https://openalex.org/I142263535"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianfeng Ren","raw_affiliation_strings":["University of Nottingham,School of Computer Science,Ningbo,China","Nottingham Ningbo China Beacons of Excellence Research and Innovation Institute, University of Nottingham Ningbo China, China","School of Computer Science, University of Nottingham, Ningbo, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nottingham,School of Computer Science,Ningbo,China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"Nottingham Ningbo China Beacons of Excellence Research and Innovation Institute, University of Nottingham Ningbo China, China","institution_ids":["https://openalex.org/I13591777"]},{"raw_affiliation_string":"School of Computer Science, University of Nottingham, Ningbo, China","institution_ids":["https://openalex.org/I13591777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085533260","display_name":"Xudong Jiang","orcid":"https://orcid.org/0000-0002-9104-2315"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xudong Jiang","raw_affiliation_strings":["Nanyang Technological University,School of Electrical &amp; Electronic Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Electrical &amp; Electronic Engineering","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7859,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74270675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"85"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9962999820709229,"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":0.989799976348877,"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":0.8415445685386658},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6777169108390808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6266384124755859},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5513033866882324},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5503770112991333},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.546403706073761},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.4980931282043457},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4931418299674988},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44912341237068176},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4166821241378784}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8415445685386658},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6777169108390808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6266384124755859},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5513033866882324},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5503770112991333},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.546403706073761},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.4980931282043457},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4931418299674988},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44912341237068176},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4166821241378784},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip49359.2023.10222286","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip49359.2023.10222286","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2406828514","https://openalex.org/W2425121537","https://openalex.org/W2741249238","https://openalex.org/W2765716052","https://openalex.org/W2885775891","https://openalex.org/W2954199749","https://openalex.org/W2962949233","https://openalex.org/W2963541336","https://openalex.org/W2963800628","https://openalex.org/W2982139784","https://openalex.org/W2997805943","https://openalex.org/W2998166190","https://openalex.org/W3034730770","https://openalex.org/W3105232955","https://openalex.org/W3168640669","https://openalex.org/W3172523222","https://openalex.org/W3176398504","https://openalex.org/W3176445421","https://openalex.org/W3181758331","https://openalex.org/W3194467497","https://openalex.org/W3197457832","https://openalex.org/W3213562172","https://openalex.org/W4200631219","https://openalex.org/W4372269167","https://openalex.org/W4383753518","https://openalex.org/W4385245566","https://openalex.org/W6684090549","https://openalex.org/W6755207826","https://openalex.org/W6784333009","https://openalex.org/W6790307280","https://openalex.org/W6791353385","https://openalex.org/W6804277322"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W2990774877","https://openalex.org/W3093339210"],"abstract_inverted_index":{"Cross-modal":[0],"learning":[1,43],"of":[2,34,73,109],"video":[3,50],"and":[4,55,66,97,104,126,129],"text":[5,56],"plays":[6],"a":[7,20,53,59,71,87],"key":[8],"role":[9],"in":[10],"Video":[11],"Question":[12],"Answering":[13],"(VideoQA).":[14],"In":[15],"this":[16],"paper,":[17],"we":[18,47],"propose":[19,86],"visual-text":[21,74,111],"attention":[22,93],"mechanism":[23],"to":[24,39,69,90,115],"utilize":[25,67],"the":[26,41,62,77,81,92,101,117],"Contrastive":[27],"Language-Image":[28],"Pre-training":[29],"(CLIP)":[30],"trained":[31],"on":[32,124],"lots":[33],"general":[35,105],"domain":[36,79,103],"language-image":[37],"pairs":[38],"guide":[40],"cross-modal":[42],"for":[44],"VideoQA.":[45],"Specifically,":[46],"first":[48],"extract":[49,70,91],"features":[51,57,75,99,112],"using":[52,58],"TimeSformer":[54],"BERT":[60],"from":[61,76],"target":[63,102],"application":[64],"domain,":[65],"CLIP":[68],"pair":[72],"general-knowledge":[78],"through":[80],"domain-specific":[82],"learning.":[83],"We":[84],"then":[85],"Cross-domain":[88],"Learning":[89],"information":[94],"between":[95],"visual":[96],"linguistic":[98],"across":[100],"domain.":[106],"The":[107,119],"set":[108],"CLIP-guided":[110],"are":[113],"integrated":[114],"predict":[116],"answer.":[118],"proposed":[120],"method":[121],"is":[122],"evaluated":[123],"MSVD-QA":[125],"MSRVTTQA":[127],"datasets":[128],"outperforms":[130],"state-of-the-art":[131],"methods.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
