{"id":"https://openalex.org/W4402402427","doi":"https://doi.org/10.1109/mapr63514.2024.10660857","title":"VISA: Video Interactive Search with Advanced Visual Programming","display_name":"VISA: Video Interactive Search with Advanced Visual Programming","publication_year":2024,"publication_date":"2024-08-15","ids":{"openalex":"https://openalex.org/W4402402427","doi":"https://doi.org/10.1109/mapr63514.2024.10660857"},"language":"en","primary_location":{"id":"doi:10.1109/mapr63514.2024.10660857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mapr63514.2024.10660857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","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/A5008315732","display_name":"Duc-Tuan Luu","orcid":"https://orcid.org/0000-0003-3893-8582"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Duc-Tuan Luu","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107104482","display_name":"Khanh-Linh Bui-Le","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khanh-Linh Bui-Le","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113376072","display_name":"Duy-Ngoc Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duy-Ngoc Nguyen","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054588832","display_name":"Vinh-Tiep Nguyen","orcid":"https://orcid.org/0000-0003-4260-7874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vinh-Tiep Nguyen","raw_affiliation_strings":["University of Information Technology,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Information Technology,Ho Chi Minh City,Vietnam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053495766","display_name":"Minh\u2013Triet Tran","orcid":"https://orcid.org/0000-0003-3046-3041"},"institutions":[{"id":"https://openalex.org/I23582244","display_name":"Ho Chi Minh City University of Science","ror":"https://ror.org/05jfbgm49","country_code":"VN","type":"education","lineage":["https://openalex.org/I123565023","https://openalex.org/I23582244"]}],"countries":["VN"],"is_corresponding":false,"raw_author_name":"Minh-Triet Tran","raw_affiliation_strings":["University of Science,Ho Chi Minh City,Vietnam"],"affiliations":[{"raw_affiliation_string":"University of Science,Ho Chi Minh City,Vietnam","institution_ids":["https://openalex.org/I23582244"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008315732"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5248,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65631733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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":0.9986000061035156,"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":0.7666034698486328},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4488449990749359},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.42334067821502686},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3320434093475342}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7666034698486328},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4488449990749359},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.42334067821502686},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3320434093475342}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mapr63514.2024.10660857","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mapr63514.2024.10660857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Multimedia Analysis and Pattern Recognition (MAPR)","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":51,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2896457183","https://openalex.org/W2963150697","https://openalex.org/W2970231061","https://openalex.org/W2998621280","https://openalex.org/W2998702515","https://openalex.org/W3090449556","https://openalex.org/W3109276915","https://openalex.org/W3199693760","https://openalex.org/W4220832562","https://openalex.org/W4220881908","https://openalex.org/W4221155340","https://openalex.org/W4224308101","https://openalex.org/W4292779060","https://openalex.org/W4312282373","https://openalex.org/W4312872987","https://openalex.org/W4312879041","https://openalex.org/W4324128075","https://openalex.org/W4379179700","https://openalex.org/W4381253588","https://openalex.org/W4385245566","https://openalex.org/W4386065691","https://openalex.org/W4386076215","https://openalex.org/W4386076532","https://openalex.org/W4389374423","https://openalex.org/W4389500158","https://openalex.org/W4390041933","https://openalex.org/W4390874575","https://openalex.org/W4391272787","https://openalex.org/W4402753778","https://openalex.org/W6620707391","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6778883912","https://openalex.org/W6784333009","https://openalex.org/W6791353385","https://openalex.org/W6796761347","https://openalex.org/W6803376173","https://openalex.org/W6810081322","https://openalex.org/W6810259195","https://openalex.org/W6811013733","https://openalex.org/W6811467201","https://openalex.org/W6811476558","https://openalex.org/W6840155194","https://openalex.org/W6847363464","https://openalex.org/W6850724118","https://openalex.org/W6850787431","https://openalex.org/W6853182488","https://openalex.org/W6859170701","https://openalex.org/W6860041859","https://openalex.org/W6861232000"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Video":[0],"retrieval":[1,92],"has":[2],"become":[3],"an":[4],"important":[5],"task":[6],"in":[7],"computer":[8],"vision,":[9],"with":[10,20,80,93,101],"video":[11,41,82,91,114],"content":[12],"uploaded":[13],"to":[14,30,44,56,158],"the":[15,22,113,132,148,160,169,179,184],"Internet":[16],"every":[17],"hour.":[18],"Along":[19],"retrieving":[21],"relevant":[23],"visual":[24,37,59,77,139],"content,":[25],"users":[26,55,117],"may":[27],"also":[28],"want":[29],"perform":[31,57],"several":[32],"post-processing":[33],"steps":[34],"such":[35,50],"as":[36,123],"editing,":[38],"understanding":[39,60,127],"or":[40],"summarizing.":[42],"However,":[43],"our":[45,86,138,165],"knowledge,":[46],"there":[47],"is":[48],"no":[49],"integrated":[51],"system":[52],"that":[53],"enables":[54],"downstream":[58],"and":[61,98,128,144,178],"editing":[62,129,181],"tasks":[63],"via":[64],"text":[65,96],"prompts.":[66],"In":[67],"this":[68],"work,":[69],"we":[70],"propose":[71],"VISA":[72,166],"framework,":[73],"which":[74],"combines":[75],"a":[76,81,106],"programming":[78,140],"module":[79,141],"search":[83,97,100],"system.":[84],"Specifically,":[85],"interactive":[87],"framework":[88,167],"offers":[89],"fundamental":[90],"semantic":[94],"search,":[95],"audio":[99],"descriptive":[102],"inputs":[103],"summarized":[104],"by":[105],"large":[107],"language":[108,121],"model":[109],"(LLM).":[110],"After":[111],"obtaining":[112],"frame":[115],"results,":[116],"can":[118],"provide":[119],"natural":[120],"instructions":[122],"guidance":[124],"for":[125],"image":[126,180],"tasks.":[130],"Having":[131],"in-context":[133],"learning":[134],"capability":[135],"of":[136],"LLMs,":[137],"generates":[142],"high-level":[143],"interpretable":[145],"pseudocodes":[146],"from":[147],"given":[149],"instructions.":[150],"The":[151],"corresponding":[152],"Python":[153],"programs":[154],"are":[155],"then":[156],"executed":[157],"achieve":[159],"desired":[161],"results.":[162],"We":[163],"evaluate":[164],"on":[168,183],"2023":[170],"Ho":[171],"Chi":[172],"Minh":[173],"City":[174],"AI":[175],"Challenge":[176],"dataset":[177],"component":[182],"MagicBrush":[185],"benchmark.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
