{"id":"https://openalex.org/W4388188440","doi":"https://doi.org/10.1145/3581783.3612838","title":"A Hierarchical Deep Video Understanding Method with Shot-Based Instance Search and Large Language Model","display_name":"A Hierarchical Deep Video Understanding Method with Shot-Based Instance Search and Large Language Model","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388188440","doi":"https://doi.org/10.1145/3581783.3612838"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5103153663","display_name":"Ruizhe Li","orcid":"https://orcid.org/0009-0003-4951-1805"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruizhe Li","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102018989","display_name":"Jiahao Guo","orcid":"https://orcid.org/0009-0008-6682-7867"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Guo","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101470602","display_name":"Mingxi Li","orcid":null},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxi Li","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011464051","display_name":"Zhengqian Wu","orcid":"https://orcid.org/0009-0002-4258-9581"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqian Wu","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100748496","display_name":"Chao Liang","orcid":"https://orcid.org/0000-0002-8287-8655"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Liang","raw_affiliation_strings":["School of Computer Science, Wuhan University, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103153663"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.3584,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.60708133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"9425","last_page":"9429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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/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":0.9973000288009644,"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":0.8332414031028748},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.8005980849266052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6282957792282104},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6194378137588501},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5873052477836609},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5630128979682922},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5494477152824402},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.48364031314849854},{"id":"https://openalex.org/keywords/structuring","display_name":"Structuring","score":0.44684451818466187},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4329034686088562},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4150164723396301},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37745237350463867},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.20230603218078613},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.1418479084968567}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8332414031028748},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.8005980849266052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6282957792282104},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6194378137588501},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5873052477836609},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5630128979682922},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5494477152824402},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.48364031314849854},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.44684451818466187},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4329034686088562},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4150164723396301},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37745237350463867},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.20230603218078613},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.1418479084968567},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2005618893","display_name":null,"funder_award_id":"2042022kf0001","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"},{"id":"https://openalex.org/G6166147921","display_name":null,"funder_award_id":"U1903214, 61876135","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W2156303437","https://openalex.org/W2940245925","https://openalex.org/W2963820951","https://openalex.org/W2969985801","https://openalex.org/W3021553284","https://openalex.org/W3035124602","https://openalex.org/W3092499653","https://openalex.org/W3105473141","https://openalex.org/W4287251776","https://openalex.org/W4299303451","https://openalex.org/W4302323844","https://openalex.org/W4304013709","https://openalex.org/W4304087177","https://openalex.org/W4304092154"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W4394443292","https://openalex.org/W4251394462","https://openalex.org/W2377919138","https://openalex.org/W1580673008","https://openalex.org/W2378857091","https://openalex.org/W2999756192","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060"],"abstract_inverted_index":{"Deep":[0],"video":[1,16,70,107],"understanding":[2,46,133],"(DVU)":[3],"is":[4,20],"often":[5],"considered":[6],"a":[7,15,61],"challenge":[8],"due":[9],"to":[10,22,64],"the":[11,29,36,48,66,114,119,123,127,130,140],"aim":[12],"of":[13,26,47,53,102,129],"interpreting":[14],"with":[17,87,126],"storyline,":[18],"which":[19,68],"designed":[21],"solve":[23,65],"two":[24,39],"levels":[25],"problems:":[27],"predicting":[28],"human":[30],"interaction":[31,76],"in":[32,41,56,111,149,158,166],"scene-level":[33,154,163],"and":[34,51,80,100,153,162],"identifying":[35],"relationship":[37],"between":[38],"entities":[40],"movie-level.":[42],"Based":[43],"on":[44,113,122],"our":[45],"movie":[49],"characteristics":[50],"analysis":[52],"DVU":[54],"tasks,":[55],"this":[57],"paper,":[58],"we":[59],"propose":[60],"four-stage":[62],"method":[63],"task,":[67],"includes":[69],"structuring,":[71],"shot":[72,93],"based":[73,94],"instance":[74,95],"search,":[75],"&":[77,83],"relation":[78],"prediction":[79],"shot-scene":[81],"summary":[82],"Question":[84],"Answering":[85],"(QA)":[86],"ChatGPT.":[88],"In":[89],"these":[90],"four":[91],"stages,":[92],"search":[96],"allows":[97],"accurate":[98],"identification":[99],"tracking":[101],"characters":[103],"at":[104],"an":[105],"appropriate":[106],"granularity.":[108],"Using":[109],"ChatGPT":[110,135],"QA,":[112],"one":[115],"hand,":[116,125],"can":[117,136],"narrow":[118],"answer":[120,139],"space,":[121],"other":[124],"help":[128,137],"powerful":[131],"text":[132],"ability,":[134],"us":[138],"questions":[141],"by":[142],"giving":[143],"background":[144],"knowledge.":[145],"We":[146],"rank":[147],"first":[148],"movie-level":[150,159],"group":[151,155,160,164],"2":[152,165],"1,":[156],"second":[157],"1":[161],"ACM":[167],"MM":[168],"2023":[169],"Grand":[170],"Challenge.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}