{"id":"https://openalex.org/W4405232240","doi":"https://doi.org/10.1109/tcsvt.2024.3514820","title":"Toward Long Video Understanding via Fine-Detailed Video Story Generation","display_name":"Toward Long Video Understanding via Fine-Detailed Video Story Generation","publication_year":2024,"publication_date":"2024-12-11","ids":{"openalex":"https://openalex.org/W4405232240","doi":"https://doi.org/10.1109/tcsvt.2024.3514820"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3514820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3514820","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5100621723","display_name":"Zeng You","orcid":"https://orcid.org/0009-0000-3808-5650"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng You","raw_affiliation_strings":["School of Future Technology, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0000-3808-5650","affiliations":[{"raw_affiliation_string":"School of Future Technology, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032934865","display_name":"Zhiquan Wen","orcid":"https://orcid.org/0000-0002-4969-0060"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiquan Wen","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4969-0060","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476441","display_name":"Yaofo Chen","orcid":"https://orcid.org/0000-0001-8916-8368"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaofo Chen","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8916-8368","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658181","display_name":"Xin Li","orcid":"https://orcid.org/0000-0002-1670-1368"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Li","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018498977","display_name":"Runhao Zeng","orcid":"https://orcid.org/0000-0001-8694-4245"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4388482657","display_name":"Shenzhen MSU-BIT University","ror":"https://ror.org/02q963474","country_code":null,"type":"education","lineage":["https://openalex.org/I4388482657"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runhao Zeng","raw_affiliation_strings":["Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China","Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, China"],"raw_orcid":"https://orcid.org/0000-0001-8694-4245","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4388482657"]},{"raw_affiliation_string":"Artificial Intelligence Research Institute, Shenzhen MSU-BIT University, China","institution_ids":["https://openalex.org/I4388482657"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100631216","display_name":"Yaowei Wang","orcid":"https://orcid.org/0000-0003-2197-9038"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-2197-9038","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032352025","display_name":"Mingkui Tan","orcid":"https://orcid.org/0000-0001-8856-756X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingkui Tan","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8856-756X","affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2262,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81023242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"35","issue":"5","first_page":"4592","last_page":"4607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9987000226974487,"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":0.9962000250816345,"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":0.7026119232177734},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.47710829973220825},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4112628102302551},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40561336278915405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3649643063545227}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7026119232177734},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.47710829973220825},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4112628102302551},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40561336278915405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3649643063545227}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3514820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3514820","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G246390336","display_name":null,"funder_award_id":"20220809180405001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4860469773","display_name":null,"funder_award_id":"62202311","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6042538324","display_name":"\u57fa\u4e8e\u533b\u7597\u89c6\u9891\u7684\u65f6\u5e8f\u5fae\u52a8\u4f5c\u5b9a\u4f4d\u4e0e\u8bc6\u522b\u7814\u7a76","funder_award_id":"62072190","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":103,"referenced_works":["https://openalex.org/W2166348853","https://openalex.org/W2337252826","https://openalex.org/W2425121537","https://openalex.org/W2765716052","https://openalex.org/W2810685774","https://openalex.org/W2885775891","https://openalex.org/W2897439619","https://openalex.org/W2950534130","https://openalex.org/W2963524571","https://openalex.org/W2963526497","https://openalex.org/W2963916161","https://openalex.org/W2964089981","https://openalex.org/W2964220823","https://openalex.org/W2970641574","https://openalex.org/W2975813532","https://openalex.org/W2990503944","https://openalex.org/W3035635319","https://openalex.org/W3043840704","https://openalex.org/W3088102655","https://openalex.org/W3104862079","https://openalex.org/W3106932221","https://openalex.org/W3118598912","https://openalex.org/W3145807616","https://openalex.org/W3155721152","https://openalex.org/W3156973125","https://openalex.org/W3168126734","https://openalex.org/W3175961224","https://openalex.org/W3197457832","https://openalex.org/W3203711169","https://openalex.org/W3205786327","https://openalex.org/W3216765867","https://openalex.org/W3217340782","https://openalex.org/W4211053420","https://openalex.org/W4221167396","https://openalex.org/W4285294723","https://openalex.org/W4285606530","https://openalex.org/W4293094783","https://openalex.org/W4293567872","https://openalex.org/W4312246181","https://openalex.org/W4312275869","https://openalex.org/W4312661097","https://openalex.org/W4312864639","https://openalex.org/W4312922092","https://openalex.org/W4313011746","https://openalex.org/W4313038481","https://openalex.org/W4313071966","https://openalex.org/W4313186260","https://openalex.org/W4313887138","https://openalex.org/W4320015929","https://openalex.org/W4321021976","https://openalex.org/W4322706621","https://openalex.org/W4377235294","https://openalex.org/W4381233075","https://openalex.org/W4382240182","https://openalex.org/W4385572645","https://openalex.org/W4386057769","https://openalex.org/W4386066385","https://openalex.org/W4386071468","https://openalex.org/W4386075572","https://openalex.org/W4386076661","https://openalex.org/W4386083024","https://openalex.org/W4386902900","https://openalex.org/W4387010387","https://openalex.org/W4387885776","https://openalex.org/W4387969779","https://openalex.org/W4389519587","https://openalex.org/W4390871765","https://openalex.org/W4390871893","https://openalex.org/W4390872529","https://openalex.org/W4390873732","https://openalex.org/W4391407093","https://openalex.org/W4391710055","https://openalex.org/W4394896960","https://openalex.org/W4396878071","https://openalex.org/W4402671548","https://openalex.org/W4403760933","https://openalex.org/W6762494229","https://openalex.org/W6766582784","https://openalex.org/W6778883912","https://openalex.org/W6791353385","https://openalex.org/W6797109355","https://openalex.org/W6803444062","https://openalex.org/W6805349323","https://openalex.org/W6809665764","https://openalex.org/W6810334672","https://openalex.org/W6838329711","https://openalex.org/W6838434436","https://openalex.org/W6845094036","https://openalex.org/W6846305988","https://openalex.org/W6846867676","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6851950068","https://openalex.org/W6852060543","https://openalex.org/W6852776751","https://openalex.org/W6852874933","https://openalex.org/W6852932568","https://openalex.org/W6854451932","https://openalex.org/W6854917811","https://openalex.org/W6856126884","https://openalex.org/W6856672271","https://openalex.org/W6858543224","https://openalex.org/W6859823276"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Long":[0],"video":[1,22,33,80],"understanding":[2,23],"has":[3],"become":[4],"a":[5,72,96],"critical":[6],"task":[7],"in":[8,92],"computer":[9],"vision,":[10],"driving":[11],"advancements":[12],"across":[13,144],"numerous":[14],"applications":[15],"from":[16,26,41,82,89],"surveillance":[17],"to":[18,63,84,133],"content":[19,81],"retrieval.":[20],"Existing":[21],"methods":[24],"suffer":[25],"two":[27],"challenges":[28],"when":[29],"dealing":[30],"with":[31],"long":[32,56,114],"understanding:":[34],"intricate":[35],"long-context":[36],"relationship":[37],"modeling":[38,66],"and":[39,108,155],"interference":[40,88],"redundancy.":[42],"To":[43,86],"tackle":[44],"these":[45,128],"challenges,":[46],"we":[47,70,94],"introduce":[48,95],"Fine-Detailed":[49],"Video":[50,74],"Story":[51],"generation":[52],"(FDVS),":[53],"which":[54],"interprets":[55,79],"videos":[57,115],"into":[58,116],"detailed":[59],"textual":[60,109,118],"representations.":[61],"Specifically,":[62],"achieve":[64],"fine-grained":[65],"of":[67,124,157],"long-temporal":[68],"content,":[69],"propose":[71],"Bottom-up":[73],"Interpretation":[75],"Mechanism":[76],"that":[77,101,120],"progressively":[78],"clips":[83],"video.":[85,126],"avoid":[87],"redundant":[90],"information":[91,123],"videos,":[93],"Semantic":[97],"Redundancy":[98],"Reduction":[99],"mechanism":[100],"removes":[102],"redundancy":[103],"at":[104],"both":[105],"the":[106,125,141,153],"visual":[107],"levels.":[110],"Our":[111],"method":[112,143],"transforms":[113],"hierarchical":[117],"representations":[119],"contain":[121],"multi-granularity":[122],"With":[127],"representations,":[129],"FDVS":[130],"is":[131],"applicable":[132],"various":[134],"tasks":[135],"without":[136],"any":[137],"fine-tuning.":[138],"We":[139],"evaluate":[140],"proposed":[142],"eight":[145],"datasets":[146],"spanning":[147],"three":[148],"tasks.":[149],"The":[150],"performance":[151],"demonstrates":[152],"effectiveness":[154],"versatility":[156],"our":[158],"method.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2024-12-11T00:00:00"}