{"id":"https://openalex.org/W4415708371","doi":"https://doi.org/10.1109/icme59968.2025.11209951","title":"Multi-sentence Video Grounding for Long Video Generation","display_name":"Multi-sentence Video Grounding for Long Video Generation","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708371","doi":"https://doi.org/10.1109/icme59968.2025.11209951"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5081703144","display_name":"Wei Feng","orcid":"https://orcid.org/0000-0002-9993-8722"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Feng","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009150883","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0002-2199-3879"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420416","display_name":"Hong Chen","orcid":"https://orcid.org/0000-0002-0943-2286"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Chen","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086592862","display_name":"Zeyang Zhang","orcid":"https://orcid.org/0000-0003-1329-1313"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyang Zhang","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100339293","display_name":"Wenwu Zhu","orcid":"https://orcid.org/0000-0003-2236-9290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwu Zhu","raw_affiliation_strings":["Tsinghua University,Department of Computer Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Computer Science and Technology","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34426268,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4966000020503998,"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":0.4966000020503998,"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":0.2020999938249588,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.16830000281333923,"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/video-tracking","display_name":"Video tracking","score":0.7103999853134155},{"id":"https://openalex.org/keywords/smacker-video","display_name":"Smacker video","score":0.6291000247001648},{"id":"https://openalex.org/keywords/video-processing","display_name":"Video processing","score":0.5612000226974487},{"id":"https://openalex.org/keywords/video-compression-picture-types","display_name":"Video compression picture types","score":0.5471000075340271},{"id":"https://openalex.org/keywords/multiview-video-coding","display_name":"Multiview Video Coding","score":0.5467000007629395},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4708999991416931},{"id":"https://openalex.org/keywords/video-editing","display_name":"Video editing","score":0.4708000123500824},{"id":"https://openalex.org/keywords/video-capture","display_name":"Video capture","score":0.4603999853134155},{"id":"https://openalex.org/keywords/video-game","display_name":"Video game","score":0.44769999384880066}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169000148773193},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.7103999853134155},{"id":"https://openalex.org/C108803254","wikidata":"https://www.wikidata.org/wiki/Q857512","display_name":"Smacker video","level":4,"score":0.6291000247001648},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.5612000226974487},{"id":"https://openalex.org/C106030495","wikidata":"https://www.wikidata.org/wiki/Q1797012","display_name":"Video compression picture types","level":4,"score":0.5471000075340271},{"id":"https://openalex.org/C23431618","wikidata":"https://www.wikidata.org/wiki/Q1404672","display_name":"Multiview Video Coding","level":4,"score":0.5467000007629395},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4708999991416931},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C151211776","wikidata":"https://www.wikidata.org/wiki/Q2778015","display_name":"Video capture","level":3,"score":0.4603999853134155},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.44769999384880066},{"id":"https://openalex.org/C166142869","wikidata":"https://www.wikidata.org/wiki/Q60061622","display_name":"Video production","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4278999865055084},{"id":"https://openalex.org/C137402728","wikidata":"https://www.wikidata.org/wiki/Q1330119","display_name":"Non-linear editing system","level":5,"score":0.4156000018119812},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.4025000035762787},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C162478608","wikidata":"https://www.wikidata.org/wiki/Q4011369","display_name":"Uncompressed video","level":4,"score":0.37369999289512634},{"id":"https://openalex.org/C50637493","wikidata":"https://www.wikidata.org/wiki/Q1136781","display_name":"Morphing","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C167510206","wikidata":"https://www.wikidata.org/wiki/Q2835824","display_name":"Block-matching algorithm","level":4,"score":0.3495999872684479},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.2888000011444092},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C2775856596","wikidata":"https://www.wikidata.org/wiki/Q25141683","display_name":"Video browsing","level":4,"score":0.27090001106262207},{"id":"https://openalex.org/C2776566319","wikidata":"https://www.wikidata.org/wiki/Q3495514","display_name":"Interactive video","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2776580754","wikidata":"https://www.wikidata.org/wiki/Q25098614","display_name":"Video decoder","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209951","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":18,"referenced_works":["https://openalex.org/W1927052826","https://openalex.org/W2111078031","https://openalex.org/W2964089981","https://openalex.org/W3180355996","https://openalex.org/W4298364821","https://openalex.org/W4385571093","https://openalex.org/W4385573866","https://openalex.org/W4386072096","https://openalex.org/W4388191850","https://openalex.org/W4390871980","https://openalex.org/W4390872297","https://openalex.org/W4390872556","https://openalex.org/W4390873054","https://openalex.org/W4402660110","https://openalex.org/W4402716132","https://openalex.org/W4402727507","https://openalex.org/W4402754238","https://openalex.org/W4414781025"],"related_works":[],"abstract_inverted_index":{"Video":[0,52,56],"generation":[1,67,182],"has":[2],"witnessed":[3],"great":[4],"success":[5],"recently,":[6],"but":[7],"its":[8],"application":[9],"in":[10,21,40,122,210],"generating":[11,230],"long":[12,78,190,201,223,231],"videos":[13,28,232],"still":[14],"remains":[15],"challenging":[16],"due":[17],"to":[18,64,111,142,184,221],"the":[19,23,30,38,59,65,70,100,106,119,123,129,149,153,186,198,208,222],"difficulty":[20],"maintaining":[22],"temporal":[24,150],"consistency":[25,151,188],"of":[26,50,83,132,152,189,200],"generated":[27],"and":[29,47,164,180,215,218],"high":[31],"memory":[32,172,236],"cost":[33],"during":[34],"generation.":[35,80,203],"To":[36],"tackle":[37],"problems,":[39],"this":[41],"paper,":[42],"we":[43,137],"propose":[44],"a":[45,74,234],"brave":[46],"new":[48,75,144],"idea":[49],"Multi-sentence":[51],"Grounding":[53],"for":[54,69,77,102,113,197,229],"Long":[55],"Generation,":[57],"connecting":[58],"massive":[60,107],"video":[61,66,79,103,108,114,124,134,139,145,178,191,202,213,219,224],"moment":[62,109,115,135],"retrieval":[63,110],"task":[68],"first":[71],"time,":[72],"providing":[73,193],"paradigm":[76],"The":[81],"method":[82],"our":[84],"work":[85],"can":[86,158],"be":[87,159],"summarized":[88],"as":[89,99],"three":[90],"steps:":[91],"(i)":[92],"We":[93,175],"design":[94],"sequential":[95],"scene":[96],"text":[97,120],"prompts":[98],"queries":[101],"grounding,":[104],"utilizing":[105],"search":[112],"segments":[116],"that":[117],"meet":[118],"requirements":[121],"database.":[125],"(ii)":[126],"Based":[127],"on":[128],"source":[130],"frames":[131],"retrieved":[133,154],"segments,":[136],"adopt":[138],"editing":[140,157],"methods":[141,183],"create":[143],"content":[146],"while":[147],"preserving":[148],"video.":[155],"Since":[156],"conducted":[160],"segment":[161,163],"by":[162,167],"even":[165],"frame":[166],"frame,":[168],"it":[169],"largely":[170],"reduces":[171],"costs.":[173],"(iii)":[174],"also":[176],"attempt":[177],"morphing":[179,214],"personalized":[181,216],"improve":[185],"subject":[187],"generation,":[192,217,225],"ablation":[194],"experimental":[195],"results":[196],"subtasks":[199],"Our":[204],"approach":[205],"seamlessly":[206],"extends":[207],"development":[209],"image/video":[211],"editing,":[212],"grounding":[220],"offering":[226],"effective":[227],"solutions":[228],"at":[233],"low":[235],"cost.":[237]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-30T00:00:00"}
