{"id":"https://openalex.org/W4417082677","doi":"https://doi.org/10.1109/iccv51701.2025.01550","title":"InsViE-1M: Effective Instruction-Based Video Editing with Elaborate Dataset Construction","display_name":"InsViE-1M: Effective Instruction-Based Video Editing with Elaborate Dataset Construction","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417082677","doi":"https://doi.org/10.1109/iccv51701.2025.01550"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.20287","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102624125","display_name":"Yuhui Wu","orcid":"https://orcid.org/0009-0007-9492-7649"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yuhui Wu","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056428506","display_name":"Liyi Chen","orcid":"https://orcid.org/0000-0003-2166-4386"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liyi Chen","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079630580","display_name":"Ruibin Li","orcid":"https://orcid.org/0000-0001-6471-7658"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ruibin Li","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707116","display_name":"Shihao Wang","orcid":"https://orcid.org/0000-0002-8688-1034"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shihao Wang","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057223376","display_name":"C. Xie","orcid":"https://orcid.org/0000-0003-2994-8551"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chenxi Xie","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100433899","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-2078-4215"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16692","last_page":"16701"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8208000063896179,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8208000063896179,"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":0.05620000138878822,"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":0.025200000032782555,"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-editing","display_name":"Video editing","score":0.7638000249862671},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7454000115394592},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6886000037193298},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6413000226020813},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6104000210762024},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5623000264167786},{"id":"https://openalex.org/keywords/non-linear-editing-system","display_name":"Non-linear editing system","score":0.5557000041007996}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.878600001335144},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.7638000249862671},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7454000115394592},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6886000037193298},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6413000226020813},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6104000210762024},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5623000264167786},{"id":"https://openalex.org/C137402728","wikidata":"https://www.wikidata.org/wiki/Q1330119","display_name":"Non-linear editing system","level":5,"score":0.5557000041007996},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5303999781608582},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4690000116825104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4681999981403351},{"id":"https://openalex.org/C87829876","wikidata":"https://www.wikidata.org/wiki/Q648877","display_name":"Post-production","level":2,"score":0.4293000102043152},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.37229999899864197},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.26080000400543213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01550","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01550","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.20287","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.20287","pdf_url":"https://arxiv.org/pdf/2503.20287","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.20287","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.20287","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.20287","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.20287","pdf_url":"https://arxiv.org/pdf/2503.20287","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Instruction-based":[0,67],"video":[1,163],"editing":[2,7,51,58,95,164,190],"allows":[3],"effective":[4,89],"and":[5,43,80,84,152,158,189,201],"interactive":[6],"of":[8,39,46,56,109,116,147,162,197],"videos":[9,48,83],"using":[10],"only":[11],"instructions":[12],"without":[13],"extra":[14],"inputs":[15],"such":[16],"as":[17],"masks":[18],"or":[19],"attributes.":[20],"However,":[21],"collecting":[22],"high-quality":[23,66,81,94,167],"training":[24],"triplets":[25,96,165],"(source":[26],"video,":[27,29,103,142],"edited":[28,107,130,141],"instruction)":[30],"is":[31,133],"a":[32,65,101,160,175],"challenging":[33],"task.":[34],"Existing":[35],"datasets":[36],"mostly":[37],"consist":[38],"low-resolution,":[40],"short":[41],"duration,":[42],"limited":[44],"amount":[45],"source":[47,82,102],"with":[49,71,113,125],"unsatisfactory":[50],"quality,":[52],"limiting":[53],"the":[54,140,170,195,202],"performance":[55],"trained":[57,203],"models.":[59],"In":[60],"this":[61],"work,":[62],"we":[63,104,173],"present":[64],"Video":[68],"Editing":[69],"dataset":[70,200],"1M":[72],"triplets,":[73],"namely":[74],"InsViE-1M.":[75],"We":[76,155],"first":[77,111,131],"curate":[78],"high-resolution":[79],"images,":[85],"then":[86],"design":[87],"an":[88],"editing-filtering":[90],"pipeline":[91],"to":[92,135,138,179],"construct":[93],"for":[97,149],"model":[98,204],"training.":[99],"For":[100],"generate":[105,157],"multiple":[106],"samples":[108],"its":[110,186],"frame":[112,132,150],"different":[114],"intensities":[115],"classifier-free":[117],"guidance,":[118],"which":[119],"are":[120,209],"automatically":[121],"filtered":[122],"by":[123,144],"GPT-4o":[124],"carefully":[126],"crafted":[127],"guidelines.":[128],"The":[129],"propagated":[134],"subsequent":[136],"frames":[137],"produce":[139],"followed":[143],"another":[145],"round":[146],"filtering":[148],"quality":[151],"motion":[153],"evaluation.":[154],"also":[156],"filter":[159],"variety":[161],"from":[166],"images.":[168],"With":[169],"InsViE-1M":[171,199],"dataset,":[172],"propose":[174],"multi-stage":[176],"learning":[177],"strategy":[178],"train":[180],"our":[181,198],"InsViE":[182],"model,":[183],"progressively":[184],"enhancing":[185],"instruction":[187],"following":[188],"ability.":[191],"Extensive":[192],"experiments":[193],"demonstrate":[194],"advantages":[196],"over":[205],"state-of-the-art":[206],"works.":[207],"Codes":[208],"available":[210],"at":[211],"\\href{https://github.com/langmanbusi/InsViE}{InsViE}.":[212]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}