{"id":"https://openalex.org/W7138948155","doi":"https://doi.org/10.1109/tip.2026.3673949","title":"SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing","display_name":"SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7138948155","doi":"https://doi.org/10.1109/tip.2026.3673949","pmid":"https://pubmed.ncbi.nlm.nih.gov/41855061"},"language":"en","primary_location":{"id":"doi:10.1109/tip.2026.3673949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3673949","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5008273094","display_name":"Rong-Cheng Tu","orcid":"https://orcid.org/0000-0002-9567-159X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rong-Cheng Tu","raw_affiliation_strings":["Nanyang Technological University, 50 Nanyang Avenue, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-9567-159X","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130198900","display_name":"Wenhao Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wenhao Sun","raw_affiliation_strings":["Nanyang Technological University, 50 Nanyang Avenue, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101809048","display_name":"Zhao Jin","orcid":"https://orcid.org/0000-0001-9757-2352"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhao Jin","raw_affiliation_strings":["Nanyang Technological University, 50 Nanyang Avenue, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130080864","display_name":"Jingyi Liao","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingyi Liao","raw_affiliation_strings":["Nanyang Technological University, 50 Nanyang Avenue, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113583675","display_name":"Juan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jiaxing Huang","raw_affiliation_strings":["Nanyang Technological University, 50 Nanyang Avenue, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-8681-0471","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130179859","display_name":"Dacheng Tao","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Dacheng Tao","raw_affiliation_strings":["Nanyang Technological University, 50 Nanyang Avenue, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7225-5449","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, 50 Nanyang Avenue, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.27336287,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"35","issue":null,"first_page":"3085","last_page":"3098"},"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":0.5778999924659729,"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":0.5778999924659729,"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":0.14980000257492065,"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":0.06069999933242798,"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/orchestration","display_name":"Orchestration","score":0.7980999946594238},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6133999824523926},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5810999870300293},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5234000086784363},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.47769999504089355},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.357699990272522},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.352400004863739},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3492000102996826},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.34139999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8748999834060669},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.7980999946594238},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6133999824523926},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5810999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5792999863624573},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5234000086784363},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.47769999504089355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4666999876499176},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.366100013256073},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.357699990272522},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.329800009727478},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25949999690055847},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C2775856596","wikidata":"https://www.wikidata.org/wiki/Q25141683","display_name":"Video browsing","level":4,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tip.2026.3673949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tip.2026.3673949","pdf_url":null,"source":{"id":"https://openalex.org/S4210173141","display_name":"IEEE Transactions on Image Processing","issn_l":"1057-7149","issn":["1057-7149","1941-0042"],"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 Image Processing","raw_type":"journal-article"},{"id":"pmid:41855061","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41855061","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on image processing : a publication of the IEEE Signal Processing Society","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2464708700","https://openalex.org/W2886641317","https://openalex.org/W3159481202","https://openalex.org/W4312933868","https://openalex.org/W4386113271","https://openalex.org/W4386289268","https://openalex.org/W4390871782","https://openalex.org/W4390873135","https://openalex.org/W4390874113","https://openalex.org/W4390874580","https://openalex.org/W4402660110","https://openalex.org/W4402667024","https://openalex.org/W4402703121","https://openalex.org/W4402713111","https://openalex.org/W4402715857","https://openalex.org/W4402716132","https://openalex.org/W4402716173","https://openalex.org/W4402726937","https://openalex.org/W4402726973","https://openalex.org/W4402727429","https://openalex.org/W4402727736","https://openalex.org/W4404782905","https://openalex.org/W4409767398","https://openalex.org/W4413010798","https://openalex.org/W4415850505","https://openalex.org/W7133250524"],"related_works":[],"abstract_inverted_index":{"Although":[0],"video":[1,35,132,140],"generation":[2,36],"and":[3,37,46,53,110,149,170,177],"editing":[4,38],"models":[5,10,26,74,152,167],"have":[6],"advanced":[7],"significantly,":[8],"individual":[9],"remain":[11],"restricted":[12],"to":[13,18,75,96,105,115,146,168],"specific":[14],"tasks,":[15],"often":[16],"failing":[17],"meet":[19],"diverse":[20],"user":[21,78],"needs.":[22],"Effectively":[23],"coordinating":[24],"these":[25,57],"in":[27,50],"pipelines":[28],"can":[29],"unlock":[30],"a":[31,66,89,128,139],"wide":[32],"range":[33],"of":[34],"capabilities.":[39],"However,":[40],"manual":[41],"orchestration":[42,85],"is":[43],"complex,":[44],"time-consuming,":[45],"requires":[47],"deep":[48],"expertise":[49],"model":[51,113],"performance":[52],"limitations.":[54],"To":[55,80,123],"address":[56],"challenges,":[58],"we":[59,87,126,135],"propose":[60],"the":[61,117],"Semantic":[62],"Planning":[63],"Agent":[64],"(SPAgent),":[65],"novel":[67],"system":[68],"that":[69,163],"automatically":[70],"coordinates":[71,166],"state-of-the-art":[72],"open-source":[73],"fulfill":[76],"complex":[77],"intents.":[79],"equip":[81],"SPAgent":[82,137,164],"with":[83,138],"robust":[84],"capabilities,":[86],"introduce":[88],"three-step":[90],"framework:":[91],"1)":[92],"decoupled":[93],"intent":[94],"recognition":[95],"accurately":[97],"parse":[98],"multi-modal":[99],"inputs;":[100],"2)":[101],"principle-guided":[102],"route":[103],"planning":[104],"design":[106],"effective":[107],"execution":[108],"chains;":[109],"3)":[111],"capability-based":[112],"selection":[114],"identify":[116],"optimal":[118],"tools":[119],"for":[120],"each":[121],"sub-task.":[122],"facilitate":[124],"training,":[125],"curate":[127],"comprehensive":[129],"multi-task":[130],"generative":[131],"dataset.":[133],"Furthermore,":[134],"enhance":[136],"quality":[141],"evaluation":[142],"module,":[143],"enabling":[144],"it":[145],"autonomously":[147],"assess":[148],"incorporate":[150],"new":[151],"into":[153],"its":[154],"tool":[155],"library":[156],"without":[157],"human":[158],"intervention.":[159],"Experimental":[160],"results":[161],"demonstrate":[162],"effectively":[165],"generate":[169],"edit":[171],"high-quality":[172],"videos,":[173],"exhibiting":[174],"superior":[175],"versatility":[176],"adaptability":[178],"across":[179],"various":[180],"tasks.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-03-20T00:00:00"}