{"id":"https://openalex.org/W7138007398","doi":"https://doi.org/10.1609/aaai.v40i4.37312","title":"RAPTOR: Real-Time High-Resolution UAV Video Prediction with Efficient Video Attention","display_name":"RAPTOR: Real-Time High-Resolution UAV Video Prediction with Efficient Video Attention","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138007398","doi":"https://doi.org/10.1609/aaai.v40i4.37312"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i4.37312","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37312","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37312/41274","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37312/41274","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129735508","display_name":"Zhan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan Chen","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)\nSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)\nSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129744767","display_name":"Zile Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zile Guo","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)\nSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)\nSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129673448","display_name":"Enze Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Enze Zhu","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)\nSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)\nSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129730251","display_name":"Peirong Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peirong Zhang","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)\nSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)\nSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129729926","display_name":"Xiaoxuan Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxuan Liu","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)","institution_ids":["https://openalex.org/I4210137199"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129700933","display_name":"Lei Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)","institution_ids":["https://openalex.org/I4210137199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129728408","display_name":"Yidan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidan Zhang","raw_affiliation_strings":["Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)\nSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Aerospace Information Research Institute, Chinese Academy of Sciences\nKey Laboratory of Target Cognition and Application Technology (TCAT)\nSchool of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210137199"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8252,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.94301994,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"40","issue":"4","first_page":"3183","last_page":"3190"},"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":0.26080000400543213,"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":0.26080000400543213,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.13249999284744263,"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":0.06689999997615814,"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/safer","display_name":"SAFER","score":0.5389999747276306},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5069000124931335},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4991999864578247},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.43779999017715454},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4203000068664551},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4036000072956085},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.39910000562667847},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3817000091075897},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.35280001163482666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749999761581421},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.522599995136261},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.515999972820282},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5069000124931335},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4991999864578247},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.47940000891685486},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4203000068664551},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.35280001163482666},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.35030001401901245},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C123614077","wikidata":"https://www.wikidata.org/wiki/Q1364905","display_name":"Propagation of uncertainty","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.25060001015663147},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i4.37312","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37312","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37312/41274","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37312","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37312","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i4.37312","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i4.37312","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37312/41274","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6796358227729797,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138007398.pdf","grobid_xml":"https://content.openalex.org/works/W7138007398.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Video":[0,104],"prediction":[1,80],"is":[2,29,45,102,175,195],"plagued":[3],"by":[4,241],"a":[5,78,107,169,176,204,212,219,236],"fundamental":[6],"trilemma:":[7],"achieving":[8],"high-resolution":[9,43,85,221],"and":[10,94,133,147,160,218,226,248],"perceptual":[11],"quality":[12],"typically":[13],"comes":[14],"at":[15,157],"the":[16,91,130,140,196,231,244],"cost":[17],"of":[18,96,116],"real-time":[19],"speed,":[20],"hindering":[21],"its":[22],"use":[23],"in":[24,35,223,235],"latency-critical":[25],"applications.":[26],"This":[27,137],"challenge":[28],"most":[30],"acute":[31],"for":[32,47,208,246],"autonomous":[33],"UAVs":[34],"dense":[36,165],"urban":[37],"environments,":[38],"where":[39],"foreseeing":[40],"events":[41],"from":[42,184],"imagery":[44],"non-negotiable":[46],"safety.":[48],"Existing":[49],"methods,":[50],"reliant":[51],"on":[52,67,164,203,215],"iterative":[53,97],"generation":[54],"(diffusion,":[55],"autoregressive":[56],"models)":[57],"or":[58,123],"quadratic-complexity":[59],"attention,":[60],"fail":[61],"to":[62,143,150,187,199],"meet":[63],"these":[64],"stringent":[65],"demands":[66],"edge":[68],"hardware.":[69],"To":[70],"break":[71],"this":[72,173],"long-standing":[73],"trade-off,":[74],"we":[75],"introduce":[76],"RAPTOR,":[77],"video":[79],"architecture":[81,174],"that":[82,111,180],"achieves":[83],"real-time,":[84],"performance.":[86],"RAPTOR\u2019s":[87],"single-pass":[88],"design":[89],"avoids":[90],"error":[92],"accumulation":[93],"latency":[95],"approaches.":[98],"Its":[99],"core":[100],"innovation":[101],"Efficient":[103],"Attention":[105],"(EVA),":[106],"novel":[108],"translator":[109],"module":[110],"factorizes":[112],"spatiotemporal":[113],"modeling.":[114],"Instead":[115],"processing":[117],"flattened":[118],"spacetime":[119],"tokens":[120],"with":[121,168],"O((ST)^2)":[122],"O(ST)":[124],"complexity,":[125],"EVA":[126],"alternates":[127],"operations":[128],"along":[129],"spatial":[131],"(S)":[132],"temporal":[134],"(T)":[135],"axes.":[136],"factorization":[138],"reduces":[139],"time":[141],"complexity":[142,149],"O(S":[144],"+":[145],"T)":[146],"memory":[148],"O(max(S,":[151],"T)),":[152],"enabling":[153],"global":[154],"context":[155],"modeling":[156],"512^2":[158,209],"resolution":[159],"beyond,":[161],"operating":[162],"directly":[163],"feature":[166],"maps":[167],"patch-free":[170],"design.":[171],"Complementing":[172],"3-stage":[177],"training":[178],"curriculum":[179],"progressively":[181],"refines":[182],"predictions":[183],"coarse":[185],"structure":[186],"sharp,":[188],"temporally":[189],"coherent":[190],"details.":[191],"Experiments":[192],"show":[193],"RAPTOR":[194,229],"first":[197],"predictor":[198],"exceed":[200],"30":[201],"FPS":[202],"Jetson":[205],"AGX":[206],"Orin":[207],"video,":[210],"setting":[211],"new":[213],"state-of-the-art":[214],"UAVid,":[216],"KTH,":[217],"custom":[220],"dataset":[222],"PSNR,":[224],"SSIM,":[225],"LPIPS.":[227],"Critically,":[228],"boosts":[230],"mission":[232],"success":[233],"rate":[234],"real-world":[237],"UAV":[238],"navigation":[239],"task":[240],"18%,":[242],"paving":[243],"way":[245],"safer":[247],"more":[249],"anticipatory":[250],"embodied":[251],"agents.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}