{"id":"https://openalex.org/W4413145704","doi":"https://doi.org/10.1109/cvpr52734.2025.00359","title":"Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers","display_name":"Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413145704","doi":"https://doi.org/10.1109/cvpr52734.2025.00359"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-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/A5092403938","display_name":"Efstathios Karypidis","orcid":"https://orcid.org/0009-0008-0714-4070"},"institutions":[{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]},{"id":"https://openalex.org/I4210130908","display_name":"Archimedia (Greece)","ror":"https://ror.org/04dxam533","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210130908"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Efstathios Karypidis","raw_affiliation_strings":["Archimedes, Athena Research Center,Greece"],"affiliations":[{"raw_affiliation_string":"Archimedes, Athena Research Center,Greece","institution_ids":["https://openalex.org/I4210156054","https://openalex.org/I4210130908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038352333","display_name":"Ioannis Kakogeorgiou","orcid":"https://orcid.org/0000-0001-5200-2620"},"institutions":[{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]},{"id":"https://openalex.org/I4210130908","display_name":"Archimedia (Greece)","ror":"https://ror.org/04dxam533","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210130908"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ioannis Kakogeorgiou","raw_affiliation_strings":["Archimedes, Athena Research Center,Greece"],"affiliations":[{"raw_affiliation_string":"Archimedes, Athena Research Center,Greece","institution_ids":["https://openalex.org/I4210156054","https://openalex.org/I4210130908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070809773","display_name":"Spyros Gidaris","orcid":"https://orcid.org/0000-0003-1515-3635"},"institutions":[{"id":"https://openalex.org/I220619192","display_name":"Valeo (France)","ror":"https://ror.org/04ryqpf83","country_code":"FR","type":"company","lineage":["https://openalex.org/I220619192"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Spyros Gidaris","raw_affiliation_strings":["valeo.ai"],"affiliations":[{"raw_affiliation_string":"valeo.ai","institution_ids":["https://openalex.org/I220619192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043423948","display_name":"Nikos Komodakis","orcid":"https://orcid.org/0009-0000-6767-5641"},"institutions":[{"id":"https://openalex.org/I4210130908","display_name":"Archimedia (Greece)","ror":"https://ror.org/04dxam533","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210130908"]},{"id":"https://openalex.org/I4210156054","display_name":"Athena Research and Innovation Center In Information Communication & Knowledge Technologies","ror":"https://ror.org/0576by029","country_code":"GR","type":"facility","lineage":["https://openalex.org/I4210156054"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikos Komodakis","raw_affiliation_strings":["Archimedes, Athena Research Center,Greece"],"affiliations":[{"raw_affiliation_string":"Archimedes, Athena Research Center,Greece","institution_ids":["https://openalex.org/I4210156054","https://openalex.org/I4210130908"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5092403938"],"corresponding_institution_ids":["https://openalex.org/I4210130908","https://openalex.org/I4210156054"],"apc_list":null,"apc_paid":null,"fwci":2.116,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.88787024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"3793","last_page":"3803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.7423999905586243,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11980","display_name":"Human Mobility and Location-Based Analysis","score":0.7423999905586243,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14369","display_name":"Diverse Interdisciplinary Research Innovations","score":0.6341999769210815,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7257799506187439},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47117263078689575},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.46471700072288513},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.46054452657699585},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3803154230117798},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12182635068893433}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257799506187439},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47117263078689575},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.46471700072288513},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.46054452657699585},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3803154230117798},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12182635068893433},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00359","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00359","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Semantic":[0],"future":[1,19,100],"prediction":[2,21,63],"is":[3],"important":[4],"for":[5,17,47,103],"autonomous":[6],"systems":[7],"navigating":[8],"dynamic":[9],"environments.":[10],"This":[11,50],"paper":[12],"introduces":[13],"FUTURIST,":[14],"a":[15,24,35,42,68],"method":[16],"multimodal":[18,36,48,87],"semantic":[20,101],"that":[22],"uses":[23],"unified":[25],"and":[26,41,81,106,114],"efficient":[27],"visual":[28,38],"sequence":[29],"transformer":[30],"architecture.":[31],"Our":[32],"approach":[33],"incorporates":[34],"masked":[37],"modeling":[39],"objective":[40],"novel":[43],"masking":[44],"mechanism":[45],"designed":[46],"training.":[49],"allows":[51],"the":[52,78,93,111],"model":[53,115],"to":[54],"effectively":[55],"integrate":[56],"visible":[57],"information":[58],"from":[59],"various":[60],"modalities,":[61],"improving":[62],"accuracy.":[64],"Additionally,":[65],"we":[66],"propose":[67],"VAE-free":[69],"hierarchical":[70],"tokenization":[71],"process,":[72],"which":[73],"reduces":[74],"computational":[75],"complexity,":[76],"streamlines":[77],"training":[79,84],"pipeline,":[80],"enables":[82],"end-to-end":[83],"with":[85],"high-resolution,":[86],"inputs.":[88],"We":[89,109],"validate":[90],"FUTURIST":[91],"on":[92],"Cityscapes":[94],"dataset,":[95],"demonstrating":[96],"state-of-the-art":[97],"performance":[98],"in":[99],"segmentation":[102],"both":[104],"short-":[105],"mid-term":[107],"forecasting.":[108],"provide":[110],"implementation":[112],"code":[113],"weights":[116],"at":[117],"https://github.com/Sta8is/FUTURIST.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}