{"id":"https://openalex.org/W7138833780","doi":"https://doi.org/10.5220/0014429100004084","title":"Spatio-Temporal Attention for Consistent Video Semantic Segmentation in Automated Driving","display_name":"Spatio-Temporal Attention for Consistent Video Semantic Segmentation in Automated Driving","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7138833780","doi":"https://doi.org/10.5220/0014429100004084"},"language":null,"primary_location":{"id":"doi:10.5220/0014429100004084","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0014429100004084","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computer Vision Theory and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0014429100004084","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Serin Varghese","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Serin Varghese","raw_affiliation_strings":["CARIAD SE, Wolfsburg, Germany","Heinrich-Heine-University D\u00fcsseldorf, Department of Computer Science, D\u00fcsseldorf, Germany"],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kevin Ro\u00df","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kevin Ro\u00df","raw_affiliation_strings":["Heinrich-Heine-University D\u00fcsseldorf, Department of Computer Science, D\u00fcsseldorf, Germany"],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Fabian H\u00fcger","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabian H\u00fcger","raw_affiliation_strings":["CARIAD SE, Wolfsburg, Germany"],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Kira Maag","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kira Maag","raw_affiliation_strings":["Heinrich-Heine-University D\u00fcsseldorf, Department of Computer Science, D\u00fcsseldorf, Germany"],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87738393,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"117","last_page":"127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.26460000872612,"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/T11439","display_name":"Video Analysis and Summarization","score":0.26460000872612,"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":0.24279999732971191,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.24240000545978546,"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/segmentation","display_name":"Segmentation","score":0.54339998960495},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.3160000145435333},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3070000112056732},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.27730000019073486},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.27570000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6489999890327454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.60589998960495},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5672000050544739},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.54339998960495},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0014429100004084","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0014429100004084","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computer Vision Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.10052","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.10052","pdf_url":"https://arxiv.org/pdf/2602.10052","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"}],"best_oa_location":{"id":"doi:10.5220/0014429100004084","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0014429100004084","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Computer Vision Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks,":[2],"especially":[3],"transformer-based":[4],"architectures,":[5],"have":[6],"achieved":[7],"remarkable":[8],"success":[9],"in":[10,37,122,132],"semantic":[11,66,152],"segmentation":[12,153],"for":[13,64,150],"environmental":[14],"perception.":[15],"However,":[16],"existing":[17,87],"models":[18],"process":[19,74],"video":[20,65],"frames":[21],"independently,":[22],"thus":[23],"failing":[24],"to":[25,55,73,86,128,138],"leverage":[26],"temporal":[27,61,123],"consistency,":[28],"which":[29],"could":[30],"significantly":[31],"improve":[32],"both":[33,101],"accuracy":[34],"and":[35,82,97,103,112,126],"stability":[36],"dynamic":[38],"scenes.":[39],"In":[40],"this":[41],"work,":[42],"we":[43],"propose":[44],"a":[45],"Spatio-Temporal":[46],"Attention":[47],"(STA)":[48],"mechanism":[49],"that":[50],"extends":[51],"transformer":[52,95],"attention":[53],"blocks":[54],"incorporate":[56],"multi-frame":[57],"context,":[58],"enabling":[59],"robust":[60],"feature":[62,76],"representations":[63],"segmentation.":[67],"Our":[68],"approach":[69],"modifies":[70],"standard":[71],"self-attention":[72],"spatio-temporal":[75],"sequences":[77],"while":[78],"maintaining":[79],"computational":[80],"efficiency":[81],"requiring":[83],"minimal":[84],"changes":[85],"architectures.":[88],"STA":[89,144],"demonstrates":[90],"broad":[91],"applicability":[92],"across":[93,100],"diverse":[94],"architectures":[96],"remains":[98],"effective":[99,147],"lightweight":[102],"larger-scale":[104],"models.":[105],"A":[106],"comprehensive":[107],"evaluation":[108],"on":[109],"the":[110],"Cityscapes":[111],"BDD100k":[113],"datasets":[114],"shows":[115],"substantial":[116],"improvements":[117],"of":[118],"9.20":[119],"percentage":[120,130],"points":[121,131],"consistency":[124],"metrics":[125],"up":[127],"1.76":[129],"mean":[133],"intersection":[134],"over":[135],"union":[136],"compared":[137],"single-frame":[139],"baselines.":[140],"These":[141],"results":[142],"demonstrate":[143],"as":[145],"an":[146],"architectural":[148],"enhancement":[149],"video-based":[151],"applications.":[154]},"counts_by_year":[],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2026-02-13T00:00:00"}