{"id":"https://openalex.org/W7137906510","doi":"https://doi.org/10.1609/aaai.v40i16.38347","title":"WinMamba: Multi-Scale Shifted Windows in State Space Model for 3D Object Detection","display_name":"WinMamba: Multi-Scale Shifted Windows in State Space Model for 3D Object Detection","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137906510","doi":"https://doi.org/10.1609/aaai.v40i16.38347"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i16.38347","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38347","pdf_url":null,"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://doi.org/10.1609/aaai.v40i16.38347","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129689276","display_name":"Longhui Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longhui Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129747374","display_name":"Qiming Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiming Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129725969","display_name":"Xiaolu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaolu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129696243","display_name":"Zhaoliang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoliang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129676669","display_name":"Chenglu Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenglu Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.8252,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93376068,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"40","issue":"16","first_page":"13432","last_page":"13440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9344000220298767,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9344000220298767,"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/T11448","display_name":"Face recognition and analysis","score":0.0071000000461936,"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":0.006899999920278788,"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/block","display_name":"Block (permutation group theory)","score":0.6358000040054321},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6176999807357788},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5758000016212463},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5554999709129333},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5076000094413757},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.48080000281333923},{"id":"https://openalex.org/keywords/voxel","display_name":"Voxel","score":0.43059998750686646},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41670000553131104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7225000262260437},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6358000040054321},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6176999807357788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5916000008583069},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5758000016212463},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5554999709129333},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5400000214576721},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5076000094413757},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.48080000281333923},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.28119999170303345},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C3019007443","wikidata":"https://www.wikidata.org/wiki/Q568742","display_name":"3d model","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i16.38347","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38347","pdf_url":null,"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"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i16.38347","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i16.38347","pdf_url":null,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"3D":[0,70],"object":[1],"detection":[2,156],"is":[3],"critical":[4],"for":[5],"autonomous":[6],"driving,":[7],"yet":[8],"it":[9],"remains":[10],"fundamentally":[11],"challenging":[12],"to":[13,103],"simultaneously":[14],"maximize":[15],"computational":[16],"efficiency":[17,43],"and":[18,44,123,131,151],"capture":[19,32],"long-range":[20,33],"spatial":[21,58],"dependencies.We":[22],"observed":[23],"that":[24,93,135],"Mamba-based":[25,69],"models,":[26],"with":[27,82,118],"their":[28],"linear":[29,110],"state-space":[30],"design,":[31],"dependencies":[34],"at":[35],"lower":[36],"cost,":[37],"offering":[38],"a":[39,53,67,90,119,124],"promising":[40],"balance":[41],"between":[42],"accuracy.However,":[45],"existing":[46],"methods":[47],"rely":[48],"on":[49,128],"axis-aligned":[50],"scanning":[51],"within":[52,108],"fixed":[54],"window,":[55],"inevitably":[56],"discarding":[57],"information.":[59],"To":[60,78],"address":[61],"this":[62],"problem,":[63],"we":[64,113],"propose":[65],"WinMamba,":[66],"novel":[68],"feature-encoding":[71],"backbone":[72,81],"composed":[73],"of":[74,148],"stacked":[75],"WinMamba":[76,87,116,136],"blocks.":[77],"enhance":[79],"the":[80,86,109,115,129,139,145,149],"robust":[83],"multi-scale":[84],"representation,":[85],"block":[88],"incorporates":[89],"window-scale-adaptive":[91],"module":[92],"compensates":[94],"voxel":[95],"features":[96],"across":[97],"varying":[98],"resolutions":[99],"during":[100],"sampling.":[101],"Meanwhile,":[102],"obtain":[104],"rich":[105],"contextual":[106],"cues":[107],"state":[111],"space,":[112],"equip":[114],"layer":[117],"learnable":[120],"positional":[121],"encoding":[122],"window-shift":[125],"strategy.Extensive":[126],"experiments":[127],"KITTI":[130],"Waymo":[132],"datasets":[133],"demonstrate":[134],"significantly":[137],"outperforms":[138],"baseline.":[140],"Ablation":[141],"studies":[142],"further":[143],"validate":[144],"individual":[146],"contributions":[147],"WSF":[150],"AWF":[152],"modules":[153],"in":[154],"improving":[155],"accuracy.":[157],"The":[158],"code":[159],"will":[160],"be":[161],"made":[162],"publicly":[163],"available.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}