{"id":"https://openalex.org/W4416748877","doi":"https://doi.org/10.1109/iros60139.2025.11245989","title":"Hybrid Transformer-Mamba Model for 3D Semantic Segmentation","display_name":"Hybrid Transformer-Mamba Model for 3D Semantic Segmentation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748877","doi":"https://doi.org/10.1109/iros60139.2025.11245989"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5044762053","display_name":"X. J. Wang","orcid":"https://orcid.org/0000-0001-8223-502X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyu Wang","raw_affiliation_strings":["Huazhong University of Science and Technology (HUST),School of Artificial Intelligence and Automation,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology (HUST),School of Artificial Intelligence and Automation,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020975065","display_name":"Jinghua Hou","orcid":"https://orcid.org/0009-0007-6555-4038"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinghua Hou","raw_affiliation_strings":["Huazhong University of Science and Technology (HUST),School of Electronic Information and Communications,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology (HUST),School of Electronic Information and Communications,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374322","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0002-1197-0390"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["The University of Hong Kong (HKU),Department of Computer Science,Pokfulam,Hong Kong,999077"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong (HKU),Department of Computer Science,Pokfulam,Hong Kong,999077","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046995124","display_name":"Yingying Zhu","orcid":"https://orcid.org/0000-0003-4068-872X"},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingying Zhu","raw_affiliation_strings":["Huazhong University of Science and Technology (HUST),School of Computer Science and Technology,Wuhan,China,430074"],"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology (HUST),School of Computer Science and Technology,Wuhan,China,430074","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5044762053"],"corresponding_institution_ids":["https://openalex.org/I47720641"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4011553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2217","last_page":"2223"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9034000039100647,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10719","display_name":"3D Shape Modeling and Analysis","score":0.9034000039100647,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.02539999969303608,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.023399999365210533,"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":0.7152000069618225},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4837000072002411},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4767000079154968},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4311999976634979},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4187000095844269},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.41190001368522644},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.40779998898506165},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4043000042438507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723800003528595},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7152000069618225},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5267000198364258},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4837000072002411},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4311999976634979},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.41190001368522644},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.40779998898506165},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2996000051498413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":38,"referenced_works":["https://openalex.org/W2460657278","https://openalex.org/W2594519801","https://openalex.org/W2737234477","https://openalex.org/W2887531143","https://openalex.org/W2892220819","https://openalex.org/W2914234035","https://openalex.org/W2963125977","https://openalex.org/W2963182550","https://openalex.org/W2991216808","https://openalex.org/W3035574168","https://openalex.org/W3109154950","https://openalex.org/W3111535274","https://openalex.org/W3116258660","https://openalex.org/W3177330511","https://openalex.org/W3181190968","https://openalex.org/W4200629389","https://openalex.org/W4214755140","https://openalex.org/W4310925503","https://openalex.org/W4312442876","https://openalex.org/W4312616477","https://openalex.org/W4313145913","https://openalex.org/W4315783786","https://openalex.org/W4372283849","https://openalex.org/W4385245566","https://openalex.org/W4386071758","https://openalex.org/W4402667891","https://openalex.org/W4403977303","https://openalex.org/W4405429270","https://openalex.org/W4407467358","https://openalex.org/W4407900973","https://openalex.org/W4409365601","https://openalex.org/W4409367296","https://openalex.org/W4410915127","https://openalex.org/W4413145454","https://openalex.org/W4413146579","https://openalex.org/W4414243662","https://openalex.org/W4415796023","https://openalex.org/W4415798919"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"methods":[1],"have":[2],"demonstrated":[3],"remarkable":[4],"capabilities":[5],"in":[6,25,58],"3D":[7,46,77],"semantic":[8,78],"segmentation":[9],"through":[10],"their":[11,20],"powerful":[12],"attention":[13,91],"mechanisms,":[14],"but":[15],"the":[16,67,84,111],"quadratic":[17],"complexity":[18],"limits":[19],"modeling":[21],"of":[22,101,115],"long-range":[23,102],"dependencies":[24,103],"large-scale":[26],"point":[27],"clouds.":[28],"While":[29],"recent":[30],"Mamba-based":[31],"approaches":[32],"offer":[33],"efficient":[34],"processing":[35],"with":[36,41],"linear":[37],"complexity,":[38],"they":[39],"struggle":[40],"feature":[42],"representation":[43],"when":[44],"extracting":[45],"features.":[47,107],"However,":[48],"effectively":[49],"combining":[50],"these":[51],"complementary":[52],"strengths":[53],"remains":[54],"an":[55],"open":[56],"challenge":[57],"this":[59,62],"field.":[60],"In":[61,80],"paper,":[63],"we":[64,82],"propose":[65,83],"HybridTM,":[66],"first":[68],"hybrid":[69],"architecture":[70],"that":[71],"integrates":[72],"Transformer":[73],"and":[74,92,104,113,121,133],"Mamba":[75,93],"for":[76],"segmentation.":[79],"addition,":[81],"Inner":[85],"Layer":[86],"Hybrid":[87],"Strategy,":[88],"which":[89],"combines":[90],"at":[94,142],"a":[95],"finer":[96],"granularity,":[97],"enabling":[98],"simultaneous":[99],"capture":[100],"fine-grained":[105],"local":[106],"Extensive":[108],"experiments":[109],"demonstrate":[110],"effectiveness":[112],"generalization":[114],"our":[116,125],"HybridTM":[117,126],"on":[118,130],"diverse":[119],"indoor":[120],"outdoor":[122],"datasets.":[123],"Furthermore,":[124],"achieves":[127],"state-of-the-art":[128],"performance":[129],"ScanNet,":[131],"ScanNet200,":[132],"nuScenes":[134],"benchmarks.":[135],"The":[136],"code":[137],"will":[138],"be":[139],"made":[140],"available":[141],"https://github.com/deepinact/HybridTM.":[143]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}