{"id":"https://openalex.org/W4406457497","doi":"https://doi.org/10.1109/tits.2025.3525542","title":"HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation","display_name":"HSPFormer: Hierarchical Spatial Perception Transformer for Semantic Segmentation","publication_year":2025,"publication_date":"2025-01-16","ids":{"openalex":"https://openalex.org/W4406457497","doi":"https://doi.org/10.1109/tits.2025.3525542"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2025.3525542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3525542","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-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/A5011556498","display_name":"Siyu Chen","orcid":"https://orcid.org/0000-0002-1432-4909"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Siyu Chen","raw_affiliation_strings":["School of Computer Engineering, Jimei University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103286073","display_name":"Ting Han","orcid":"https://orcid.org/0009-0002-9474-8337"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ting Han","raw_affiliation_strings":["School of Geospatial Engineering and Science, Sun Yat-sen University, Zhuhai, China"],"affiliations":[{"raw_affiliation_string":"School of Geospatial Engineering and Science, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088514748","display_name":"Changshe Zhang","orcid":"https://orcid.org/0009-0002-9659-4888"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changshe Zhang","raw_affiliation_strings":["School of Ocean Information Engineering, Jimei University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Ocean Information Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049203004","display_name":"Jinhe Su","orcid":"https://orcid.org/0000-0003-1707-5685"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhe Su","raw_affiliation_strings":["School of Computer Engineering, Jimei University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101647875","display_name":"Ruisheng Wang","orcid":"https://orcid.org/0000-0003-0745-5158"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ruisheng Wang","raw_affiliation_strings":["Department of Geomatics Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Geomatics Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, Canada","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100374691","display_name":"Yiping Chen","orcid":"https://orcid.org/0000-0003-1465-6599"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiping Chen","raw_affiliation_strings":["School of Geospatial Engineering and Science, Sun Yat-sen University, Zhuhai, China"],"affiliations":[{"raw_affiliation_string":"School of Geospatial Engineering and Science, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081721333","display_name":"Zongyue Wang","orcid":"https://orcid.org/0000-0003-2409-7065"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongyue Wang","raw_affiliation_strings":["School of Computer Engineering, Jimei University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100620003","display_name":"Guorong Cai","orcid":"https://orcid.org/0000-0001-8091-271X"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guorong Cai","raw_affiliation_strings":["School of Computer Engineering, Jimei University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Jimei University, Xiamen, China","institution_ids":["https://openalex.org/I161346416"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5011556498"],"corresponding_institution_ids":["https://openalex.org/I161346416"],"apc_list":null,"apc_paid":null,"fwci":2.4362,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.86674927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"26","issue":"4","first_page":"4975","last_page":"4987"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.8902999758720398,"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":0.8902999758720398,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.8815000057220459,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.8137999773025513,"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":0.6253145337104797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5747747421264648},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5481966137886047},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5113091468811035},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4895106554031372},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40875744819641113},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3507957458496094},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3328976631164551},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19363966584205627},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18235427141189575},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09281212091445923},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.08188784122467041}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6253145337104797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5747747421264648},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5481966137886047},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5113091468811035},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4895106554031372},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40875744819641113},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3507957458496094},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3328976631164551},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19363966584205627},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18235427141189575},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09281212091445923},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.08188784122467041},{"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/tits.2025.3525542","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2025.3525542","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G1779093446","display_name":null,"funder_award_id":"2023J01799","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G2331034857","display_name":null,"funder_award_id":"2022J01819","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G2721776513","display_name":null,"funder_award_id":"2022J011394","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G3389261439","display_name":null,"funder_award_id":"3502Z202373036","funder_id":"https://openalex.org/F4320316884","funder_display_name":"Natural Science Foundation of Xiamen City"},{"id":"https://openalex.org/G3458291489","display_name":null,"funder_award_id":"2022J01337","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G3525545207","display_name":null,"funder_award_id":"2022J05157","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G4052947816","display_name":null,"funder_award_id":"42371457","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4801485154","display_name":null,"funder_award_id":"61902330","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G539368931","display_name":null,"funder_award_id":"41971424","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7477423354","display_name":null,"funder_award_id":"2023J01801","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G8359015589","display_name":null,"funder_award_id":"42371343","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G873737750","display_name":null,"funder_award_id":"42301468","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316884","display_name":"Natural Science Foundation of Xiamen City","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W125693051","https://openalex.org/W1903029394","https://openalex.org/W2108598243","https://openalex.org/W2115579991","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2560023338","https://openalex.org/W2963617879","https://openalex.org/W2971014764","https://openalex.org/W3015871565","https://openalex.org/W3108601100","https://openalex.org/W3112819693","https://openalex.org/W3118453581","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3170841864","https://openalex.org/W3172509117","https://openalex.org/W3175515048","https://openalex.org/W3194841206","https://openalex.org/W3203597819","https://openalex.org/W3203701986","https://openalex.org/W3215888920","https://openalex.org/W4200495456","https://openalex.org/W4214493665","https://openalex.org/W4214614183","https://openalex.org/W4220849367","https://openalex.org/W4226039775","https://openalex.org/W4293680532","https://openalex.org/W4301603159","https://openalex.org/W4307231856","https://openalex.org/W4308236200","https://openalex.org/W4312372834","https://openalex.org/W4312443924","https://openalex.org/W4312685069","https://openalex.org/W4312820606","https://openalex.org/W4312912496","https://openalex.org/W4313142416","https://openalex.org/W4367309081","https://openalex.org/W4372270072","https://openalex.org/W4376132550","https://openalex.org/W4378189111","https://openalex.org/W4385245566","https://openalex.org/W4386065578","https://openalex.org/W4386065590","https://openalex.org/W4386065698","https://openalex.org/W4386071550","https://openalex.org/W4386071792","https://openalex.org/W4386075493","https://openalex.org/W4386075877","https://openalex.org/W4386076340","https://openalex.org/W4386076613","https://openalex.org/W4386179772","https://openalex.org/W4390873795","https://openalex.org/W4390873847","https://openalex.org/W4390873955","https://openalex.org/W4390874575","https://openalex.org/W4391407164","https://openalex.org/W6788135285","https://openalex.org/W6792695861","https://openalex.org/W6794345597","https://openalex.org/W6796761347","https://openalex.org/W6797399245","https://openalex.org/W6802648153","https://openalex.org/W6803650990","https://openalex.org/W6839002298"],"related_works":["https://openalex.org/W2628861693","https://openalex.org/W4379231730","https://openalex.org/W3203087560","https://openalex.org/W4389858081","https://openalex.org/W4361279463","https://openalex.org/W2501551404","https://openalex.org/W4298131179","https://openalex.org/W4232814730","https://openalex.org/W2975814312","https://openalex.org/W2113201962"],"abstract_inverted_index":{"Semantic":[0],"perception":[1],"in":[2,9,26],"driving":[3,28],"scenarios":[4],"plays":[5],"a":[6,57,75,91],"crucial":[7],"role":[8],"intelligent":[10],"transportation":[11],"systems.":[12],"However,":[13],"existing":[14],"Transformer-based":[15],"semantic":[16,72,128],"segmentation":[17,73],"methods":[18,32],"often":[19],"do":[20],"not":[21],"fully":[22],"exploit":[23],"their":[24,44],"potential":[25],"understanding":[27],"scene":[29],"dynamically.":[30],"These":[31],"typically":[33],"lack":[34],"spatial":[35,45,105],"reasoning,":[36],"failing":[37],"to":[38,48,102,124],"effectively":[39],"correlate":[40],"image":[41],"pixels":[42],"with":[43,158],"positions,":[46],"leading":[47],"attention":[49],"drift.":[50],"To":[51],"address":[52],"this":[53],"issue,":[54],"we":[55,108],"propose":[56],"novel":[58],"architecture,":[59],"the":[60,79,84,110],"Hierarchical":[61,111],"Spatial":[62,85],"Perception":[63,87],"Transformer":[64,113],"(HSPFormer),":[65],"which":[66,116],"integrates":[67],"monocular":[68],"depth":[69,99,118],"estimation":[70,119],"and":[71,97,130,143,154,168],"into":[74],"unified":[76],"framework":[77,92],"for":[78,93],"first":[80],"time.":[81],"We":[82],"introduce":[83],"Depth":[86,145,173],"Auxiliary":[88],"Network":[89,114],"(SDPNet),":[90],"multiscale":[94],"feature":[95],"extraction":[96],"multilayer":[98],"map":[100],"prediction":[101],"establish":[103],"hierarchical":[104],"coherence.":[106],"Additionally,":[107],"design":[109],"Pyramid":[112],"(HPTNet),":[115],"uses":[117],"as":[120,140],"learnable":[121],"position":[122],"embeddings":[123],"form":[125],"spatially":[126],"correlated":[127],"representations":[129],"generate":[131],"global":[132],"contextual":[133],"information.":[134],"Experiments":[135],"on":[136,162,166,171],"benchmark":[137],"datasets":[138],"such":[139],"KITTI-360,":[141,163],"Cityscapes,":[142,167],"NYU":[144,172],"V2,":[146,174],"demonstrate":[147],"that":[148],"HSPFormer":[149],"outperforms":[150],"several":[151],"state-of-the-art":[152],"networks,":[153],"achieves":[155],"promising":[156],"performance":[157],"66.82%":[159],"top-1":[160],"mIoU":[161,165,170],"83.8%":[164],"57.7%":[169],"respectively.":[175],"The":[176],"code":[177],"will":[178],"be":[179],"made":[180],"publicly":[181],"available":[182],"at":[183],"<uri":[184],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[185],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/SY-Ch/HSPFormer</uri>.":[186]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}