{"id":"https://openalex.org/W4416749868","doi":"https://doi.org/10.1109/iros60139.2025.11246334","title":"TerraX: Visual Terrain Classification Enhanced by Vision-Language Models","display_name":"TerraX: Visual Terrain Classification Enhanced by Vision-Language Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416749868","doi":"https://doi.org/10.1109/iros60139.2025.11246334"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246334","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":"conference-paper","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/A5101461241","display_name":"Hongze Li","orcid":"https://orcid.org/0000-0002-3985-6805"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongze Li","raw_affiliation_strings":["School of Intelligence Science and Technology, Peking University,National Key Lab of General Artificial Intelligence,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Peking University,National Key Lab of General Artificial Intelligence,Beijing,China,100871","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuchuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuchuan Huang","raw_affiliation_strings":["School of Intelligence Science and Technology, Peking University,National Key Lab of General Artificial Intelligence,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Peking University,National Key Lab of General Artificial Intelligence,Beijing,China,100871","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinhai Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhai Chang","raw_affiliation_strings":["School of Intelligence Science and Technology, Peking University,National Key Lab of General Artificial Intelligence,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Peking University,National Key Lab of General Artificial Intelligence,Beijing,China,100871","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045140292","display_name":"Jun Zhou","orcid":"https://orcid.org/0000-0001-6033-6102"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Zhou","raw_affiliation_strings":["School of Intelligence Science and Technology, Peking University,National Key Lab of General Artificial Intelligence,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Peking University,National Key Lab of General Artificial Intelligence,Beijing,China,100871","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101153354","display_name":"Huijing Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huijing Zhao","raw_affiliation_strings":["School of Intelligence Science and Technology, Peking University,National Key Lab of General Artificial Intelligence,Beijing,China,100871"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Intelligence Science and Technology, Peking University,National Key Lab of General Artificial Intelligence,Beijing,China,100871","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210100255"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"15383","last_page":"15390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.30979999899864197,"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":0.30979999899864197,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.17829999327659607,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10689","display_name":"Remote-Sensing Image Classification","score":0.13729999959468842,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/terrain","display_name":"Terrain","score":0.8137000203132629},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.676800012588501},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5677000284194946},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5519000291824341},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5425000190734863},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4431000053882599},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4189000129699707},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.39910000562667847}],"concepts":[{"id":"https://openalex.org/C161840515","wikidata":"https://www.wikidata.org/wiki/Q186131","display_name":"Terrain","level":2,"score":0.8137000203132629},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562000155448914},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.676800012588501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5831000208854675},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4431000053882599},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3846000134944916},{"id":"https://openalex.org/C99695388","wikidata":"https://www.wikidata.org/wiki/Q350514","display_name":"Raised-relief map","level":3,"score":0.37599998712539673},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2928999960422516},{"id":"https://openalex.org/C118350294","wikidata":"https://www.wikidata.org/wiki/Q17341992","display_name":"Terrain rendering","level":3,"score":0.28299999237060547},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.26170000433921814},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246334","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2023504165","https://openalex.org/W2027809320","https://openalex.org/W2089652819","https://openalex.org/W2108598243","https://openalex.org/W2133587673","https://openalex.org/W2194775991","https://openalex.org/W2963163009","https://openalex.org/W2997591391","https://openalex.org/W3032150799","https://openalex.org/W3096411729","https://openalex.org/W3135285255","https://openalex.org/W3194873387","https://openalex.org/W4285610291","https://openalex.org/W4286776321","https://openalex.org/W4312551089","https://openalex.org/W4365420262","https://openalex.org/W4386065742","https://openalex.org/W4390190234","https://openalex.org/W4392172801","https://openalex.org/W4402727922","https://openalex.org/W4403570551","https://openalex.org/W4405785566","https://openalex.org/W4405786911"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"Terrain":[1],"Classification":[2],"(VTC)":[3],"plays":[4],"a":[5,60,80,90,109],"vital":[6],"role":[7],"in":[8,127,180],"enabling":[9],"unmanned":[10],"ground":[11],"vehicles":[12],"to":[13,45,120,145],"understand":[14],"complex":[15,181],"environments.":[16,182],"Existing":[17],"research":[18],"relies":[19],"on":[20,133],"image-label":[21],"pairs":[22],"annotated":[23,107],"by":[24],"static":[25],"label":[26],"sets,":[27],"where":[28],"semantic":[29],"ambiguity":[30],"and":[31,49,89,104,125,142,151,153,164],"high":[32],"annotation":[33,113],"costs":[34],"constrain":[35],"fine-grained":[36,73],"terrain":[37,47,93,100,129,149],"characterization.":[38],"These":[39],"limitations":[40],"hinder":[41],"the":[42,134],"model\u2019s":[43],"adaptation":[44],"real-world":[46,128,165],"diversity":[48],"restrict":[50],"its":[51,176],"applicability.":[52],"To":[53],"address":[54],"these":[55],"issues,":[56],"we":[57],"propose":[58],"TerraX,":[59],"vision-language":[61,111],"learning":[62],"framework":[63,78],"that":[64,168],"integrates":[65],"multi-modal":[66],"image-label-text":[67],"data,":[68],"unifying":[69],"structured":[70],"annotations":[71],"with":[72],"natural":[74],"language":[75],"descriptions.":[76],"The":[77],"introduces":[79],"composite":[81],"dataset":[82],"TerraData,":[83],"an":[84],"evaluation":[85,118],"benchmark":[86],"suite":[87],"TerraBench,":[88],"CLIP-based":[91],"visual":[92],"classification":[94,130],"model":[95,123],"TerraCLIP.":[96],"TerraData":[97],"aggregates":[98],"multi-source":[99],"images":[101],"from":[102],"public":[103],"self-collected":[105],"datasets,":[106],"through":[108],"VLM-based":[110],"data":[112],"pipeline.":[114],"TerraBench":[115],"defines":[116],"three":[117],"benchmarks":[119,163],"systematically":[121],"assess":[122],"robustness":[124],"adaptability":[126],"scenarios.":[131],"Built":[132],"CLIP":[135],"model,":[136],"TerraCLIP":[137],"utilizes":[138],"multi-granularity":[139],"contrastive":[140],"loss":[141],"LoRA":[143],"fine-tuning":[144],"enhance":[146],"understanding":[147],"for":[148,157,178],"categories":[150],"attributes,":[152],"incorporates":[154],"confidence-weighted":[155],"inference":[156],"accurate":[158],"predictions.":[159],"Extensive":[160],"experiments":[161],"across":[162],"platforms":[166],"demonstrate":[167],"our":[169],"approach":[170],"significantly":[171],"enhances":[172],"VTC":[173],"performance,":[174],"highlighting":[175],"potential":[177],"deployment":[179]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}