{"id":"https://openalex.org/W4416748647","doi":"https://doi.org/10.1109/iros60139.2025.11246766","title":"TASeg: Text-aware RGB-T Semantic Segmentation based on Fine-tuning Vision Foundation Models","display_name":"TASeg: Text-aware RGB-T Semantic Segmentation based on Fine-tuning Vision Foundation Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748647","doi":"https://doi.org/10.1109/iros60139.2025.11246766"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246766","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/A5102893512","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0003-4737-917X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109736425","display_name":"Te Cui","orcid":"https://orcid.org/0009-0002-3265-3148"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Te Cui","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041758470","display_name":"Q. P. Chu","orcid":"https://orcid.org/0000-0002-1260-3672"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qitong Chu","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004063144","display_name":"Wenjie Song","orcid":"https://orcid.org/0000-0003-3688-017X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Song","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105111708","display_name":"Yi Yang","orcid":"https://orcid.org/0009-0008-0117-8181"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068949782","display_name":"Yufeng Yue","orcid":"https://orcid.org/0000-0001-6628-7946"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufeng Yue","raw_affiliation_strings":["Beijing Institute of Technology,School of Automation,Beijing,China,100081"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology,School of Automation,Beijing,China,100081","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102893512"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.36889733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4136","last_page":"4141"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.626800000667572,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.626800000667572,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.17560000717639923,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.037300001829862595,"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":0.7590000033378601},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5044999718666077},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47099998593330383},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.39980000257492065},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.38600000739097595},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.35910001397132874},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.35409998893737793},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.32679998874664307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8004000186920166},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7590000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6662999987602234},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5044999718666077},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.38600000739097595},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3691999912261963},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.35910001397132874},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.35409998893737793},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.3172999918460846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3147999942302704},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.26330000162124634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246766","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2752782242","https://openalex.org/W2774839435","https://openalex.org/W2921749009","https://openalex.org/W3091001089","https://openalex.org/W3182674219","https://openalex.org/W3198062544","https://openalex.org/W4200635035","https://openalex.org/W4296913506","https://openalex.org/W4312912313","https://openalex.org/W4313139043","https://openalex.org/W4313639507","https://openalex.org/W4367663172","https://openalex.org/W4386075561","https://openalex.org/W4386179772","https://openalex.org/W4388191449","https://openalex.org/W4390190100","https://openalex.org/W4390489106","https://openalex.org/W4390873110","https://openalex.org/W4390874575","https://openalex.org/W4390971106","https://openalex.org/W4404809244"],"related_works":[],"abstract_inverted_index":{"Reliable":[0],"semantic":[1,18,127,138],"segmentation":[2,19,36,74],"of":[3],"open":[4],"environments":[5],"is":[6,57],"essential":[7],"for":[8],"intelligent":[9],"systems,":[10],"yet":[11],"significant":[12],"problems":[13],"remain:":[14],"1)":[15],"Existing":[16],"RGB-T":[17,73],"models":[20],"mainly":[21],"rely":[22],"on":[23],"low-level":[24],"visual":[25,41,107],"features":[26,104],"and":[27,55,62,135],"lack":[28],"high-level":[29],"textual":[30],"information,":[31],"which":[32,101,129],"struggle":[33],"with":[34,52,156],"accurate":[35],"when":[37],"categories":[38],"share":[39],"similar":[40],"characteristics.":[42],"2)":[43],"While":[44],"SAM":[45],"excels":[46],"in":[47,97,121,153],"instance-level":[48],"segmentation,":[49],"integrating":[50],"it":[51],"thermal":[53],"images":[54],"text":[56,119],"hindered":[58],"by":[59,76],"modality":[60],"heterogeneity":[61],"computational":[63],"inefficiency.":[64],"To":[65],"address":[66],"these,":[67],"we":[68,89,116],"propose":[69,90],"TASeg,":[70],"a":[71,91],"text-aware":[72],"framework":[75],"using":[77],"Low-Rank":[78],"Adaptation":[79],"(LoRA)":[80],"fine-tuning":[81],"technology":[82],"to":[83,125],"adapt":[84],"vision":[85],"foundation":[86],"models.":[87],"Specifically,":[88],"Dynamic":[92],"Feature":[93],"Fusion":[94],"Module":[95],"(DFFM)":[96],"the":[98,122,132,137],"image":[99],"encoder,":[100],"effectively":[102],"merges":[103],"from":[105],"multiple":[106],"modalities":[108],"while":[109],"freezing":[110],"SAM\u2019s":[111],"original":[112],"transformer":[113],"blocks.":[114],"Additionally,":[115],"incorporate":[117],"CLIP-generated":[118],"embeddings":[120],"mask":[123],"decoder":[124],"enable":[126],"alignment,":[128],"further":[130],"rectifies":[131],"classification":[133],"error":[134],"improves":[136],"understanding":[139],"accuracy.":[140],"Experimental":[141],"results":[142],"across":[143],"diverse":[144],"datasets":[145],"demonstrate":[146],"that":[147],"our":[148],"method":[149],"achieves":[150],"superior":[151],"performance":[152],"challenging":[154],"scenarios":[155],"fewer":[157],"trainable":[158],"parameters.":[159]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}