{"id":"https://openalex.org/W4375869027","doi":"https://doi.org/10.1109/icassp49357.2023.10096716","title":"Adaptive Semantic Fusion Framework for Unsupervised Monocular Depth Estimation","display_name":"Adaptive Semantic Fusion Framework for Unsupervised Monocular Depth Estimation","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869027","doi":"https://doi.org/10.1109/icassp49357.2023.10096716"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5027057491","display_name":"Ruoqi Li","orcid":"https://orcid.org/0000-0003-3730-9370"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruoqi Li","raw_affiliation_strings":["University of Electronic Science Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035885712","display_name":"Huimin Yu","orcid":"https://orcid.org/0000-0002-8206-3747"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin Yu","raw_affiliation_strings":["University of Electronic Science Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104122760","display_name":"Kaiyang Du","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyang Du","raw_affiliation_strings":["University of Electronic Science Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103052017","display_name":"Zhuoling Xiao","orcid":"https://orcid.org/0000-0002-8118-2330"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoling Xiao","raw_affiliation_strings":["University of Electronic Science Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081115024","display_name":"Bo Yan","orcid":"https://orcid.org/0000-0003-0256-9682"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Yan","raw_affiliation_strings":["University of Electronic Science Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064713266","display_name":"Zhengxi Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengxi Yuan","raw_affiliation_strings":["University of Electronic Science Technology of China"],"affiliations":[{"raw_affiliation_string":"University of Electronic Science Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5027057491"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":0.7254,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71660586,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":1.0,"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/T10531","display_name":"Advanced Vision and Imaging","score":1.0,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.7622718214988708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7056643962860107},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7007924318313599},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.6413791179656982},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6178643703460693},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6061897873878479},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6033565998077393},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5415601134300232},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4776840806007385},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.46889418363571167},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.43063366413116455},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38970327377319336}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7622718214988708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7056643962860107},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7007924318313599},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.6413791179656982},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6178643703460693},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6061897873878479},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6033565998077393},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5415601134300232},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4776840806007385},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.46889418363571167},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43063366413116455},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38970327377319336},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/4"}],"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/W1905829557","https://openalex.org/W2083047701","https://openalex.org/W2117248802","https://openalex.org/W2150066425","https://openalex.org/W2520707372","https://openalex.org/W2609883120","https://openalex.org/W2916798096","https://openalex.org/W2951234442","https://openalex.org/W2963412495","https://openalex.org/W2981518351","https://openalex.org/W2985775862","https://openalex.org/W2990791152","https://openalex.org/W3008061557","https://openalex.org/W3097932847","https://openalex.org/W3138768133","https://openalex.org/W3145609993","https://openalex.org/W3174211490","https://openalex.org/W3194533273","https://openalex.org/W3206647015","https://openalex.org/W4206764080","https://openalex.org/W4224920414","https://openalex.org/W6685261749","https://openalex.org/W6785345353"],"related_works":["https://openalex.org/W2353179089","https://openalex.org/W2923538289","https://openalex.org/W2353125546","https://openalex.org/W2470643824","https://openalex.org/W4400595174","https://openalex.org/W2349635380","https://openalex.org/W4353089801","https://openalex.org/W2353819554","https://openalex.org/W3080403000","https://openalex.org/W2378011361"],"abstract_inverted_index":{"Unsupervised":[0],"monocular":[1],"depth":[2,53,101,124],"estimation":[3,54],"plays":[4],"an":[5],"important":[6],"role":[7],"in":[8,18,34,38,137,169],"autonomous":[9],"driving,":[10],"and":[11,36,85,135,145,163],"has":[12],"been":[13],"received":[14],"considerable":[15],"research":[16],"attention":[17],"recent":[19],"years.":[20],"Nevertheless,":[21],"numerous":[22],"existing":[23],"methods":[24,156],"relying":[25],"on":[26,142],"photometric":[27],"consistency":[28,134],"are":[29,89],"excessively":[30],"susceptible":[31],"to":[32,62,66,113,132],"variations":[33],"illumination":[35],"suffer":[37],"the":[39,60,79,86,111,123,127,143,153,170],"regions":[40,171],"with":[41,110],"strong":[42],"reflection.":[43,174],"To":[44],"overcome":[45],"this":[46],"limitation,":[47],"we":[48,70],"propose":[49],"a":[50,97],"novel":[51],"unsupervised":[52],"framework":[55],"named":[56],"ColorDepth,":[57],"which":[58],"forces":[59],"model":[61,109],"explore":[63],"object":[64],"semantic":[65,73,80,129],"infer":[67],"depth.":[68],"Specifically,":[69],"extract":[71],"pixel-level":[72],"prior":[74],"clues":[75],"of":[76,105,172],"objects":[77],"using":[78],"segmentation":[81],"network.":[82],"These":[83],"priors":[84],"original":[87],"image":[88],"then":[90],"adaptively":[91],"fused":[92,119],"into":[93],"color":[94],"data":[95,120],"by":[96,160],"learnable":[98],"parameter":[99],"for":[100],"estimation.":[102],"The":[103,118],"incorporation":[104],"semantics":[106],"endows":[107],"our":[108,150],"ability":[112],"perceive":[114],"scene":[115],"structure":[116],"information.":[117],"effectively":[121],"alleviates":[122],"ambiguity":[125],"within":[126],"same":[128],"block,":[130],"leading":[131],"improved":[133],"robustness":[136],"challenging":[138],"scenarios.":[139],"Extensive":[140],"experiments":[141],"KITTI":[144],"Make3D":[146],"datasets":[147],"show":[148],"that":[149],"method":[151],"surpasses":[152],"previous":[154],"state-of-the-art":[155],"even":[157],"those":[158],"supervised":[159],"additional":[161],"constraints,":[162],"brings":[164],"significant":[165],"performance":[166],"improvement":[167],"particularly":[168],"high":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-26T15:22:09.906841","created_date":"2025-10-10T00:00:00"}