{"id":"https://openalex.org/W4392903840","doi":"https://doi.org/10.1109/icassp48485.2024.10447321","title":"Self-Supervised Multi-Scale Hierarchical Refinement Method for Joint Learning of Optical Flow and Depth","display_name":"Self-Supervised Multi-Scale Hierarchical Refinement Method for Joint Learning of Optical Flow and Depth","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903840","doi":"https://doi.org/10.1109/icassp48485.2024.10447321"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5051282546","display_name":"Rokia Abdein","orcid":"https://orcid.org/0000-0003-2510-1804"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Rokia Abdein","raw_affiliation_strings":["Harbin Engineering University,School of Information and Communication Engineering,Harbin,China,150001","Key Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,School of Information and Communication Engineering,Harbin,China,150001","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"Key Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information Technology, Harbin, China","institution_ids":["https://openalex.org/I890469752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019337921","display_name":"Xuezhi Xiang","orcid":"https://orcid.org/0000-0002-6185-833X"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuezhi Xiang","raw_affiliation_strings":["Harbin Engineering University,School of Information and Communication Engineering,Harbin,China,150001","Key Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,School of Information and Communication Engineering,Harbin,China,150001","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"Key Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information Technology, Harbin, China","institution_ids":["https://openalex.org/I890469752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333357","display_name":"Yiming Chen","orcid":"https://orcid.org/0009-0002-3658-2754"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]},{"id":"https://openalex.org/I890469752","display_name":"Ministry of Industry and Information Technology","ror":"https://ror.org/0385nmy68","country_code":"CN","type":"government","lineage":["https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Chen","raw_affiliation_strings":["Harbin Engineering University,School of Information and Communication Engineering,Harbin,China,150001","Key Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information Technology, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University,School of Information and Communication Engineering,Harbin,China,150001","institution_ids":["https://openalex.org/I151727225"]},{"raw_affiliation_string":"Key Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information Technology, Harbin, China","institution_ids":["https://openalex.org/I890469752"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056275425","display_name":"Mingliang Zhai","orcid":"https://orcid.org/0000-0001-5475-9221"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingliang Zhai","raw_affiliation_strings":["Nanjing University of Posts and Telecommunications,School of Automation,Nanjing,China","School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Posts and Telecommunications,School of Automation,Nanjing,China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"School of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109797436","display_name":"Abdulmotaleb El Saddik","orcid":null},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Abdulmotaleb El Saddik","raw_affiliation_strings":["University of Ottawa,School of Electrical Engineering and Computer Science,Ottawa,Canada,ON K1N 6N5"],"affiliations":[{"raw_affiliation_string":"University of Ottawa,School of Electrical Engineering and Computer Science,Ottawa,Canada,ON K1N 6N5","institution_ids":["https://openalex.org/I153718931"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051282546"],"corresponding_institution_ids":["https://openalex.org/I151727225","https://openalex.org/I890469752"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46907152,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2925","last_page":"2929"},"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9973000288009644,"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":0.9896000027656555,"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/optical-flow","display_name":"Optical flow","score":0.7956379055976868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7811387777328491},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.6662502288818359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6463915705680847},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6254345178604126},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.542125940322876},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5398421287536621},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.5321390628814697},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43997079133987427},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.43543633818626404},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42566749453544617},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4119880497455597},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3145348131656647},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.14402687549591064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09596630930900574},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07138407230377197}],"concepts":[{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.7956379055976868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811387777328491},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6662502288818359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6463915705680847},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6254345178604126},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.542125940322876},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5398421287536621},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.5321390628814697},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43997079133987427},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.43543633818626404},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42566749453544617},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4119880497455597},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3145348131656647},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.14402687549591064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09596630930900574},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07138407230377197},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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"},{"id":"https://openalex.org/F4320323085","display_name":"Natural Science Foundation of Heilongjiang Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W764651262","https://openalex.org/W1921093919","https://openalex.org/W2115579991","https://openalex.org/W2520707372","https://openalex.org/W2890949887","https://openalex.org/W2949023359","https://openalex.org/W2953804911","https://openalex.org/W2962864875","https://openalex.org/W2963583471","https://openalex.org/W2963782415","https://openalex.org/W2964677288","https://openalex.org/W2964968086","https://openalex.org/W3007774126","https://openalex.org/W3014263713","https://openalex.org/W3034642839","https://openalex.org/W3034896357","https://openalex.org/W3109908659","https://openalex.org/W3184023119","https://openalex.org/W4210254627","https://openalex.org/W4312275038","https://openalex.org/W4381930141"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Recurrently":[0],"refining":[1],"the":[2,16,27,43,59,69,75,87,95,120,127,137,145],"optical":[3,31,88],"flow":[4,32,89,97],"based":[5],"on":[6,47,136],"a":[7,23,64,111],"single":[8,65],"high-resolution":[9,66],"feature":[10],"demonstrates":[11,133],"high":[12],"performance.":[13],"We":[14,108],"exploit":[15],"strength":[17],"of":[18,30,45],"this":[19],"strategy":[20],"to":[21,40,73,84,104,116,123],"build":[22],"novel":[24],"architecture":[25,37],"for":[26,58],"joint":[28],"learning":[29],"and":[33,101],"depth.":[34],"Our":[35,130],"pro-posed":[36],"is":[38,51,56],"improved":[39],"work":[41],"in":[42,78,126,144],"case":[44],"training":[46],"unlabeled":[48],"data,":[49],"which":[50],"extremely":[52],"challenging.":[53],"The":[54],"loss":[55,71,115,122],"computed":[57],"iterations":[60],"carried":[61],"out":[62],"over":[63],"feature,":[67],"where":[68],"reconstruction":[70,121],"fails":[72],"optimize":[74],"accuracy":[76,125],"particularity":[77],"occluded":[79,128,146],"regions.":[80,129,147],"Therefore,":[81],"we":[82],"propose":[83,110],"hierarchically":[85],"refine":[86],"across":[90],"multiple":[91],"scales":[92],"while":[93],"feeding":[94],"rigid":[96],"calculated":[98],"from":[99],"depth":[100],"camera":[102],"pose":[103],"provide":[105],"more":[106,142],"refinement.":[107],"further":[109],"self-supervised":[112],"patch-based":[113],"similarity":[114],"be":[117],"optimized":[118],"with":[119,141],"improve":[124],"proposed":[131],"method":[132],"efficient":[134],"performance":[135],"KITTI":[138],"2015":[139],"dataset,":[140],"improvement":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}