{"id":"https://openalex.org/W4416252228","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227192","title":"Lightweight Self-Supervised Monocular Depth Estimation Based on Multi-Scale Hybrid Attention","display_name":"Lightweight Self-Supervised Monocular Depth Estimation Based on Multi-Scale Hybrid Attention","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252228","doi":"https://doi.org/10.1109/ijcnn64981.2025.11227192"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11227192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5029445062","display_name":"Yi Xue","orcid":"https://orcid.org/0000-0001-7728-1531"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xue Yi","raw_affiliation_strings":["School of Software Engineering Beijing Jiaotong University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016181167","display_name":"Ruipeng Gao","orcid":"https://orcid.org/0000-0002-2490-6654"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruipeng Gao","raw_affiliation_strings":["School of Software Engineering Beijing Jiaotong University,Beijing,China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering Beijing Jiaotong University,Beijing,China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043102837","display_name":"Gang Han","orcid":"https://orcid.org/0000-0002-5717-4509"},"institutions":[{"id":"https://openalex.org/I4210136859","display_name":"Xi\u2019an University of Posts and Telecommunications","ror":"https://ror.org/04jn0td46","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210136859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Han","raw_affiliation_strings":["School of Cyberspace Security Xi’an University of Posts and Telecommunications,Xi’an,China"],"affiliations":[{"raw_affiliation_string":"School of Cyberspace Security Xi’an University of Posts and Telecommunications,Xi’an,China","institution_ids":["https://openalex.org/I4210136859"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029445062"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37590436,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.5745999813079834,"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":0.5745999813079834,"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":0.1665000021457672,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.05530000105500221,"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/computation","display_name":"Computation","score":0.633400022983551},{"id":"https://openalex.org/keywords/monocular","display_name":"Monocular","score":0.6051999926567078},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5508000254631042},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.503600001335144},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.37630000710487366},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3458999991416931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7213000059127808},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.633400022983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6299999952316284},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.6051999926567078},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5508000254631042},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.503600001335144},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3822000026702881},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.303600013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11227192","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11227192","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1803059841","https://openalex.org/W2108598243","https://openalex.org/W2115579991","https://openalex.org/W2132947399","https://openalex.org/W2300779272","https://openalex.org/W2520707372","https://openalex.org/W2593414960","https://openalex.org/W2609883120","https://openalex.org/W2793286375","https://openalex.org/W2886322387","https://openalex.org/W2962807621","https://openalex.org/W2963155035","https://openalex.org/W2963265330","https://openalex.org/W2963412495","https://openalex.org/W2963488291","https://openalex.org/W2963583471","https://openalex.org/W2963654727","https://openalex.org/W2963906250","https://openalex.org/W2981518351","https://openalex.org/W2985775862","https://openalex.org/W3034428934","https://openalex.org/W3083550621","https://openalex.org/W3107156787","https://openalex.org/W3173274332","https://openalex.org/W3173727695","https://openalex.org/W3204559841","https://openalex.org/W4206545998","https://openalex.org/W4292974688","https://openalex.org/W4307896876","https://openalex.org/W4319300392","https://openalex.org/W4321512633","https://openalex.org/W4385245566","https://openalex.org/W4386075593","https://openalex.org/W4386076206","https://openalex.org/W4403944333","https://openalex.org/W4411245018"],"related_works":[],"abstract_inverted_index":{"Self-supervised":[0],"monocular":[1],"depth":[2,19,76],"estimation":[3,77],"has":[4],"gained":[5],"significant":[6],"traction":[7],"due":[8],"to":[9,12,33,158],"its":[10],"capacity":[11],"train":[13],"models":[14],"without":[15],"the":[16,126,141,152],"need":[17],"for":[18],"annotations.":[20],"However,":[21],"CNNs":[22],"are":[23],"inherently":[24],"constrained":[25],"by":[26,50,155],"limited":[27],"receptive":[28],"fields,":[29],"restricting":[30],"their":[31],"ability":[32],"infer":[34],"beyond":[35],"local":[36,94],"contexts.":[37],"To":[38],"address":[39],"this,":[40],"hybrid":[41],"architectures":[42],"that":[43,79],"integrate":[44],"Transformers":[45],"have":[46],"demonstrated":[47],"exceptional":[48],"performance":[49],"capturing":[51],"long-range":[52],"dependencies.":[53],"Nevertheless,":[54],"such":[55],"large":[56],"backbones":[57],"impose":[58],"substantial":[59],"demands":[60],"on":[61,140],"both":[62,93],"computation":[63],"and":[64,74,95,119,128,132],"storage":[65],"resources.":[66],"In":[67],"this":[68],"study,":[69],"we":[70],"propose":[71],"a":[72],"lightweight":[73],"computation-efficient":[75],"network":[78],"synergistically":[80],"combines":[81],"traditional":[82],"convolutions":[83],"with":[84],"attention":[85],"mechanisms.":[86],"Our":[87,135],"model":[88],"is":[89],"capable":[90],"of":[91,130,148],"conducting":[92],"global":[96],"reasoning,":[97],"thereby":[98],"preserving":[99],"high":[100],"accuracy":[101,147],"while":[102,150],"significantly":[103],"reducing":[104,151],"computational":[105],"overhead.":[106],"We":[107],"present":[108],"our":[109],"novel":[110],"architectural":[111],"components,":[112],"including":[113],"convolutional":[114],"samplers,":[115],"cross-feature":[116],"extraction":[117,127],"modules,":[118,122],"interactive":[120],"fusion":[121,129],"which":[123],"collectively":[124],"enhance":[125],"multi-dimensional":[131],"multi-scale":[133],"features.":[134],"approach":[136],"establishes":[137],"new":[138],"benchmarks":[139],"KITTI":[142],"dataset,":[143],"achieving":[144],"an":[145],"inference":[146],"98.4%":[149],"parameter":[153],"count":[154],"52.4%":[156],"relative":[157],"Monodepth2.":[159]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}