{"id":"https://openalex.org/W3016093065","doi":"https://doi.org/10.1109/icassp40776.2020.9053408","title":"Deep Monocular Video Depth Estimation Using Temporal Attention","display_name":"Deep Monocular Video Depth Estimation Using Temporal Attention","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016093065","doi":"https://doi.org/10.1109/icassp40776.2020.9053408","mag":"3016093065"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101616704","display_name":"Haoyu Ren","orcid":"https://orcid.org/0000-0001-9658-719X"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoyu Ren","raw_affiliation_strings":["Samsung Semiconductor Inc., San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Semiconductor Inc., San Diego, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022805456","display_name":"Mostafa El\u2010Khamy","orcid":"https://orcid.org/0000-0001-9421-6037"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mostafa El-khamy","raw_affiliation_strings":["Samsung Semiconductor Inc., San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Semiconductor Inc., San Diego, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331815","display_name":"Jungwon Lee","orcid":"https://orcid.org/0000-0001-8922-063X"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jungwon Lee","raw_affiliation_strings":["Samsung Semiconductor Inc., San Diego, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Semiconductor Inc., San Diego, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210101778"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1988","last_page":"1992"},"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":0.9983000159263611,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9976999759674072,"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/monocular","display_name":"Monocular","score":0.8662521839141846},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7716683149337769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.734415590763092},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.7153398990631104},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5711252689361572},{"id":"https://openalex.org/keywords/motion-compensation","display_name":"Motion compensation","score":0.5646316409111023},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.550719678401947},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.4194231629371643},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2381238043308258}],"concepts":[{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.8662521839141846},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716683149337769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.734415590763092},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.7153398990631104},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5711252689361572},{"id":"https://openalex.org/C128840427","wikidata":"https://www.wikidata.org/wiki/Q1302174","display_name":"Motion compensation","level":2,"score":0.5646316409111023},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.550719678401947},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.4194231629371643},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2381238043308258},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053408","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053408","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1905829557","https://openalex.org/W2074254947","https://openalex.org/W2115579991","https://openalex.org/W2171740948","https://openalex.org/W2300779272","https://openalex.org/W2520707372","https://openalex.org/W2560474170","https://openalex.org/W2609883120","https://openalex.org/W2949058227","https://openalex.org/W2949208911","https://openalex.org/W2951234442","https://openalex.org/W2963488291","https://openalex.org/W2963591054","https://openalex.org/W2963654727","https://openalex.org/W2963782415","https://openalex.org/W2966444020","https://openalex.org/W2982102242","https://openalex.org/W6685261749","https://openalex.org/W6697658144","https://openalex.org/W6763285803"],"related_works":["https://openalex.org/W1579157894","https://openalex.org/W1967654336","https://openalex.org/W2060632806","https://openalex.org/W1530267862","https://openalex.org/W2030154815","https://openalex.org/W3005839910","https://openalex.org/W2995690499","https://openalex.org/W1494405360","https://openalex.org/W2051121715","https://openalex.org/W2050955821"],"abstract_inverted_index":{"Monocular":[0],"video":[1,21],"depth":[2,22,77,85,107],"estimation":[3,23,78,108],"(MVDE)":[4],"plays":[5],"a":[6,33,57],"crucial":[7],"role":[8],"in":[9],"3D":[10],"computer":[11],"vision.":[12],"In":[13],"this":[14],"paper,":[15],"we":[16],"propose":[17],"an":[18],"end-to-end":[19],"monocular":[20,76],"network":[24,30,42,79],"based":[25],"on":[26],"temporal":[27,40,58,73],"attention.":[28],"Our":[29],"starts":[31],"by":[32],"motion":[34],"compensation":[35],"module":[36,60],"where":[37],"the":[38,48,52,67,72,84,87,103],"spatial":[39],"transformer":[41],"(STN)":[43],"is":[44,61,80],"utilized":[45],"to":[46,63,82,102],"warp":[47],"input":[49],"frames":[50],"using":[51],"estimated":[53],"optical":[54],"flow.":[55],"Next,":[56],"attention":[59],"used":[62,81],"combine":[64],"features":[65],"from":[66,86],"warped":[68],"frames,":[69],"while":[70],"emphasizing":[71],"consistency.":[74],"A":[75],"estimate":[83],"temporally":[88],"combined":[89],"features.":[90],"Experimental":[91],"results":[92],"demonstrate":[93],"that":[94],"our":[95],"proposed":[96],"framework":[97],"achieves":[98],"better":[99],"performance":[100],"compared":[101],"state-of-the-art":[104],"single":[105],"image":[106],"(SIDE)":[109],"networks,":[110],"as":[111,113],"well":[112],"existing":[114],"MVDE":[115],"methods.":[116]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}