{"id":"https://openalex.org/W4200126852","doi":"https://doi.org/10.1109/dicta52665.2021.9647140","title":"Attention-based Long-term Modeling for Deep Visual Odometry","display_name":"Attention-based Long-term Modeling for Deep Visual Odometry","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W4200126852","doi":"https://doi.org/10.1109/dicta52665.2021.9647140"},"language":"en","primary_location":{"id":"doi:10.1109/dicta52665.2021.9647140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta52665.2021.9647140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Digital Image Computing: Techniques and Applications (DICTA)","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/A5047533368","display_name":"Sangni Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Sangni Xu","raw_affiliation_strings":["School of Computer Science, University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604456","display_name":"Hao Xiong","orcid":"https://orcid.org/0000-0002-6842-1667"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Hao Xiong","raw_affiliation_strings":["Australian Institute of Health Innovation, Macquarie University, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Australian Institute of Health Innovation, Macquarie University, Sydney, Australia","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064063888","display_name":"Qiuxia Wu","orcid":"https://orcid.org/0000-0002-2284-7806"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuxia Wu","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443935","display_name":"Zhiyong Wang","orcid":"https://orcid.org/0000-0002-8043-0312"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhiyong Wang","raw_affiliation_strings":["School of Computer Science, University of Sydney, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5047533368"],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":0.4803,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.66066993,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"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":0.9998999834060669,"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":0.9998999834060669,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"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/T12549","display_name":"Image and Object Detection Techniques","score":0.9980000257492065,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.8206237554550171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8057900071144104},{"id":"https://openalex.org/keywords/visual-odometry","display_name":"Visual odometry","score":0.703258752822876},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6218934655189514},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.617036759853363},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6062731146812439},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.591545820236206},{"id":"https://openalex.org/keywords/motion-estimation","display_name":"Motion estimation","score":0.5695199966430664},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.555645763874054},{"id":"https://openalex.org/keywords/odometry","display_name":"Odometry","score":0.5522218346595764},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5431212186813354},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.46827220916748047},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.44315701723098755},{"id":"https://openalex.org/keywords/pose","display_name":"Pose","score":0.4111762046813965},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38129764795303345},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3158903121948242},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.25022563338279724},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.1147005558013916}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.8206237554550171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8057900071144104},{"id":"https://openalex.org/C5799516","wikidata":"https://www.wikidata.org/wiki/Q4110915","display_name":"Visual odometry","level":3,"score":0.703258752822876},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6218934655189514},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.617036759853363},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6062731146812439},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.591545820236206},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.5695199966430664},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.555645763874054},{"id":"https://openalex.org/C49441653","wikidata":"https://www.wikidata.org/wiki/Q2014717","display_name":"Odometry","level":4,"score":0.5522218346595764},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5431212186813354},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.46827220916748047},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.44315701723098755},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.4111762046813965},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38129764795303345},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3158903121948242},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.25022563338279724},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.1147005558013916},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dicta52665.2021.9647140","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dicta52665.2021.9647140","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 Digital Image Computing: Techniques and Applications (DICTA)","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":44,"referenced_works":["https://openalex.org/W612478963","https://openalex.org/W764651262","https://openalex.org/W1485009520","https://openalex.org/W1522301498","https://openalex.org/W1612997784","https://openalex.org/W1677182931","https://openalex.org/W1716229439","https://openalex.org/W2150066425","https://openalex.org/W2474281075","https://openalex.org/W2535547924","https://openalex.org/W2558027072","https://openalex.org/W2560474170","https://openalex.org/W2598706937","https://openalex.org/W2609883120","https://openalex.org/W2749379418","https://openalex.org/W2765767940","https://openalex.org/W2798483995","https://openalex.org/W2884962765","https://openalex.org/W2887825894","https://openalex.org/W2890860133","https://openalex.org/W2958731371","https://openalex.org/W2963264402","https://openalex.org/W2963782415","https://openalex.org/W2964019655","https://openalex.org/W2964314455","https://openalex.org/W2971000934","https://openalex.org/W2983619469","https://openalex.org/W3034233942","https://openalex.org/W3034364596","https://openalex.org/W3034549682","https://openalex.org/W3034906411","https://openalex.org/W3035583493","https://openalex.org/W3100901464","https://openalex.org/W3102327032","https://openalex.org/W3106440972","https://openalex.org/W3108746553","https://openalex.org/W3165610079","https://openalex.org/W4252201060","https://openalex.org/W6628877408","https://openalex.org/W6631190155","https://openalex.org/W6637636807","https://openalex.org/W6767088534","https://openalex.org/W6780004381","https://openalex.org/W6795742097"],"related_works":["https://openalex.org/W2979950214","https://openalex.org/W87609089","https://openalex.org/W3024737167","https://openalex.org/W2414561716","https://openalex.org/W3161199934","https://openalex.org/W2303855011","https://openalex.org/W2312326526","https://openalex.org/W2412578866","https://openalex.org/W3105866016","https://openalex.org/W4312703710"],"abstract_inverted_index":{"Visual":[0],"odometry":[1],"(VO)":[2],"aims":[3],"to":[4,64,82,102,114,232],"determine":[5],"the":[6,84,90,106,145,164,178,187,190,217,260,268],"positions":[7],"of":[8,94,151,264],"a":[9,140,210,226],"moving":[10],"camera":[11,66,91],"from":[12,51,169,206],"an":[13,61,95,132],"image":[14,62,96],"sequence":[15,63],"it":[16,228],"acquired.":[17],"It":[18],"has":[19],"been":[20],"extensively":[21],"utilized":[22],"in":[23,46,97,105,198],"many":[24],"applications":[25],"such":[26],"as":[27],"AR/VR,":[28],"autonomous":[29],"driving,":[30],"and":[31,41,49,157,214,237,253,262],"robotics.":[32],"Conventional":[33],"VO":[34,56,98],"methods":[35,72],"largely":[36],"rely":[37],"on":[38,248],"hand-crafted":[39],"features":[40,172],"data":[42],"association":[43],"that":[44],"are":[45,174],"fact":[47],"unreliable":[48],"suffering":[50],"fast":[52],"motions.":[53],"Therefore,":[54],"learning-based":[55,71],"utilizes":[57],"neural":[58],"networks":[59,81],"mapping":[60],"corresponding":[65],"poses":[67],"directly.":[68],"Most":[69],"existing":[70],"also":[73],"integrate":[74],"with":[75,181,221],"additional":[76],"Long":[77],"Short-Term":[78],"Memory":[79],"(LSTM)":[80],"model":[83,115,231],"temporal":[85,121,184,196,235],"context":[86,122],"across":[87],"images,":[88],"since":[89],"pose":[92],"estimation":[93,240],"is":[99,112],"highly":[100],"relevant":[101],"other":[103],"images":[104,170],"same":[107],"sequence.":[108],"However,":[109],"traditional":[110],"LSTM":[111,146],"limited":[113],"short-term":[116],"dependency":[117],"rather":[118],"than":[119],"long-term":[120,135,183,195,204,223,234],"or":[123],"global":[124,159],"information.":[125,185,224],"To":[126],"mitigate":[127],"this":[128],"issue,":[129],"we":[130],"propose":[131],"attention":[133,212],"based":[134],"modelling":[136],"approach":[137],"by":[138,177],"devising":[139],"new":[141],"fusion":[142,192],"gate":[143,193],"into":[144],"cell.":[147],"Our":[148],"method":[149,247,266],"consists":[150],"two":[152,199,249],"modules:":[153],"convolutional":[154,165],"motion":[155,160,166,171],"encoder":[156,167],"recurrent":[158],"refinement":[161,179,188],"module.":[162],"Specifically,":[163],"extracts":[168],"which":[173],"then":[175],"fused":[176],"module":[180],"more":[182],"In":[186],"module,":[189],"devised":[191,211],"generates":[194],"information":[197,205,236],"phases:":[200],"(1)":[201],"extracting":[202],"correlated":[203],"previous":[207],"predictions":[208],"through":[209],"module;":[213],"(2)":[215],"updating":[216],"current":[218],"hidden":[219],"state":[220],"extracted":[222],"As":[225],"result,":[227],"enables":[229],"our":[230,245,265],"gather":[233],"further":[238],"enhance":[239],"accuracy.":[241],"We":[242],"comprehensively":[243],"evaluate":[244],"proposed":[246],"public":[250],"datasets,":[251],"KITTI":[252],"Oxford":[254],"RobotCar.":[255],"The":[256],"experimental":[257],"results":[258],"demonstrate":[259],"effectiveness":[261],"superiority":[263],"over":[267],"baseline":[269],"model.":[270]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}