{"id":"https://openalex.org/W6906271636","doi":"https://doi.org/10.15496/publikation-66935","title":"Towards Recognition as a Regularizer in Autonomous Driving","display_name":"Towards Recognition as a Regularizer in Autonomous Driving","publication_year":2022,"publication_date":"2022-03-25","ids":{"openalex":"https://openalex.org/W6906271636","doi":"https://doi.org/10.15496/publikation-66935"},"language":"en","primary_location":{"id":"doi:10.15496/publikation-66935","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-66935","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.15496/publikation-66935","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Behl, Aseem","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Behl, Aseem","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18170953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.2896000146865845,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.2896000146865845,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10036","display_name":"Advanced Neural Network Applications","score":0.1574999988079071,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.09200000017881393,"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/optical-flow","display_name":"Optical flow","score":0.6320000290870667},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5139999985694885},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5128999948501587},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.5099999904632568},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4832000136375427},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4674000144004822},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.42419999837875366},{"id":"https://openalex.org/keywords/advanced-driver-assistance-systems","display_name":"Advanced driver assistance systems","score":0.41909998655319214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7770000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7361999750137329},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.6320000290870667},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6312000155448914},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5139999985694885},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5128999948501587},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.5099999904632568},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4832000136375427},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3603000044822693},{"id":"https://openalex.org/C52102323","wikidata":"https://www.wikidata.org/wiki/Q1671968","display_name":"Pose","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C16345878","wikidata":"https://www.wikidata.org/wiki/Q107472979","display_name":"Orientation (vector space)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C107551265","wikidata":"https://www.wikidata.org/wiki/Q1458245","display_name":"Displacement (psychology)","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2989000082015991},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.296999990940094},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2662999927997589},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.26579999923706055},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C109950114","wikidata":"https://www.wikidata.org/wiki/Q4464732","display_name":"3D reconstruction","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.15496/publikation-66935","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-66935","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.15496/publikation-66935","is_oa":true,"landing_page_url":"https://doi.org/10.15496/publikation-66935","pdf_url":null,"source":{"id":"https://openalex.org/S7407053000","display_name":"Universit\u00e4tsbibliothek T\u00fcbingen","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"driving":[1,12,47,550,573,586,610,637,692],"promises":[2],"great":[3],"potential":[4],"for":[5,156,168,193,273,403,607],"social":[6],"and":[7,40,130,139,160,176,242,266,376,432,476,486,507,516,636,657],"economic":[8],"benefits.":[9],"While":[10],"autonomous":[11,29,61,102,124,133,144],"remains":[13],"an":[14,143,541],"unsolved":[15],"problem,":[16],"recent":[17],"advances":[18],"in":[19,26,78,107,119,123,153,187,200,218,319,321,337,390,598,681,702],"computer":[20],"vision":[21],"have":[22,73],"enabled":[23],"considerable":[24],"progress":[25],"development":[27],"of":[28,53,67,96,114,203,228,263,284,345,364,385,397,468,522,555,570,618,642,647,699],"vehicles.":[30],"For":[31,491],"instance,":[32],"recognition":[33,71,91,115,236,245,285,311,531],"methods":[34,72,84,92,192],"such":[35,169,238,533,588],"as":[36,116,239,400,425,427,534,540,589],"object":[37,300,440,452,661],"detection,":[38],"semantic":[39,42,87,240,398,535,558],"instance":[41,295,330],"segmentation":[43,331,536,559,564,620],"affords":[44],"the":[45,50,65,112,154,188,201,226,282,315,329,343,381,395,428,435,447,464,520,523,553,571,616,631,640,645,653],"self":[46],"vehicles":[48],"with":[49,64,182,366,501,514,697],"precise":[51],"understanding":[52],"their":[54,141,150,658],"surroundings":[55],"which":[56,215,580],"is":[57,164,180,333,527],"critical":[58],"to":[59,85,93,100,147,246,297,355,406,444,456,482,488,545,584,614,651],"safe":[60],"driving.":[62,103,134],"Furthermore,":[63,563],"advent":[66],"deep":[68,494],"learning,":[69],"machine":[70],"reached":[74],"human-like":[75],"performance.":[76],"Therefore,":[77,222,388,596],"this":[79,105,108,304,391,417,484,599],"thesis,":[80,109],"we":[81,110,224,306,326,341,393,454,496,601,688],"propose":[82,477],"different":[83],"exploit":[86],"cues":[88,237,254,312,532],"from":[89,287,310,380,411,500],"state-of-the-art":[90,691],"improve":[94],"performance":[95,693],"other":[97],"tasks":[98,157],"required":[99],"solve":[101],"To":[104],"end,":[106],"examine":[111],"effectiveness":[113,344],"a":[117,165,173,259,270,360,401,478,682],"regularizer":[118,402],"two":[120],"prominent":[121,166],"problems":[122],"driving,":[125],"namely,":[126],"scene":[127,195,248,276,316,350,423,557],"flow":[128,163,196,249,277,317,351,424],"estimation":[129,171,197],"end-to-end":[131,548,608],"learned":[132,549,609,624],"Besides":[135],"recognizing":[136],"traffic":[137],"participants":[138],"predicting":[140,421],"position,":[142],"car":[145],"needs":[146],"precisely":[148],"predict":[149,457],"3D":[151,174,177,194,275,299,404,407,422,429,439,451],"position":[152,175],"future":[155],"like":[158],"navigation":[159],"planning.":[161],"Scene":[162],"representation":[167,467,481,544],"motion":[170,178,405,436,448,471],"where":[172],"vector":[179],"associated":[181],"every":[183],"observed":[184],"surface":[185],"point":[186,408],"scene.":[189],"However,":[190,552],"existing":[191],"often":[198,567],"fail":[199],"presence":[202],"large":[204,229],"displacement":[205],"or":[206,212,231,591],"local":[207,232],"ambiguities,":[208],"e.g.,":[209],"at":[210],"texture-less":[211],"reflective":[213],"surfaces":[214],"are":[216,370,566,581],"omnipresent":[217],"dynamic":[219],"road":[220],"scenes.":[221],"first,":[223],"address":[225],"problem":[227,485],"displacements":[230],"ambiguities":[233],"by":[234,334,373,419,474],"exploiting":[235],"grouping":[241,399,434],"fine-grained":[243,298],"geometric":[244],"regularize":[247,546],"estimation.":[250,278],"We":[251,279,415,461,612,628],"compute":[252],"these":[253],"using":[255,438,450,575],"CNNs":[256],"trained":[257,568],"on":[258,348,623],"newly":[260],"annotated":[261],"dataset":[262],"stereo":[264,386],"images":[265],"integrate":[267],"them":[268],"into":[269,673],"CRF-based":[271],"model":[272],"robust":[274],"also":[280],"investigate":[281],"importance":[283],"granularity,":[286],"coarse":[288],"2D":[289,294,664],"bounding":[290,430,665],"box":[291,431],"estimates":[292],"over":[293],"segmentations":[296],"part":[301],"predictions.":[302],"From":[303],"study,":[305],"show":[307,462],"that":[308,328,463,530,690],"regularization":[309],"significantly":[313],"boosts":[314],"accuracy,":[318],"particular":[320],"challenging":[322,349],"foreground":[323],"regions.":[324],"Secondly,":[325],"conclude":[327],"cue":[332],"far":[335],"strongest,":[336],"our":[338,346,493],"setting.":[339],"Alongside,":[340],"demonstrate":[342],"method":[347],"benchmarks.":[352],"In":[353,442],"contrast":[354],"cameras,":[356],"laser":[357],"scanners":[358],"provide":[359],"360":[361],"degree":[362],"field":[363],"view":[365],"just":[367],"one":[368],"sensor,":[369],"generally":[371],"unaffected":[372],"lighting":[374],"conditions,":[375],"do":[377],"not":[378,582],"suffer":[379],"quadratic":[382],"error":[383],"behavior":[384,625],"cameras.":[387],"second,":[389],"work,":[392,600],"extend":[394],"idea":[396],"cloud":[409],"measurements":[410],"LIDAR":[412],"sensor":[413,509],"observations.":[414],"achieve":[416],"goal":[418],"jointly":[420],"well":[426,528],"semantically":[433,445],"vectors":[437,449],"detections.":[441],"order":[443],"group":[446],"detections,":[453],"need":[455],"pointiwise":[458],"rigid":[459,469],"motion.":[460],"traditional":[465],"global":[466],"body":[470],"prohibits":[472],"inference":[473],"CNNs,":[475],"translation":[479],"equivariant":[480],"circumvent":[483],"amenable":[487],"CNN":[489],"learning.":[490],"training":[492],"network,":[495],"augment":[497],"real":[498],"scans":[499],"virtual":[502],"objects,":[503],"realistically":[504],"modeling":[505],"occlusions":[506],"simulating":[508],"noise.":[510],"A":[511],"thorough":[512],"comparison":[513],"classic":[515],"learning-based":[517],"techniques":[518],"highlights":[519],"robustness":[521],"proposed":[524],"approach.":[525],"It":[526],"known":[529],"can":[537,678,694],"be":[538,679,695],"used":[539,650],"effective":[542],"intermediate":[543,605],"learning":[547],"policies.":[551,611],"task":[554],"street":[556],"requires":[560],"expensive":[561],"annotations.":[562],"algorithms":[565],"irrespective":[569],"actual":[572],"task,":[574],"auxiliary":[576],"image-space":[577],"loss":[578],"functions":[579],"guaranteed":[583],"maximize":[585],"metrics":[587],"safety":[590],"distance":[592],"traveled":[593],"per":[594],"intervention.":[595],"third,":[597],"analyze":[602],"several":[603,670],"recognition-based":[604],"representations":[606],"seek":[613],"quantify":[615],"impact":[617],"reducing":[619],"annotation":[621,634,703],"costs":[622],"cloning":[626],"agents.":[627],"systematically":[629],"study":[630],"trade-off":[632],"between":[633],"efficiency":[635],"performance,":[638],"i.e.,":[639],"types":[641],"classes":[643],"labeled,":[644],"number":[646],"image":[648],"samples":[649],"learn":[652],"visual":[654,676],"abstraction":[655],"model,":[656],"granularity":[659],"(e.g.,":[660],"masks":[662],"vs.":[663],"boxes).":[666],"Our":[667],"analysis":[668],"uncovers":[669],"practical":[671],"insights":[672],"how":[674],"segmentation-based":[675],"abstractions":[677],"exploited":[680],"more":[683],"label":[684],"efficient":[685],"manner.":[686],"Surprisingly,":[687],"find":[689],"achieved":[696],"orders":[698],"magnitude":[700],"reduction":[701],"cost.":[704]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}