{"id":"https://openalex.org/W6967297413","doi":"https://doi.org/10.5075/epfl-thesis-8994","title":"Visual Scene Understanding for Transportation: From Detecting Objects To Relationships","display_name":"Visual Scene Understanding for Transportation: From Detecting Objects To Relationships","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W6967297413","doi":"https://doi.org/10.5075/epfl-thesis-8994"},"language":"en","primary_location":{"id":"pmh:doi:10.5075/epfl-thesis-8994","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoral thesis"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://infoscience.epfl.ch/handle/20.500.14299/192769","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Adaimi, George","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Adaimi, George","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"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":0.2867000102996826,"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":0.2867000102996826,"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":0.22380000352859497,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1476999968290329,"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/leverage","display_name":"Leverage (statistics)","score":0.6769999861717224},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5462999939918518},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.43059998750686646},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.42739999294281006},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.40470001101493835},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.37380000948905945},{"id":"https://openalex.org/keywords/pedestrian","display_name":"Pedestrian","score":0.36649999022483826}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7109000086784363},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6769999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6204000115394592},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5462999939918518},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49149999022483826},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4618000090122223},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.40470001101493835},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C2777113093","wikidata":"https://www.wikidata.org/wiki/Q221488","display_name":"Pedestrian","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.33079999685287476},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3149999976158142},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.30959999561309814},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29739999771118164},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.273499995470047},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:doi:10.5075/epfl-thesis-8994","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoral thesis"},{"id":"pmh:oai:infoscience.epfl.ch:298436","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/192769","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoral thesis"},{"id":"doi:10.5075/epfl-thesis-8994","is_oa":true,"landing_page_url":"https://doi.org/10.5075/epfl-thesis-8994","pdf_url":null,"source":{"id":"https://openalex.org/S4306400488","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","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":"thesis"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:298436","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/192769","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doctoral thesis"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Transportation,":[0],"which":[1,241],"deals":[2],"with":[3,43,102,265],"moving":[4],"people":[5,223,233],"and":[6,20,27,51,85,109,132,135,159,190,210,222,234,270,299,304,309,316,358,375,429,438,442],"goods":[7,221],"around,":[8],"has":[9,61],"a":[10,72,140,144,266,272,289,292,307,320,346,351,403,407],"clear":[11],"impact":[12],"on":[13,306],"the":[14,44,66,126,130,195,205,218,247,282,297,323,355,420,424,439],"economic":[15],"development":[16],"of":[17,46,143,207,220,276,281,284,301,350,406,415,426,444],"our":[18,21,201,302,434,445],"society":[19],"well-being.":[22],"Traditionally,":[23],"transportation":[24,67,104,131,230,430],"was":[25],"studied":[26],"analyzed":[28],"using":[29,339],"expensive":[30],"sensors,":[31],"such":[32,164,381],"as":[33,165,183,186,368],"induction":[34],"loops,":[35],"that":[36,48,78,123,250,344,380,390,401],"are":[37,49,136,258,365],"difficult":[38],"to":[39,82,116,177,182,188,203,246,370,419],"maintain.":[40],"However,":[41],"nowadays":[42],"prevalence":[45],"cameras,":[47],"inexpensive":[50],"can":[52,124,242,336],"be":[53,243,337,383],"easily":[54],"mounted":[55],"in":[56,74,94,107,129,138,152,161,194,213,274,319,332,423],"various":[57,118,229],"areas,":[58],"computer":[59,95,427],"vision":[60,70,428],"found":[62],"its":[63],"way":[64],"into":[65],"domain.":[68],"Computer":[69],"is":[71,226,288,328,378,412],"field":[73,425],"artificial":[75],"intelligence":[76],"(AI)":[77],"uses":[79],"visual":[80,248],"data":[81],"extract":[83,345],"high-level":[84,141],"relevant":[86],"information.":[87],"While":[88],"there":[89],"have":[90],"been":[91],"several":[92,97,277],"advances":[93],"vision,":[96],"challenges":[98,127,206],"arise":[99],"when":[100,252],"dealing":[101],"vision-based":[103,119],"systems":[105],"deployed":[106],"complex":[108],"uncontrolled":[110],"environments.":[111],"This":[112,334],"doctoral":[113],"thesis":[114],"aims":[115],"introduce":[117],"deep":[120],"learning":[121,268],"methods":[122,279,343,382],"handle":[125,204],"suffered":[128],"mobility":[133],"domain":[134],"crucial":[137],"providing":[139,386],"understanding":[142,217,405],"scene.":[145,196,408],"We":[146,294],"first":[147],"tackle":[148],"an":[149,394,413],"important":[150,310,330,379],"task":[151,331],"transportation,":[153,362],"detecting":[154,315,354],"different":[155,326],"agents":[156,238,318],"(e.g.":[157],"vehicles":[158],"pedestrians)":[160],"diverse":[162],"environments":[163],"roads,":[166],"parking":[167],"lots,":[168],"or":[169,291],"sidewalks.":[170],"To":[171],"solve":[172,262],"this":[173,263],"task,":[174],"we":[175,261,392,417],"propose":[176],"leverage":[178],"dense":[179,198],"fields,":[180],"referred":[181],"Butterfly":[184],"Fields,":[185],"representations":[187,199],"localize":[189],"classify":[191],"all":[192],"objects":[193,235,327,356],"Using":[197],"enables":[200],"method":[202,400],"object":[208],"occlusion":[209],"scale":[211],"variations":[212],"aerial":[214],"images.":[215],"Furthermore,":[216],"movement":[219],"over":[224],"time":[225],"critical":[227],"for":[228],"operations.":[231],"Tracking":[232],"requires":[236],"re-identifying":[237,317],"across":[239],"images":[240],"challenging":[244],"due":[245],"ambiguity":[249],"occurs":[251],"independent":[253],"traffic":[254,311],"agents,":[255],"especially":[256],"vehicles,":[257],"visually-similar.":[259],"Thus,":[260],"challenge":[264],"confidence-based":[267],"framework":[269],"demonstrate":[271],"boost":[273],"performance":[275],"re-identification":[278],"irrespective":[280],"type":[283],"agent,":[285],"whether":[286],"it":[287,377],"vehicle":[290],"person.":[293],"further":[295],"show":[296],"benefit":[298],"efficacy":[300],"detector":[303],"tracker":[305],"common":[308],"management":[312],"task.":[313],"Beyond":[314],"scene,":[321],"extracting":[322],"relationship":[324],"between":[325],"another":[329],"transportation.":[333],"problem":[335],"solved":[338],"scene":[340,352,363,397],"graph":[341,398],"generation":[342,399],"structured":[347],"semantic":[348],"representation":[349],"by":[353,431],"present":[357],"their":[359],"relationships.":[360],"In":[361],"graphs":[364],"mainly":[366],"used":[367],"inputs":[369],"real-time":[371],"downstream":[372],"decision-making":[373],"tasks":[374],"thus":[376],"efficient":[384,395],"while":[385],"good":[387],"performance.":[388],"Towards":[389],"end,":[391],"develop":[393],"one-step":[396],"provides":[402],"comprehensive":[404],"Finally,":[409],"since":[410],"open-source":[411],"enabler":[414],"innovation,":[416],"contribute":[418],"collective":[421],"knowledge":[422],"publicly":[432],"sharing":[433],"new":[435],"roundabout":[436],"dataset,":[437],"source":[440],"code":[441],"models":[443],"work.":[446]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}