{"id":"https://openalex.org/W4402201451","doi":"https://doi.org/10.32657/10356/179521","title":"Leveraging deep learning for visual understanding of videos","display_name":"Leveraging deep learning for visual understanding of videos","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402201451","doi":"https://doi.org/10.32657/10356/179521"},"language":"en","primary_location":{"id":"doi:10.32657/10356/179521","doi":"https://doi.org/10.32657/10356/179521","is_oa":true,"landing_page_url":"https://doi.org/10.32657/10356/179521","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nanyang Technological University","raw_type":"dissertation"},"parent_works":[],"lineage":["https://openalex.org/W4402201451"],"child_works_count":0,"type":"dissertation","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.32657/10356/179521","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054920409","display_name":"Clement Xian Ren Tan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tan, Clement Xian Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5054920409"],"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":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.44510000944137573,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.44510000944137573,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.2816999852657318,"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":0.08089999854564667,"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/video-object-segmentation","display_name":"video object segmentation","score":0.8619999885559082},{"id":"https://openalex.org/keywords/self-supervised-learning","display_name":"self-supervised learning","score":0.8650000095367432},{"id":"https://openalex.org/keywords/attention-mechanism","display_name":"attention mechanism","score":0.7620000243186951},{"id":"https://openalex.org/keywords/object-relational-model","display_name":"object-relational model","score":0.7799999713897705},{"id":"https://openalex.org/keywords/scene-graph-generation","display_name":"scene graph generation","score":0.5149999856948853},{"id":"https://openalex.org/keywords/video-understanding","display_name":"video understanding","score":0.34200000762939453},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"visual reasoning","score":0.7409999966621399},{"id":"https://openalex.org/keywords/object-tracking","display_name":"object tracking","score":0.46799999475479126},{"id":"https://openalex.org/keywords/occlusion","display_name":"occlusion","score":0.7300000190734863},{"id":"https://openalex.org/keywords/appearance-changes","display_name":"appearance changes","score":0.5860000252723694},{"id":"https://openalex.org/keywords/youtube-videos","display_name":"YouTube videos","score":0.41100001335144043},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.6899999976158142},{"id":"https://openalex.org/keywords/human-robot-collaboration","display_name":"human-robot collaboration","score":0.6970000267028809},{"id":"https://openalex.org/keywords/autonomous-vehicles","display_name":"autonomous vehicles","score":0.968999981880188},{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.4429999887943268},{"id":"https://openalex.org/keywords/semantic-segmentation","display_name":"semantic segmentation","score":0.8669999837875366},{"id":"https://openalex.org/keywords/instance-segmentation","display_name":"instance segmentation","score":0.9660000205039978},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.5189999938011169}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5703434944152832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.466683954000473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46118125319480896},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3696761131286621},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3408324122428894}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.32657/10356/179521","doi":"https://doi.org/10.32657/10356/179521","is_oa":true,"landing_page_url":"https://doi.org/10.32657/10356/179521","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nanyang Technological University","raw_type":"dissertation"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/179521","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/10356/179521","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis-Doctor of Philosophy"}],"best_oa_location":{"id":"doi:10.32657/10356/179521","doi":"https://doi.org/10.32657/10356/179521","is_oa":true,"landing_page_url":"https://doi.org/10.32657/10356/179521","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nanyang Technological University","raw_type":"dissertation"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416551569","https://openalex.org/W7149249821","https://openalex.org/W2947963855","https://openalex.org/W4417010001","https://openalex.org/W3182236906","https://openalex.org/W4410104723","https://openalex.org/W7115928071","https://openalex.org/W4226083961","https://openalex.org/W7148185107","https://openalex.org/W4409150028"],"abstract_inverted_index":{"In":[0,50,246],"the":[1,7,23,29,41,57,93,172,239,272,312,326,350,366,385,393,402,443,449,460,480,505,547,550,593,600,611,620],"field":[2],"of":[3,9,14,31,43,60,103,126,149,155,233,242,274,328,352,387,396,406,416,462,479,483,525,595],"Computer":[4],"Vision":[5],"(CV),":[6],"pursuit":[8],"human-level":[10,493],"recognition":[11,98,105,131,146],"and":[12,46,65,68,87,115,147,164,183,197,218,235,260,364,427,434,521,632],"reasoning":[13,139,148,404,481,494,591],"visual":[15,52,71,95,104,130,138,181,412,497,527,558],"scenes":[16],"has":[17,133],"been":[18,34,119],"a":[19,101,152,253,321,488,513,537,572,578],"long-standing":[20],"aspiration.":[21],"Over":[22],"past":[24],"decade,":[25],"significant":[26,489],"contributions":[27],"to":[28,136,158,238,282,348,379,400,448,577,628,635],"progress":[30],"CV":[32],"have":[33,118],"made":[35],"by":[36,40,121,257,359],"deep":[37,127,177,224,361,407,463,484],"learning,":[38],"facilitated":[39],"availability":[42],"big":[44],"data":[45,287],"increased":[47],"computational":[48],"power.":[49],"CV,":[51],"understanding":[53,182,478,559],"encompasses":[54],"not":[55],"only":[56],"fundamental":[58],"aspect":[59],"recognition,":[61],"which":[62,76,141,324],"involves":[63,77,325,507],"identifying":[64],"categorizing":[66],"objects":[67,150,249],"patterns":[69],"within":[70,151,250,338,549],"data,":[72],"but":[73],"also":[74,377],"reasoning,":[75],"higher-level":[78],"cognitive":[79,590],"processes":[80],"such":[81,107,160,288],"as":[82,108,161,289,571],"inferring":[83],"relationships,":[84],"predicting":[85,508,526],"outcomes,":[86],"drawing":[88],"meaningful":[89],"conclusions":[90],"based":[91,516,598],"on":[92,186,215,517,599],"observed":[94],"information.":[96],"Human-like":[97],"capabilities":[99,495],"across":[100,262],"variety":[102],"tasks":[106,132],"image":[109,454],"classification,":[110],"object":[111,191,205,209,279,303,356],"detection,":[112],"semantic":[113],"segmentation,":[114,117,192,280],"instance":[116],"achieved":[120],"machines.":[122],"The":[123,145,265,457],"huge":[124],"success":[125],"learning":[128,178,217,225,276,299,362,371,408,464,485],"for":[129,180,223,277,292,301,422,512,529],"prompted":[134],"researchers":[135],"tackle":[137],"tasks,":[140],"are":[142,439],"more":[143],"challenging.":[144],"scene":[153,200,450,502,509,538,564,602,630,639],"is":[154,207,229,343,425,473,534],"paramount":[156],"importance":[157],"applications":[159],"human-robot":[162],"collaborations":[163],"autonomous":[165],"vehicles.":[166],"This":[167,345,471],"thesis":[168,270,391,609,618],"aims":[169,347,378],"at":[170],"addressing":[171],"issues":[173,232],"associated":[174,368],"with":[175,231,369,384,429,441,561],"current":[176],"models":[179,358,383,409,419,438,465],"will":[184],"focus":[185,313],"three":[187],"tasks:":[188],"(1)":[189],"video":[190,204,263,278,302,331,355,563],"(2)":[193],"abductive":[194,397,403,468],"action":[195,398,445,469,596,633],"inference,":[196],"(3)":[198],"action-conditioned":[199,501],"graph":[201,503,510,539,565,640],"prediction.":[202],"Firstly,":[203],"segmentation":[206,304,357],"an":[208,334,339,453,518,522,582],"tracking":[210,248,327],"task":[211,395,424,506,554],"that":[212,305,446],"traditionally":[213],"relies":[214],"supervised":[216,370],"necessitates":[219],"extensive":[220],"annotated":[221,374],"datasets":[222],"model":[226,293,306],"training.":[227,294],"It":[228,376],"confronted":[230],"repetitiveness":[234],"impracticality":[236],"due":[237],"manual":[240],"labeling":[241],"these":[243],"vast":[244],"datasets.":[245,375],"addition,":[247],"videos":[251,291],"presents":[252],"unique":[254],"challenge":[255],"caused":[256],"appearance":[258],"changes":[259],"occlusion":[261],"frames.":[264],"work":[266],"proposed":[267],"in":[268,410,452,466,475,496,500,557],"this":[269,309,390,423,553,606,608,617],"explores":[271],"potential":[273,461],"self-supervised":[275,298,341,354,382],"aiming":[281],"harness":[283],"freely":[284],"available":[285],"internet":[286],"YouTube":[290],"Different":[295],"from":[296],"existing":[297,353,381,430],"approaches":[300,567],"pixel-to-pixel":[307],"correspondence,":[308],"research":[310,472],"shifts":[311],"towards":[314],"modeling":[315],"superpixel-to-superpixel":[316],"correspondence.":[317],"To":[318,604],"achieve":[319],"this,":[320],"novel":[322],"approach":[323,346],"superpixels":[329],"between":[330],"frames":[332],"through":[333],"attention":[335],"mechanism":[336],"trained":[337],"end-to-end":[340],"framework":[342],"proposed.":[344],"enhance":[349,380],"performance":[351],"leveraging":[360],"techniques":[363],"mitigating":[365],"limitations":[367],"using":[372],"large-scale":[373],"benefits":[386],"superpixels.":[388],"Secondly,":[389],"introduces":[392,610],"complex":[394],"inference":[399,594],"assess":[401],"abilities":[405],"comprehending":[411],"scenes.":[413],"A":[414],"set":[415],"innovative":[417],"object-relational":[418],"designed":[420,627],"specifically":[421],"presented":[426],"compared":[428],"state-of-the-art":[431],"image,":[432],"video,":[433],"vision-language":[435],"models.":[436],"These":[437],"tasked":[440],"abducting":[442],"human-performed":[444],"led":[447],"depicted":[451],"or":[455],"snapshot.":[456],"experiments":[458],"demonstrate":[459],"performing":[467],"inference.":[470],"vital":[474],"advancing":[476],"our":[477],"capacities":[482],"models,":[486],"representing":[487],"stride":[490],"toward":[491],"attaining":[492],"comprehension.":[498],"Lastly,":[499],"prediction,":[504],"relations":[511,631],"future":[514,530,638],"state":[515,520,533,580,584],"initial":[519,601],"action.":[523],"Instead":[524],"representations":[528],"states,":[531],"each":[532],"organized":[535],"into":[536],"comprising":[540],"human-object":[541],"relationship":[542],"triplets,":[543],"thereby":[544],"succinctly":[545],"encapsulating":[546],"dynamics":[548],"scene.":[551],"Notably,":[552],"remains":[555],"underdeveloped":[556],"research,":[560],"prior":[562],"generation":[566],"largely":[568],"overlooking":[569],"actions":[570],"crucial":[573],"signal.":[574],"Actions":[575],"applied":[576],"preconditioned":[579],"generate":[581],"effect":[583],"embodying":[585],"their":[586],"anticipated":[587],"outcomes.":[588],"Human":[589],"allows":[592],"consequences":[597],"context.":[603],"address":[605],"challenge,":[607],"Action-conditioned":[612],"Scene":[613],"Graph":[614],"dataset.":[615],"Furthermore,":[616],"proposes":[619],"AERT":[621],"(Action-conditioned":[622],"Effect":[623],"Relational":[624],"Transformer)":[625],"model,":[626],"capture":[629],"context":[634],"effectively":[636],"predict":[637],"relations.":[641]},"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2024-09-04T00:00:00"}