{"id":"https://openalex.org/W4394843422","doi":"https://doi.org/10.1109/wacvw60836.2024.00068","title":"RDIR: Capturing Temporally-Invariant Representations of Multiple Objects in Videos","display_name":"RDIR: Capturing Temporally-Invariant Representations of Multiple Objects in Videos","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4394843422","doi":"https://doi.org/10.1109/wacvw60836.2024.00068"},"language":"en","primary_location":{"id":"doi:10.1109/wacvw60836.2024.00068","doi":"https://doi.org/10.1109/wacvw60836.2024.00068","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wacvw60836.2024.00068","pdf_url":null,"source":{"id":"https://openalex.org/S7407086155","display_name":"IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5061034771","display_name":"Piotr Zieli\u0144ski","orcid":"https://orcid.org/0000-0001-6831-4602","observed_orcids":["https://orcid.org/0000-0001-6831-4602"]},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Piotr Zieli\u0144ski","raw_affiliation_strings":["Wroclaw University of Science and Technology,Department of Artificial Intelligence","Department of Artificial Intelligence, Wroclaw University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wroclaw University of Science and Technology,Department of Artificial Intelligence","institution_ids":["https://openalex.org/I11923345"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Wroclaw University of Science and Technology","institution_ids":["https://openalex.org/I11923345"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050914099","display_name":"Tomasz Jan Kajdanowicz","orcid":"https://orcid.org/0000-0002-8417-1012","observed_orcids":["https://orcid.org/0000-0002-8417-1012"]},"institutions":[{"id":"https://openalex.org/I11923345","display_name":"Wroc\u0142aw University of Science and Technology","ror":"https://ror.org/008fyn775","country_code":"PL","type":"education","lineage":["https://openalex.org/I11923345"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Tomasz Kajdanowicz","raw_affiliation_strings":["Wroclaw University of Science and Technology,Department of Artificial Intelligence","Department of Artificial Intelligence, Wroclaw University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wroclaw University of Science and Technology,Department of Artificial Intelligence","institution_ids":["https://openalex.org/I11923345"]},{"raw_affiliation_string":"Department of Artificial Intelligence, Wroclaw University of Science and Technology","institution_ids":["https://openalex.org/I11923345"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I11923345"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs/2004.10934","issue":null,"first_page":"588","last_page":"597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.5619999766349792,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.5619999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.29910001158714294,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03779999911785126,"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-representation-learning","display_name":"video representation learning","score":0.6660000085830688},{"id":"https://openalex.org/keywords/unsupervised-representation-learning","display_name":"unsupervised feature learning","score":0.7450000047683716},{"id":"https://openalex.org/keywords/object-tracking","display_name":"object tracking","score":0.847000002861023},{"id":"https://openalex.org/keywords/temporal-coherence","display_name":"temporal coherence","score":0.5}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6740537881851196},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6358413696289062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.577786922454834},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5487247109413147},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3894757926464081},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21887406706809998},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacvw60836.2024.00068","doi":"https://doi.org/10.1109/wacvw60836.2024.00068","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/wacvw60836.2024.00068","pdf_url":null,"source":{"id":"https://openalex.org/S7407086155","display_name":"IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1521019969","https://openalex.org/W1861492603","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W1981276685","https://openalex.org/W2064675550","https://openalex.org/W2163922914","https://openalex.org/W2193145675","https://openalex.org/W2327562811","https://openalex.org/W2807242871","https://openalex.org/W2903585023","https://openalex.org/W2911448865","https://openalex.org/W2914304175","https://openalex.org/W2919112510","https://openalex.org/W2927928207","https://openalex.org/W2950635152","https://openalex.org/W2950747681","https://openalex.org/W2951005624","https://openalex.org/W2994971263","https://openalex.org/W2997593239","https://openalex.org/W2999417551","https://openalex.org/W3004808386","https://openalex.org/W3018757597","https://openalex.org/W3086436251","https://openalex.org/W3102696055","https://openalex.org/W3106250896","https://openalex.org/W3136070008","https://openalex.org/W3154552141","https://openalex.org/W3167945274","https://openalex.org/W3216088010","https://openalex.org/W4285264302","https://openalex.org/W4312339971","https://openalex.org/W6777046832","https://openalex.org/W6792018038","https://openalex.org/W6793805516","https://openalex.org/W6891621606","https://openalex.org/W7133215866"],"related_works":["https://openalex.org/W4405561877","https://openalex.org/W4213346590","https://openalex.org/W4413144398","https://openalex.org/W4309995343","https://openalex.org/W2748412507","https://openalex.org/W4285264302","https://openalex.org/W2560590061","https://openalex.org/W3091878427","https://openalex.org/W4404089153","https://openalex.org/W3037581554"],"abstract_inverted_index":{"Learning":[0],"temporally":[1],"coherent":[2],"representations":[3,34,57,79],"of":[4,93,103,119,153,156],"multiple":[5,65],"objects":[6],"in":[7,67,126],"videos":[8],"is":[9],"crucial":[10],"for":[11,76,98],"understanding":[12],"their":[13,124],"complex":[14],"dynamics":[15],"and":[16,60,108,116,143],"interactions":[17],"over":[18],"time.":[19],"In":[20],"this":[21],"paper,":[22],"we":[23,112,144],"present":[24],"a":[25,42,49,74,81,101],"deep":[26],"generative":[27],"neural":[28],"network,":[29],"which":[30],"can":[31],"learn":[32],"such":[33,129],"by":[35,138],"leveraging":[36],"pretraining.":[37],"Our":[38],"model":[39],"builds":[40],"upon":[41],"scale-invariant":[43],"structured":[44],"autoencoder,":[45],"extending":[46],"it":[47,146],"with":[48],"convolutional":[50],"recurrent":[51],"module":[52],"to":[53,89,147],"refine":[54],"the":[55,87,96,114,120,135,151,154],"learned":[56,121],"through":[58],"time":[59],"enable":[61],"information":[62],"sharing":[63],"among":[64],"cells":[66],"multi-scale":[68],"grids.":[69],"This":[70],"novel":[71],"approach":[72],"provides":[73],"framework":[75],"learning":[77],"perobject":[78],"from":[80],"pretrained":[82],"object":[83,131],"detection":[84],"model,":[85],"offering":[86],"ability":[88],"infer":[90],"predefined":[91],"types":[92],"objects,":[94],"without":[95],"need":[97],"supervision.":[99],"Through":[100],"series":[102],"experiments":[104],"on":[105],"benchmark":[106],"datasets":[107],"real-life":[109],"video":[110],"footage,":[111],"demonstrate":[113],"spatial":[115],"temporal":[117],"coherence":[118],"representations,":[122],"showcasing":[123],"applicability":[125],"downstream":[127],"tasks":[128],"as":[130],"tracking.":[132],"We":[133],"analyze":[134],"method's":[136],"robustness":[137],"conducting":[139],"an":[140],"ablation":[141],"study,":[142],"compare":[145],"other":[148],"methods,":[149],"highlighting":[150],"importance":[152],"quality":[155],"objects'":[157],"representations.":[158]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2024-04-17T00:00:00"}