{"id":"https://openalex.org/W4213346590","doi":"https://doi.org/10.1109/wacvw54805.2022.00059","title":"Video representation learning through prediction for online object detection","display_name":"Video representation learning through prediction for online object detection","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4213346590","doi":"https://doi.org/10.1109/wacvw54805.2022.00059"},"language":"en","primary_location":{"id":"doi:10.1109/wacvw54805.2022.00059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacvw54805.2022.00059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","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/A5051026262","display_name":"Masato Fujitake","orcid":"https://orcid.org/0000-0001-7702-499X"},"institutions":[{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Fujitake","raw_affiliation_strings":["The Graduate University for Advanced Studies,Dept. of Informatics,SOKENDAI,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Graduate University for Advanced Studies,Dept. of Informatics,SOKENDAI,Tokyo,Japan","institution_ids":["https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101463320","display_name":"Akihiro Sugimoto","orcid":"https://orcid.org/0000-0001-9148-9822"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Sugimoto","raw_affiliation_strings":["National Institute of Informatics,Tokyo,Japan","National Institute of Informatics, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics,Tokyo,Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7107,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69141743,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"530","last_page":"539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","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/T10036","display_name":"Advanced Neural Network Applications","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.8484730124473572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7651665806770325},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6595773100852966},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6562713384628296},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5903627276420593},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.5651658773422241},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.563774585723877},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5148012042045593},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4192524552345276},{"id":"https://openalex.org/keywords/object-class-detection","display_name":"Object-class detection","score":0.4187259376049042},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3774562180042267},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34730273485183716},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.12453588843345642},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.08334130048751831}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8484730124473572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7651665806770325},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6595773100852966},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6562713384628296},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5903627276420593},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.5651658773422241},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.563774585723877},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5148012042045593},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4192524552345276},{"id":"https://openalex.org/C71681937","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object-class detection","level":5,"score":0.4187259376049042},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3774562180042267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34730273485183716},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.12453588843345642},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.08334130048751831},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacvw54805.2022.00059","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacvw54805.2022.00059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)","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":85,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1485009520","https://openalex.org/W1686810756","https://openalex.org/W2107775979","https://openalex.org/W2116435618","https://openalex.org/W2117539524","https://openalex.org/W2118688707","https://openalex.org/W2133665775","https://openalex.org/W2150066425","https://openalex.org/W2194775991","https://openalex.org/W2502312327","https://openalex.org/W2549139847","https://openalex.org/W2552900565","https://openalex.org/W2565639579","https://openalex.org/W2590174509","https://openalex.org/W2592463526","https://openalex.org/W2601564443","https://openalex.org/W2615413256","https://openalex.org/W2619034550","https://openalex.org/W2797306806","https://openalex.org/W2800283575","https://openalex.org/W2898044248","https://openalex.org/W2919935710","https://openalex.org/W2950800384","https://openalex.org/W2962855257","https://openalex.org/W2963092440","https://openalex.org/W2963163009","https://openalex.org/W2963212638","https://openalex.org/W2963351448","https://openalex.org/W2963435596","https://openalex.org/W2963625188","https://openalex.org/W2964086649","https://openalex.org/W2964241181","https://openalex.org/W2964286567","https://openalex.org/W2969727121","https://openalex.org/W2973966280","https://openalex.org/W2980037812","https://openalex.org/W2982770724","https://openalex.org/W2983827899","https://openalex.org/W2989604896","https://openalex.org/W2990578161","https://openalex.org/W2991019415","https://openalex.org/W2994810768","https://openalex.org/W2995484963","https://openalex.org/W2996680032","https://openalex.org/W3034467781","https://openalex.org/W3035540643","https://openalex.org/W3035564946","https://openalex.org/W3093047473","https://openalex.org/W3097550038","https://openalex.org/W3100094580","https://openalex.org/W3103358580","https://openalex.org/W3106250896","https://openalex.org/W3106643287","https://openalex.org/W3160833223","https://openalex.org/W3162638538","https://openalex.org/W3171077524","https://openalex.org/W3174944154","https://openalex.org/W3204023867","https://openalex.org/W4288408844","https://openalex.org/W4293437100","https://openalex.org/W4294554810","https://openalex.org/W4298157202","https://openalex.org/W6628877408","https://openalex.org/W6637373629","https://openalex.org/W6677326919","https://openalex.org/W6677477928","https://openalex.org/W6695799263","https://openalex.org/W6713563955","https://openalex.org/W6714138976","https://openalex.org/W6724804524","https://openalex.org/W6738465933","https://openalex.org/W6738467200","https://openalex.org/W6745420753","https://openalex.org/W6746085279","https://openalex.org/W6746472748","https://openalex.org/W6748516020","https://openalex.org/W6750605158","https://openalex.org/W6750642828","https://openalex.org/W6755259929","https://openalex.org/W6760166208","https://openalex.org/W6761178061","https://openalex.org/W6771200186","https://openalex.org/W6785652829","https://openalex.org/W6795031447"],"related_works":["https://openalex.org/W2129974284","https://openalex.org/W2534746541","https://openalex.org/W2343908003","https://openalex.org/W3177406559","https://openalex.org/W2548411843","https://openalex.org/W1487175407","https://openalex.org/W2557461402","https://openalex.org/W2922421953","https://openalex.org/W2381610189","https://openalex.org/W2404567486"],"abstract_inverted_index":{"We":[0,82],"present":[1],"a":[2,21,62],"video":[3,9,26,40,44,52,69,98,103],"representation":[4,99],"learning":[5,39,100],"framework":[6,48],"for":[7],"real-time":[8],"object":[10,31,55,76],"detection.":[11],"Our":[12,46],"approach":[13,116],"is":[14],"based":[15],"on":[16,87,110,125],"the":[17,50,80,95],"interesting":[18],"observation":[19],"that":[20,58,114],"powerful":[22],"prior":[23,63],"knowledge":[24,64],"of":[25,65,97],"context":[27],"helps":[28],"to":[29,67,75,78,93],"improve":[30,79],"recognition,":[32],"and":[33,71,90],"it":[34],"can":[35],"be":[36],"acquired":[37],"via":[38,101],"representations":[41,70],"through":[42],"stochastic":[43,51],"prediction.":[45,104],"proposed":[47,85],"utilizes":[49],"prediction":[53],"into":[54],"detection":[56,77],"so":[57],"we":[59],"first":[60],"acquire":[61],"videos":[66],"have":[68],"then":[72],"adjust":[73],"them":[74],"accuracy.":[81],"validate":[83],"our":[84,107,115],"method":[86],"ImageNet":[88,111],"VID":[89,112],"VisDrone-VID2019":[91],"datasets":[92],"demonstrate":[94],"effectiveness":[96],"future":[102],"In":[105],"particular,":[106],"extensive":[108],"experiments":[109],"show":[113],"achieves":[117],"73.1%":[118],"mAP":[119],"at":[120],"54":[121],"fps":[122],"with":[123],"ResNet-50":[124],"commercial":[126],"GPUs":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}