{"id":"https://openalex.org/W2971320590","doi":"https://doi.org/10.1109/icip.2019.8802920","title":"Modeling Long- and Short-Term Temporal Context for Video Object Detection","display_name":"Modeling Long- and Short-Term Temporal Context for Video Object Detection","publication_year":2019,"publication_date":"2019-08-26","ids":{"openalex":"https://openalex.org/W2971320590","doi":"https://doi.org/10.1109/icip.2019.8802920","mag":"2971320590"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2019.8802920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8802920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","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/A5100374170","display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0003-2068-7279"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076689613","display_name":"Joohee Kim","orcid":"https://orcid.org/0000-0001-8833-0319"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joohee Kim","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100374170"],"corresponding_institution_ids":["https://openalex.org/I180949307"],"apc_list":null,"apc_paid":null,"fwci":1.0122,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.80857759,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"75"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998000264167786,"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":0.9994000196456909,"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":0.8354869484901428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6914234757423401},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6397166848182678},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6336843371391296},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6223777532577515},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5819656252861023},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5531055331230164},{"id":"https://openalex.org/keywords/optical-flow","display_name":"Optical flow","score":0.5397163033485413},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5189399719238281},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4710390865802765},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.4669215679168701},{"id":"https://openalex.org/keywords/reference-frame","display_name":"Reference frame","score":0.44416943192481995},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.4184929132461548},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.362776517868042},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.15168756246566772}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8354869484901428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6914234757423401},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6397166848182678},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6336843371391296},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6223777532577515},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5819656252861023},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5531055331230164},{"id":"https://openalex.org/C155542232","wikidata":"https://www.wikidata.org/wiki/Q736111","display_name":"Optical flow","level":3,"score":0.5397163033485413},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5189399719238281},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4710390865802765},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.4669215679168701},{"id":"https://openalex.org/C172849965","wikidata":"https://www.wikidata.org/wiki/Q3148875","display_name":"Reference frame","level":3,"score":0.44416943192481995},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.4184929132461548},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.362776517868042},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.15168756246566772},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip.2019.8802920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8802920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","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":38,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W764651262","https://openalex.org/W1536680647","https://openalex.org/W2064675550","https://openalex.org/W2117539524","https://openalex.org/W2161969291","https://openalex.org/W2163605009","https://openalex.org/W2183182206","https://openalex.org/W2282391807","https://openalex.org/W2336589871","https://openalex.org/W2407521645","https://openalex.org/W2557728737","https://openalex.org/W2569778727","https://openalex.org/W2613718673","https://openalex.org/W2770156722","https://openalex.org/W2793130599","https://openalex.org/W2798710031","https://openalex.org/W2888845200","https://openalex.org/W2898044248","https://openalex.org/W2950800384","https://openalex.org/W2962855257","https://openalex.org/W2963037989","https://openalex.org/W2963212638","https://openalex.org/W2963585656","https://openalex.org/W2963625188","https://openalex.org/W2964086649","https://openalex.org/W2964286567","https://openalex.org/W3106250896","https://openalex.org/W4293437100","https://openalex.org/W6684191040","https://openalex.org/W6695799263","https://openalex.org/W6714138976","https://openalex.org/W6746472748","https://openalex.org/W6748516020","https://openalex.org/W6749530778","https://openalex.org/W6751085028","https://openalex.org/W6755600014","https://openalex.org/W6785652829"],"related_works":["https://openalex.org/W2950183183","https://openalex.org/W2341338763","https://openalex.org/W2030799363","https://openalex.org/W2032415964","https://openalex.org/W2288425735","https://openalex.org/W2349923317","https://openalex.org/W2894081631","https://openalex.org/W2986063033","https://openalex.org/W2040439981","https://openalex.org/W2900482274"],"abstract_inverted_index":{"Video":[0],"object":[1,10,25,64],"detection":[2,11,44],"enhances":[3],"the":[4,7,22,71,102,106,112,123,139],"performance":[5,155],"of":[6,21,32,87],"still-image":[8],"based":[9,110],"by":[12,100],"exploiting":[13],"temporal":[14,88,95,117,124,147],"context":[15,89,96,118,148],"information":[16,90,97,119],"from":[17,78,105,122,130],"neighboring":[18],"frames.":[19],"Most":[20],"state-of-the-art":[23],"video":[24,63],"detectors":[26],"are":[27,48,91,134],"non-causal":[28],"and":[29,34,74,136,145],"require":[30],"lots":[31],"preceding":[33,76,108,132],"succeeding":[35,46],"frames,":[36],"which":[37],"makes":[38],"them":[39],"impractical":[40],"for":[41,61],"real-time":[42],"online":[43,62],"where":[45,127],"frames":[47,133],"not":[49],"available.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54],"propose":[55],"a":[56,163],"causal":[57],"recurrent":[58],"flow-based":[59],"method":[60,68,152],"detection.":[65],"The":[66,93,115],"proposed":[67,151],"reads":[69],"only":[70],"current":[72],"frame":[73,77,109],"one":[75],"memory":[79],"buffer":[80],"at":[81,162],"each":[82],"time":[83],"step.":[84],"Two":[85],"types":[86],"utilized.":[92],"short-term":[94,146],"is":[98,120],"utilized":[99],"warping":[101],"feature":[103],"map":[104],"nearby":[107],"on":[111,158],"optical":[113],"flow.":[114],"long-term":[116],"extracted":[121],"convolutional":[125],"LSTM,":[126],"informative":[128],"features":[129],"distant":[131],"stored":[135],"propagated":[137],"through":[138],"time.":[140],"By":[141],"aggregating":[142],"both":[143],"long-":[144],"information,":[149],"our":[150],"achieves":[153],"competitive":[154],"(75.5%":[156],"mAP)":[157],"ImageNet":[159],"VID":[160],"dataset":[161],"relatively":[164],"high":[165],"speed.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}