{"id":"https://openalex.org/W4285203457","doi":"https://doi.org/10.1109/tcsvt.2022.3183646","title":"Multilevel Spatial-Temporal Feature Aggregation for Video Object Detection","display_name":"Multilevel Spatial-Temporal Feature Aggregation for Video Object Detection","publication_year":2022,"publication_date":"2022-06-16","ids":{"openalex":"https://openalex.org/W4285203457","doi":"https://doi.org/10.1109/tcsvt.2022.3183646"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3183646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3183646","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-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/A5049888271","display_name":"Chao Xu","orcid":"https://orcid.org/0000-0001-9300-4497"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Xu","raw_affiliation_strings":["Institute of Cyber-System and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9300-4497","affiliations":[{"raw_affiliation_string":"Institute of Cyber-System and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861529","display_name":"Jiangning Zhang","orcid":"https://orcid.org/0000-0001-8891-6766"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangning Zhang","raw_affiliation_strings":["Institute of Cyber-System and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-8891-6766","affiliations":[{"raw_affiliation_string":"Institute of Cyber-System and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100429685","display_name":"Mengmeng Wang","orcid":"https://orcid.org/0000-0003-4035-0630"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengmeng Wang","raw_affiliation_strings":["Institute of Cyber-System and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4035-0630","affiliations":[{"raw_affiliation_string":"Institute of Cyber-System and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014432572","display_name":"Guanzhong Tian","orcid":"https://orcid.org/0000-0002-7292-4056"},"institutions":[{"id":"https://openalex.org/I109935558","display_name":"Ningbo University","ror":"https://ror.org/03et85d35","country_code":"CN","type":"education","lineage":["https://openalex.org/I109935558"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanzhong Tian","raw_affiliation_strings":["Ningbo Research Institute, Zhejiang University, Ningbo, China"],"raw_orcid":"https://orcid.org/0000-0002-7292-4056","affiliations":[{"raw_affiliation_string":"Ningbo Research Institute, Zhejiang University, Ningbo, China","institution_ids":["https://openalex.org/I109935558","https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100724297","display_name":"Yong Liu","orcid":"https://orcid.org/0000-0003-4822-8939"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Institute of Cyber-System and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4822-8939","affiliations":[{"raw_affiliation_string":"Institute of Cyber-System and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9364,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.9243648,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"32","issue":"11","first_page":"7809","last_page":"7820"},"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":0.9995999932289124,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8111133575439453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6694931387901306},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6476460695266724},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6057386994361877},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5861212611198425},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5579158663749695},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.49665218591690063},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4823267161846161},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4781409502029419},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.46671292185783386},{"id":"https://openalex.org/keywords/spatial-contextual-awareness","display_name":"Spatial contextual awareness","score":0.4501016139984131},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.44595271348953247},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4369657635688782},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4145025610923767},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.4114103615283966},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20804157853126526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07770034670829773}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8111133575439453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6694931387901306},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6476460695266724},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6057386994361877},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5861212611198425},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5579158663749695},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.49665218591690063},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4823267161846161},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4781409502029419},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.46671292185783386},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.4501016139984131},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.44595271348953247},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4369657635688782},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4145025610923767},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.4114103615283966},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20804157853126526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07770034670829773},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/tcsvt.2022.3183646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3183646","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":86,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W764651262","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2097117768","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2109255472","https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2335901184","https://openalex.org/W2336589871","https://openalex.org/W2341528187","https://openalex.org/W2549139847","https://openalex.org/W2552900565","https://openalex.org/W2570343428","https://openalex.org/W2579152745","https://openalex.org/W2590174509","https://openalex.org/W2601564443","https://openalex.org/W2618530766","https://openalex.org/W2792121015","https://openalex.org/W2793130599","https://openalex.org/W2794363460","https://openalex.org/W2799256316","https://openalex.org/W2898044248","https://openalex.org/W2901412525","https://openalex.org/W2912834795","https://openalex.org/W2924873663","https://openalex.org/W2950800384","https://openalex.org/W2962777203","https://openalex.org/W2962855257","https://openalex.org/W2963037989","https://openalex.org/W2963091558","https://openalex.org/W2963113370","https://openalex.org/W2963150697","https://openalex.org/W2963299996","https://openalex.org/W2963351448","https://openalex.org/W2963446712","https://openalex.org/W2963585656","https://openalex.org/W2963653352","https://openalex.org/W2963786238","https://openalex.org/W2963856926","https://openalex.org/W2963927307","https://openalex.org/W2964080601","https://openalex.org/W2964086649","https://openalex.org/W2964241181","https://openalex.org/W2964286567","https://openalex.org/W2969727121","https://openalex.org/W2981689412","https://openalex.org/W2982770724","https://openalex.org/W2983827899","https://openalex.org/W2990578161","https://openalex.org/W2994810768","https://openalex.org/W3010594275","https://openalex.org/W3012573144","https://openalex.org/W3018902719","https://openalex.org/W3031154432","https://openalex.org/W3034467781","https://openalex.org/W3084874594","https://openalex.org/W3086026735","https://openalex.org/W3097550038","https://openalex.org/W3100094580","https://openalex.org/W3100935401","https://openalex.org/W3101476123","https://openalex.org/W3101998545","https://openalex.org/W3103358580","https://openalex.org/W3104010045","https://openalex.org/W3108457314","https://openalex.org/W3164816468","https://openalex.org/W3169512507","https://openalex.org/W3180954604","https://openalex.org/W3186193138","https://openalex.org/W3188582951","https://openalex.org/W3204023867","https://openalex.org/W3205156060","https://openalex.org/W3206873062","https://openalex.org/W4293437100","https://openalex.org/W4293584584","https://openalex.org/W6637373629","https://openalex.org/W6695799263","https://openalex.org/W6714138976","https://openalex.org/W6739901393","https://openalex.org/W6750227808","https://openalex.org/W6760424586","https://openalex.org/W6910687937"],"related_works":["https://openalex.org/W3148227991","https://openalex.org/W1486593826","https://openalex.org/W2771174107","https://openalex.org/W1536965844","https://openalex.org/W2344941099","https://openalex.org/W4322212724","https://openalex.org/W2106788855","https://openalex.org/W3081561710","https://openalex.org/W2477413883","https://openalex.org/W2463773089"],"abstract_inverted_index":{"Video":[0],"object":[1,120,125,151],"detection":[2],"(VOD)":[3],"focuses":[4],"on":[5,187,212],"detecting":[6],"objects":[7],"for":[8,179],"each":[9],"frame":[10,47],"in":[11,23,90,100],"a":[12,16,67,75,91,163,173],"video,":[13],"which":[14],"is":[15],"challenging":[17],"task":[18],"due":[19],"to":[20,37,82,103,122,128,144,156,171],"appearance":[21],"deterioration":[22],"certain":[24],"video":[25],"frames.":[26],"Recent":[27],"works":[28],"usually":[29],"distill":[30],"crucial":[31],"information":[32,89,132],"from":[33,133],"multiple":[34],"support":[35,150],"frames":[36],"improve":[38],"the":[39,157,195],"reference":[40,112,124],"features,":[41],"but":[42],"they":[43],"only":[44,110],"perform":[45],"at":[46],"level":[48,51],"or":[49],"proposal":[50,152],"that":[52,154,193],"cannot":[53],"integrate":[54],"spatial-temporal":[55,68],"features":[56,70,107,147,153],"sufficiently.":[57],"To":[58],"deal":[59],"with":[60,210],"this":[61],"challenge,":[62],"we":[63,138,161],"treat":[64],"VOD":[65],"as":[66],"hierarchical":[69],"interacting":[71],"process":[72],"and":[73,87,136,190,208,220],"introduce":[74,139],"Multi-level":[76],"Spatial-Temporal":[77],"(MST)":[78],"feature":[79,116,181],"aggregation":[80,117],"framework":[81],"fully":[83],"exploit":[84],"frame-level,":[85],"proposal-level,":[86],"instance-level":[88,146],"unified":[92],"framework.":[93],"Specifically,":[94],"MST":[95,170],"first":[96],"measures":[97],"context":[98],"similarity":[99],"pixel":[101],"space":[102],"enhance":[104],"all":[105],"frame-level":[106],"rather":[108],"than":[109],"update":[111],"features.":[113],"The":[114],"proposal-level":[115],"then":[118],"models":[119],"relation":[121],"augment":[123],"proposals.":[126],"Furthermore,":[127],"filter":[129],"out":[130],"irrelevant":[131],"other":[134],"classes":[135],"backgrounds,":[137],"an":[140],"instance":[141],"ID":[142],"constraint":[143],"boost":[145],"by":[148,218],"leveraging":[149],"belong":[155],"same":[158],"object.":[159],"Besides,":[160],"propose":[162],"Deformable":[164],"Feature":[165],"Alignment":[166],"(DAlign)":[167],"module":[168],"before":[169],"achieve":[172],"more":[174],"accurate":[175],"pixel-level":[176],"spatial":[177],"alignment":[178],"better":[180],"aggregation.":[182],"Extensive":[183],"experiments":[184],"are":[185],"conducted":[186],"ImageNet":[188],"VID":[189],"UAVDT":[191],"datasets":[192],"demonstrate":[194],"superiority":[196],"of":[197],"our":[198],"method":[199,205],"over":[200],"state-of-the-art":[201],"(SOTA)":[202],"methods.":[203],"Our":[204],"achieves":[206],"83.3%":[207],"62.1%":[209],"ResNet-101":[211],"two":[213],"datasets,":[214],"outperforming":[215],"SOTA":[216],"MEGA":[217],"0.4%":[219],"2.7%.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
