{"id":"https://openalex.org/W3016072980","doi":"https://doi.org/10.1109/icassp40776.2020.9054080","title":"Spatial-Temporal Feature Aggregation Network For Video Object Detection","display_name":"Spatial-Temporal Feature Aggregation Network For Video Object Detection","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016072980","doi":"https://doi.org/10.1109/icassp40776.2020.9054080","mag":"3016072980"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5042177280","display_name":"Chen Zhu","orcid":"https://orcid.org/0000-0002-2510-3271"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu Chen","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102001334","display_name":"Weihai Li","orcid":"https://orcid.org/0000-0002-4023-8385"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihai Li","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000881228","display_name":"Chi Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Fei","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395493","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0002-3977-8800"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064573190","display_name":"Nenghai Yu","orcid":"https://orcid.org/0000-0003-4417-9316"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nenghai Yu","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3916,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.60723801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1858","last_page":"1862"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","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/T10812","display_name":"Human Pose and Action Recognition","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":0.9997000098228455,"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":0.834010660648346},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7237133383750916},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6674798727035522},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5788069367408752},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5728100538253784},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.5211722254753113},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4690167307853699},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4636097848415375},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4547835886478424},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.45295464992523193},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4260498881340027},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.42577892541885376},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24698767066001892},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.11843588948249817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.834010660648346},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7237133383750916},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6674798727035522},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5788069367408752},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5728100538253784},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.5211722254753113},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4690167307853699},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4636097848415375},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4547835886478424},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.45295464992523193},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4260498881340027},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.42577892541885376},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24698767066001892},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.11843588948249817},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1970819022","https://openalex.org/W2117539524","https://openalex.org/W2123099218","https://openalex.org/W2194775991","https://openalex.org/W2335901184","https://openalex.org/W2336589871","https://openalex.org/W2407521645","https://openalex.org/W2552900565","https://openalex.org/W2590174509","https://openalex.org/W2601564443","https://openalex.org/W2613718673","https://openalex.org/W2777578098","https://openalex.org/W2898044248","https://openalex.org/W2950800384","https://openalex.org/W2962855257","https://openalex.org/W2963150697","https://openalex.org/W2963418361","https://openalex.org/W2963585656","https://openalex.org/W2963653352","https://openalex.org/W2964015378","https://openalex.org/W2964086649","https://openalex.org/W2964286567","https://openalex.org/W2964321699","https://openalex.org/W3100591638","https://openalex.org/W3100935401","https://openalex.org/W4293437100","https://openalex.org/W6620707391","https://openalex.org/W6695799263","https://openalex.org/W6703451452","https://openalex.org/W6714138976","https://openalex.org/W6720006811","https://openalex.org/W6726873649","https://openalex.org/W6746949076"],"related_works":["https://openalex.org/W2085033728","https://openalex.org/W4285411112","https://openalex.org/W2171299904","https://openalex.org/W1647606319","https://openalex.org/W4390494008","https://openalex.org/W2053596378","https://openalex.org/W2922442631","https://openalex.org/W2168523118","https://openalex.org/W2084942241","https://openalex.org/W4309346246"],"abstract_inverted_index":{"Video":[0],"object":[1],"detection":[2],"is":[3,63,99],"a":[4,15,29,46],"challenging":[5],"problem":[6],"in":[7,42],"computer":[8],"vision.":[9],"In":[10],"this":[11,24],"paper,":[12],"we":[13,27,44,80],"propose":[14],"novel":[16,30],"spatial-temporal":[17],"feature":[18,32,40,76],"aggregation":[19,33],"network":[20],"to":[21,37,51,65,73,90,101],"deal":[22],"with":[23],"issue.":[25],"Specifically,":[26],"present":[28],"instance-level":[31,75,84],"module":[34,50],"as":[35],"complementary":[36,95],"traditional":[38],"pixel-level":[39,82],"aggregation,":[41],"which":[43,107],"build":[45],"new":[47],"movement":[48],"estimation":[49],"learn":[52],"instance":[53],"movements":[54],"across":[55],"frames.":[56],"Then":[57],"the":[58,112],"Graph":[59],"Convolutional":[60],"Networks":[61],"(GCNs)":[62],"applied":[64],"obtain":[66],"temporal":[67],"relation":[68],"among":[69],"instances":[70],"over":[71],"frames":[72],"implement":[74,102],"aggregation.":[77],"At":[78],"last,":[79],"combine":[81],"and":[83,103],"features":[85],"by":[86,116],"learnable":[87],"soft":[88],"weights":[89],"make":[91],"use":[92],"of":[93],"their":[94],"information.":[96],"Our":[97],"framework":[98],"simple":[100],"enables":[104],"end-to-end":[105],"training,":[106],"achieves":[108],"state-of-art":[109],"performance":[110],"on":[111],"ImageNet":[113],"VID":[114],"dataset":[115],"extensive":[117],"experiments.":[118]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}