{"id":"https://openalex.org/W4383108418","doi":"https://doi.org/10.1109/icra48891.2023.10160564","title":"AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning","display_name":"AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108418","doi":"https://doi.org/10.1109/icra48891.2023.10160564"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","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/A5100709597","display_name":"Xijun Wang","orcid":"https://orcid.org/0000-0003-3504-9763"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xijun Wang","raw_affiliation_strings":["University of Maryland, College Park,Dept. of Computer Science,MD,USA","Dept. of Computer Science, University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park,Dept. of Computer Science,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept. of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083695837","display_name":"Ruiqi Xian","orcid":null},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ruiqi Xian","raw_affiliation_strings":["University of Maryland, College Park,Dept. of Electrical and Computer Engineering,MD,USA","Dept. of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park,Dept. of Electrical and Computer Engineering,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014003390","display_name":"Tianrui Guan","orcid":"https://orcid.org/0000-0002-6892-9778"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianrui Guan","raw_affiliation_strings":["University of Maryland, College Park,Dept. of Computer Science,MD,USA","Dept. of Computer Science, University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park,Dept. of Computer Science,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept. of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066072868","display_name":"Celso M. de Melo","orcid":"https://orcid.org/0000-0003-2680-8334"},"institutions":[{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Celso M. de Melo","raw_affiliation_strings":["Adelphi,Computational and Information Sciences Directorate, DEVCOM U.S. Army Research Laboratory,MD,USA","Computational and Information Sciences Directorate, DEVCOM U.S. Army Research Laboratory, Adelphi, MD, USA"],"affiliations":[{"raw_affiliation_string":"Adelphi,Computational and Information Sciences Directorate, DEVCOM U.S. Army Research Laboratory,MD,USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]},{"raw_affiliation_string":"Computational and Information Sciences Directorate, DEVCOM U.S. Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026230432","display_name":"Stephen Nogar","orcid":"https://orcid.org/0000-0002-5233-6767"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen M. Nogar","raw_affiliation_strings":["Adelphi,Computational and Information Sciences Directorate, DEVCOM U.S. Army Research Laboratory,MD,USA","Computational and Information Sciences Directorate, DEVCOM U.S. Army Research Laboratory, Adelphi, MD, USA"],"affiliations":[{"raw_affiliation_string":"Adelphi,Computational and Information Sciences Directorate, DEVCOM U.S. Army Research Laboratory,MD,USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]},{"raw_affiliation_string":"Computational and Information Sciences Directorate, DEVCOM U.S. Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058453308","display_name":"Aniket Bera","orcid":"https://orcid.org/0000-0002-0182-6985"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aniket Bera","raw_affiliation_strings":["Purdue University,Dept. of Computer Science,West Lafayette,IN,USA","Dept. of Computer Science, Purdue University, West Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University,Dept. of Computer Science,West Lafayette,IN,USA","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"Dept. of Computer Science, Purdue University, West Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland, College Park,Dept. of Computer Science,MD,USA","Dept. of Computer Science, University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park,Dept. of Computer Science,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Dept. of Computer Science, University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100709597"],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":2.2386,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89991257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1312","last_page":"1318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","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/T10812","display_name":"Human Pose and Action Recognition","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":0.9972000122070312,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.7384769916534424},{"id":"https://openalex.org/keywords/zoom","display_name":"Zoom","score":0.7075985074043274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6280779838562012},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6163690686225891},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.551206648349762},{"id":"https://openalex.org/keywords/action-recognition","display_name":"Action recognition","score":0.4619271159172058},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08519136905670166}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384769916534424},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.7075985074043274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6280779838562012},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6163690686225891},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.551206648349762},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.4619271159172058},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08519136905670166},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"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/C15336307","wikidata":"https://www.wikidata.org/wiki/Q1766051","display_name":"Lens (geology)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160564","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160564","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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":58,"referenced_works":["https://openalex.org/W1744759976","https://openalex.org/W2034014085","https://openalex.org/W2413983136","https://openalex.org/W2625286981","https://openalex.org/W2823177849","https://openalex.org/W2891505129","https://openalex.org/W2911055311","https://openalex.org/W2918626955","https://openalex.org/W2962777203","https://openalex.org/W2963037989","https://openalex.org/W2963163009","https://openalex.org/W2963524571","https://openalex.org/W2970977083","https://openalex.org/W2981304952","https://openalex.org/W2984287396","https://openalex.org/W2989728968","https://openalex.org/W2990152177","https://openalex.org/W2990501806","https://openalex.org/W2990949296","https://openalex.org/W2996950367","https://openalex.org/W3007751154","https://openalex.org/W3009803092","https://openalex.org/W3012438347","https://openalex.org/W3034572008","https://openalex.org/W3034600407","https://openalex.org/W3090348690","https://openalex.org/W3090602253","https://openalex.org/W3091747220","https://openalex.org/W3098057674","https://openalex.org/W3111842428","https://openalex.org/W3130218528","https://openalex.org/W3132959232","https://openalex.org/W3134822545","https://openalex.org/W3134909472","https://openalex.org/W3160608582","https://openalex.org/W3162090017","https://openalex.org/W3169064633","https://openalex.org/W3173018607","https://openalex.org/W3173621652","https://openalex.org/W3174053790","https://openalex.org/W3202511256","https://openalex.org/W4225493839","https://openalex.org/W4281641544","https://openalex.org/W4285102286","https://openalex.org/W4297775537","https://openalex.org/W4312895250","https://openalex.org/W4313170858","https://openalex.org/W4385245566","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6750245737","https://openalex.org/W6753261499","https://openalex.org/W6770390784","https://openalex.org/W6787904228","https://openalex.org/W6790830454","https://openalex.org/W6801564760","https://openalex.org/W6810913163","https://openalex.org/W6838618513"],"related_works":["https://openalex.org/W2755342338","https://openalex.org/W2058170566","https://openalex.org/W2036807459","https://openalex.org/W2775347418","https://openalex.org/W1969923398","https://openalex.org/W2166024367","https://openalex.org/W2772917594","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2079911747"],"abstract_inverted_index":{"We":[0,27,61],"propose":[1],"a":[2,29,81],"novel":[3],"approach":[4,31,86],"for":[5,14,107],"aerial":[6],"video":[7],"action":[8,72],"recognition.":[9],"Our":[10,85],"method":[11],"is":[12],"designed":[13],"videos":[15],"captured":[16],"using":[17],"UAVs":[18],"and":[19,43,56,77,90,99,109,135],"can":[20],"run":[21],"on":[22,93,100,125,131,138],"edge":[23],"or":[24],"mobile":[25],"devices.":[26],"present":[28,63],"learning-based":[30],"that":[32],"uses":[33],"customized":[34],"auto":[35],"zoom":[36],"to":[37,51,69],"automatically":[38],"identify":[39],"the":[40,53,58,71,75,94,101,126,132,139],"human":[41],"target":[42],"scale":[44],"it":[45,49],"appropriately.":[46],"This":[47],"makes":[48],"easier":[50],"extract":[52],"key":[54],"features":[55],"reduces":[57],"computational":[59,83],"overhead.":[60],"also":[62],"an":[64],"efficient":[65],"temporal":[66,78],"reasoning":[67],"algorithm":[68],"capture":[70],"information":[73],"along":[74],"spatial":[76],"domains":[79],"within":[80],"controllable":[82],"cost.":[84],"has":[87],"been":[88],"implemented":[89],"evaluated":[91],"both":[92],"desktop":[95],"with":[96],"high-end":[97],"GPUs":[98],"low":[102],"power":[103],"Robotics":[104],"RB5":[105],"Platform":[106],"robots":[108],"drones.":[110],"In":[111],"practice,":[112],"we":[113],"achieve":[114],"<tex":[115],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[116],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$6.1-7.4":[117],"\\%$</tex>":[118],"improvement":[119,130,137],"over":[120],"SOTA":[121],"in":[122],"Top-1":[123],"accuracy":[124],"RoCoG-v2":[127],"dataset,":[128],"8.3-10.4%":[129],"UAV-Human":[133],"dataset":[134],"3.2%":[136],"Drone":[140],"Action":[141],"dataset.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":4}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}
