{"id":"https://openalex.org/W2995879646","doi":"https://doi.org/10.1109/tmm.2019.2960656","title":"Deep Multimodality Learning for UAV Video Aesthetic Quality Assessment","display_name":"Deep Multimodality Learning for UAV Video Aesthetic Quality Assessment","publication_year":2019,"publication_date":"2019-12-18","ids":{"openalex":"https://openalex.org/W2995879646","doi":"https://doi.org/10.1109/tmm.2019.2960656","mag":"2995879646"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2019.2960656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2960656","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.02356","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qi Kuang","orcid":"https://orcid.org/0000-0002-1675-1197"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Kuang","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1675-1197","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Jin","orcid":"https://orcid.org/0000-0003-3873-1653"},"institutions":[{"id":"https://openalex.org/I202334528","display_name":"Beijing Electronic Science and Technology Institute","ror":"https://ror.org/01xdzh226","country_code":"CN","type":"education","lineage":["https://openalex.org/I202334528"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jin","raw_affiliation_strings":["Beijing Electronic Science and Technology Institute, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3873-1653","affiliations":[{"raw_affiliation_string":"Beijing Electronic Science and Technology Institute, Beijing, China","institution_ids":["https://openalex.org/I202334528"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qinping Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinping Zhao","raw_affiliation_strings":["State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bin Zhou","orcid":"https://orcid.org/0000-0003-2091-1090"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Zhou","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China","State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2091-1090","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0918,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.82369867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"22","issue":"10","first_page":"2623","last_page":"2634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9890999794006348,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9890999794006348,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.0034000000450760126,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0007999999797903001,"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/drone","display_name":"Drone","score":0.7531999945640564},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.47769999504089355},{"id":"https://openalex.org/keywords/video-quality","display_name":"Video quality","score":0.47269999980926514},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45329999923706055},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.45239999890327454},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4440999925136566},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.4291999936103821},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41510000824928284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8658999800682068},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.7531999945640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6909999847412109},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6503999829292297},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.47769999504089355},{"id":"https://openalex.org/C103910844","wikidata":"https://www.wikidata.org/wiki/Q2631256","display_name":"Video quality","level":3,"score":0.47269999980926514},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.45239999890327454},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.414000004529953},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.3346000015735626},{"id":"https://openalex.org/C2987819851","wikidata":"https://www.wikidata.org/wiki/Q191839","display_name":"Aerial imagery","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.30720001459121704},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.2838999927043915},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.2651999890804291}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tmm.2019.2960656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2019.2960656","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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 Multimedia","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2011.02356","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02356","pdf_url":"https://arxiv.org/pdf/2011.02356","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2011.02356","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2011.02356","pdf_url":"https://arxiv.org/pdf/2011.02356","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5158269727","display_name":null,"funder_award_id":"61932003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7762195423","display_name":null,"funder_award_id":"VRLAB2019C03","funder_id":"https://openalex.org/F4320326839","funder_display_name":"State Key Laboratory of Virtual Reality Technology and Systems"},{"id":"https://openalex.org/G7953880188","display_name":null,"funder_award_id":"U1736217","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326839","display_name":"State Key Laboratory of Virtual Reality Technology and Systems","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1607823124","https://openalex.org/W1777628566","https://openalex.org/W1896080482","https://openalex.org/W1923404803","https://openalex.org/W1938565953","https://openalex.org/W1972482772","https://openalex.org/W1972942324","https://openalex.org/W1976414467","https://openalex.org/W1996514462","https://openalex.org/W2007773296","https://openalex.org/W2009678853","https://openalex.org/W2016053056","https://openalex.org/W2048835603","https://openalex.org/W2053611776","https://openalex.org/W2055600015","https://openalex.org/W2078807908","https://openalex.org/W2080754665","https://openalex.org/W2100454127","https://openalex.org/W2108598243","https://openalex.org/W2138761185","https://openalex.org/W2144945173","https://openalex.org/W2161107932","https://openalex.org/W2162991084","https://openalex.org/W2165024080","https://openalex.org/W2217895792","https://openalex.org/W2293846591","https://openalex.org/W2342662179","https://openalex.org/W2467531333","https://openalex.org/W2474281075","https://openalex.org/W2516010014","https://openalex.org/W2526479943","https://openalex.org/W2580835135","https://openalex.org/W2580899942","https://openalex.org/W2603816353","https://openalex.org/W2604528050","https://openalex.org/W2781685787","https://openalex.org/W2798868169","https://openalex.org/W2803030343","https://openalex.org/W2898070459","https://openalex.org/W2903335068","https://openalex.org/W2904572228","https://openalex.org/W2926312400","https://openalex.org/W2962733873","https://openalex.org/W2963645879","https://openalex.org/W4236769309","https://openalex.org/W6630520941","https://openalex.org/W6631794248","https://openalex.org/W6675445837","https://openalex.org/W6682864246","https://openalex.org/W6683413062","https://openalex.org/W6685083886","https://openalex.org/W6717040974","https://openalex.org/W6727508588","https://openalex.org/W6763422710"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,20,32,122,134,165],"growing":[2],"number":[3],"of":[4,16,22,35,45,152],"unmanned":[5],"aerial":[6,10,23,36],"vehicles":[7],"(UAVs)":[8],"and":[9,75,138,159],"videos,":[11],"there":[12],"is":[13,60,85],"a":[14,43,57,94,110],"paucity":[15],"studies":[17],"focusing":[18],"on":[19],"aesthetics":[21],"videos":[24],"that":[25,130],"can":[26,107],"provide":[27],"valuable":[28],"information":[29],"for":[30,49,87,142],"improving":[31],"aesthetic":[33,52,64],"quality":[34,53],"photography.":[37],"In":[38,145],"this":[39,88],"article,":[40],"we":[41,147],"present":[42,148],"method":[44,132],"deep":[46],"multimodality":[47],"learning":[48],"UAV":[50,98,111,153,161],"video":[51,99,112,135,143,154],"assessment.":[54],"More":[55],"specifically,":[56],"multistream":[58,90],"framework":[59],"designed":[61,81],"to":[62],"exploit":[63],"attributes":[65],"from":[66],"multiple":[67],"modalities,":[68],"including":[69],"spatial":[70],"appearance,":[71],"drone":[72,103],"camera":[73],"motion,":[74],"scene":[76,123],"structure.":[77],"A":[78],"novel":[79],"specially":[80],"motion":[82],"stream":[83],"network":[84],"proposed":[86,166],"new":[89],"framework.":[91],"We":[92],"construct":[93],"dataset":[95],"with":[96,121],"6,000":[97],"shots":[100],"captured":[101],"by":[102,115],"cameras.":[104],"Our":[105],"model":[106],"judge":[108],"whether":[109],"was":[113],"shot":[114],"professional":[116,156],"photographers":[117],"or":[118],"amateurs":[119],"together":[120],"type":[124],"classification.":[125],"The":[126],"experimental":[127],"results":[128],"reveal":[129],"our":[131],"outperforms":[133],"classification":[136],"methods":[137,141],"traditional":[139],"SVM-based":[140],"aesthetics.":[144],"addition,":[146],"three":[149],"application":[150],"examples":[151],"grading,":[155],"segment":[157],"detection":[158],"aesthetic-based":[160],"path":[162],"planning":[163],"using":[164],"method.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2019-12-26T00:00:00"}