{"id":"https://openalex.org/W4406860639","doi":"https://doi.org/10.1109/vcip63160.2024.10849901","title":"MAESR360: Masked autoencoder-based 360-degree video streaming via multi-scale feature fusion","display_name":"MAESR360: Masked autoencoder-based 360-degree video streaming via multi-scale feature fusion","publication_year":2024,"publication_date":"2024-12-08","ids":{"openalex":"https://openalex.org/W4406860639","doi":"https://doi.org/10.1109/vcip63160.2024.10849901"},"language":"en","primary_location":{"id":"doi:10.1109/vcip63160.2024.10849901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip63160.2024.10849901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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/A5011732131","display_name":"Li Yu","orcid":"https://orcid.org/0000-0002-8855-8089"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Yu","raw_affiliation_strings":["Nanjing University of Information Science & Technology,School of Computer Science,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science & Technology,School of Computer Science,Nanjing,China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114106195","display_name":"Zhiyu Pang","orcid":"https://orcid.org/0000-0002-1303-2381"},"institutions":[{"id":"https://openalex.org/I200845125","display_name":"Nanjing University of Information Science and Technology","ror":"https://ror.org/02y0rxk19","country_code":"CN","type":"education","lineage":["https://openalex.org/I200845125"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyu Pang","raw_affiliation_strings":["Nanjing University of Information Science & Technology,School of Computer Science,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"Nanjing University of Information Science & Technology,School of Computer Science,Nanjing,China","institution_ids":["https://openalex.org/I200845125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007583477","display_name":"Moncef Gabbouj","orcid":"https://orcid.org/0000-0002-9788-2323"},"institutions":[{"id":"https://openalex.org/I166825849","display_name":"Tampere University","ror":"https://ror.org/033003e23","country_code":"FI","type":"education","lineage":["https://openalex.org/I166825849"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Moncef Gabbouj","raw_affiliation_strings":["Tampere University,Department of Computing Sciences,Tampere,Finland,33100"],"affiliations":[{"raw_affiliation_string":"Tampere University,Department of Computing Sciences,Tampere,Finland,33100","institution_ids":["https://openalex.org/I166825849"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011732131"],"corresponding_institution_ids":["https://openalex.org/I200845125"],"apc_list":null,"apc_paid":null,"fwci":0.26,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58864305,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.968500018119812,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.968500018119812,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9480000138282776,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9311000108718872,"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/autoencoder","display_name":"Autoencoder","score":0.8551914691925049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7428017854690552},{"id":"https://openalex.org/keywords/video-streaming","display_name":"Video streaming","score":0.5899616479873657},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5712805986404419},{"id":"https://openalex.org/keywords/degree","display_name":"Degree (music)","score":0.560204029083252},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5332127809524536},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.430084228515625},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3971385359764099},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.17129471898078918},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1645902395248413},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.056810617446899414},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.04653164744377136}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8551914691925049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7428017854690552},{"id":"https://openalex.org/C2986160907","wikidata":"https://www.wikidata.org/wiki/Q220499","display_name":"Video streaming","level":2,"score":0.5899616479873657},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5712805986404419},{"id":"https://openalex.org/C2775997480","wikidata":"https://www.wikidata.org/wiki/Q586277","display_name":"Degree (music)","level":2,"score":0.560204029083252},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5332127809524536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.430084228515625},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3971385359764099},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.17129471898078918},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1645902395248413},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.056810617446899414},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.04653164744377136},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip63160.2024.10849901","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip63160.2024.10849901","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Visual Communications and Image Processing (VCIP)","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":26,"referenced_works":["https://openalex.org/W2055165550","https://openalex.org/W2620871200","https://openalex.org/W2622637199","https://openalex.org/W2809682753","https://openalex.org/W2920378308","https://openalex.org/W2963372104","https://openalex.org/W2986102820","https://openalex.org/W2996368995","https://openalex.org/W2996939355","https://openalex.org/W3030482512","https://openalex.org/W3032637606","https://openalex.org/W3043547428","https://openalex.org/W3047354607","https://openalex.org/W3087814885","https://openalex.org/W3119350460","https://openalex.org/W3136920339","https://openalex.org/W3176531424","https://openalex.org/W4205792818","https://openalex.org/W4226270831","https://openalex.org/W4301297902","https://openalex.org/W4304098311","https://openalex.org/W4313156423","https://openalex.org/W4321488193","https://openalex.org/W6784333009","https://openalex.org/W6810265253","https://openalex.org/W6810371877"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2566616303","https://openalex.org/W2159052453","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2803255133","https://openalex.org/W4297051394","https://openalex.org/W2752972570","https://openalex.org/W4386815338","https://openalex.org/W2351424232"],"abstract_inverted_index":{"360-degree":[0,50,95],"video":[1,51,96,144],"streaming":[2,14,52,97],"is":[3,40,152],"becoming":[4],"increasingly":[5],"popular":[6],"for":[7,94],"its":[8],"immersive":[9],"experience.":[10],"Traditional":[11],"adaptive":[12],"tile-based":[13],"methods":[15],"allocate":[16],"the":[17,37,57,79,102,106,120,140],"bitrates":[18],"according":[19],"to":[20,117,138],"view-port":[21],"prediction,":[22],"which":[23,54,74,99],"effectively":[24,118],"reduces":[25],"required":[26],"transmission":[27],"bandwidth,":[28],"but":[29],"it":[30],"will":[31],"cause":[32],"serious":[33],"quality":[34,142],"degradation":[35],"when":[36],"viewport":[38],"prediction":[39],"inaccurate.":[41],"Thus,":[42],"some":[43],"researchers":[44],"propose":[45,87],"visual":[46,71,130,141],"reconstruction":[47,72,131],"and":[48,112],"enhancement-based":[49],"framework,":[53],"can":[55],"reconstructs":[56],"whole":[58],"frame":[59],"at":[60],"very":[61],"low":[62],"bitrates.":[63],"However,":[64],"existing":[65],"frameworks":[66],"are":[67],"built":[68],"upon":[69],"image-based":[70],"methods,":[73],"do":[75],"not":[76],"fully":[77,100],"consider":[78],"characteristics":[80],"of":[81,105,122,143,148],"videos.":[82],"In":[83],"this":[84],"paper,":[85],"we":[86,126],"a":[88,128],"masked":[89],"autoencoder-based,":[90],"multi-scale":[91,135],"optimized":[92],"framework":[93],"(MAESR360),":[98],"considers":[101],"temporal":[103],"relevance":[104],"video.":[107],"We":[108],"utilize":[109],"spatio-temporal":[110],"downsampling":[111],"high-ratio":[113],"tube":[114],"masking":[115],"strategies":[116],"reduce":[119],"amount":[121],"transmitted":[123],"data.":[124],"Additionally,":[125],"design":[127],"lightweight":[129],"model":[132],"based":[133],"on":[134],"feature":[136],"fusion":[137],"recover":[139],"frames.":[145],"The":[146],"effectiveness":[147],"our":[149],"proposed":[150],"method":[151],"demonstrated":[153],"through":[154],"extensive":[155],"experiments.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}