{"id":"https://openalex.org/W4387148495","doi":"https://doi.org/10.1145/3581783.3613809","title":"Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer","display_name":"Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387148495","doi":"https://doi.org/10.1145/3581783.3613809"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3613809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.14704","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103324108","display_name":"Zhiahao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiahao Zhang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-3791-8785","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103325728","display_name":"Yiwei Chen","orcid":"https://orcid.org/0000-0002-0219-9143"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiwei Chen","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-0219-9143","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028268587","display_name":"Weizhan Zhang","orcid":"https://orcid.org/0000-0003-0330-5435"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhan Zhang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-0330-5435","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102759804","display_name":"Caixia Yan","orcid":"https://orcid.org/0000-0001-7763-2987"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caixia Yan","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0001-7763-2987","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041083459","display_name":"Qinghua Zheng","orcid":"https://orcid.org/0000-0002-8436-4754"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinghua Zheng","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-8436-4754","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341340","display_name":"Qi Wang","orcid":"https://orcid.org/0000-0002-0639-2119"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-0639-2119","affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054843059","display_name":"Wangdu Chen","orcid":"https://orcid.org/0000-0002-8921-0092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wangdu Chen","raw_affiliation_strings":["MIGU Video, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8921-0092","affiliations":[{"raw_affiliation_string":"MIGU Video, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3560","last_page":"3568"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11165","display_name":"Image and Video Quality Assessment","score":0.9994999766349792,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9994999766349792,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9886999726295471,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.9876999855041504,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/viewport","display_name":"Viewport","score":0.9572105407714844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.782799482345581},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.6175022721290588},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5456829071044922},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5369408130645752},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5259487628936768},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3632051944732666},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33809399604797363}],"concepts":[{"id":"https://openalex.org/C2778090530","wikidata":"https://www.wikidata.org/wiki/Q2523931","display_name":"Viewport","level":2,"score":0.9572105407714844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.782799482345581},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.6175022721290588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5456829071044922},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5369408130645752},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5259487628936768},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3632051944732666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33809399604797363},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3613809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3613809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2309.14704","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.14704","pdf_url":"https://arxiv.org/pdf/2309.14704","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:2309.14704","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.14704","pdf_url":"https://arxiv.org/pdf/2309.14704","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/G3227670556","display_name":null,"funder_award_id":"62172326","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4896784468","display_name":null,"funder_award_id":"62137002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7592982503","display_name":null,"funder_award_id":"2020AAA0108800","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/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387148495.pdf","grobid_xml":"https://content.openalex.org/works/W4387148495.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W2612690371","https://openalex.org/W2766324256","https://openalex.org/W2784243934","https://openalex.org/W2799064164","https://openalex.org/W2884414611","https://openalex.org/W2895957446","https://openalex.org/W2896449077","https://openalex.org/W2896457183","https://openalex.org/W2914790472","https://openalex.org/W2943420393","https://openalex.org/W2947567055","https://openalex.org/W2954684697","https://openalex.org/W2963163009","https://openalex.org/W2963428739","https://openalex.org/W2966715458","https://openalex.org/W2990039632","https://openalex.org/W2992753629","https://openalex.org/W2998356391","https://openalex.org/W3021395787","https://openalex.org/W3030482512","https://openalex.org/W3034727271","https://openalex.org/W3038754372","https://openalex.org/W3081459285","https://openalex.org/W3083847600","https://openalex.org/W3091202141","https://openalex.org/W3094338163","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3126792443","https://openalex.org/W3136920339","https://openalex.org/W3138516171","https://openalex.org/W3154476408","https://openalex.org/W3165727273","https://openalex.org/W3179280609","https://openalex.org/W4213019189","https://openalex.org/W4221086736","https://openalex.org/W4251137679","https://openalex.org/W4283375183","https://openalex.org/W4288089799","https://openalex.org/W4293794975","https://openalex.org/W4312560592","https://openalex.org/W4318148331","https://openalex.org/W4360764276","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4389095575","https://openalex.org/W2908978341","https://openalex.org/W4294975495","https://openalex.org/W4308233970","https://openalex.org/W3161069372","https://openalex.org/W2992753629","https://openalex.org/W3171203216","https://openalex.org/W3123914255","https://openalex.org/W4225714298","https://openalex.org/W2948809149"],"abstract_inverted_index":{"Viewport":[0],"prediction":[1,49,165],"is":[2],"a":[3,44],"crucial":[4],"aspect":[5],"of":[6,18,24,81,163],"tile-based":[7],"360\u00b0":[8],"video":[9,86],"streaming":[10],"system.":[11],"However,":[12],"existing":[13],"trajectory":[14],"based":[15,47,126],"methods":[16,160],"lack":[17],"robustness,":[19],"also":[20,170],"oversimplify":[21],"the":[22,35,64,78,110],"process":[23],"information":[25],"construction":[26],"and":[27,73,85,105,135,151,167],"fusion":[28],"between":[29],"different":[30],"modality":[31],"inputs,":[32],"leading":[33],"to":[34,62,76],"error":[36],"accumulation":[37],"problem.":[38],"In":[39,92],"this":[40],"paper,":[41],"we":[42,142],"propose":[43],"tile":[45],"classification":[46,130],"viewport":[48,90,108,125],"method":[50],"with":[51,119],"Multi-modal":[52],"Fusion":[53],"Transformer,":[54],"namely":[55],"MFTR.":[56],"Specifically,":[57],"MFTR":[58,94,154],"utilizes":[59],"transformer-based":[60],"networks":[61],"extract":[63],"long-range":[65],"dependencies":[66],"within":[67],"each":[68],"modality,":[69],"then":[70],"mine":[71],"intra-":[72],"inter-modality":[74],"relations":[75],"capture":[77],"combined":[79],"impact":[80],"user":[82,101,115],"historical":[83],"inputs":[84],"contents":[87],"on":[88,127,146],"future":[89,96,107,124],"selection.":[91],"addition,":[93],"categorizes":[95],"tiles":[97],"into":[98],"two":[99,147],"categories:":[100],"interested":[102,116],"or":[103],"not,":[104],"selects":[106],"as":[109],"region":[111],"that":[112],"contains":[113],"most":[114],"tiles.":[117],"Comparing":[118],"predicting":[120],"head":[121],"trajectories,":[122],"choosing":[123],"tile's":[128],"binary":[129],"results":[131],"exhibits":[132],"better":[133],"robustness":[134],"interpretability.":[136],"To":[137],"evaluate":[138],"our":[139],"proposed":[140],"MFTR,":[141],"conduct":[143],"extensive":[144],"experiments":[145],"widely":[148],"used":[149],"PVS-HM":[150],"Xu-Gaze":[152],"dataset.":[153],"shows":[155],"superior":[156],"performance":[157],"over":[158],"state-of-the-art":[159],"in":[161],"terms":[162],"average":[164],"accuracy":[166],"overlap":[168],"ratio,":[169],"presents":[171],"competitive":[172],"computation":[173],"efficiency.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
