{"id":"https://openalex.org/W3190982062","doi":"https://doi.org/10.14264/accb67e","title":"Multimedia content analytics with modality transition","display_name":"Multimedia content analytics with modality transition","publication_year":2021,"publication_date":"2021-07-30","ids":{"openalex":"https://openalex.org/W3190982062","doi":"https://doi.org/10.14264/accb67e","mag":"3190982062"},"language":"en","primary_location":{"id":"doi:10.14264/accb67e","is_oa":false,"landing_page_url":"https://doi.org/10.14264/accb67e","pdf_url":null,"source":{"id":"https://openalex.org/S7407053192","display_name":"The University of Queensland","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The University of Queensland","raw_type":"dissertation"},"type":"dissertation","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"last","author":{"id":"https://openalex.org/A5100389369","display_name":"Ziwei Wang","orcid":"https://orcid.org/0000-0002-0107-7347"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziwei Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0107-7347","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9947999715805054,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9868000149726868,"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":0.7883856296539307},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.7485201358795166},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.6353969573974609},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5957197546958923},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5230960845947266},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5015878677368164},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.48215028643608093},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4491429924964905},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44752371311187744},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.27915576100349426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.274955153465271},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.2594764232635498},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14039930701255798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7883856296539307},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.7485201358795166},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.6353969573974609},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5957197546958923},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5230960845947266},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5015878677368164},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.48215028643608093},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4491429924964905},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44752371311187744},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27915576100349426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.274955153465271},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2594764232635498},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14039930701255798},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14264/accb67e","is_oa":false,"landing_page_url":"https://doi.org/10.14264/accb67e","pdf_url":null,"source":{"id":"https://openalex.org/S7407053192","display_name":"The University of Queensland","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The University of Queensland","raw_type":"dissertation"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6200000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W73545470","https://openalex.org/W4224266612","https://openalex.org/W2383394264","https://openalex.org/W4320153225","https://openalex.org/W4293261942","https://openalex.org/W3125968744","https://openalex.org/W2167701463","https://openalex.org/W2110287964","https://openalex.org/W4307407935","https://openalex.org/W649759291"],"abstract_inverted_index":{"Multimedia":[0],"integrating":[1],"different":[2],"modalities":[3,97],"such":[4,163],"as":[5,132,134,164],"text,":[6,209],"image,":[7],"and":[8,29,39,64,72,76,95,122,125,182,203,234,249,274,280,318,337,350,447,478],"video,":[9],"provides":[10],"users":[11],"with":[12,220,452,499],"much":[13],"convenience":[14],"in":[15,332,357,389,400,457,508],"the":[16,26,42,46,49,91,100,117,126,135,167,186,193,215,225,228,260,265,277,287,292,297,328,343,352,372,381,384,401,419,442,486,490],"digital":[17],"era.":[18],"Researchers":[19],"have":[20,170],"been":[21],"establishing":[22],"multimedia":[23,31,50,57,86,104,112],"infrastructure":[24],"over":[25],"recent":[27],"decades,":[28],"nowadays":[30],"content":[32,58,73,81,105,113,124,142,201],"can":[33,151,368,505],"be":[34,218,232,506],"delivered":[35],"to":[36,62,98,174,240,257,285,310,345,417,421,472],"almost":[37],"everyone":[38],"everywhere.":[40],"With":[41],"fast":[43],"development":[44],"of":[45,84,103,111,120,227,242,383,394,489],"media":[47],"world,":[48],"research":[51],"community":[52],"has":[53],"focused":[54],"attention":[55,299,502],"on":[56,271,437],"analytics,":[59],"which":[60,504],"aims":[61],"recognise":[63],"represent":[65],"semantic":[66,473],"information":[67],"from":[68,116,189,291,342,371,407,423,469],"various":[69,85],"data":[70,230,405,425],"sources":[71],"types.":[74],"Vision":[75],"language":[77,96,191,194,385,448],"are":[78,156,254,283,325,340,398],"two":[79],"representative":[80],"forms":[82],"out":[83],"formats.":[87],"This":[88],"dissertation":[89,269],"investigates":[90],"interactions":[92,339],"between":[93,130,445],"vision":[94,161,446],"enhance":[99,259,286],"comprehension":[101,177],"ability":[102],"analytics":[106,114],"methods.":[107],"The":[108,322,335,364,412,460,494,510],"main":[109],"challenges":[110],"come":[115],"feature":[118],"representations":[119,169,289],"visual":[121,141,153,176,183,288,312,329,374,470],"textual":[123,200],"intrinsic":[127],"modality":[128,247,443,454,462],"gap":[129,444],"them,":[131],"well":[133],"time-consuming":[136],"training":[137,229,251,404,424,435,487,495,511],"process.":[138,379],"From":[139],"a":[140,145,190,347,358,432,453,466,500],"aspect,":[143,192],"although":[144],"convolutional":[146,362],"neural":[147],"network":[148],"based":[149],"model":[150,216,250,261,272,300,331,386,420,520],"extract":[152],"features":[154,375,471],"that":[155,426],"effective":[157],"for":[158,199,213,301,314,327,475],"conventional":[159],"computer":[160],"tasks":[162,178],"image":[165,180,211,302,344,402,491],"classification,":[166],"learned":[168],"limitations":[171],"when":[172],"generalising":[173],"advanced":[175],"including":[179],"captioning":[181,492],"dialogue.":[184],"On":[185],"other":[187],"hand,":[188],"models":[195],"learn":[196,422],"word":[197],"embeddings":[198,474],"representation":[202],"generation.":[204,321,481],"To":[205,263],"generate":[206],"high":[207,221,433,438],"quality":[208,222,226,396,439],"an":[210,408],"caption":[212,403,480],"instance,":[214],"must":[217],"trained":[219,507],"data.":[223],"However,":[224],"cannot":[231],"guaranteed,":[233],"imperfect":[235,428],"annotations":[236,429],"will":[237],"inevitably":[238],"lead":[239],"output":[241],"subpar":[243],"quality.":[244],"In":[245],"addition,":[246],"transition":[248,455,463,468],"efficiency":[252,488],"problems":[253],"worth":[255],"investigating":[256],"further":[258],"usability.":[262],"address":[264],"aforementioned":[266],"challenges,":[267],"this":[268,378],"concentrates":[270],"effectiveness":[273,382],"efficiency.":[275],"Firstly,":[276],"depth":[278,306],"map":[279,307],"scene":[281,348],"graph":[282,353,361],"exploited":[284],"derived":[290],"image.":[293],"Chapter":[294,333,390,458,483],"2":[295],"introduces":[296],"depth-aware":[298],"paragraph":[303,320],"captioning.":[304],"A":[305,392],"is":[308,355,387,415,449,497],"estimated":[309],"augment":[311],"cues":[313],"more":[315,476],"accurate,":[316],"logical":[317],"diverse":[319],"object":[323],"relationships":[324],"discovered":[326],"dialogue":[330,365],"3.":[334],"objects":[336],"their":[338],"extracted":[341,376],"form":[346],"graph,":[349],"then":[351,369],"structure":[354],"preserved":[356],"novel":[359],"hierarchical":[360],"network.":[363],"reasoning":[366],"module":[367,456,464],"benefit":[370],"comprehensive":[373],"via":[377],"Secondly,":[380],"investigated":[388],"4.":[391],"number":[393],"annotation":[395],"issues":[397],"identified":[399],"collected":[406],"online":[409],"crowd-sourcing":[410],"platform.":[411],"human-consensus":[413],"loss":[414],"proposed":[416,461],"allow":[418],"includes":[427],"by":[430],"setting":[431],"priority":[434],"focus":[436],"annotations.":[440],"Thirdly,":[441],"explicitly":[450],"addressed":[451,498],"5.":[459],"ensures":[465],"smooth":[467],"precise":[477],"context-aware":[479],"Lastly,":[482],"6":[484],"considers":[485],"model.":[493],"deficiency":[496],"well-engineered":[501],"mechanism":[503],"parallel.":[509],"time":[512],"is,":[513],"therefore,":[514],"significantly":[515],"reduced,":[516],"whilst":[517],"maintaining":[518],"competitive":[519],"performance.":[521]},"counts_by_year":[],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2021-08-16T00:00:00"}