{"id":"https://openalex.org/W3206527789","doi":"https://doi.org/10.1145/3474085.3475568","title":"Text is NOT Enough","display_name":"Text is NOT Enough","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W3206527789","doi":"https://doi.org/10.1145/3474085.3475568","mag":"3206527789"},"language":"en","primary_location":{"id":"doi:10.1145/3474085.3475568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101586835","display_name":"Lei Shen","orcid":"https://orcid.org/0000-0002-9786-2605"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Shen","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043429023","display_name":"Haolan Zhan","orcid":"https://orcid.org/0000-0001-9628-5992"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haolan Zhan","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624454","display_name":"Xin Shen","orcid":"https://orcid.org/0009-0006-2699-3292"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Shen","raw_affiliation_strings":["Australian National University, Canberra, ACT, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, ACT, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101557904","display_name":"Yonghao Song","orcid":"https://orcid.org/0000-0003-1700-1133"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghao Song","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100750786","display_name":"Xiaofang Zhao","orcid":"https://orcid.org/0000-0002-1898-1359"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofang Zhao","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4287","last_page":"4296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.98580002784729,"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/T10028","display_name":"Topic Modeling","score":0.9851999878883362,"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":0.8745883703231812},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6883147954940796},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6210378408432007},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5868974328041077},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5580393671989441},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5121207237243652},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5104343295097351},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5074614882469177},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.49206775426864624},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4764942526817322},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4400354325771332},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4340890049934387},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.419541597366333},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4178731441497803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34856978058815},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10246467590332031},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.10041970014572144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8745883703231812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6883147954940796},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6210378408432007},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5868974328041077},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5580393671989441},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5121207237243652},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5104343295097351},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5074614882469177},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.49206775426864624},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4764942526817322},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4400354325771332},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4340890049934387},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.419541597366333},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4178731441497803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34856978058815},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10246467590332031},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.10041970014572144},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3474085.3475568","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3474085.3475568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5699999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1581505603","https://openalex.org/W1895577753","https://openalex.org/W2101105183","https://openalex.org/W2531638282","https://openalex.org/W2549139847","https://openalex.org/W2605246398","https://openalex.org/W2795571593","https://openalex.org/W2798786641","https://openalex.org/W2799014768","https://openalex.org/W2799037524","https://openalex.org/W2807873315","https://openalex.org/W2888093771","https://openalex.org/W2892245540","https://openalex.org/W2897182555","https://openalex.org/W2917061951","https://openalex.org/W2937971956","https://openalex.org/W2951114218","https://openalex.org/W2951450739","https://openalex.org/W2956125353","https://openalex.org/W2962796276","https://openalex.org/W2963206148","https://openalex.org/W2963287297","https://openalex.org/W2963544536","https://openalex.org/W2963748384","https://openalex.org/W2963825865","https://openalex.org/W2963903950","https://openalex.org/W2964352131","https://openalex.org/W2965597639","https://openalex.org/W2970231061","https://openalex.org/W2970355596","https://openalex.org/W2972437240","https://openalex.org/W2981591098","https://openalex.org/W2988023442","https://openalex.org/W2997547717","https://openalex.org/W2998356391","https://openalex.org/W3006130793","https://openalex.org/W3015322406","https://openalex.org/W3093418251","https://openalex.org/W3098177778","https://openalex.org/W3103651098","https://openalex.org/W3160293015","https://openalex.org/W3172448816","https://openalex.org/W3176956817","https://openalex.org/W4239019441"],"related_works":["https://openalex.org/W2067317451","https://openalex.org/W3203142394","https://openalex.org/W4390516098","https://openalex.org/W2154771632","https://openalex.org/W4211085505","https://openalex.org/W4302615923","https://openalex.org/W2181948922","https://openalex.org/W1974101135","https://openalex.org/W2221419418","https://openalex.org/W2797876554"],"abstract_inverted_index":{"Open-domain":[0],"dialogue":[1,55,68,145,152,248],"generation":[2],"in":[3,125,178,218,261],"natural":[4],"language":[5],"processing":[6],"(NLP)":[7],"is":[8,73,94],"by":[9,26],"default":[10],"a":[11,136,159,169,179,184,203],"pure-language":[12,144],"task,":[13],"which":[14],"aims":[15],"to":[16,53,97,138,182,226],"satisfy":[17],"human":[18],"need":[19],"for":[20,150,164],"daily":[21],"communication":[22],"on":[23,143,168,238,245],"open-ended":[24],"topics":[25],"producing":[27],"related":[28],"and":[29,57,70,79,92,118,147,154,190,220,241,266],"informative":[30],"responses.":[31,61],"In":[32],"this":[33],"paper,":[34],"we":[35,134,157,201],"point":[36],"out":[37],"that":[38,206,251],"hidden":[39],"images,":[40],"named":[41],"as":[42],"visual":[43,85,101,111,189],"impressions":[44,86,102,112],"(VIs),":[45],"can":[46],"be":[47],"explored":[48],"from":[49],"the":[50,63,84,99,105,109,116,126,131,194,215,222,231,235,239],"text-only":[51],"data":[52],"enhance":[54],"understanding":[56,153],"help":[58],"generate":[59],"better":[60,151],"Besides,":[62],"semantic":[64],"dependency":[65],"between":[66],"an":[67],"post":[69,110,166,185,240],"its":[71,119],"response":[72,100,117,236],"complicated,":[74],"e.g.,":[75],"few":[76],"word":[77],"alignments":[78],"some":[80],"topic":[81],"transitions.":[82],"Therefore,":[83],"of":[87,161,208,263],"them":[88,149],"are":[89,121,176,196],"not":[90,122,197],"shared,":[91],"it":[93],"more":[95],"reasonable":[96],"integrate":[98],"(RVIs)":[103],"into":[104],"decoder,":[106],"rather":[107],"than":[108],"(PVIs).":[113],"However,":[114],"both":[115,188],"RVIs":[120,195],"given":[123],"directly":[124],"test":[127],"process.":[128],"To":[129],"handle":[130],"above":[132],"issues,":[133],"propose":[135],"framework":[137],"explicitly":[139],"construct":[140],"VIs":[141],"based":[142,167,237],"datasets":[146,249],"utilize":[148],"generation.":[155],"Specifically,":[156],"obtain":[158],"group":[160],"images":[162],"(PVIs)":[163],"each":[165],"pre-trained":[170],"word-image":[171,223],"mapping":[172,224],"model.":[173],"These":[174],"PVIs":[175],"used":[177],"co-attention":[180],"encoder":[181],"get":[183,227],"representation":[186],"with":[187],"textual":[191],"information.":[192],"Since":[193],"provided":[198],"during":[199],"testing,":[200],"design":[202],"cascade":[204],"decoder":[205],"consists":[207],"two":[209,246],"sub-decoders.":[210],"The":[211],"first":[212],"sub-decoder":[213,233],"predicts":[214],"content":[216],"words":[217],"response,":[219],"applies":[221],"model":[225],"corresponding":[228],"RVIs.":[229,242],"Then,":[230],"second":[232],"generates":[234],"Experimental":[243],"results":[244],"open-domain":[247],"show":[250],"our":[252],"proposed":[253],"approach":[254],"achieves":[255],"superior":[256],"performance":[257],"over":[258],"competitive":[259],"baselines":[260],"terms":[262],"fluency,":[264],"relatedness,":[265],"diversity.":[267]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2021-10-25T00:00:00"}