{"id":"https://openalex.org/W3157509826","doi":"https://doi.org/10.1145/3444685.3446302","title":"C3VQG","display_name":"C3VQG","publication_year":2021,"publication_date":"2021-03-07","ids":{"openalex":"https://openalex.org/W3157509826","doi":"https://doi.org/10.1145/3444685.3446302","mag":"3157509826"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3444685.3446302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.1145/3444685.3446302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045000053","display_name":"Shagun Uppal","orcid":"https://orcid.org/0000-0002-4502-4650"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shagun Uppal","raw_affiliation_strings":["IIIT-Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIIT-Delhi, India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016792855","display_name":"Anish Madan","orcid":null},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anish Madan","raw_affiliation_strings":["IIIT-Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIIT-Delhi, India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079864567","display_name":"Sarthak Bhagat","orcid":"https://orcid.org/0000-0002-9067-0926"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sarthak Bhagat","raw_affiliation_strings":["IIIT-Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIIT-Delhi, India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054054198","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0002-6286-4985"},"institutions":[],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yi Yu","raw_affiliation_strings":["NII, Japan"],"affiliations":[{"raw_affiliation_string":"NII, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079357056","display_name":"Rajiv Ratn Shah","orcid":"https://orcid.org/0000-0003-1028-9373"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajiv Ratn Shah","raw_affiliation_strings":["IIIT-Delhi, India"],"affiliations":[{"raw_affiliation_string":"IIIT-Delhi, India","institution_ids":["https://openalex.org/I119939252","https://openalex.org/I68891433"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.431,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":7,"citation_normalized_percentile":{"value":0.738958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":83,"max":84},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9965,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9943,"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":0.5792656},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.48357242},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.468812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74961615},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6546755},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.64521617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6008765},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5792656},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.57058835},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.56687033},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.48357242},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48171884},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.468812},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.40090948},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3770529},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33956772},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33646923},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.14182442},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1278607},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3444685.3446302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3444685.3446302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":17,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W2563399268","https://openalex.org/W2750725664","https://openalex.org/W2889586584","https://openalex.org/W2896348597","https://openalex.org/W2898071615","https://openalex.org/W2908694412","https://openalex.org/W2951619830","https://openalex.org/W2962749469","https://openalex.org/W2963051286","https://openalex.org/W2963744743","https://openalex.org/W2964532449","https://openalex.org/W2970746059","https://openalex.org/W2994303421","https://openalex.org/W3109393163","https://openalex.org/W4255556797","https://openalex.org/W4301045096"],"related_works":["https://openalex.org/W4380551139","https://openalex.org/W4365211920","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W3034474024","https://openalex.org/W3014948380","https://openalex.org/W2965095304","https://openalex.org/W2953501176","https://openalex.org/W2470043383","https://openalex.org/W2280377497"],"abstract_inverted_index":{"Visual":[0],"Question":[1],"Generation":[2],"(VQG)":[3],"is":[4,120,143,165],"the":[5,18,47,65,97,117,132,136,139,146,153,169,178,192,218],"task":[6],"of":[7,91,99,156,195],"generating":[8],"natural":[9],"questions":[10,33,76,105],"based":[11,202],"on":[12,191,203],"an":[13,35,72],"image.":[14],"Popular":[15],"methods":[16,225],"in":[17,71,152],"past":[19],"have":[20,29],"explored":[21],"image-to-sequence":[22],"architectures":[23],"trained":[24],"with":[25,106,175,226],"maximum":[26],"likelihood":[27],"which":[28],"demonstrated":[30],"meaningful":[31],"generated":[32],"given":[34],"image":[36,48,73,137],"and":[37,69,101,138,149,183,205],"its":[38,54],"associated":[39],"ground-truth":[40,83],"answer.":[41],"VQG":[42,93,224],"becomes":[43],"more":[44],"challenging":[45],"if":[46],"contains":[49],"rich":[50],"contextual":[51],"information":[52,142],"describing":[53],"different":[55,66,123,129],"semantic":[56],"categories.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,186],"try":[62],"to":[63,74,127,167,171,177,199],"exploit":[64,128],"visual":[67],"cues":[68],"concepts":[70,130],"generate":[75,172],"using":[77],"a":[78],"variational":[79],"autoencoder":[80],"(VAE)":[81],"without":[82],"answers.":[84],"Our":[85],"approach":[86],"solves":[87],"two":[88],"major":[89],"shortcomings":[90],"existing":[92],"systems:":[94],"(i)":[95],"minimize":[96],"level":[98],"supervision":[100,119],"(ii)":[102],"replace":[103],"generic":[104],"category":[107,151,161],"relevant":[108],"generations.":[109],"Most":[110],"importantly,":[111],"by":[112,208],"eliminating":[113],"expensive":[114],"answer":[115,150,179],"annotations,":[116],"required":[118],"weakened.":[121],"Using":[122],"categories":[124,204],"enables":[125],"us":[126],"as":[131],"inference":[133],"requires":[134],"only":[135],"category.":[140],"Mutual":[141],"maximized":[144],"between":[145],"image,":[147],"question,":[148],"latent":[154,193],"space":[155,194],"our":[157,196],"VAE.":[158],"A":[159],"novel":[160],"consistent":[162,173],"cyclic":[163],"loss":[164],"proposed":[166,219],"enable":[168],"model":[170,198],"predictions":[174],"respect":[176],"category,":[180],"reducing":[181],"redundancies":[182],"irregularities.":[184],"Additionally,":[185],"also":[187],"impose":[188],"supplementary":[189],"constraints":[190],"generative":[197],"provide":[200],"structure":[201],"enhance":[206],"generalization":[207],"encapsulating":[209],"decorrelated":[210],"features":[211],"within":[212],"each":[213],"dimension.":[214],"Through":[215],"extensive":[216],"experiments,":[217],"model,":[220],"C3VQG":[221],"outperforms":[222],"state-of-the-art":[223],"weak":[227],"supervision.":[228]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3157509826","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2024-12-13T02:06:05.301912","created_date":"2021-05-10"}