{"id":"https://openalex.org/W4396782889","doi":"https://doi.org/10.1109/taslp.2024.3399061","title":"Analyzing the Robustness of Vision & Language Models","display_name":"Analyzing the Robustness of Vision & Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4396782889","doi":"https://doi.org/10.1109/taslp.2024.3399061"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3399061","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3399061","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10526392.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10526392.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027053688","display_name":"Alexander Shirnin","orcid":null},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Alexander Shirnin","raw_affiliation_strings":["HSE University, Moskva, Russian Federation"],"affiliations":[{"raw_affiliation_string":"HSE University, Moskva, Russian Federation","institution_ids":["https://openalex.org/I118501908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103119663","display_name":"Nikita Andreev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nikita Andreev","raw_affiliation_strings":["CAIT, Applied AI Institute, Moskva, Russian Federation"],"affiliations":[{"raw_affiliation_string":"CAIT, Applied AI Institute, Moskva, Russian Federation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058519434","display_name":"Sofia Potapova","orcid":"https://orcid.org/0009-0005-2701-700X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sofia Potapova","raw_affiliation_strings":["SmallTalk2Me, Covina, CA, USA"],"affiliations":[{"raw_affiliation_string":"SmallTalk2Me, Covina, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103157023","display_name":"Ekaterina Artemova","orcid":"https://orcid.org/0000-0001-8689-7514"},"institutions":[{"id":"https://openalex.org/I118501908","display_name":"National Research University Higher School of Economics","ror":"https://ror.org/055f7t516","country_code":"RU","type":"education","lineage":["https://openalex.org/I118501908"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ekaterina Artemova","raw_affiliation_strings":["HSE University, Moskva, Russian Federation"],"affiliations":[{"raw_affiliation_string":"HSE University, Moskva, Russian Federation","institution_ids":["https://openalex.org/I118501908"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027053688"],"corresponding_institution_ids":["https://openalex.org/I118501908"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0550296,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"2751","last_page":"2763"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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":0.7134438753128052},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6278319954872131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6023643016815186},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5940200686454773},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.5276764035224915},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4980041980743408},{"id":"https://openalex.org/keywords/intuition","display_name":"Intuition","score":0.49481481313705444},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4706522524356842},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4587656855583191},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38602814078330994},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.10399636626243591},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09864819049835205},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.09161683917045593}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7134438753128052},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6278319954872131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6023643016815186},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5940200686454773},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5276764035224915},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4980041980743408},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.49481481313705444},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4706522524356842},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4587656855583191},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38602814078330994},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.10399636626243591},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09864819049835205},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.09161683917045593},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3399061","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3399061","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10526392.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2024.3399061","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3399061","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/10526392.pdf","source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396782889.pdf"},"referenced_works_count":91,"referenced_works":["https://openalex.org/W1485981043","https://openalex.org/W1773149199","https://openalex.org/W1933349210","https://openalex.org/W2064675550","https://openalex.org/W2105482032","https://openalex.org/W2194775991","https://openalex.org/W2561715562","https://openalex.org/W2636355936","https://openalex.org/W2767249564","https://openalex.org/W2889985731","https://openalex.org/W2896457183","https://openalex.org/W2912371042","https://openalex.org/W2919115771","https://openalex.org/W2963143606","https://openalex.org/W2963383024","https://openalex.org/W2963448089","https://openalex.org/W2963518342","https://openalex.org/W2963609017","https://openalex.org/W2964051877","https://openalex.org/W2964345792","https://openalex.org/W2970231061","https://openalex.org/W2970641574","https://openalex.org/W2972119347","https://openalex.org/W2972324944","https://openalex.org/W2979826702","https://openalex.org/W2981851019","https://openalex.org/W2990283237","https://openalex.org/W2998356391","https://openalex.org/W3023993913","https://openalex.org/W3030163527","https://openalex.org/W3034381157","https://openalex.org/W3034837210","https://openalex.org/W3035635319","https://openalex.org/W3038035611","https://openalex.org/W3086323974","https://openalex.org/W3090449556","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3099319035","https://openalex.org/W3101662419","https://openalex.org/W3115547597","https://openalex.org/W3138516171","https://openalex.org/W3143373604","https://openalex.org/W3173909648","https://openalex.org/W3176196997","https://openalex.org/W3177487519","https://openalex.org/W3184369217","https://openalex.org/W3201877472","https://openalex.org/W3203711169","https://openalex.org/W3204588463","https://openalex.org/W3212246833","https://openalex.org/W4221167444","https://openalex.org/W4249013746","https://openalex.org/W4251372957","https://openalex.org/W4281633937","https://openalex.org/W4285250231","https://openalex.org/W4294170691","https://openalex.org/W4307069702","https://openalex.org/W4307207710","https://openalex.org/W4312261477","https://openalex.org/W4312791030","https://openalex.org/W4321353834","https://openalex.org/W4362720788","https://openalex.org/W4385245566","https://openalex.org/W4385572962","https://openalex.org/W4394659899","https://openalex.org/W6623517193","https://openalex.org/W6637373629","https://openalex.org/W6691231616","https://openalex.org/W6748452836","https://openalex.org/W6758704467","https://openalex.org/W6759580348","https://openalex.org/W6766904570","https://openalex.org/W6767211374","https://openalex.org/W6767908396","https://openalex.org/W6773996589","https://openalex.org/W6777503850","https://openalex.org/W6779473860","https://openalex.org/W6781410233","https://openalex.org/W6784761581","https://openalex.org/W6791353385","https://openalex.org/W6793851205","https://openalex.org/W6802158148","https://openalex.org/W6803084059","https://openalex.org/W6809938868","https://openalex.org/W6810313920","https://openalex.org/W6810984273","https://openalex.org/W6839015040","https://openalex.org/W6839020486","https://openalex.org/W6857510985","https://openalex.org/W6864544085"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W2903810591","https://openalex.org/W3026554633","https://openalex.org/W2888520903","https://openalex.org/W2890256614","https://openalex.org/W2949454572","https://openalex.org/W3066373881","https://openalex.org/W2970247882","https://openalex.org/W4389523797"],"abstract_inverted_index":{"We":[0,86,142],"present":[1],"an":[2,126],"approach":[3],"to":[4,15,41,99,112,129,139,186,198],"evaluate":[5],"the":[6,51,92,95,100,132,192,201],"robustness":[7],"of":[8,53,79,94,102,135,200],"pre-trained":[9],"vision":[10,30],"and":[11,38,63,68,82,117,150],"language":[12,34],"(V&L)":[13],"models":[14,73,96,175],"noise":[16],"in":[17,97,107,114],"input":[18],"data.":[19],"Given":[20],"a":[21,42,76,83],"source":[22],"image/text,":[23],"we":[24,49,59,124],"perturb":[25],"it":[26,40],"using":[27],"standard":[28],"computer":[29],"(CV)":[31],"/":[32],"natural":[33],"processing":[35],"(NLP)":[36],"techniques":[37,67],"feed":[39],"V&L":[43,72,136,174,195],"model.":[44],"To":[45],"track":[46],"performance":[47,93,108],"changes,":[48],"explore":[50],"problem":[52],"visual":[54],"questions":[55],"answering":[56],"(VQA).":[57],"Overall,":[58],"utilize":[60],"5":[61],"image":[62],"9":[64],"text":[65],"perturbation":[66],"probe":[69],"three":[70],"Transformer-based":[71],"followed":[74],"by":[75],"broad":[77],"analysis":[78],"their":[80,115],"behavior":[81],"detailed":[84],"comparison.":[85],"discovered":[87],"several":[88],"key":[89],"findings":[90],"regarding":[91],"relation":[98],"impact":[101],"various":[103],"perturbations.":[104],"These":[105],"discrepancies":[106],"can":[109],"be":[110,153],"attributed":[111],"differences":[113],"architectures":[116],"learning":[118],"objectives.":[119],"Last,":[120],"but":[121],"not":[122,177],"least,":[123],"perform":[125],"empirical":[127],"study":[128,164],"assess":[130],"whether":[131],"attention":[133,145],"mechanism":[134],"Transformers":[137,196],"learns":[138],"align":[140],"modalities.":[141,202],"hypothesize,":[143],"that":[144,194],"weights":[146],"for":[147,158,170],"related":[148],"objects":[149],"words,":[151],"should":[152],"on":[154],"average":[155],"higher":[156],"than":[157],"random":[159],"object/word":[160],"pairs.":[161],"However,":[162],"our":[163],"shows":[165],"that,":[166],"unlike":[167],"is":[168],"believed":[169],"machine":[171],"translation":[172],"models,":[173],"do":[176,187],"learn":[178],"alignment":[179],"at":[180],"all":[181],"or":[182],"exhibit":[183],"less":[184],"evidence":[185],"so.":[188],"This":[189],"may":[190],"support":[191],"intuition":[193],"overfit":[197],"either":[199]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}