{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:00:30Z","timestamp":1784131230308,"version":"3.55.0"},"reference-count":89,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3399061","type":"journal-article","created":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T17:38:26Z","timestamp":1715276306000},"page":"2751-2763","source":"Crossref","is-referenced-by-count":3,"title":["Analyzing the Robustness of Vision & Language Models"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1842-1988","authenticated-orcid":false,"given":"Alexander","family":"Shirnin","sequence":"first","affiliation":[{"name":"HSE University, Moskva, Russian Federation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0880-3620","authenticated-orcid":false,"given":"Nikita","family":"Andreev","sequence":"additional","affiliation":[{"name":"CAIT, Applied AI Institute, Moskva, Russian Federation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2701-700X","authenticated-orcid":false,"given":"Sofia","family":"Potapova","sequence":"additional","affiliation":[{"name":"SmallTalk2Me, Covina, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8689-7514","authenticated-orcid":false,"given":"Ekaterina","family":"Artemova","sequence":"additional","affiliation":[{"name":"HSE University, Moskva, Russian Federation"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","first-page":"842","article-title":"A primer in BERTology: What we know about how BERT works","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"8","author":"Rogers","year":"2020"},{"key":"ref3","first-page":"1699","article-title":"SentEval: An evaluation toolkit for universal sentence representations","volume-title":"Proc. 11th Int. Conf. Lang. Resour. Eval.","author":"Conneau","year":"2018"},{"key":"ref4","first-page":"2021","article-title":"Adversarial GLUE: A multi-task benchmark for robustness evaluation of language models","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Wang"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"276","DOI":"10.18653\/v1\/W19-4828","article-title":"What does BERT look at? An analysis of BERTs attention","volume-title":"Proc. ACL Workshop BlackboxNLP: Analyzing Interpreting Neural Netw. NLP","author":"Clark","year":"2019"},{"key":"ref6","first-page":"566","article-title":"Accurate word alignment induction from neural machine translation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Chen","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18287\/2412-6179-CO-678"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00254"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25075-0_4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3188390"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00774"},{"key":"ref19","first-page":"2484","article-title":"Simple black-box adversarial attacks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo","year":"2019"},{"key":"ref20","first-page":"621","article-title":"An empirical study on robustness to spurious correlations using pre-trained language models","volume-title":"Trans. Assoc. Comput. Linguistics","volume":"8","author":"Tu","year":"2020"},{"key":"ref21","article-title":"Vision-language intelligence: Tasks, representation learning, and large models","author":"Li","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref23","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref25","first-page":"787","article-title":"ReferItGame: Referring to objects in photographs of natural scenes","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process","author":"Kazemzadeh","year":"2014"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(97)80111-2"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1044"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref30","article-title":"Supervised multimodal bitransformers for classifying images and text","author":"Kiela","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.469"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref33","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref34","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.171"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref37","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gan","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16431"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00728"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref43","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Kenton","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref45","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chorowski","year":"2015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02072"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.22"},{"key":"ref49","first-page":"135","article-title":"InterpreT: An interactive visualization tool for interpreting transformers","volume-title":"Proc. 16th Conf. Eur. Chapter Assoc. Comput. Linguistics: Syst. Demonstrations","author":"Lal","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-demo.26"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.15"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11832"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00385"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11238"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3136755.3136801"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1181"},{"key":"ref60","first-page":"1","article-title":"MultiViz: Towards visualizing and understanding multimodal models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liang","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.586"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.100"},{"key":"ref65","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown Askell","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.318"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-demos.4"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.567"},{"key":"ref69","first-page":"34405","article-title":"Robustness analysis of video-language models against visual and language perturbations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chantry","year":"2022"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref72","first-page":"22605","article-title":"COOT: Cooperative hierarchical transformer for video-text representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ging","year":"2020"},{"key":"ref73","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.3115\/1225403.1225421"},{"key":"ref76","article-title":"spaCy: Industrial-strength Natural Language Processing in Python","author":"Honnibal","year":"2020"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref78","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Wang","year":"2022"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref80","first-page":"20841","article-title":"Black-box tuning for language-model-as-a-service","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun","year":"2022"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3390\/make3040048"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.3390\/info11020125"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.3384\/nejlt.2000-1533.2023.4725"},{"key":"ref85","first-page":"1009","article-title":"Robustifying language models with test-time adaptation","volume-title":"Proc. Workshop Pitfalls Limited Data Computation Trustworthy ML","author":"McDermott","year":"2023"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref87","first-page":"4326","article-title":"Informativeness and invariance: Two perspectives on spurious correlations in natural language","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Eisenstein","year":"2022"},{"key":"ref88","first-page":"1719","article-title":"Identifying and mitigating spurious correlations for improving robustness in NLP models","volume-title":"Proc. Findings Assoc. Comput. Linguistics: NAACL","author":"Wang","year":"2022"},{"key":"ref89","first-page":"91","article-title":"F. R- CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2015"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10526392.pdf?arnumber=10526392","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T05:35:58Z","timestamp":1717047358000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10526392\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3399061","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}