{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:33:50Z","timestamp":1775579630700,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730302","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T14:55:26Z","timestamp":1752504926000},"page":"3782-3791","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["LUMA: A Benchmark Dataset for Learning from Uncertain and Multimodal Data"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0428-1973","authenticated-orcid":false,"given":"Grigor","family":"Bezirganyan","sequence":"first","affiliation":[{"name":"Doctoral School in Mathematics and Computer Science, Aix-Marseille University, Marseille, France and CNRS, Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8302-3053","authenticated-orcid":false,"given":"Sana","family":"Sellami","sequence":"additional","affiliation":[{"name":"Aix-Marseille University, Marseille, France and CNRS, Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8046-0570","authenticated-orcid":false,"given":"Laure","family":"Berti-\u00c9quille","sequence":"additional","affiliation":[{"name":"IRD, Montpellier, France and ESPACE-DEV, Montpellier, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1611-0744","authenticated-orcid":false,"given":"S\u00e9bastien","family":"Fournier","sequence":"additional","affiliation":[{"name":"Aix-Marseille University, Marseille, France and CNRS, Marseille, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Moloud Abdar Farhad Pourpanah Sadiq Hussain Dana Rezazadegan Li Liu Mohammad Ghavamzadeh Paul Fieguth Xiaochun Cao Abbas Khosravi U Rajendra Acharya et al. 2021. A review of uncertainty quantification in deep learning: Techniques applications and challenges. Information fusion Vol. 76 (2021) 243-297.","DOI":"10.1016\/j.inffus.2021.05.008"},{"key":"e_1_3_2_1_2_1","first-page":"4211","volume-title":"Proceedings of the 12th Conference on Language Resources and Evaluation (LREC","author":"Ardila R.","year":"2020","unstructured":"R. Ardila, M. Branson, K. Davis, M. Henretty, M. Kohler, J. Meyer, R. Morais, L. Saunders, F. M. Tyers, and G. Weber. 2020. Common Voice: A Massively-Multilingual Speech Corpus. In Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020). 4211-4215."},{"key":"e_1_3_2_1_3_1","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, Vol. 33 (2020), 12449-12460."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-021-02166-7"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N19-1423"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N19-1423"},{"key":"e_1_3_2_1_7_1","volume-title":"international conference on machine learning. PMLR, 1050-1059","author":"Gal Yarin","year":"2016","unstructured":"Yarin Gal and Zoubin Ghahramani. 2016. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In international conference on machine learning. PMLR, 1050-1059."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3171983"},{"key":"e_1_3_2_1_9_1","volume-title":"International Conference on Learning Representations.","author":"Hendrycks Dan","year":"2018","unstructured":"Dan Hendrycks and Thomas Dietterich. 2018. Benchmarking Neural Network Robustness to Common Corruptions and Perturbations. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_10_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al., 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation. In Advances in Neural Information Processing Systems","author":"Jung Myong Chol","year":"2023","unstructured":"Myong Chol Jung, He Zhao, Joanna Dipnall, and Lan Du. 2023. Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation. In Advances in Neural Information Processing Systems, , , A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 42191-42216. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/839e23e5b1c52cfd1268f4023a3af0d6-Paper-Conference.pdf"},{"key":"e_1_3_2_1_12_1","first-page":"6517","article-title":"Uncertainty estimation for multi-view data: the power of seeing the whole picture","volume":"35","author":"Jung Myong Chol","year":"2022","unstructured":"Myong Chol Jung, He Zhao, Joanna Dipnall, Belinda Gabbe, and Lan Du. 2022. Uncertainty estimation for multi-view data: the power of seeing the whole picture. Advances in Neural Information Processing Systems, Vol. 35 (2022), 6517-6530.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","volume-title":"Proc. NeurIPS.","author":"Karras Tero","year":"2022","unstructured":"Tero Karras, Miika Aittala, Timo Aila, and Samuli Laine. 2022. Elucidating the Design Space of Diffusion-Based Generative Models. In Proc. NeurIPS."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.strusafe.2008.06.020"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)","author":"K\u00f6hn Arne","year":"2016","unstructured":"Arne K\u00f6hn, Florian Stegen, and Timo Baumann. 2016. Mining the Spoken Wikipedia for Speech Data and Beyond. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016) (Portoro\u017e, Slovenia, 23-28), Nicoletta Calzolari (Conference Chair), Khalid Choukri, Thierry Declerck, Marko Grobelnik, Bente Maegaard, Joseph Mariani, Asuncion Moreno, Jan Odijk, and Stelios Piperidis (Eds.). European Language Resources Association (ELRA), Paris, France."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582269.3615599"},{"key":"e_1_3_2_1_17_1","first-page":"18237","article-title":"Improving model calibration with accuracy versus uncertainty optimization","volume":"33","author":"Krishnan Ranganath","year":"2020","unstructured":"Ranganath Krishnan and Omesh Tickoo. 2020. Improving model calibration with accuracy versus uncertainty optimization. Advances in Neural Information Processing Systems, Vol. 33 (2020), 18237-18248.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","unstructured":"Alex Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images . (2009)."},{"key":"e_1_3_2_1_19_1","volume-title":"Review of multimodal machine learning approaches in healthcare. ArXiv","author":"Krones Felix","year":"2024","unstructured":"Felix Krones, Umar Marikkar, Guy Parsons, Adam Szmul, and Adam Mahdi. 2024. Review of multimodal machine learning approaches in healthcare. ArXiv, Vol. abs\/2402.02460 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267412288"},{"key":"e_1_3_2_1_20_1","volume-title":"Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems","author":"Lakshminarayanan Balaji","year":"2017","unstructured":"Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-019-03101-3"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20724"},{"key":"e_1_3_2_1_23_1","unstructured":"Edward Ma. 2019. NLP Augmentation. https:\/\/github.com\/makcedward\/nlpaug."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.34740\/KAGGLE\/M\/3301"},{"key":"#cr-split#-e_1_3_2_1_26_1.1","unstructured":"Zachary Nado Neil Band Mark Collier Josip Djolonga Michael W Dusenberry Sebastian Farquhar Qixuan Feng Angelos Filos Marton Havasi Rodolphe Jenatton et al. 2021. Uncertainty baselines: Benchmarks for uncertainty &#38"},{"key":"#cr-split#-e_1_3_2_1_26_1.2","unstructured":"robustness in deep learning. arXiv preprint arXiv:2106.04015 (2021)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"28518","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine Mcleavey, and Ilya Sutskever. 2023. Robust Speech Recognition via Large-Scale Weak Supervision. In Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 28492-28518. https:\/\/proceedings.mlr.press\/v202\/radford23a.html"},{"key":"e_1_3_2_1_30_1","volume-title":"3rd International Conference on Learning Representations, ICLR","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. http:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_1_31_1","unstructured":"Maxim Tkachenko Mikhail Malyuk Andrey Holmanyuk and Nikolai Liubimov. 2020-2022. Label Studio: Data labeling software. https:\/\/github.com\/heartexlabs\/label-studio Open source software available from https:\/\/github.com\/heartexlabs\/label-studio."},{"key":"e_1_3_2_1_32_1","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 1508-1516","author":"Valdenegro-Toro Matias","year":"2022","unstructured":"Matias Valdenegro-Toro and Daniel Saromo Mori. 2022. A deeper look into aleatoric and epistemic uncertainty disentanglement. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 1508-1516."},{"key":"e_1_3_2_1_33_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research, Vol. 9, 86 (2008), 2579-2605. http:\/\/jmlr.org\/papers\/v9\/vandermaaten08a.html","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3013234"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29546"},{"key":"e_1_3_2_1_36_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zheng Chenyu","year":"2024","unstructured":"Chenyu Zheng, Guoqiang Wu, and Chongxuan Li. 2024. Toward understanding generative data augmentation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3730302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:35:22Z","timestamp":1755887722000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730302"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":37,"alternative-id":["10.1145\/3726302.3730302","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730302","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}