{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:01:18Z","timestamp":1776931278105,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476165,62472315,62406182"],"award-info":[{"award-number":["62476165,62472315,62406182"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Program of Shanxi Province","award":["202403021212176"],"award-info":[{"award-number":["202403021212176"]}]},{"name":"Science and Technology Innovation Project for Higher Education Institutions of Shanxi Province","award":["2024L004"],"award-info":[{"award-number":["2024L004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3770929","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:08:11Z","timestamp":1765008491000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Dual-View Gradient Probes: Disentangling Uncertainty for Deep Active Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1361-0673","authenticated-orcid":false,"given":"Dongqi","family":"Xia","sequence":"first","affiliation":[{"name":"Shanghai University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0536-1345","authenticated-orcid":false,"given":"Xiaodong","family":"Yue","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3645-9046","authenticated-orcid":false,"given":"Yufei","family":"Chen","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4369-8400","authenticated-orcid":false,"given":"Jie","family":"Shi","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7416-6455","authenticated-orcid":false,"given":"Shijie","family":"Ding","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"International Conference on Learning Representations","author":"Ash Jordan\u00a0T","year":"2020","unstructured":"Jordan\u00a0T Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, and Alekh Agarwal. 2020. Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds. In International Conference on Learning Representations."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.5555\/1768841.1768848"},{"key":"e_1_3_3_1_4_2","first-page":"1","volume-title":"Machine Learning for Health Workshop","author":"Blanch Marc\u00a0Gorriz","year":"2017","unstructured":"Marc\u00a0Gorriz Blanch, Xavier Giro\u00a0I Nieto, Axel Carlier, and Emmanuel Faure. 2017. Cost-Effective Active Learning for Melanoma Segmentation. In Machine Learning for Health Workshop. 1\u20135."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01550"},{"key":"e_1_3_3_1_6_2","first-page":"1050","volume-title":"International Conference on Machine Learning","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\u20131059."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01514"},{"key":"e_1_3_3_1_9_2","unstructured":"Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in bayesian deep learning for computer vision?Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_10_2","unstructured":"Andreas Kirsch Joost Van\u00a0Amersfoort and Yarin Gal. 2019. Batchbald: Efficient and diverse batch acquisition for deep bayesian active learning. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_1_11_2","unstructured":"Ksenia Konyushkova Raphael Sznitman and Pascal Fua. 2017. Learning active learning from data. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_3_1_12_2","unstructured":"Alex Krizhevsky et\u00a0al. 2009. Learning multiple layers of features from tiny images. Master\u2019s thesis University of Tront (2009)."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Yann LeCun Yoshua Bengio and Geoffrey Hinton. 2015. Deep learning. nature 521 7553 (2015) 436\u2013444.","DOI":"10.1038\/nature14539"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Yann LeCun L\u00e9on Bottou Yoshua Bengio and Patrick Haffner. 2002. Gradient-based learning applied to document recognition. Proc. IEEE 86 11 (2002) 2278\u20132324.","DOI":"10.1109\/5.726791"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29270"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681297"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34088"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01445"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26066"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Wei Liu Yufei Chen Xiaodong Yue Changqing Zhang and Shaorong Xie. 2025. Enhancing Reliability in Medical Image Classification of Imperfect Views. IEEE Transactions on Circuits and Systems for Video Technology (2025).","DOI":"10.1109\/TCSVT.2025.3610762"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20724"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00914"},{"key":"e_1_3_3_1_23_2","unstructured":"Wenjie Luo Alex Schwing and Raquel Urtasun. 2013. Latent structured active learning. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_3_1_24_2","first-page":"7","volume-title":"Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning","volume":"2011","author":"Netzer Yuval","year":"2011","unstructured":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Baolin Wu, Andrew\u00a0Y Ng, et\u00a0al. 2011. Reading digits in natural images with unsupervised feature learning. In Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning , Vol.\u00a02011. Granada, 7."},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Geir\u00a0K Nilsen Antonella\u00a0Z Munthe-Kaas Hans\u00a0J Skaug and Morten Brun. 2022. Epistemic uncertainty quantification in deep learning classification by the Delta method. Neural networks 145 (2022) 164\u2013176.","DOI":"10.1016\/j.neunet.2021.10.014"},{"key":"e_1_3_3_1_26_2","unstructured":"Adam Paszke Sam Gross Francisco Massa Adam Lerer James Bradbury Gregory Chanan Trevor Killeen Zeming Lin Natalia Gimelshein Luca Antiga et\u00a0al. 2019. Pytorch: An imperative style high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01544"},{"key":"e_1_3_3_1_28_2","volume-title":"International Conference on Learning Representations","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Silvio Savarese. 2018. Active Learning for Convolutional Neural Networks: A Core-Set Approach. In International Conference on Learning Representations."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01536"},{"key":"e_1_3_3_1_30_2","first-page":"112","volume-title":"International Joint Conference on Neural Networks","author":"Wang Dan","year":"2014","unstructured":"Dan Wang and Yi Shang. 2014. A new active labeling method for deep learning. In International Joint Conference on Neural Networks. IEEE, 112\u2013119."},{"key":"e_1_3_3_1_31_2","unstructured":"Haonan Wang Wei Huang Ziwei Wu Hanghang Tong Andrew\u00a0J Margenot and Jingrui He. 2022. Deep active learning by leveraging training dynamics. Advances in Neural Information Processing Systems 35 (2022) 25171\u201325184."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Keze Wang Dongyu Zhang Ya Li Ruimao Zhang and Liang Lin. 2016. Cost-effective active learning for deep image classification. IEEE Transactions on Circuits and Systems for Video Technology 27 12 (2016) 2591\u20132600.","DOI":"10.1109\/TCSVT.2016.2589879"},{"key":"e_1_3_3_1_33_2","unstructured":"Yang Yang Yuxuan Zhang Xin Song and Yi Xu. 2023. Not all out-of-distribution data are harmful to open-set active learning. Advances in Neural Information Processing Systems 36 (2023) 13802\u201313818."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683089"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3770929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:09:27Z","timestamp":1765008567000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3770929"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":33,"alternative-id":["10.1145\/3743093.3770929","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3770929","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}