{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:46:26Z","timestamp":1771893986553,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612463","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"3434-3445","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Towards Balanced Active Learning for Multimodal Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2502-3500","authenticated-orcid":false,"given":"Meng","family":"Shen","sequence":"first","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4539-7377","authenticated-orcid":false,"given":"Yizheng","family":"Huang","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4686-2768","authenticated-orcid":false,"given":"Jianxiong","family":"Yin","sequence":"additional","affiliation":[{"name":"NVIDIA, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0038-2822","authenticated-orcid":false,"given":"Heqing","family":"Zou","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7788-8368","authenticated-orcid":false,"given":"Deepu","family":"Rajan","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4958-9237","authenticated-orcid":false,"given":"Simon","family":"See","sequence":"additional","affiliation":[{"name":"NVIDIA AI Tech Center, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2007","author":"Arthur David","year":"2007","unstructured":"David Arthur and Sergei Vassilvitskii. 2007. k-means: the advantages of careful seeding. In Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2007, New Orleans, Louisiana, USA, January 7-9, 2007. SIAM, 1027--1035. http:\/\/dl.acm.org\/citation.cfm?id=1283383.1283494"},{"key":"e_1_3_2_1_3_1","volume-title":"Uncertain Gradient Lower Bounds. In 8th International Conference on Learning Representations, ICLR 2020","author":"Ash Jordan T.","year":"2020","unstructured":"Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, and Alekh Agarwal. 2020. Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net. https:\/\/openreview.net\/forum?id=ryghZJBKPS"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00976"},{"key":"e_1_3_2_1_6_1","volume-title":"Batch Active Learning Using Determinantal Point Processes. CoRR","author":"Biyik Erdem","year":"2019","unstructured":"Erdem Biyik, Kenneth Wang, Nima Anari, and Dorsa Sadigh. 2019. Batch Active Learning Using Determinantal Point Processes. CoRR, Vol. abs\/1906.07975 (2019). showeprint[arXiv]1906.07975 http:\/\/arxiv.org\/abs\/1906.07975"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00946"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"e_1_3_2_1_10_1","volume-title":"Adversarial Active Learning for Deep Networks: a Margin Based Approach. CoRR","author":"Ducoffe Melanie","year":"2018","unstructured":"Melanie Ducoffe and Fr\u00e9d\u00e9ric Precioso. 2018. Adversarial Active Learning for Deep Networks: a Margin Based Approach. CoRR, Vol. abs\/1802.09841 (2018). showeprint[arXiv]1802.09841 http:\/\/arxiv.org\/abs\/1802.09841"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.775"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016 (JMLR Workshop and Conference Proceedings","volume":"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 Proceedings of the 33nd International Conference on Machine Learning, ICML 2016, New York City, NY, USA, June 19-24, 2016 (JMLR Workshop and Conference Proceedings, Vol. 48). JMLR.org, 1050--1059. http:\/\/proceedings.mlr.press\/v48\/gal16.html"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning, ICML 2017","author":"Gal Yarin","year":"2017","unstructured":"Yarin Gal, Riashat Islam, and Zoubin Ghahramani. 2017. Deep Bayesian Active Learning with Image Data. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6-11 August 2017 (Proceedings of Machine Learning Research, Vol. 70). PMLR, 1183--1192. http:\/\/proceedings.mlr.press\/v70\/gal17a.html"},{"key":"e_1_3_2_1_14_1","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Gat Itai","year":"2021","unstructured":"Itai Gat, Idan Schwartz, and Alexander G. Schwing. 2021. Perceptual Score: What Data Modalities Does Your Model Perceive?. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan (Eds.). 21630--21643. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/b51a15f382ac914391a58850ab343b00-Abstract.html"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning, ICML 2022","volume":"8195","author":"Hacohen Guy","year":"2022","unstructured":"Guy Hacohen, Avihu Dekel, and Daphna Weinshall. 2022. Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162). PMLR, 8175--8195. https:\/\/proceedings.mlr.press\/v162\/hacohen22a.html"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.62"},{"key":"e_1_3_2_1_18_1","volume-title":"International Conference on Machine Learning, ICML 2022","volume":"9259","author":"Huang Yu","year":"2022","unstructured":"Yu Huang, Junyang Lin, Chang Zhou, Hongxia Yang, and Longbo Huang. 2022. Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably). In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162). PMLR, 9226--9259. https:\/\/proceedings.mlr.press\/v162\/huang22e.html"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Leon Kaufman and Peter Rousseeuw. 1990. Finding Groups in Data. (1990).","DOI":"10.1002\/9780470316801"},{"key":"e_1_3_2_1_20_1","volume-title":"Karen Simonyan, Brian Zhang, Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, Trevor Back, Paul Natsev, Mustafa Suleyman, and Andrew Zisserman.","author":"Kay Will","year":"2017","unstructured":"Will Kay, Jo a o Carreira, Karen Simonyan, Brian Zhang, Chloe Hillier, Sudheendra Vijayanarasimhan, Fabio Viola, Tim Green, Trevor Back, Paul Natsev, Mustafa Suleyman, and Andrew Zisserman. 2017. The Kinetics Human Action Video Dataset. CoRR, Vol. abs\/1705.06950 (2017). showeprint[arXiv]1705.06950 http:\/\/arxiv.org\/abs\/1705.06950"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00914"},{"key":"e_1_3_2_1_22_1","volume-title":"Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019","author":"Loshchilov Ilya","year":"2019","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=Bkg6RiCqY7"},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Scott","year":"2017","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett (Eds.). 4765--4774. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/8a20a8621978632d76c43dfd28b67767-Abstract.html"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.51"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015349"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01192"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_40"},{"key":"e_1_3_2_1_31_1","volume-title":"6th International Conference on Learning Representations, ICLR","author":"Sener Ozan","year":"2018","unstructured":"Ozan Sener and Silvio Savarese. 2018. Active Learning for Convolutional Neural Networks: A Core-Set Approach. In 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=H1aIuk-RW"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.2200\/S00429ED1V01Y201207AIM018"},{"key":"e_1_3_2_1_33_1","first-page":"307","article-title":"A value for n-person games","volume":"28","author":"LS","year":"1953","unstructured":"LS SHAPLEY. 1953. A value for n-person games. Annals of Mathematics Studies, Vol. 28 (1953), 307--318.","journal-title":"Annals of Mathematics Studies"},{"key":"e_1_3_2_1_34_1","volume-title":"Deep Active Learning: Unified and Principled Method for Query and Training. In The 23rd International Conference on Artificial Intelligence and Statistics, AISTATS 2020","volume":"1318","author":"Shui Changjian","year":"2020","unstructured":"Changjian Shui, Fan Zhou, Christian Gagn\u00e9, and Boyu Wang. 2020. Deep Active Learning: Unified and Principled Method for Query and Training. In The 23rd International Conference on Artificial Intelligence and Statistics, AISTATS 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy] (Proceedings of Machine Learning Research, Vol. 108). PMLR, 1308--1318. http:\/\/proceedings.mlr.press\/v108\/shui20a.html"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00607"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093390"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_1_38_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA. 5998--6008. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/3f5ee243547dee91fbd053c1c4a845aa-Abstract.html"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05817-y"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2015.7169757"},{"key":"e_1_3_2_1_43_1","volume-title":"Characterizing and Overcoming the Greedy Nature of Learning in Multi-modal Deep Neural Networks. In International Conference on Machine Learning, ICML 2022","volume":"24055","author":"Wu Nan","year":"2022","unstructured":"Nan Wu, Stanislaw Jastrzebski, Kyunghyun Cho, and Krzysztof J. Geras. 2022. Characterizing and Overcoming the Greedy Nature of Learning in Multi-modal Deep Neural Networks. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162). PMLR, 24043--24055. https:\/\/proceedings.mlr.press\/v162\/wu22d.html"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.637"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00529"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612463","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:07:09Z","timestamp":1755821229000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612463"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":45,"alternative-id":["10.1145\/3581783.3612463","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612463","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}