{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:18:59Z","timestamp":1772932739244,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1722822, 1750439, IIS1763562"],"award-info":[{"award-number":["1722822, 1750439, IIS1763562"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N000141812861"],"award-info":[{"award-number":["N000141812861"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01MH125740, R01MH096951, U01MH116925, U01MH116923"],"award-info":[{"award-number":["R01MH125740, R01MH096951, U01MH116925, U01MH116923"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1145\/3474085.3475247","type":"proceedings-article","created":{"date-parts":[[2021,10,18]],"date-time":"2021-10-18T22:11:38Z","timestamp":1634595098000},"page":"2680-2689","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment"],"prefix":"10.1145","author":[{"given":"Paul Pu","family":"Liang","sequence":"first","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Wu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liu","family":"Ziyin","sequence":"additional","affiliation":[{"name":"University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Louis-Philippe","family":"Morency","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruslan","family":"Salakhutdinov","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,17]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Sami Abu-El-Haija Nisarg Kothari Joonseok Lee Apostol (Paul) Natsev George Toderici Balakrishnan Varadarajan and Sudheendra Vijayanarasimhan. 2016. YouTube-8M: A Large-Scale Video Classification Benchmark. In arXiv:1609.08675. https:\/\/arxiv.org\/pdf\/1609.08675v1.pdf  Sami Abu-El-Haija Nisarg Kothari Joonseok Lee Apostol (Paul) Natsev George Toderici Balakrishnan Varadarajan and Sudheendra Vijayanarasimhan. 2016. YouTube-8M: A Large-Scale Video Classification Benchmark. In arXiv:1609.08675. https:\/\/arxiv.org\/pdf\/1609.08675v1.pdf"},{"key":"e_1_3_2_1_2_1","volume-title":"Data augmentation generative adversarial networks. arXiv preprint arXiv:1711.04340","author":"Antoniou Antreas","year":"2017"},{"key":"e_1_3_2_1_3_1","volume-title":"Effectiveness of self-supervised pre-training for speech recognition. arXiv preprint arXiv:1911.03912","author":"Baevski Alexei","year":"2019"},{"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","volume-title":"Carnegie Mellon University Wilderness Multilingual Speech Dataset. In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 5971--5975","author":"Black A. W.","year":"2019"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.5555\/3298239.3298253"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"e_1_3_2_1_8_1","volume-title":"Yu-Chiang Frank Wang, and Jia-Bin Huang","author":"Chen Wei-Yu","year":"2019"},{"key":"e_1_3_2_1_9_1","volume-title":"On the Measure of Intelligence. CoRR","author":"Chollet Francc","year":"2019"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00150"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_12_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018"},{"key":"e_1_3_2_1_13_1","volume-title":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 573--588","author":"Dong Nanqing","year":"2018"},{"key":"e_1_3_2_1_14_1","volume-title":"Cross-Modal Data Programming Enables Rapid Medical Machine Learning. CoRR","author":"Dunnmon Jared","year":"2019"},{"key":"e_1_3_2_1_15_1","volume-title":"Notes on noise contrastive estimation and negative sampling. arXiv preprint arXiv:1410.8251","author":"Dyer Chris","year":"2014"},{"key":"e_1_3_2_1_16_1","volume-title":"Jamie Ryan Kiros, and Sanja Fidler","author":"Faghri Fartash","year":"2017"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305381.3305498"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999849"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"e_1_3_2_1_20_1","volume-title":"Beam, and Rajesh Ranganath","author":"Ghassemi Marzyeh","year":"2018"},{"key":"e_1_3_2_1_21_1","volume-title":"Unsupervised Alignment of Embeddings with Wasserstein Procrustes. CoRR","author":"Grave Edouard","year":"2018"},{"key":"e_1_3_2_1_22_1","volume-title":"Li","author":"Gu Jiatao","year":"2018"},{"key":"e_1_3_2_1_23_1","volume-title":"Co-sampling: Training Robust Networks for Extremely Noisy Supervision. CoRR","author":"Han Bo","year":"2018"},{"key":"e_1_3_2_1_24_1","volume-title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation. CoRR","author":"Hoffman Judy","year":"2017"},{"key":"e_1_3_2_1_25_1","volume-title":"Meta-learning in neural networks: A survey. arXiv preprint arXiv:2004.05439","author":"Hospedales Timothy","year":"2020"},{"key":"e_1_3_2_1_26_1","volume-title":"Unsupervised Learning via Meta-Learning. CoRR","author":"Hsu Kyle","year":"2018"},{"key":"e_1_3_2_1_27_1","volume-title":"Learning to cluster in order to transfer across domains and tasks. arXiv preprint arXiv:1711.10125","author":"Hsu Yen-Chang","year":"2017"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172151"},{"key":"e_1_3_2_1_29_1","volume-title":"Efros","author":"Huh Mi-Young","year":"2016"},{"key":"e_1_3_2_1_30_1","volume-title":"Frustratingly Easy Domain Adaptation. CoRR","author":"Hal Daum\u00e9 III.","year":"1815"},{"key":"e_1_3_2_1_31_1","volume-title":"Geometry-aware Domain Adaptation for Unsupervised Alignment of Word Embeddings. arXiv preprint arXiv:2004.08243","author":"Jawanpuria Pratik","year":"2020"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Somnath Basu Roy Chowdhury Annervaz K M","year":"2018"},{"key":"e_1_3_2_1_33_1","volume-title":"Provable Guarantees for Gradient-Based Meta-Learning. CoRR","author":"Khodak Mikhail","year":"2019"},{"key":"e_1_3_2_1_34_1","volume-title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations. CoRR","author":"Krishna Ranjay","year":"2016"},{"key":"e_1_3_2_1_35_1","unstructured":"Alex Krizhevsky Geoffrey Hinton etal 2009. Learning multiple layers of features from tiny images. (2009).  Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462200"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045555"},{"key":"e_1_3_2_1_38_1","volume-title":"SANTLR: Speech Annotation Toolkit for Low Resource Languages. arXiv preprint arXiv:1908.01067","author":"Li Xinjian","year":"2019"},{"key":"e_1_3_2_1_39_1","volume-title":"Think locally, act globally: Federated learning with local and global representations. arXiv preprint arXiv:2001.01523","author":"Liang Paul Pu","year":"2020"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1152"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243019"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2639382"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3305945"},{"key":"e_1_3_2_1_45_1","volume-title":"Reptile: a scalable metalearning algorithm. arXiv preprint arXiv:1803.02999","author":"Nichol Alex","year":"2018"},{"key":"e_1_3_2_1_46_1","volume-title":"Bob McGrew, Jakub W. Pachocki, Jakub Pachocki, Arthur Petron, Matthias Plappert, Glenn Powell, Alex Ray, Jonas Schneider, Szymon Sidor, Josh Tobin, Peter Welinder, Lilian Weng, and Wojciech Zaremba.","author":"Marcin Andrychowicz AI","year":"2018"},{"key":"e_1_3_2_1_47_1","volume-title":"Semantic Correspondence: A Hierarchical Approach. CoRR","author":"Pemasiri Akila","year":"2018"},{"key":"e_1_3_2_1_48_1","volume-title":"Utterance-Level Multimodal Sentiment Analysis","author":"Perez-Rosas Veronica"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"e_1_3_2_1_50_1","volume-title":"Subspace Alignment Based Domain Adaptation for RCNN Detector. CoRR","author":"Raj Anant","year":"2015"},{"key":"e_1_3_2_1_51_1","unstructured":"Sachin Ravi and Hugo Larochelle. 2016. Optimization as a model for few-shot learning. (2016).  Sachin Ravi and Hugo Larochelle. 2016. Optimization as a model for few-shot learning. (2016)."},{"key":"e_1_3_2_1_52_1","volume-title":"TResNet: High Performance GPU-Dedicated Architecture. arXiv preprint arXiv:2003.13630","author":"Ridnik Tal","year":"2020"},{"key":"e_1_3_2_1_53_1","volume-title":"Hoi","author":"Sahoo Doyen","year":"2019"},{"key":"e_1_3_2_1_54_1","volume-title":"Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing. CoRR","author":"Schuster Tal","year":"2019"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.5555\/2999611.2999716"},{"key":"e_1_3_2_1_57_1","volume-title":"A Survey on Deep Transfer Learning. CoRR","author":"Tan Chuanqi","year":"1974"},{"key":"e_1_3_2_1_58_1","volume-title":"Improving One-Shot Learning through Fusing Side Information. CoRR","author":"Hubert Tsai Yao-Hung","year":"2017"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"e_1_3_2_1_60_1","volume-title":"Deep Domain Confusion: Maximizing for Domain Invariance. CoRR","author":"Tzeng Eric","year":"2014"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157504"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.5555\/2283516.2283652"},{"key":"e_1_3_2_1_63_1","volume-title":"Cross-lingual Alignment vs Joint Training: A Comparative Study and A Simple Unified Framework. arXiv preprint arXiv:1910.04708","author":"Wang Zirui","year":"2019"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3454723"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68783-4_35"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.001"},{"key":"e_1_3_2_1_67_1","volume-title":"Soujanya Poria, Erik Cambria, and Louis-Philippe Morency.","author":"Bagher Zadeh AmirAli","year":"2018"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321408.3322629"}],"event":{"name":"MM '21: ACM Multimedia Conference","location":"Virtual Event China","acronym":"MM '21","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 29th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475247","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475247","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474085.3475247","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:48:16Z","timestamp":1750193296000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474085.3475247"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":68,"alternative-id":["10.1145\/3474085.3475247","10.1145\/3474085"],"URL":"https:\/\/doi.org\/10.1145\/3474085.3475247","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]},"assertion":[{"value":"2021-10-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}