Unsupervised Learning

Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation Interspeech 2022 Lifelong Unsupervised Domain Adaptive Person Re-Identification With Coordinated Anti-Forgetting and Adaptation CVPR 2022 Linearization and Identification of Multiple-Attractor Dynamical Systems through Laplacian Eigenmaps JMLR 2022 Lipschitz-constrained Unsupervised Skill Discovery ICLR 2022 Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition Interspeech 2022 Local-Adaptive Face Recognition via Graph-Based Meta-Clustering and Regularized Adaptation CVPR 2022 Low-Budget Active Learning via Wasserstein Distance: An Integer Programming Approach ICLR 2022 Low-Resource Neural Machine Translation: A Case Study of Cantonese COLING 2022 MACK: Multimodal Aligned Conceptual Knowledge for Unpaired Image-text Matching NeurIPS 2022 MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-Based Image Captioning AAAI 2022 Making Sense of Raw Input (Extended Abstract) IJCAI 2022 Many processors, little time: MCMC for partitions via optimal transport couplings AISTATS 2022 Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging? NAACL 2022 MCPG: A Flexible Multi-Level Controllable Framework for Unsupervised Paraphrase Generation EMNLP 2022 MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction ACL 2022 Mode estimation on matrix manifolds: Convergence and robustness AISTATS 2022 Modeling speech recognition and synthesis simultaneously: Encoding and decoding lexical and sublexical semantic information into speech with no direct access to speech data Interspeech 2022 More Than Words: Collocation Retokenization for Latent Dirichlet Allocation Models ACL 2022 Morphological Processing of Low-Resource Languages: Where We Are and What’s Next ACL 2022 MOVE: Unsupervised Movable Object Segmentation and Detection NeurIPS 2022 Multilingual unsupervised sequence segmentation transfers to extremely low-resource languages ACL 2022 Multi-Modal Multi-Correlation Learning for Audio-Visual Speech Separation Interspeech 2022 Multi-Mode Tensor Space Clustering Based on Low-Tensor-Rank Representation AAAI 2022 Multi-Scale Anomaly Detection for Time Series with Attention-based Recurrent Autoencoders ACML 2022 Multi-Source Uncertainty Mining for Deep Unsupervised Saliency Detection CVPR 2022