Self-Supervised Learning

CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild CVPR 2021 Can Scale-Consistent Monocular Depth Be Learned in a Self-Supervised Scale-Invariant Manner? ICCV 2021 Can Transformer Language Models Predict Psychometric Properties? ACL 2021 CanvasVAE: Learning To Generate Vector Graphic Documents ICCV 2021 Capturing document context inside sentence-level neural machine translation models with self-training EMNLP 2021 Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations NeurIPS 2021 Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization EMNLP 2021 CARMS: Categorical-Antithetic-REINFORCE Multi-Sample Gradient Estimator NeurIPS 2021 Cascaded Multilingual Audio-Visual Learning from Videos Interspeech 2021 CASTing Your Model: Learning To Localize Improves Self-Supervised Representations CVPR 2021 Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization ICML 2021 Causal Attention for Unbiased Visual Recognition ICCV 2021 Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning ICML 2021 CCVS: Context-aware Controllable Video Synthesis NeurIPS 2021 CDLM: Cross-Document Language Modeling EMNLP 2021 CDS: Cross-Domain Self-Supervised Pre-Training ICCV 2021 Changing the Mind of Transformers for Topically-Controllable Language Generation EACL 2021 Character Transformations for Non-Autoregressive GEC Tagging EMNLP 2021 Civil Rephrases Of Toxic Texts With Self-Supervised Transformers EACL 2021 CLAR: Contrastive Learning of Auditory Representations AISTATS 2021 Classification of COVID-19 from Cough Using Autoregressive Predictive Coding Pretraining and Spectral Data Augmentation Interspeech 2021 CLIP: A Dataset for Extracting Action Items for Physicians from Hospital Discharge Notes ACL 2021 Cluster Analysis of Online Mental Health Discourse using Topic-Infused Deep Contextualized Representations EACL 2021 Clustering by Maximizing Mutual Information Across Views ICCV 2021 Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification MIDL 2021