Self-Supervised Learning

Unsupervised Self-Training for Sentiment Analysis of Code-Switched Data NAACL 2021 Unsupervised Skill Discovery with Bottleneck Option Learning ICML 2021 Unsupervised Speech Recognition NeurIPS 2021 Unsupervised Video Representation Learning by Bidirectional Feature Prediction WACV 2021 Unsupervised Visual Attention and Invariance for Reinforcement Learning CVPR 2021 Unsupervised Visual Representation Learning by Tracking Patches in Video CVPR 2021 UP-DETR: Unsupervised Pre-Training for Object Detection With Transformers CVPR 2021 Using Large Self-Supervised Models for Low-Resource Speech Recognition Interspeech 2021 Using Pause Information for More Accurate Entity Recognition EMNLP 2021 Utilizing Self-Supervised Representations for MOS Prediction Interspeech 2021 UTNLP at SemEval-2021 Task 5: A Comparative Analysis of Toxic Span Detection using Attention-based, Named Entity Recognition, and Ensemble Models SemEval 2021 UWSpeech: Speech to Speech Translation for Unwritten Languages AAAI 2021 Variational Prototype Learning for Deep Face Recognition CVPR 2021 VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text NeurIPS 2021 VDSM: Unsupervised Video Disentanglement With State-Space Modeling and Deep Mixtures of Experts CVPR 2021 Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting CVPR 2021 Vector Quantized Bayesian Neural Network Inference for Data Streams AAAI 2021 Vi2CLR: Video and Image for Visual Contrastive Learning of Representation ICCV 2021 Video Annotation for Visual Tracking via Selection and Refinement ICCV 2021 Viewmaker Networks: Learning Views for Unsupervised Representation Learning ICLR 2021 ViewNet: Unsupervised Viewpoint Estimation From Conditional Generation ICCV 2021 Viewpoint Invariant Dense Matching for Visual Geolocalization ICCV 2021 VirTex: Learning Visual Representations From Textual Annotations CVPR 2021 Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained Models EMNLP 2021 Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction ICCV 2021