Self-Supervised Learning

VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning ICLR 2022 Video Language Co-Attention with Multimodal Fast-Learning Feature Fusion for VideoQA ACL 2022 VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training NeurIPS 2022 Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training CVPR 2022 Video-Text Representation Learning via Differentiable Weak Temporal Alignment CVPR 2022 Vision-Language Pretraining: Current Trends and the Future ACL 2022 Vision-Language Pre-Training With Triple Contrastive Learning CVPR 2022 Visual Emotion Representation Learning via Emotion-Aware Pre-training IJCAI 2022 VisualHow: Multimodal Problem Solving CVPR 2022 Visually Guided Sound Source Separation and Localization Using Self-Supervised Motion Representations WACV 2022 ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation NeurIPS 2022 VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix ICML 2022 Voice Activity Projection: Self-supervised Learning of Turn-taking Events Interspeech 2022 VORTEX: Physics-Driven Data Augmentations Using Consistency Training for Robust Accelerated MRI Reconstruction MIDL 2022 VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature Interspeech 2022 WALT: Watch and Learn 2D Amodal Representation From Time-Lapse Imagery CVPR 2022 WA-Transformer: Window Attention-based Transformer with Two-stage Strategy for Multi-task Audio Source Separation Interspeech 2022 wav2vec2-based Speech Rating System for Children with Speech Sound Disorder Interspeech 2022 Wav2Vec-Aug: Improved self-supervised training with limited data Interspeech 2022 Wav2vec-S: Semi-Supervised Pre-Training for Low-Resource ASR Interspeech 2022 Weakly Paired Associative Learning for Sound and Image Representations via Bimodal Associative Memory CVPR 2022 Weakly-supervised learning for image-based classification of primary melanomas into genomic immune subgroups MIDL 2022 Weighted self Distillation for Chinese word segmentation ACL 2022 What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment EMNLP 2022 When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it NAACL 2022