cv
- Joint Deep Learning of Facial Expression Synthesis and Recognition.
arxiv
- U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation.
arxiv code :star:
Contrastive Learning
- A Simple Framework for Contrastive Learning of Visual Representations.
arxiv
Object Detect
- YOLOv4: Optimal Speed and Accuracy of Object Detection.
arxiv code
Video
- Adversarial Distortion for Learned Video Compression.
arxiv
- A Review on Deep Learning Techniques for Video Prediction.
arxiv
- FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding.
arxiv
- Labelling unlabelled videos from scratch with multi-modal self-supervision.
arxiv
- Multi-modal Self-Supervision from Generalized Data Transformations.
arxiv
- Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning.
arxiv