Hey everybody,
Today I'll share some papers on Learning Scalable Rich Representations for Robotics; in particular these are very useful for touch features; but could be of use for many domains:
Today I'll share some papers on Learning Scalable Rich Representations for Robotics; in particular these are very useful for touch features; but could be of use for many domains:
Look, Listen and Learn.
Learning rich touch representations through cross-modal self-supervision.
Time-Contrastive Networks: Self-Supervised Learning from Video.
Representation Learning with Contrastive Predictive Coding.
Image-to-Image Translation with Conditional Adversarial Networks.
Deep Cross-Modal Audio-Visual Generation.
Photographic Image Synthesis with Cascaded Refinement Networks.
De Curtò i DíAz.