Multimodal machine learning (MML) is a tempting multidisciplinary research area where
heterogeneous data from multiple modalities and machine learning (ML) are combined to …

Over the last decade, supervised deep learning on manually annotated big data has been
progressing significantly on computer vision tasks. But, the application of deep learning in …

Self-supervised learning algorithms based on instance discrimination train encoders to be
invariant to pre-defined transformations of the same instance. While most methods treat …

Imitation learning from human demonstrations is a promising paradigm for teaching robots
manipulation skills in the real world. However, learning complex long-horizon tasks often …

We present a self-supervised Contrastive Video Representation Learning (CVRL) method to
learn spatiotemporal visual representations from unlabeled videos. Our representations are …

The goal of self-supervised learning from images is to construct image representations that
are semantically meaningful via pretext tasks that do not require semantic annotations. Many …

Skeleton sequence representation learning has shown great advantages for action
recognition due to its promising ability to model human joints and topology. However, the …

MoCo is effective for unsupervised image representation learning. In this paper, we propose
VideoMoCo for unsupervised video representation learning. Given a video sequence as an …

We approach the problem of learning by watching humans in the wild. While traditional
approaches in Imitation and Reinforcement Learning are promising for learning in the real …

Abstract Visual Transformers (VTs) are emerging as an architectural paradigm alternative to
Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations …