Human motion recognition is one of the most important branches of human-centered
research activities. In recent years, motion recognition based on RGB-D data has attracted …

Abstract We propose a Unified Pose Sequence Modeling approach to unify heterogeneous
human behavior understanding tasks based on pose data, eg, action recognition, 3D pose …

Many believe that the successes of deep learning on image understanding problems can be
replicated in the realm of video understanding. However, due to the scale and temporal …

Egocentric action anticipation consists in understanding which objects the camera wearer
will interact with in the near future and which actions they will perform. We tackle the …

Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence
modeling tasks. However, training RNNs on long sequences often face challenges like slow …

In this paper, we tackle the problem of egocentric action anticipation, ie, predicting what
actions the camera wearer will perform in the near future and which objects they will interact …

Analyzing human actions in videos has gained increased attention recently. While most
works focus on classifying and labeling observed video frames or anticipating the very …

Pedestrian action prediction has been a topic of active research in recent years resulting in
many new algorithmic solutions. However, measuring the overall progress towards solving …

Forecasting human dynamics is a very interesting but challenging task with several
prospective applications in robotics, health-care, among others. Researchers have recently …

Human motion prediction, the task of predicting future 3D human poses given a sequence of
observed ones, has been mostly treated as a deterministic problem. However, human …