Related papers: Hidden Footprints: Learning Contextual Walkability…

A core challenge for an agent learning to interact with the world is to predict how its actions affect objects in its environment. Many existing methods for learning the dynamics of physical interactions require labeled object information.…

Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories. This closed-set paradigm is…

The problem of predicting human motion given a sequence of past observations is at the core of many applications in robotics and computer vision. Current state-of-the-art formulate this problem as a sequence-to-sequence task, in which a…

The use of gait for person identification has important advantages such as being non-invasive, unobtrusive, not requiring cooperation and being less likely to be obscured compared to other biometrics. Existing methods for gait recognition…

Robots and other intelligent systems navigating in complex dynamic environments should predict future actions and intentions of surrounding agents to reach their goals efficiently and avoid collisions. The dynamics of those agents strongly…

Smooth and seamless robot navigation while interacting with humans depends on predicting human movements. Forecasting such human dynamics often involves modeling human trajectories (global motion) or detailed body joint movements (local…

Accurate 3D object detection in real-world environments requires a huge amount of annotated data with high quality. Acquiring such data is tedious and expensive, and often needs repeated effort when a new sensor is adopted or when the…

Gait, i.e., the movement pattern of human limbs during locomotion, is a promising biometric for the identification of persons. Despite significant improvement in gait recognition with deep learning, existing studies still neglect a more…

Recent advances in 3D human shape estimation build upon parametric representations that model very well the shape of the naked body, but are not appropriate to represent the clothing geometry. In this paper, we present an approach to model…

Training a deep network to perform semantic segmentation requires large amounts of labeled data. To alleviate the manual effort of annotating real images, researchers have investigated the use of synthetic data, which can be labeled…

Landmark-based human action recognition in videos is a challenging task in computer vision. One key step is to design a generic approach that generates discriminative features for the spatial structure and temporal dynamics. To this end, we…

Many human social phenomena, such as cooperation, the growth of settlements, traffic dynamics and pedestrian movement, appear to be accessible to mathematical descriptions that invoke self-organization. Here we develop a model of pedestrian…

Traditional path-planning techniques treat humans as obstacles. This has changed since robots started to enter human environments. On modern robots, social navigation has become an important aspect of navigation systems. To use…

We develop a human movement trajectory prediction system that incorporates the scene information (Scene-LSTM) as well as human movement trajectories (Pedestrian movement LSTM) in the prediction process within static crowded scenes. We…

From an image of a person in action, we can easily guess the 3D motion of the person in the immediate past and future. This is because we have a mental model of 3D human dynamics that we have acquired from observing visual sequences of…

Human motion prediction is essential for the safe and smooth operation of mobile service robots and intelligent vehicles around people. Commonly used neural network-based approaches often require large amounts of complete trajectories to…

Estimation of human shape and pose from a single image is a challenging task. It is an even more difficult problem to map the identified human shape onto a 3D human model. Existing methods map manually labelled human pixels in real 2D…

Tracking-by-detection has become the de facto standard approach to people tracking. To increase robustness, some approaches incorporate re-identification using appearance models and regressing motion offset, which requires costly identity…

We present a novel hierarchical model for human activity recognition. In contrast to approaches that successively recognize actions and activities, our approach jointly models actions and activities in a unified framework, and their labels…

Autonomous vehicles require knowledge of the surrounding road layout, which can be predicted by state-of-the-art CNNs. This work addresses the current lack of data for determining lane instances, which are needed for various driving…