arXiv research

Deep learning animates objects from input images and videos.

Two insurance companies collaborate to maximize the probability of none going bankrupt.

GCRL learns causal factors for motion forecasting, improving out-of-distribution prediction.

Long-term human motion can be represented as a series of motion modes---motion sequences that capture short-term temporal dynamics---with transitions between them. We leverage this structure and present a novel Motion Transformation Variational Auto-Encoders (MT-VAE) for learning motion sequence generation. Our model j…

Inertial information processing plays a pivotal role in ego-motion awareness for mobile agents, as inertial measurements are entirely egocentric and not environment dependent. However, they are affected greatly by changes in sensor placement/orientation or motion dynamics, and it is infeasible to collect labelled data …

A major bottleneck for developing general reinforcement learning agents is determining rewards that will yield desirable behaviors under various circumstances. We introduce a general mechanism for automatically specifying meaningful behaviors from raw pixels. In particular, we train a generative adversarial network to …

The cohomology of the pure string motion group PSigma_n admits a natural action by the hyperoctahedral group W_n. Church and Farb conjectured that for each k > 0, the sequence of degree k rational cohomology groups of PSigma_n is uniformly representation stable with respect to the induced action by W_n, that is, the de…

Modular method predicts motion in crowded scenes using learned environment models.

Paper studies how discrete space curves with constant torsion deform to model linkage motions.

Paper proposes a method to compose task-agnostic skills for solving new problems.

This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation. Specifically, we use unsupervised motion-based segmentation on videos to obtain segme…

Understanding the relationship between the structure of light-harvesting systems and their excitation energy transfer properties is of fundamental importance in many applications including the development of next generation photovoltaics. Natural light harvesting in photosynthesis shows remarkable excitation energy tra…

Geometric approach improves motion alignment accuracy and efficiency.

Study evaluates discretized arbitrage strategies in fractional financial markets.

We investigate metric learning in the context of dynamic time warping (DTW), the by far most popular dissimilarity measure used for the comparison and analysis of motion capture data. While metric learning enables a problem-adapted representation of data, the majority of methods has been proposed for vectorial data onl…

This paper optimizes insurance reinsurance design under solvency constraints.

Paper tackles transfer RL under unobserved context, developing methods to reduce bias.

Learning robot tasks or controllers using deep reinforcement learning has been proven effective in simulations. Learning in simulation has several advantages. For example, one can fully control the simulated environment, including halting motions while performing computations. Another advantage when robots are involved…

PPGnet model estimates heart rate from PPG signals without motion artifacts.

Timewarp accelerates molecular dynamics by learning to simulate long timescales.

We present a novel solution to the problem of simulation-to-real transfer, which builds on recent advances in robot skill decomposition. Rather than focusing on minimizing the simulation-reality gap, we learn a set of diverse policies that are parameterized in a way that makes them easily reusable. This diversity and p…

Paper learns versatile balancing and recovery motions for humanoid robots.

Study improves tongue contour recognition in ultrasound images using transfer learning.

Paper describes a video surveillance system for highway traffic events.

Simulation-to-real transfer is an important strategy for making reinforcement learning practical with real robots. Successful sim-to-real transfer systems have difficulty producing policies which generalize across tasks, despite training for thousands of hours equivalent real robot time. To address this shortcoming, we…

Study presents a low-cost local motion planner for vineyard navigation.

Introduces Motion Programs for better video analysis of human motion.

New approach links 2D fluid dynamics to matrix theory.

Study motion planning for points avoiding obstacles in a plane.

Paper introduces new motion synthesis model using normalizing flows.

Programmatic Motion Concepts learn human actions from paired videos.

Unified framework for human motion generation on Riemannian manifolds.

Study on determinants of unitary Brownian motion and their asymptotic laws.

New framework predicts diverse, contextually plausible 3D human motions.

Study refracted skew Brownian motion, find densities and asymptotics.

Neural network predicts vessel motions with high accuracy.

Study fractal dimension for motion without crossing a subset.

Let $E$ be a closed set in the Riemann sphere $\widehat{\mathbb{C}}$. We consider a holomorphic motion $φ$ of $E$ over a complex manifold $M$, that is, a holomorphic family of injections on $E$ parametrized by $M$. It is known that if $M$ is the unit disk $Δ$ in the complex plane, then any holomorphic motion of $E$ ove…

Neural network estimates rigid motion in stroke imaging to improve image quality.

Study cohomological equation for robotic screw motions on SE(3).

We introduce the Speculative Influence Network (SIN) to decipher the causal relationships between sectors (and/or firms) during financial bubbles. The SIN is constructed in two steps. First, we develop a Hidden Markov Model (HMM) of regime-switching between a normal market phase represented by a geometric Brownian moti…

New approach for obstacle avoidance in robotics using learned representations.

The paper presents a method to reduce arm motion complexity for prosthetics and robotics.

Paper defines multi-dimensional fractional Brownian motion under volatility uncertainty.

Paper introduces a new method for generating diverse human motion predictions.

Researchers calculate the Laplace transform of a geometric Brownian motion integral.

Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment. An open problem in this setting is that of developing good strategies for integrating or merging policies for multiple skills, where each…

Researchers created a continuous Markov martingale that mimics Brownian motion but lacks the strong Markov property.