arXiv research

mm-Pose detects human skeletons in real-time using mmWave radar and CNNs.

Skeletal signatures were introduced in [J W Anderson and A Wootton, A Lower Bound for the Number of Group Actions on a Compact Riemann Surface, Algebr. Geom. Topol. 12 (2012) 19--35.] as a tool to describe the space of all signatures with which a group can act on a surface of genus $σ\geq 2$. In the present paper we pr…

We consider a generic configuration of regions, consisting of a collection of distinct compact regions $\{Ω_i\}$ in $\mathbb{R}^{n+1}$ which may be either smooth regions disjoint from the others or regions which meet on their piecewise smooth boundaries $\mathcal{B}_i$ in a generic way. We introduce a skeletal linking …

New method recovers differential cohomology from diffeological spaces.

ES-VAE models skeletal pose trajectories by removing nuisance factors.

We prove that if $M$ is a CW-complex, then the homotopy type of the skeletal filtration of $M$ does not depend on the cell decomposition of $M$ up to wedge products with $n$-disks $D^n$, when the later are given their natural CW-decomposition with unique cells of order 0, $(n-1)$ and $n$; a result resembling J.H.C. Whi…

New homology theory for metric spaces, proving stability and anticipating topological changes.

Novel singularity models for 4D harmonic forms and spinors from polytopes.

Voice-controlled personal and home assistants (such as the Amazon Echo and Apple Siri) are becoming increasingly popular for a variety of applications. However, the benefits of these technologies are not readily accessible to Deaf or Hard-ofHearing (DHH) users. The objective of this study is to develop and evaluate a s…

We prove that the number of distinct group actions on compact Riemann surfaces of a fixed genus $σ\geq 2$ is at least quadratic in $σ$. We do this through the introduction of a coarse signature space, the space $\mathcal{K}_σ$ of {\em skeletal signatures} of group actions on compact Riemann surfaces of genus $σ$. We di…

The recognition of sign language is a challenging task with an important role in society to facilitate the communication of deaf persons. We propose a new approach of Spatial-Temporal Graph Convolutional Network to sign language recognition based on the human skeletal movements. The method uses graphs to capture the si…

We propose the time-dependent generalization of an `ordinary' autonomous human biomechanics, in which total mechanical + biochemical energy is not conserved. We introduce a general framework for time-dependent biomechanics in terms of jet manifolds derived from the extended musculo-skeletal configuration manifold. The …

In this article we describe a canonical way to expand a certain kind of $(\mathbb Z_2)^{n+1}$-colored regular graphs into closed $n$-manifolds by adding cells determined by the edge-colorings inductively. We show that every closed combinatorial $n$-manifold can be obtained in this way. When $n\leq 3$, we give simple eq…

In this paper, we present our approach to solve a physics-based reinforcement learning challenge "Learning to Run" with objective to train physiologically-based human model to navigate a complex obstacle course as quickly as possible. The environment is computationally expensive, has a high-dimensional continuous actio…

Novel approach uses quasi-conformal geometry for OSA classification from cephalometry.

We study Weinstein 4-manifolds which admit Lagrangian skeleta given by attaching disks to a surface along a collection of simple closed curves. In terms of the curves describing one such skeleton, we describe surgeries that preserve the ambient Weinstein manifold, but change the skeleton. The surgeries can be iterated …

This paper contributes to the challenge of learning a function on streamed multimodal data through evaluation. The core of the result of our paper is the combination of two quite different approaches to this problem. One comes from the mathematically principled technology of signatures and log-signatures as representat…

Universal model for soft tissue mechanics under shock waves.

In this paper we propose the time-dependent generalization of an `ordinary' autonomous human biomechanics, in which total mechanical + biochemical energy is not conserved. We introduce a general framework for time-dependent biomechanics in terms of jet manifolds associated to the extended musculo-skeletal configuration…

New method extracts hidden phases in binary mixtures using tubular tilings.

In recent years, Generative Adversarial Networks (GAN) have emerged as a powerful method for learning the mapping from noisy latent spaces to realistic data samples in high-dimensional space. So far, the development and application of GANs have been predominantly focused on spatial data such as images. In this project,…

The paper explores the relationship between joint mixability and negative dependence structures.

Digitwashing gap boosts stock crash risk, study finds.

We discuss the general properties of the theory of joint invariants of a smooth Lie group action in a manifold. Many of the known results about differential invariants, including Lie's finiteness theorem, have simpler versions in the context of joint invariants. We explore the relation between joint and differential in…

FJS method improves multinomial classification accuracy.

Paper proposes a new method to evaluate joint risk under uncertainty.

Introduces joint Shapley values to measure feature importance in models.

Study proposes a new model for joint survival annuity valuation.

Unified policy controls diverse agents through modular neural networks.

Estimates joint causal effects using single-variable interventions on nonlinear models.

Study joint invariants on symplectic spaces, extending group and space variations.

Objective: Joint analysis of multi-subject brain imaging datasets has wide applications in biomedical engineering. In these datasets, some sources belong to all subjects (joint), a subset of subjects (partially-joint), or a single subject (individual). In this paper, this source model is referred to as joint/partially-…

Proposes joint LCA for multiview data to identify shared and view-specific components.

Joint diffusion models improve data representation for both generation and prediction.

The Neural Testbed evaluates joint predictions of neural agents, revealing their limitations.

We consider the problem of approximate joint triangularization of a set of noisy jointly diagonalizable real matrices. Approximate joint triangularizers are commonly used in the estimation of the joint eigenstructure of a set of matrices, with applications in signal processing, linear algebra, and tensor decomposition.…

New Bayesian method for joint sparse parameter inference.

We discuss possible extensions of the classical Chern-Weil formalism to an infinite dimensional setup. This is based on joint work with Steven Rosenberg, joint work with Simon Scott and joint work with Jouko Mickelsson.

Unified theorem for deep and shallow joint-equivariant machines.

The space of graphs is often characterised by a non-trivial geometry, which complicates learning and inference in practical applications. A common approach is to use embedding techniques to represent graphs as points in a conventional Euclidean space, but non-Euclidean spaces have often been shown to be better suited f…

A broad range of cross-$m$-domain generation researches boil down to matching a joint distribution by deep generative models (DGMs). Hitherto algorithms excel in pairwise domains while as $m$ increases, remain struggling to scale themselves to fit a joint distribution. In this paper, we propose a domain-scalable DGM, i…

Paper uses non-Euclidean analysis to classify brain structure variations.

We investigate the non-identifiability issues associated with bidirectional adversarial training for joint distribution matching. Within a framework of conditional entropy, we propose both adversarial and non-adversarial approaches to learn desirable matched joint distributions for unsupervised and supervised tasks. We…

We employ the language of Cartan's geometry to present a model for studying vector spaces of Killing two-tensors defined in pseudo-Riemannian spaces of constant curvature under the action of the corresponding isometry group. We also discuss geometric properties of joint invariants of Killing two-tensors defined in the …

A new metric DJP-MMD improves domain adaptation by balancing transferability and discriminability.

This work proposes a new method to estimate joint probability from pairwise marginals, reducing sample complexity.

The paper emphasizes the importance of joint predictions over marginal predictions for decision-making.

A new generative adversarial network is developed for joint distribution matching. Distinct from most existing approaches, that only learn conditional distributions, the proposed model aims to learn a joint distribution of multiple random variables (domains). This is achieved by learning to sample from conditional dist…