A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
CP uses geometric information to improve conformal prediction robustness.
This research improves representation learning for new domains with limited new supervision.
LLoCa makes any network Lorentz-equivariant, achieving high accuracy and efficiency.
This article reviews entity resolution methods and their applications.
SymPE breaks symmetries in equivariant networks, improving performance across various tasks.
DeepWeightFlow generates diverse neural network weights efficiently.
Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper introduces a collectio…
LoRAs enable efficient adaptation of large models; this paper explores processing LoRA weights with machine learning.
Docking is an important tool in computational drug discovery that aims to predict the binding pose of a ligand to a target protein through a combination of pose scoring and optimization. A scoring function that is differentiable with respect to atom positions can be used for both scoring and gradient-based optimization…
We propose a method to generate multiple diverse and valid human pose hypotheses in 3D all consistent with the 2D detection of joints in a monocular RGB image. We use a novel generative model uniform (unbiased) in the space of anatomically plausible 3D poses. Our model is compositional (produces a pose by combining par…
The paper learns pose variations within shape populations using constrained mixtures of factor analyzers.
The paper analyzes the observability of relative pose estimation using dual quaternions.
Recent advances in deep pose estimation models have proven to be effective in a wide range of applications such as health monitoring, sports, animations, and robotics. However, pose estimation models fail to generalize when facing images acquired from in-bed pressure sensing systems. In this paper, we address this chal…
Paper introduces EnDKF for more accurate pose tracking.
Person Re-identification (re-id) faces two major challenges: the lack of cross-view paired training data and learning discriminative identity-sensitive and view-invariant features in the presence of large pose variations. In this work, we address both problems by proposing a novel deep person image generation model for…
Unsupervised mesh disentanglement separates identity and pose.
New CNN architecture improves pediatric image segmentation by homogenizing pose and size.
In this paper, we deal with two challenges for measuring the similarity of the subject identities in practical video-based face recognition - the variation of the head pose in uncontrolled environments and the computational expense of processing videos. Since the frame-wise feature mean is unable to characterize the po…
Capsule models enforce object pose relationships for robustness, explored with probabilistic generative and variational methods.
Deep generative modelling for human body analysis is an emerging problem with many interesting applications. However, the latent space learned by such approaches is typically not interpretable, resulting in less flexibility. In this work, we present deep generative models for human body analysis in which the body pose …
We propose a method to learn object representations from 3D point clouds using bundles of geometrically interpretable hidden units, which we call geometric capsules. Each geometric capsule represents a visual entity, such as an object or a part, and consists of two components: a pose and a feature. The pose encodes whe…
Posing Kepler's problem of motion around a fixed "sun" requires the geometric mechanician to choose a metric and a Laplacian. The metric provides the kinetic energy. The fundamental solution to the Laplacian (with delta source at the "sun") provides the potential energy. Posing Kepler's three laws (with input from Gali…
We are given a video of a person performing a certain activity, from which we extract a controllable model. The model generates novel image sequences of that person, according to arbitrary user-defined control signals, typically marking the displacement of the moving body. The generated video can have an arbitrary back…
We introduce SARR for symmetric object pose estimation, improving CNN performance.
We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by inferring the depth of facial keypoints of an input image in an unsupervised manne…
We investigate nearest neighbor and generative models for transferring pose between persons. We take in a video of one person performing a sequence of actions and attempt to generate a video of another person performing the same actions. Our generative model (pix2pix) outperforms k-NN at both generating corresponding f…
We consider the problem of estimating human pose and trajectory by an aerial robot with a monocular camera in near real time. We present a preliminary solution whose distinguishing feature is a dynamic classifier selection architecture. In our solution, each video frame is corrected for perspective using projective tra…
Augment small datasets with synthetic backgrounds to train lightweight CNNs for human pose estimation.
Human motion prediction is a stochastic process: Given an observed sequence of poses, multiple future motions are plausible. Existing approaches to modeling this stochasticity typically combine a random noise vector with information about the previous poses. This combination, however, is done in a deterministic manner,…
Computational approaches to drug discovery can reduce the time and cost associated with experimental assays and enable the screening of novel chemotypes. Structure-based drug design methods rely on scoring functions to rank and predict binding affinities and poses. The ever-expanding amount of protein-ligand binding an…
This paper proposes a framework which is able to generate a sequence of three-dimensional human dance poses for a given music. The proposed framework consists of three components: a music feature encoder, a pose generator, and a music genre classifier. We focus on integrating these components for generating a realistic…
In this article, we solve the strong openness conjecture on the multiplier ideal sheaves for the plurisubharmonic functions posed by Demailly. We prove two conjectures about the growth of the volumes of the sublevel sets of plurisubharmonic functions related to the complex singularity exponents and quasi-plurisubharmon…
Previous work has shown that popular trending events are important external factors which pose significant influence on user search behavior and also provided a way to computationally model this influence. However, their problem formulation was based on the strong assumption that each event poses its influence independ…
Surveying 33 mapping questions posed by Heinonen and Semmes.
The Fredholm integral equation of the first kind improves solutions for ill-posed supervised learning problems with limited data.
Study rates of convergence for approximate solutions to linear ill-posed problems in Hilbert scales.
New framework assesses regularization norms in ill-posed problems, revealing L2 instability and proposing adaptive fractional RKHS solutions.
Tensor neural network improves human pose classification from 3D skeleton data.
The use of drug combinations often leads to polypharmacy side effects (POSE). A recent method formulates POSE prediction as a link prediction problem on a graph of drugs and proteins, and solves it with Graph Convolutional Networks (GCNs). However, due to the complex relationships in POSE, this method has high computat…
The paper proposes a method to learn 3D object pose manifolds using GANs and elasticae.
MCGDiff uses SGM to guide SMC for solving ill-posed linear inverse problems.
We study the geodesic X-ray transform on compact Riemannian surfaces with conjugate points. Regardless of the type of the conjugate points, we show that we cannot recover the singularities and therefore, this transform is always unstable (ill-posed). We describe the microlocal kernel of and relate it to the con…
In the present paper we consider application of overcomplete dictionaries to solution of general ill-posed linear inverse problems. In the context of regression problems, there has been enormous amount of effort to recover an unknown function using such dictionaries. One of the most popular methods, lasso and its versi…
New diffiety theory leads to a well-posed KP hierarchy.
We introduce Tempered Geodesic Markov Chain Monte Carlo (TG-MCMC) algorithm for initializing pose graph optimization problems, arising in various scenarios such as SFM (structure from motion) or SLAM (simultaneous localization and mapping). TG-MCMC is first of its kind as it unites asymptotically global non-convex opti…
P3I learns holistic scene representations from a single image.
The reduced thin-sandwich equations (RTSE) appear within Wheeler's thin-sandwich approach towards the Einstein constraint equations (ECE) of general relativity. It is known that these equations cannot be well-posed in general, but, on closed manifolds, sufficient conditions for well-posedness have been established. In …
We present LumièreNet, a simple, modular, and completely deep-learning based architecture that synthesizes, high quality, full-pose headshot lecture videos from instructor's new audio narration of any length. Unlike prior works, LumièreNet is entirely composed of trainable neural network modules to learn mapping functi…