Generates realistic person images for re-id, overcoming pose variations.
problem Lack of cross-view paired training data and pose variations in person re-identification.
method Pose-normalization GAN (PN-GAN) for generating images conditioned on pose.
result Synthesized images enable learning invariant features free of pose variations.
We give a complete list of normal forms for the 2-dimensional metrics that admit a transitive Lie pseudogroup of geodesic-preserving transformations and we show that these normal forms are mutually non-isometric. This solves a problem posed by Sophus Lie.
New CNN architecture improves pediatric image segmentation by homogenizing pose and size.
problem Challenges in segmenting pediatric images due to pose and size heterogeneity.
method Spatial Transformer Network (STN) for pose and scale invariance, combined with UNet for segmentation.
result Improved pediatric segmentation, especially renal tumor delineation, with accelerated processing.
In this paper we present a self-contained combinatorial proof of the lower bound theorem for normal pseudomanifolds, including a treatment of the cases of equality in this theorem. We also discuss McMullen and Walkup's generalised lower bound conjecture for triangulated spheres in the context of the lower bound theorem…
Unsupervised mesh disentanglement separates identity and pose.
problem Geometric disentanglement for 3D deformable models.
method CFAN-VAE architecture using conformal factor and normal features.
result CFAN-VAE achieves state-of-the-art performance on unsupervised geometric disentanglement.
We give local criteria for smooth non-embeddablity of Levi-flat manifolds. For this purpose, we pose an analogue of Ueda theory on the neighborhood structure of hypersurfaces in complex manifolds with topologically trivial normal bundles.
We give a complete list of mutually non-diffeomorphic normal forms for the two-dimensional metrics that admit one essential (i.e., non-homothetic) projective vector field. This revises a result from the literature and extends the results of two papers, by R.L. Bryant & G. Manno & V.S. Matveev (2008) and V.S. Matveev (2…
New method for estimating parameters in inverse problems using double robustness.
problem Estimating parameters defined as linear functionals of solutions to linear inverse problems.
method Source condition double robust inference method that uses iterated Tikhonov regularized adversarial estimators.
result Asymptotic normality of the parameter of interest as long as either the primal or dual inverse problem is sufficiently well-posed.
We consider conformal immersions of Riemann surfaces in $\bb{S}^4$ and study their Gauss maps with values in the Grassmann bundle F=SO5/T2→S4. The energy of maps from Riemann surfaces into F is considered with respect to the normal metric on the target and immersions with harmo…
A new model uses normalizing flows for discrete sequences, improving generation speed.
problem Modeling discrete sequences like text using normalizing flows poses challenges.
method Proposes a VAE-based model with autoregressive and non-autoregressive flow architectures.
result Flow-based models can match or improve on autoregressive baselines for discrete sequence tasks.
Researchers extend reparameterization to Lie groups for better probability modeling.
problem Lack of reparameterization for distributions on Lie groups.
method Developed a general framework for creating reparameterizable densities on Lie groups.
result Demonstrated complex and multimodal distributions on SO(3) for pose estimation.
A new neural layer normalizes time series data for improved DL performance.
problem Degradation of DL model performance due to inappropriate normalization of time series data.
method Adaptive normalization neural layer trained end-to-end using back-propagation.
result Significant performance improvements over other normalization schemes.
Smooth surface encloses less volume than a ball.
problem Can a smooth surface enclose less volume than a ball?
method Example of a smooth closed surface in R3 with specific curvature constraints. result No, a supersqueezed sphere encloses less volume than a unit ball.
BiN normalizes financial time-series for better forecasting.
problem Non-stationarity and multimodality in financial time-series data.
method Bilinear Normalization (BiN) incorporated into TABL networks.
result BiN-TABL outperforms other normalization methods in financial forecasting.
Paper proposes a debiased estimator for adaptive linear regression.
problem Non-normal asymptotic behavior of OLS estimator in adaptive linear regression.
method Adaptive linear estimating equations to construct debiased estimator.
result Established asymptotic normality of the debiased estimator.
Paper introduces new motion synthesis model using normalizing flows.
problem Data-driven motion synthesis with probabilistic and controllable models.
method Probabilistic, generative, autoregressive model using normalizing flows and LSTMs.
result Randomly sampled motion from the model outperforms task-agnostic baselines.
New method improves deep learning model robustness and accuracy for long sequences.
problem Challenges in learning long-range sequence tasks using state-space models.
method Proposes a perturb-then-diagonalize (PTD) methodology to address ill-posed diagonalization problems in SSMs.
result Demonstrates improved robustness and accuracy of S5-PTD model on Long-Range Arena benchmark.
Researchers relax the CVF's smoothness requirement to create more flexible flow models.
problem Challenges in constructing flexible density models due to the CVF's smoothness requirement.
method Introduce L-diffeomorphisms as generalized transformations that may violate smoothness on zero Lebesgue-measure sets. result The relaxation allows for the use of non-smooth activation functions like ReLU in residual flows.
A simple graphical model for correlated defaults is proposed, with explicit formulas for the loss distribution. Algebraic geometry techniques are employed to show that this model is well posed for default dependence: it represents any given marginal distribution for single firms and pairwise correlation matrix. These t…
A novel method quantizes Batch Normalization for QNNs, maintaining accuracy and efficiency.
problem Quantization challenges in Batch Normalization for QNNs.
method Converts BN to fixed-point operation with shared scale, suitable for hardware.
result Maintains same outputs through rigorous analysis and experiments.
ULES embeds dynamic networks with stability guarantees.
problem Stability of time-varying node embeddings in evolving networks.
method Unfolded Laplacian Spectral Embedding (ULSE) using normalized Laplacian operators.
result ULES satisfies cross-sectional and longitudinal stability under dynamic stochastic block model.
In this paper, two sequences of minimal isoparametric hypersurfaces are constructed via representations of Clifford algebras. Based on these, we give estimates on eigenvalues of the Laplacian of the focal submanifolds of isoparametric hypersurfaces in unit spheres. This improves results of [TY13] and [TXY14]. Eells and…
Study shows skewed data labels significantly impact decentralized ML accuracy.
problem Skewed data labels across devices/locations cause significant accuracy loss in decentralized ML.
method Detailed experimental study on skewed data labels, presenting SkewScout system-level approach.
result Skewed data labels are a fundamental challenge for decentralized learning, affecting many applications and models.
New method uses IB to train normalizing flows for better generative classification.
problem Training generative models with information theory for improved classification.
method Developed IB-INNs, a class of conditional normalizing flows trained with IB objective.
result IB-INNs offer improved uncertainty quantification and out-of-distribution detection compared to traditional generative classifiers.
This paper explains how batch normalization auto-tunes the regularization parameter based on data statistics.
problem Batch normalization accelerates deep learning training but the exact relationship to regularization is unclear.
method Theoretical analysis and empirical validation of batch normalization's role in auto-tuning the regularization parameter.
result Batch normalization auto-tunes the regularization parameter based on data statistics.
This paper solves the structure of link concordance groups, proving they are infinitely generated.
problem Determining the structure of link concordance groups with a marked component.
method Proving the complements are isomorphic to Z^∞ ⊕ (Z/2Z)^∞ and introducing prime elements.
result Proves both complements of link concordance groups are Z^∞ ⊕ (Z/2Z)^∞.
NF-ULA combines Langevin Monte Carlo with normalizing flows for imaging inverse problems.
problem Solving inverse problems in imaging with uncertainty quantification.
method Langevin Monte Carlo with normalizing flow prior.
result NF-ULA outperforms competing methods for severely ill-posed inverse problems.
This paper investigates the space of codimension zero embeddings of a Poincare duality space in a disk. One of our main results exhibits a tower that interpolates from the space of Poincare immersions to a certain space of "unlinked" Poincare embeddings. The layers of this tower are described in terms of the coefficien…
New Siamese Capsule Networks improve face verification in limited data settings.
problem Few-shot face verification with limited labeled data.
method Siamese Capsule Networks with contrastive loss and normalized pose features.
result Siamese Capsule Networks outperform baselines in few-shot face verification.
Ensemble learning improves anomaly detection for milder symptoms.
problem Difficulty in detecting incipient anomalies due to similarity to normal conditions.
method Utilize uncertainty information from ensemble learning to identify misclassified incipient anomalies.
result Ensemble learning methods show improved performance on incipient anomaly detection.
mm-Pose detects human skeletons in real-time using mmWave radar and CNNs.
problem Real-time human skeletal posture estimation in various scenarios.
method mmWave radar, radar-to-image representation, forked CNN architecture.
result Accurate predictions for human skeletal joints in 3D space.
The paper discusses the impossibility of eliminating surplus intersections in Lagrangian submanifolds.
problem Can surplus intersections in Lagrangian submanifolds be eliminated by Hamiltonian isotopy?
method Analyzing the intersections and isotopies of Lagrangian submanifolds and auxiliary Lagrangians.
result Surplusection cannot be eliminated in several important situations, highlighting the need for better understanding.
Ensemble models struggle with detecting mild faults.
problem Difficulty in detecting Intermediate-Severity faults due to their resemblance to normal conditions.
method Extensive experiments with ensemble models to identify and address common pitfalls.
result Designing more effective ensemble models for IS fault detection and diagnosis.
Improved anomaly detection for incipient faults using ensemble learning.
problem Difficulty in detecting milder anomalies due to similarity to normal conditions.
method Utilize uncertainty information from ensemble learning to identify misclassified incipient anomalies.
result Ensemble learning improves performance on incipient anomaly detection.
We study the microlocal properties of the geodesic X-ray transform X on a manifold with boundary allowing the presence of conjugate points. Assuming that there are no self-intersecting geodesics and all conjugate pairs are nonsingular we show that the normal operator $\mathcal{N} = \mathcal{X}^t \circ \math…
Novel method uses Gaussian process to estimate particle sizes from scattering data.
problem Estimating particle size distributions from noisy optical scattering measurements.
method Constrained Gaussian process regression with normalization constraints.
result Accurately reconstructs particle size distributions from noisy data.
We prove that the exponential growth rate of the regular language of penetration sequences is smaller than the growth rate of the regular language of normal form words, if the acceptor of the regular language of normal form words is strongly connected. Moreover, we show that the latter property is satisfied for all irr…
Improved statistical inference for adaptive Thompson Sampling.
problem Statistical inference challenges in Thompson Sampling.
method Inflating posterior variance in Thompson Sampling.
result Asymptotically normal estimates of arm means with logarithmic regret increase.
Optimizes ligand binding poses using CNNs and atomic grids.
problem Improving the accuracy of docking predictions for drug discovery.
method Differentiable atomic grid representation, CNN for scoring and optimization.
result Iteratively-trained CNNs outperform single CNNs in optimizing poses.
The inference of correlated signal fields with unknown correlation structures is of high scientific and technological relevance, but poses significant conceptual and numerical challenges. To address these, we develop the correlated signal inference (CSI) algorithm within information field theory (IFT) and discuss its n…
Neural network estimates network models efficiently.
problem Estimating flexible ERGMs is challenging due to intractable normalizing constants.
method Trains a neural network on parameter-simulation pairs to invert and estimate parameters quickly and in parallel.
result The method performs well in practice and accommodates extra network statistics.
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…
Paper tackles in-bed pressure-based pose estimation, improving accuracy.
problem Pose estimation models fail to generalize with in-bed pressure data.
method End-to-end framework with a deep neural network pre-processing pressure data.
result Model accurately reconstructs unclear body parts for improved pose estimation.
The paper learns pose variations within shape populations using constrained mixtures of factor analyzers.
problem Learning pose variations within a shape population with articulated parts and relative rotations.
method Formulated as mixtures of factor analyzers, segmentation by component posterior probabilities, and constraints on factor loading matrices for rotation matrices.
result Automatic learning of pose variations from shape populations, resulting in smooth and realistic animations.
For each odd integer r greater than one and not divisible by three we give explicit examples of infinite families of simply and tangentially homotopy equivalent but pairwise non-homeomorphic closed homogeneous spaces with fundamental group isomorphic to Z/r. As an application we construct the first examples of manifold…
Solve Beltrami problem in dimension two
problem Geodesically equivalent metric pairs in dimension two
method Provide a complete local classification
result Full solution of the problem in dimension two
The paper analyzes the observability of relative pose estimation using dual quaternions.
problem Estimating relative pose in robotics applications.
method Lie algebraic nonlinear observability analysis on a dual quaternion system.
result Dual quaternion representation yields an observability matrix with a simple block triangular structure and full rank.
Study on Kähler-Einstein metrics on quasi-projective manifolds.
problem Constructing and analyzing Kähler-Einstein metrics on quasi-projective manifolds.
method Utilizes singular Kähler-Einstein metrics and conic Kähler-Einstein metrics of negative curvature.
result Established the weak convergence of conic Kähler-Einstein metrics to singular Kähler-Einstein metrics.