arXiv research

GIBLy adds geometric priors to 3D segmentation models, improving performance with minimal overhead.

VarDeepPCA: A Sampling-Free Variational DNN Plugin for OOD Segmentation with Uncertainty Estimation

A new snake model improves segmentation of SEM images.

A new probabilistic polygonal curve representation using Gaussian Mixture Models.

SCENE-Net improves 3D point cloud segmentation with low resource usage and transparency.

Intensity augmentation improves breast MRI segmentation accuracy.

In this paper we show that on a complete Riemannian manifold of negative curvature and dimension $n>1$ every two points which realize a local maximum for the distance function are connected by at least $2n+1$ geometrically distinct geodesic segments (i.e. length minimizing). Using a similar method, we obtain that in th…

Develops a fast BMF approach for binary matrices.

Santaló calculated the measures for all positions of a moving line segment in which it lies inside a fixed circle and intersects this circle in one or two points. From these measures he concluded hitting probabilities for a line segment thrown randomly onto an unbounded lattice of circles. In the present paper these re…

Paper tackles musical version matching at segment level using contrastive learning from weakly-labeled data.

We provide a proof and analyze the asymptotic behavior of a formula for the linking number of line segments.

Connected flip graphs for triangulations on hyperbolic surfaces.

VarDeepPCA refines medical image segmentation from small datasets, improving anatomical plausibility and reducing errors.

We propose a new analytical approximation to the $χ^2$ kernel that converges geometrically. The analytical approximation is derived with elementary methods and adapts to the input distribution for optimal convergence rate. Experiments show the new approximation leads to improved performance in image classification and …

DeepCap automates coronary artery segmentation from IVOCT images.

Extending the earlier results for analytic curve segments, in this article we describe the asymptotic behaviour of evolution of a finite segment of a C^n-smooth curve under the geodesic flow on the unit tangent bundle of a finite volume hyperbolic n-manifold. In particular, we show that if the curve satisfies certain n…

The aim of this paper is to develop a new axiomatization of planar geometry by reinterpreting the original axioms of Euclid. The basic concept is still that of a line segment but its equivalent notion of betweenness is viewed as a topological, not a metric concept. That leads quickly to the notion of connectedness with…

Approximating complex curves with simple parametric curves is widely used in CAGD, CG, and CNC. This paper presents an algorithm to compute a certified approximation to a given parametric space curve with cubic B-spline curves. By certified, we mean that the approximation can approximate the given curve to any given pr…

New gait segmentation method identifies users and adversaries with high accuracy.

We add two new 1-parameter families to the short list of known embedded triply periodic minimal surfaces of genus 4 in $\mathbb{R}^3$. Both surfaces can be tiled by minimal pentagons with two straight segments and three planar symmetry curves as boundary. In one case (which has the appearance of the CLP surface of Schw…

Benguria and Loss have conjectured that, amongst all smooth closed curves of length $2π$ in the plane, the lowest possible eigenvalue of the operator $L=-Δ+κ^2$ was one. They observed that this value was achieved on a two-parameter family, $\mathcal{O}$, of geometrically distinct ovals containing the round circle and c…

Let $l =[l_0,l_1]$ be the directed line segment from $l_0\in {\mathbb R}^n$ to $l_1\in{\mathbb R}^n.$ Suppose $\bar l=[\bar l_0,\bar l_1]$ is a second segment of equal length such that $l, \bar l$ satisfy the "two sticks condition": $\| l_1-\bar l_0\| \ge \| l_1-l_0\|, \| \bar l_1-l_0\| \ge \| \bar l_1-\bar l_0\|.$ He…

As in a symmetric space of noncompact type, one can associate to an oriented geodesic segment in a Euclidean building a vector valued length in the Euclidean Weyl chamber; in addition to the metric length it contains information on the direction of the segment. We study in this paper restrictions on the vector valued s…

Segmental structure is a common pattern in many types of sequences such as phrases in human languages. In this paper, we present a probabilistic model for sequences via their segmentations. The probability of a segmented sequence is calculated as the product of the probabilities of all its segments, where each segment …

Bayesian nonparametric method segments multi-sequence time series data.

Segmentation has been a major task in neuroimaging. A large number of automated methods have been developed for segmenting healthy and diseased brain tissues. In recent years, deep learning techniques have attracted a lot of attention as a result of their high accuracy in different segmentation problems. We present a n…

The visual systems of many mammals, including humans, is able to integrate the geometric information of visual stimuli and to perform cognitive tasks already at the first stages of the cortical processing. This is thought to be the result of a combination of mechanisms, which include feature extraction at single cell l…

BiPE blends intra-segment and inter-segment encodings for better length extrapolation.

CNNs can be trained with clinically available segmentations for OARs in radiotherapy.

Billiard trajectories and geodesics are closely related geometrically.

Smooth curves from polygonal chains with vertex preservation and explicit curvature control.

Learning-based methods for visual segmentation have made progress on particular types of segmentation tasks, but are limited by the necessary supervision, the narrow definitions of fixed tasks, and the lack of control during inference for correcting errors. To remedy the rigidity and annotation burden of standard appro…

Image segmentation is one of the most fundamental tasks of computer vision. In many practical applications, it is essential to properly evaluate the reliability of individual segmentation results. In this study, we propose a novel framework to provide the statistical significance of segmentation results in the form of …

DNA rearrangement processes recombine gene segments that are organized on the chromosome in a variety of ways. The segments can overlap, interleave or one may be a subsegment of another. We use directed graphs to represent segment organizations on a given locus where contigs containing rearranged segments represent ver…

Preformer improves Transformer for long-term time series forecasting.

The Hausdorff Distance (HD) is widely used in evaluating medical image segmentation methods. However, existing segmentation methods do not attempt to reduce HD directly. In this paper, we present novel loss functions for training convolutional neural network (CNN)-based segmentation methods with the goal of reducing HD…

We introduce a novel Deep Learning framework, which quantitatively estimates image segmentation quality without the need for human inspection or labeling. We refer to this method as a Quality Assurance Network -- QANet. Specifically, given an image and a `proposed' corresponding segmentation, obtained by any method inc…

Study uses LLM to extract and compare segment disclosures from financial filings.

Spatially-aware metrics improve uncertainty evaluation in segmentation.

LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify the speaker, which results in a critical mismatch between testing and training. T…

Deep learning improves automatic image segmentation.

To accurately analyze changes of anatomical structures in longitudinal imaging studies, consistent segmentation across multiple time-points is required. Existing solutions often involve independent registration and segmentation components. Registration between time-points is used either as a prior for segmentation in a…

This paper reviews deep learning for multi-modality medical image segmentation.

A novel 3D U-Net approach improves kidney tumor segmentation in medical imaging.

We derive a convex optimization problem for the task of segmenting sequential data, which explicitly treats presence of outliers. We describe two algorithms for solving this problem, one exact and one a top-down novel approach, and we derive a consistency results for the case of two segments and no outliers. Robustness…

A new heuristic LM algorithm improves $k$-segmentation accuracy with less computation.

Paper studies geometric and combinatorial properties of circular snakes.

Todays interactive devices such as smart-phone assistants and smart speakers often deal with short-duration speech segments. As a result, speaker recognition systems integrated into such devices will be much better suited with models capable of performing the recognition task with short-duration utterances. In this pap…