English
Related papers

Related papers: A Higher-Order Poincar\'e Ellipsoid representation…

200 papers

A Pyramidal Histogram Of Characters (PHOC) represents the spatial location of symbols as binary vectors. The vectors are composed of levels that split a formula into equal-sized regions of one or more types (e.g., rectangles or ellipses).…

Information Retrieval · Computer Science 2024-08-20 Matt Langsenkamp , Bryan Amador , Richard Zanibbi

There are several improvements proposed over the baseline Absolute Positional Encoding (APE) method used in original transformer. In this study, we aim to investigate the implications of inadequately representing positional encoding in…

Computation and Language · Computer Science 2024-05-09 Arpit Aggarwal

Hierarchies allow feature sharing between objects at multiple levels of representation, can code exponential variability in a very compact way and enable fast inference. This makes them potentially suitable for learning and recognizing a…

Computer Vision and Pattern Recognition · Computer Science 2014-08-26 Sanja Fidler , Marko Boben , Ales Leonardis

Recognizing unknown objects is crucial for safety-critical applications such as autonomous driving and robotics. Open-Set Panoptic Segmentation (OPS) aims to segment known thing and stuff classes while identifying valid unknown objects as…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Yao Lu , Rohit Mohan , Florian Drews , Yakov Miron , Abhinav Valada

We introduce a two-level direct solver for the Hierarchical Poincar\'e-Steklov (HPS) method for solving linear elliptic PDEs. HPS combines multidomain spectral collocation with a direct solver, enabling high-order discretizations for highly…

Numerical Analysis · Mathematics 2025-09-19 Joseph Kump , Anna Yesypenko , Per-Gunnar Martinsson

Hyperbolic ordinal embedding (HOE) represents entities as points in hyperbolic space so that they agree as well as possible with given constraints in the form of entity i is more similar to entity j than to entity k. It has been…

Machine Learning · Computer Science 2021-05-24 Atsushi Suzuki , Atsushi Nitanda , Jing Wang , Linchuan Xu , Marc Cavazza , Kenji Yamanishi

Vector beams are often regarded as non-separable superpositions of spatial and polarization degrees of freedom that satisfy the wave equation. This interpretation ties their polarization structure to their spatial shape. Here, we introduce…

Exceptional points (EPs), which arose early from non-Hermitian physics, significantly amplify the system's response to minor perturbations, and they act as a useful concept to enhance measurement in metrology. In particular, such a…

Quantum Physics · Physics 2025-06-04 Minwei Shi , Guzhi Bao , Jinxian Guo , Weiping Zhang

Hyperbolic space has proven to be well-suited for capturing hierarchical relations in data, such as trees and directed acyclic graphs. Prior work introduced the concept of entailment cones, which uses partial orders defined by nested cones…

Machine Learning · Computer Science 2024-04-10 Tao Yu , Toni J. B. Liu , Albert Tseng , Christopher De Sa

We consider embedded ring-type surfaces (that is, compact, connected, orientable surfaces with two boundary components and Euler-Poincar\'{e} characteristic zero) in ${\bold R}^3$ of constant mean curvature which meet planes $\Pi_1$ and…

Differential Geometry · Mathematics 2016-09-06 John McCuan

Let $K$ be a number field, $\OK$ be its ring of integers. We introduce the notion of compactified representation of $GL_N(\OK)$ and, we see how to associate to a hermitian vector bundle $\E$ over $\Spec(\OK)$ and a compactified…

alg-geom · Mathematics 2008-02-03 Carlo Gasbarri

The combination of two quarter-wave plates and one half-wave plate, regardless of their sequential arrangement, constitutes a well-established universal SU(2) gadget capable of implementing all polarization transformations on the standard…

Optics · Physics 2025-09-16 Mohammad Umar , Paramasivam Senthilkumaran

Neural implicit surface reconstruction has become a new trend in reconstructing a detailed 3D shape from images. In previous methods, however, the 3D scene is only encoded by the MLPs which do not have an explicit 3D structure. To better…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Xiaodong Gu , Weihao Yuan , Heng Li , Zilong Dong , Ping Tan

A generalized family of scalar structured Gaussian modes including helical-Ince--Gaussian (HIG) and Hermite--Laguerre--Gaussian (HLG) beams is presented with physical insight upon a hybrid topological evolution nature of multi-singularity…

Optics · Physics 2019-03-27 Yijie Shen , Yuan Meng , Xing Fu , Mali Gong

Organic molecule exciton-polaritons in photonic lattices are a versatile platform to emulate unconventional phases of matter at ambient conditions, including protected interface modes in topological insulators. Here, we investigate bosonic…

The traditional head-up display (HUD) system has the disadvantages of a small area and a single display plane, here we propose and design an augmented reality (AR) HUD system with multi-plane, large area, high diffraction efficiency and a…

Human-Computer Interaction · Computer Science 2021-04-30 Zhenlv Lv , Juan Liu , Liangfa Xu

We present an experimental method for the generation of amplitude squeezed high-order vector beams. The light is modified twice by a spatial light modulator such that the vector beam is created by means of a collinear interferometric…

Estimating the 3D pose of hand and potential hand-held object from monocular images is a longstanding challenge. Yet, existing methods are specialized, focusing on either bare-hand or hand interacting with object. No method can flexibly…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Yinqiao Wang , Hao Xu , Pheng-Ann Heng , Chi-Wing Fu

Optical holography has undergone rapid development since its invention in 1948, but the accompanying speckles with randomly distributed intensity are still untamed now due to the fundamental difficulty of eliminating intrinsic fluctuations…

Optics · Physics 2022-11-21 Dong Zhao , Weiwei Fu , Ziqin Li , Jun He , Kun Huang

Human vision is able to capture the part-whole hierarchical information from the entire scene. This paper presents the Visual Parser (ViP) that explicitly constructs such a hierarchy with transformers. ViP divides visual representations…

Computer Vision and Pattern Recognition · Computer Science 2022-01-11 Shuyang Sun , Xiaoyu Yue , Song Bai , Philip Torr