Related papers: Prediction of Dashed Caf\'e Wall illusion by the C…
The challenge of object categorization in images is largely due to arbitrary translations and scales of the foreground objects. To attack this difficulty, we propose a new approach called collaborative receptive field learning to extract…
We consider a general theory of curvatures of discrete surfaces equipped with edgewise parallel Gauss images, and where mean and Gaussian curvatures of faces are derived from the faces' areas and mixed areas. Remarkably these notions are…
Modern neural networks achieve strong performance but remain difficult to interpret in high-dimensional visual domains. Counterfactual explanations (CFEs) provide a principled approach to interpreting black-box predictions by identifying…
The resistivity due to a domain wall in ferromagnetic metallic wire is calculated based on the linear response theory. The interaction between conduction electrons and the wall is expressed in terms of a classical gauge field which is…
The visual system is hierarchically organized to process visual information in successive stages. Neural representations vary drastically across the first stages of visual processing: at the output of the retina, ganglion cell receptive…
Visual interpretability of Convolutional Neural Networks (CNNs) has gained significant popularity because of the great challenges that CNN complexity imposes to understanding their inner workings. Although many techniques have been proposed…
We discuss in the planar approximation the effect of double-trace deformations on CFT's. We show that this large class of models posses a conformal window describing a non-trivial flow between two fixed points of the renormalization group,…
We present a mathematical model of the curvature blindness illusion in which sinusoids appear as angular zigzags when drawn with alternating contrast polarity against a gray background. The model identifies two complementary mechanisms,…
We experimentally test the effects of tilting a turbulent Rayleigh-B{\'e}nard convection cell on the dynamics of the large-scale circulation (LSC) orientation $\theta_0$. The probability distribution of $\theta_0$ is measured, and used to…
Electrons in graphene follow unconventional trajectories at PN junctions, driven by their pseudospintronic degree of freedom. Significant is the prominent angular dependence of transmission, capturing the chiral nature of the electrons and…
Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…
Temporal Graph Learning (TGL) is crucial for capturing the evolving nature of stock markets. Traditional methods often ignore the interplay between dynamic temporal changes and static relational structures between stocks. To address this…
We employ a linear stability analysis and direct numerical simulations to study the characteristics of wall-modes in thermal convection in a rectangular box under strong and inclined magnetic fields. The walls of the convection cell are…
Discrete symmetry-breaking phase transitions in the early universe may have caused the formation of networks of sheet-like topological defects, usually referred to as domain walls, which separate regions that have settled into different…
We define and study Conformal Turaev-Viro (CTV) theory, a dual formulation of Virasoro TQFT based on triangulating 3-manifolds with tetrahedra. Edges of the triangulation are labeled by continuous conformal weights, and tetrahedra are glued…
An iterated function system $\Phi$ consisting of contractive similarity mappings has a unique attractor $F \subseteq \mathbb{R}^d$ which is invariant under the action of the system, as was shown by Hutchinson [Hut]. This paper shows how the…
A simple, yet unifying method is provided for the construction of tilings by tiles obtained from the attractor of an iterated function system (IFS). Many examples appearing in the literature in ad hoc ways, as well as new examples, can be…
Three decades ago, Atick et al. suggested that human frequency sensitivity may emerge from the enhancement required for a more efficient analysis of retinal images. Here we reassess the relevance of low-level vision tasks in the explanation…
A longstanding puzzle of fundamental importance in modern cosmology has been the origin of the nearly universal density profiles of dark matter halos found in N-body simulations -- the so-called NFW profile. We show how this behavior may be…
The cross-sensor gap is one of the challenges that have aroused much research interests in Heterogeneous Face Recognition (HFR). Although recent methods have attempted to fill the gap with deep generative networks, most of them suffer from…