Related papers: Analytic model for feature maps in the primary vis…
Mobile robots require comprehensive scene understanding to operate effectively in diverse environments, enriched with contextual information such as layouts, objects, and their relationships. Although advances like neural radiation fields…
LLM-based agents have demonstrated impressive zero-shot performance in vision-language navigation (VLN) task. However, existing LLM-based methods often focus only on solving high-level task planning by selecting nodes in predefined…
This paper gives an in-depth theoretical analysis of the direction and speed selectivity properties of idealized models of the spatio-temporal receptive fields of simple cells and complex cells, based on the generalized Gaussian derivative…
Orientation learning plays a pivotal role in many tasks. However, the rotation group SO(3) is a Riemannian manifold. As a result, the distortion caused by non-Euclidean geometric nature introduces difficulties to the incorporation of local…
Spin-lattice relaxation time ($T_1$) is an important biomarker in cardiac parametric mapping for characterizing myocardial tissue and diagnosing cardiomyopathies. Conventional Modified Look-Locker Inversion Recovery (MOLLI) acquires 11…
We continue our study of operator algebras with contractive approximate identities (cais) by presenting a couple of interesting examples of operator algebras with cais, which in particular answer questions raised in previous papers in this…
When it comes to the optimization of CAD models in the automation domain, neural networks currently play only a minor role. Optimizing abstract features such as automation capability is challenging, since they can be very difficult to…
In this article we discuss the convergence of first order operators on a thickened graph (a graph-like space) towards a similar operator on the underlying metric graph. On the graph-like space, the first order operator is of the form…
We introduce Adaptive Functional Principal Component Analysis, a novel method to capture directions of variation in functional data that exhibit sharp changes in smoothness. We first propose a new adaptive scatterplot smoothing technique…
Self-Organizing Map (SOM) is a neural network model which is used to obtain a topology-preserving mapping from the (usually high dimensional) input/feature space to an output/map space of fewer dimensions (usually two or three in order to…
Graph-based representations play a key role in machine learning. The fundamental step in these representations is the association of a graph structure to a dataset. In this paper, we propose a method that aims at finding a block sparse…
By means of hypercyclic operator theory, we complement our previous results on hypercyclic holomorphic maps between complex Euclidean spaces having slow growth rates,by showing {\it abstract abundance} rather than {\it explicit existence}.…
Accurate 3D perception is essential for understanding the environment in autonomous driving. Recent advancements in 3D semantic occupancy prediction have leveraged camera-LiDAR fusion to improve robustness and accuracy. However, current…
Grid maps, especially occupancy grid maps, are ubiquitous in many mobile robot applications. To simplify the process of learning the map, grid maps subdivide the world into a grid of cells whose occupancies are independently estimated using…
Anterior Segment Optical Coherence Tomography (AS-OCT) is an emerging imaging technique with great potential for diagnosing anterior uveitis, a vision-threatening ocular inflammatory condition. A hallmark of this condition is the presence…
This paper presents results of combining (i) theoretical analysis regarding connections between the orientation selectivity and the elongation of receptive fields for the affine Gaussian derivative model with (ii) biological measurements of…
Manually specifying features that capture the diversity in traffic environments is impractical. Consequently, learning-based agents cannot realize their full potential as neural motion planners for autonomous vehicles. Instead, this work…
Three dimensional Polarized Light Imaging (3D-PLI) is an optical technique which allows mapping the spatial fiber architecture of fibrous postmortem tissues, at sub-millimeter resolutions. Here, we propose an analytical and fast approach to…
Vision-Language Pre-training (VLP) models like CLIP have achieved remarkable success in computer vision and particularly demonstrated superior robustness to distribution shifts of 2D images. However, their robustness under 3D viewpoint…
Weakly supervised object localization (WSOL) aims at predicting object locations in an image using only image-level category labels. Common challenges that image classification models encounter when localizing objects are, (a) they tend to…