Related papers: Corrigendum to "Random grid-based visual secret sh…
An Extended Visual Cryptography Scheme (EVCS) was proposed by Ateniese et al. [3] to protect a binary secret image with meaningful (innocent-looking) shares. This is implemented by concatenating an extended matrix to each basis matrix. The…
Deep visual Simultaneous Localization and Mapping (SLAM) techniques, e.g., DROID, have made significant advancements by leveraging deep visual odometry on dense flow fields. In general, they heavily rely on global visual similarity…
Contrastive learning has proven to be highly efficient and adaptable in shaping representation spaces across diverse modalities by pulling similar samples together and pushing dissimilar ones apart. However, two key limitations persist: (1)…
Image steganography is a technique of hiding secret information inside another image, so that the secret is not visible to human eyes and can be recovered when needed. Most of the existing image steganography methods have low hiding…
Contrast is a crucial factor in visual information processing. It is desired for a visual system - irrespective of being biological or artificial - to "perceive" the world robustly under large potential changes in illumination. In this…
Exoplanet imaging is a major challenge in astrophysics due to the need for high angular resolution and high contrast. We present a multi-scale statistical model for the nuisance component corrupting multivariate image series at high…
Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this paper, we discover that a high-quality visual saliency model can be learned from multiscale features extracted using…
This paper presents a randomized quaternion singular value decomposition (QSVD) algorithm for low-rank matrix approximation problems, which are widely used in color face recognition, video compression, and signal processing problems. With…
Accurate and robust image-based geo-localization at a global scale is challenging due to diverse environments, visually ambiguous scenes, and the lack of distinctive landmarks in many regions. While contrastive learning methods show…
Deep learning techniques have achieved great success in remote sensing image change detection. Most of them are supervised techniques, which usually require large amounts of training data and are limited to a particular application.…
The reversed and shift (RAS) sparse array scheme, which is based on the difference and sum co-array (DSCA) and remarkably enhances the capability of identifying sources, is proposed. For the original nested array (NA) or co-prime array…
We present a new approach to obtaining photometric redshifts using a kernel learning technique called Support Vector Machines (SVMs). Unlike traditional spectral energy distribution fitting, this technique requires a large and…
Despite the success of a number of recent techniques for visual self-supervised deep learning, there has been limited investigation into the representations that are ultimately learned. By leveraging recent advances in the comparison of…
This article presents the numerical verification and validation of several inversion algorithms for V-line transforms (VLTs) acting on symmetric 2-tensor fields in the plane. The analysis of these transforms and the theoretical foundation…
This paper offers a mini review of Visual Word Sense Disambiguation (VWSD), which is a multimodal extension of traditional Word Sense Disambiguation (WSD). VWSD helps tackle lexical ambiguity in vision-language tasks. While conventional WSD…
We consider the estimation distortion of a distributed sensing system with finite number of sensor nodes, in which the nodes observe a common phenomenon and transmit their observations to a fusion center over orthogonal channels. In…
An access structure specifying the qualified sets of a secret sharing scheme must have information rate less than or equal to one. The Vamos matroid induces two non-isomorphic access structures V1 and V6, which were shown by Marti-Farre and…
Despite their output being ultimately consumed by human viewers, 3D Gaussian Splatting (3DGS) methods often rely on ad-hoc combinations of pixel-level losses, resulting in blurry renderings. To address this, we systematically explore…
Automated detection of vulnerabilities in source code is an essential cybersecurity challenge, underpinning trust in digital systems and services. Graph Neural Networks (GNNs) have emerged as a promising approach as they can learn…
Models for Visual Question Answering (VQA) often rely on the spurious correlations, i.e., the language priors, that appear in the biased samples of training set, which make them brittle against the out-of-distribution (OOD) test data.…