相关论文: Corrigendum to "Random grid-based visual secret sh…
Recently, Guidorzi et al. (2005) expanded the size of the sample of GRBs for which variabilities and peak luminosities have been measured, from 11 to 32. They confirm the existence of a correlation, but find a dramatically different…
Accurate camera pose estimation result is essential for visual SLAM (VSLAM). This paper presents a novel pose correction method to improve the accuracy of the VSLAM system. Firstly, the relationship between the camera pose estimation error…
Unlike many urban localization methods that return point-valued estimates, a set-valued representation enables robustness by ensuring that a continuum of possible positions obeys safety constraints. One strategy with the potential for…
In out-of-distribution (OOD) detection, one is asked to classify whether a test sample comes from a known inlier distribution or not. We focus on the case where the inlier distribution is defined by a training dataset and there exists no…
A ($t$, $n$) threshold quantum secret sharing (QSS) is proposed based on a single $d$-level quantum system. It enables the ($t$, $n$) threshold structure based on Shamir's secret sharing and simply requires sequential communication in…
Contrastive learning relies on an assumption that positive pairs contain related views, e.g., patches of an image or co-occurring multimodal signals of a video, that share certain underlying information about an instance. But what if this…
The unparalleled theoretical performance of an ideal vector vortex coronagraph makes it one of the most promising technologies for directly imaging exoplanets with a future, off-axis space telescope. However, the image contrast required for…
Visually sorted grid layouts provide an efficient method for organizing high-dimensional vectors in two-dimensional space by aligning spatial proximity with similarity relationships. This approach facilitates the effective sorting of…
Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases. Given the promising performance contrastive learning has shown recently in…
We compare the rms contrast in observed speckle reconstructed G-band images with synthetic filtergrams computed from two magneto-hydrodynamic simulation snapshots. The observations consist of 103 bursts of 80 frames each taken at the Dunn…
We introduce algorithms to visualize feature spaces used by object detectors. Our method works by inverting a visual feature back to multiple natural images. We found that these visualizations allow us to analyze object detection systems in…
Novel idea of hierarchical visual cryptography is stated in this paper. The key concept of hierarchical visual cryptography is based upon visual cryptography. Visual cryptography encrypts secret information into two pieces called as shares.…
Distribution matching is central to many vision and graphics tasks, where the widely used Wasserstein distance is too costly to compute for high dimensional distributions. The Sliced Wasserstein Distance (SWD) offers a scalable alternative,…
For two correlated graphs which are independently sub-sampled from a common Erd\H{o}s-R\'enyi graph $\mathbf{G}(n, p)$, we wish to recover their \emph{latent} vertex matching from the observation of these two graphs \emph{without labels}.…
In this work, we assess two widely used scissors-correction schemes for first-principles calculations of second-harmonic generation in representative borate and phosphate ultraviolet nonlinear-optical (UV-NLO) crystals, namely scheme-L…
Vision-language models (VLMs) such as CLIP have demonstrated remarkable zero-shot generalization, yet remain highly vulnerable to adversarial examples (AEs). While test-time defenses are promising, existing methods fail to provide…
In this paper, we propose a novel high dimensional constellation design scheme for visible light communication (VLC) systems employing red/green/blue light emitting diodes (RGB LEDs). It is in fact a generalized color shift keying (CSK)…
High-dimensional and complex spectral structures make the clustering of hyperspectral images (HSI) a challenging task. Subspace clustering is an effective approach for addressing this problem. However, current subspace clustering algorithms…
Stereo matching estimates the disparity between a rectified image pair, which is of great importance to depth sensing, autonomous driving, and other related tasks. Previous works built cost volumes with cross-correlation or concatenation of…
Recently, a novel image encryption scheme based on improved hyperchaotic sequences was proposed. A pseudo-random number sequence, generated by a hyper-chaos system, is used to determine two involved encryption functions, bitwise exclusive…