Related papers: Acquisition system for the CLIC Module
The integration of vision-language models such as CLIP and Concept Bottleneck Models (CBMs) offers a promising approach to explaining deep neural network (DNN) decisions using concepts understandable by humans, addressing the black-box…
Vision-Language Models (VLMs) like CLIP struggle to understand negation, often embedding affirmatives and negatives similarly (e.g., matching "no dog" with dog images). Existing methods refine negation understanding via fine-tuning CLIP's…
The CLIC study of a high-energy (0.5 - 5 TeV), high-luminosity (1034 - 1035 cm-2 sec-1) e+e- linear collider is presented. Beam acceleration using high frequency (30 GHz) normal-conducting structures operating at high accelerating fields…
On a very fundamental level, particle detectors share similar requirements for their read-out chain. This is reflected in the way that typical read-out solutions are developed, where a previous design is taken and modified to fit some…
The CLIC Tracker Detector (CLICTD) is a monolithic pixelated sensor chip produced in a $180$ nm imaging CMOS process built on a high-resistivity epitaxial layer. The chip, designed in the context of the CLIC tracking detector study,…
Contrastive Language-Image Pre-training (CLIP) has achieved widely applications in various computer vision tasks, e.g., text-to-image generation, Image-Text retrieval and Image captioning. However, CLIP suffers from high memory and…
The popularity of low-voltage ac distribution networks is increasing day by day. However, an efficient protection scheme for low-voltage ac distribution systems is still challenging. This paper introduces a protection scheme suitable for…
Tailoring critical light-matter coupling is a fundamental challenge of nanophotonics, impacting diverse fields from higher harmonic generation and energy conversion to surface-enhanced spectroscopy. Plasmonic perfect absorbers (PAs), where…
The goal of the EUDET project is the development and construction of infrastructure to permit detector R&D for the International Linear Collider (ILC) with larger scale prototypes. It encompasses major detector components: the vertex…
Machine learning interatomic potentials (MLIPs) have become widely used tools in atomistic simulations. For much of the history of this field, the most commonly employed architectures were based on short-ranged atomic energy contributions,…
The retail sector presents several open and challenging problems that could benefit from advanced pattern recognition and computer vision techniques. One such critical challenge is planogram compliance control. In this study, we propose a…
Current Scene text image super-resolution approaches primarily focus on extracting robust features, acquiring text information, and complex training strategies to generate super-resolution images. However, the upsampling module, which is…
Modeling in Computer Vision has evolved to MLPs. Vision MLPs naturally lack local modeling capability, to which the simplest treatment is combined with convolutional layers. Convolution, famous for its sliding window scheme, also suffers…
In this paper, a plasmonic absorber consisting of a metal-dielectric-metal stack with a top layer of Sierpinski nanocarpet is theoretically investigated. Such compact absorber depicts broadband angle-independent behavior over a wide optical…
This paper reports the latest developmental efforts for a position-sensitive glass-based Resistive Plate Chamber (RPC) and a multi-channel Data AcQuisition (DAQ) system tailored for muon tracking in muography applications. The designed…
This paper presents a novel setup for automatic visual inspection of cracks in ceramic tile as well as studies the effect of various classifiers and height-varying illumination conditions for this task. The intuition behind this setup is…
A new generation of Resistive Plate Chambers have been developed for the ATLAS phase-2 upgrade in sight of the High-Luminosity phase of the Large Hadron Collider. These RPCs consist of three independent 1 mm gas gaps(singlets) equipped with…
Robot grasping of desktop object is widely used in intelligent manufacturing, logistics, and agriculture.Although vision-language models (VLMs) show strong potential for robotic manipulation, their deployment in low-level grasping faces key…
In multimodal learning, CLIP has emerged as the de-facto approach for mapping different modalities into a shared latent space by bringing semantically similar representations closer while pushing apart dissimilar ones. However, CLIP-based…
Capture stages are high-end sources of state-of-the-art recordings for downstream applications in movies, games, and other media. One crucial step in almost all pipelines is matting, i.e., separating captured performances from the…