English
Related papers

Related papers: Deep Image Reconstruction for Background Subtracti…

200 papers

One of the greatest impediments to extracting useful information from high luminosity hadron-collider data is radiation from secondary collisions (i.e. pileup) which can overlap with that of the primary interaction. In this paper we…

High Energy Physics - Phenomenology · Physics 2014-10-03 David Krohn , Matthew Low , Matthew D. Schwartz , Lian-Tao Wang

The theoretical interpretation of jet observables in heavy-ion collisions is a complex task due to the intricate interplay of perturbative and non-perturbative effects. One way to reduce this complexity is to groom away soft, wide-angle…

High Energy Physics - Phenomenology · Physics 2026-01-21 Liliana Apolinário , Diogo Costa , Alba Soto-Ontoso

Deep reinforcement learning has achieved great success in laser-based collision avoidance work because the laser can sense accurate depth information without too much redundant data, which can maintain the robustness of the algorithm when…

Robotics · Computer Science 2021-08-24 Lingping Gao , Jianchuan Ding , Wenxi Liu , Haiyin Piao , Yuxin Wang , Xin Yang , Baocai Yin

Recent literature on deep neural networks for tagging of highly energetic jets resulting from top quark decays has focused on image based techniques or multivariate approaches using high-level jet substructure variables. Here, a sequential…

High Energy Physics - Experiment · Physics 2017-08-10 Jannicke Pearkes , Wojciech Fedorko , Alison Lister , Colin Gay

In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and quality in…

Image and Video Processing · Electrical Eng. & Systems 2024-09-18 Ryugo Morita , Hitoshi Nishimura , Ko Watanabe , Andreas Dengel , Jinjia Zhou

The development of fast and accurate image reconstruction algorithms is a central aspect of computed tomography. In this paper, we investigate this issue for the sparse data problem in photoacoustic tomography (PAT). We develop a direct and…

Computer Vision and Pattern Recognition · Computer Science 2018-08-31 Stephan Antholzer , Markus Haltmeier , Johannes Schwab

\textsc{Jewel} is a fully dynamical event generator for jet evolution in a dense QCD medium, which has been validated for multiple jet and jet-like observables. Jet constituents (partons) undergo collisions with thermal partons from the…

Nuclear Theory · Physics 2016-12-16 Raghav Kunnawalkam Elayavalli , Korinna Christine Zapp

Subtraction of the large background in reconstruction is a key ingredient in jet studies in high-energy heavy-ion collisions at RHIC and the LHC. Here we address the question to which extent the most commonly used subtraction techniques are…

High Energy Physics - Phenomenology · Physics 2015-06-12 Liliana Apolinário , Néstor Armesto , Leticia Cunqueiro

In this work, we present a novel background subtraction system that uses a deep Convolutional Neural Network (CNN) to perform the segmentation. With this approach, feature engineering and parameter tuning become unnecessary since the…

Computer Vision and Pattern Recognition · Computer Science 2017-02-07 Mohammadreza Babaee , Duc Tung Dinh , Gerhard Rigoll

Low-energy strong interactions are a major source of background at hadron colliders, and methods of subtracting the associated energy flow are well established in the field. Traditional approaches treat the contamination as diffuse, and…

Data Analysis, Statistics and Probability · Physics 2014-12-22 Federico Colecchia

In a recent study [1] we have extended the opacity expansion approach to describe jet-medium interactions including medium motion effects in the context of heavy-ion collisions. We have computed color field of the in-medium sources,…

High Energy Physics - Phenomenology · Physics 2022-07-19 Andrey V. Sadofyev , Matthew D. Sievert , Ivan Vitev

Based on a pQCD inspired dynamical model of jet-medium interactions, Jewel, we have studied possible modifications to inclusive jet yields and a set of jet shape observables, namely, the fragmentation functions and radial momentum…

High Energy Physics - Phenomenology · Physics 2019-07-25 Rathijit Biswas , Subikash Choudhury , Sidharth Kumar Prasad , Supriya Das

An approach to incorporate deep learning within an iterative image reconstruction framework to reconstruct images from severely incomplete measurement data is presented. Specifically, we utilize a convolutional neural network (CNN) as a…

Computer Vision and Pattern Recognition · Computer Science 2017-09-05 Brendan Kelly , Thomas P. Matthews , Mark A. Anastasio

The dense medium created in Au + Au collisions at the Relativistic Heavy-Ion Collider (RHIC) significantly suppresses particle production from hard scattering processes and their characteristic back-to-back angular correlation. We present a…

Nuclear Theory · Physics 2008-11-26 Axel Drees , Haidong Feng , Jiangyong Jia

The structure of heavy nuclei is difficult to disentangle in high-energy heavy-ion collisions. The deep convolution neural network (DCNN) might be helpful in mapping the complex final states of heavy-ion collisions to the nuclear structure…

Nuclear Theory · Physics 2019-06-26 Long-Gang Pang , Kai Zhou , Xin-Nian Wang

Jet substructure in heavy-ion collisions is a rapidly evolving area with lots of intriguing new measurements. This contribution presents a selection of recent jet-substructure measurements from experiments at the LHC, in particular,…

Nuclear Experiment · Physics 2024-10-08 Robert Vertesi

Observables from nuclear and high-energy experiments can be degraded by detector performance and/or methodology in extracting the observables, such as of the final-state characteristics of heavy-ion collisions in relation to a coarsely…

Nuclear Theory · Physics 2022-03-14 Pawel Danielewicz , Mizuki Kurata-Nishimura

The challenges in recovering underwater images are the presence of diverse degradation factors and the lack of ground truth images. Although synthetic underwater image pairs can be used to overcome the problem of inadequately observing…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Zhenwei Zhang , Haorui Yan , Ke Tang , Yuping Duan

We propose new methodologies in multi-dimensional unfolding in dense environments, and show that incorporating auxiliary observables can significantly improve performance. Our approach builds on the ML-based OmniFold algorithm, which we…

High Energy Physics - Phenomenology · Physics 2025-07-10 Alexandre Falcão , Adam Takacs

Full jet reconstruction in heavy-ion collisions enables a complete study of the modification of jet structure due to energy loss in hot and dense QCD matter, but is challenging due to the high multiplicity environment. The STAR and PHENIX…

Nuclear Experiment · Physics 2009-11-26 Jan Kapitan