相关论文: Online Pattern Recognition for the ALICE High Leve…

Physics collisions at 13 TeV are expected at the LHC with an average of 40-50 proton-proton collisions per bunch crossing under nominal conditions. Tracking at trigger level is an essential tool to control the rate in high-pileup conditions…

The ALICE collaboration measured charged particle production in $\sqrt{s_{NN}}=2.76$ TeV Pb--Pb collisions at the LHC. We report on results on charged particle multiplicity and transverse momentum spectra. All the results are presented as a…

To address the challenges of table structure recognition, we propose a novel Split-Merge-based top-down model optimized for large, densely populated tables. Our approach formulates row and column splitting as sequence labeling tasks,…

The Transition Radiation Detector (TRD) provides particle identification in the ALICE central barrel. In particular, it allows electron identification via the measurement of transition radiation for $\rm p >$ 1 GeV/$c$, where pions can no…

Contrastive Learning (CL) has attracted enormous attention due to its remarkable capability in unsupervised representation learning. However, recent works have revealed the vulnerability of CL to backdoor attacks: the feature extractor…

Angular correlations of two and more particles are a sensitive probe of the initial state and the transport properties of the system produced in heavy-ion collisions. Two recent results of the ALICE collaboration are presented. Event-shape…

The ALICE experiment features multiple particle identification systems. The measurement of the identified charged hadron $p_{t}$ spectra in proton-proton collisions at $\sqrt{s}=900$ GeV will be discussed. In the central rapidity region…

Concurrent Constraint Programming (CCP) is a declarative model for concurrency where agents interact by telling and asking constraints (pieces of information) in a shared store. Some previous works have developed (approximated) declarative…

The CYGNO experiment employs an optical-readout Time Projection Chamber (TPC) to search for rare low-energy interactions using finely resolved scintillation images. While the optical readout provides rich topological information, it…

Jet flavour identification algorithms are of paramount importance to maximise the physics potential of future collider experiments. This work describes a novel set of tools allowing for a realistic simulation and reconstruction of particle…

Tracking multiple particles in noisy and cluttered scenes remains challenging due to a combinatorial explosion of trajectory hypotheses, which scales super-exponentially with the number of particles and frames. The transformer architecture…

In online multi-target tracking, modeling of appearance and geometric similarities between pedestrians visual scenes is of great importance. The higher dimension of inherent information in the appearance model compared to the geometric…

The Transition Radiation Detector (TRD) for the ALICE experiment at the Large Hadron Collider (LHC) identifies electrons in p+p and in the challenging high multiplicity environment of heavy-ion collisions and provides fast online tracking…

Combinatorial inverse problems in high energy physics span enormous algorithmic challenges. This work presents a new deep learning driven clustering algorithm that utilizes a space-time non-local trainable graph constructor, a graph neural…

Subspace clustering refers to the problem of clustering high-dimensional data into a union of low-dimensional subspaces. Current subspace clustering approaches are usually based on a two-stage framework. In the first stage, an affinity…

This paper proposes to perform online clustering by conducting twin contrastive learning (TCL) at the instance and cluster level. Specifically, we find that when the data is projected into a feature space with a dimensionality of the target…

Modern data acquisition routinely produces massive amounts of network data. Though many methods and models have been proposed to analyze such data, the research of network data is largely disconnected with the classical theory of…

Many observables which are used as a signature of the collective effects in heavy-ion collisions when measured in high multiplicity pp and pA interactions reveal a very similar behaviour. We will present first measurements of different…

Deep neural networks have achieved strong performance in image classification tasks due to their ability to learn complex patterns from high-dimensional data. However, their large computational and memory requirements often limit deployment…

Process discovery algorithms automatically extract process models from event logs, but high variability often results in complex and hard-to-understand models. To mitigate this issue, trace clustering techniques group process executions…