Related papers: A hybrid deep learning approach to vertexing
We present four different robust transfer learning and data augmentation strategies for robust mobile scene recognition. By training three mobile-ready (EfficientNetB0, MobileNetV2, MobileNetV3) and two large-scale baseline (VGG16,…
Self-driving vehicles have the potential to reduce accidents and fatalities on the road. Many production vehicles already come equipped with basic self-driving capabilities, but have trouble following lanes in adverse lighting and weather…
The single electron track-reconstruction efficiency is calibrated using a sample corresponding to $1.3~\mathrm{fb}^{-1}$of $pp$ collision data recorded with the LHCb detector in 2017. This measurement exploits $B^+\to J/\psi (e^+e^-)K^+$…
Vehicle tracking is an integral part of intelligent traffic management systems. Previous implementations of vehicle tracking used Global Positioning System(GPS) based systems that gave location of the vehicle of an individual on their…
Deep learning inference that needs to largely take place on the 'edge' is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications.…
The purpose of this work is to examine the application of a deep learning model in event reconstruction of neutrino interactions. The challenges faced in event reconstruction include the placement of an accurate primary neutrino interaction…
Deep image hashing aims to map input images into simple binary hash codes via deep neural networks and thus enable effective large-scale image retrieval. Recently, hybrid networks that combine convolution and Transformer have achieved…
We present scalable hybrid-parallel algorithms for training large-scale 3D convolutional neural networks. Deep learning-based emerging scientific workflows often require model training with large, high-dimensional samples, which can make…
This project aims to develop a robust video surveillance system, which can segment videos into smaller clips based on the detection of activities. It uses CCTV footage, for example, to record only major events-like the appearance of a…
The growing luminosity frontier at the Large Hadron Collider is challenging the reconstruction and analysis of particle collision events. Increased particle multiplicities are straining latency and storage requirements at the data…
The LHCb experiment is designed to perform high-precision measurements of CP violation and search for New Physics using the enormous flux involving beauty and charm quarks produced at the LHC. The operation and the results obtained from the…
The LHCb experiment at the Large Hadron Collider (LHC) is designed to perform high-precision measurements of heavy-hadron decays, which requires the collection of large data samples and a good understanding and suppression of multiple…
The Vertex Locator (VELO) is a silicon microstrip detector that surrounds the proton-proton interaction region in the LHCb experiment. The performance of the detector during the first years of its physics operation is reviewed. The system…
Visual perception tasks often require vast amounts of labelled data, including 3D poses and image space segmentation masks. The process of creating such training data sets can prove difficult or time-intensive to scale up to efficacy for…
The empirical success of deep convolutional networks on tasks involving high-dimensional data such as images or audio suggests that they can efficiently approximate certain functions that are well-suited for such tasks. In this paper, we…
Self-driving vehicles and autonomous ground robots require a reliable and accurate method to analyze the traversability of the surrounding environment for safe navigation. This paper proposes and evaluates a real-time machine learning-based…
We propose a novel algorithm for accelerating dense long-term 3D point tracking in videos. Through analysis of existing state-of-the-art methods, we identify two major computational bottlenecks. First, transformer-based iterative tracking…
The PHOBOS experiment at the Relativistic Heavy Ion Collider (RHIC) at Brookhaven National Laboratory is studying interactions of heavy nuclei at the largest energies available in the laboratory. The high multiplicity of particles created…
ATLAS has developed a new approach for vertex selection in VBF invisible events at HL-LHC conditions, exploiting its new forward tracking capabilities, integrating calorimeter and tracking information to mitigate the impact of pileup vertex…
With the LHC successfully collecting data at 7 TeV, plans are actively advancing for a series of upgrades leading eventually to about five times the LHC design-luminosity some 10-years from now in the High-Luminosity LHC (HL-LHC) project.…