Related papers: Heterogeneous Point Set Transformers for Segmentat…
The well-established neutrino oscillation phenomenon, which confirms neutrinos have mass and the charged and neutral leptons are mixed, has been widely exploited to investigate the physics of this elusive particle. The complete description…
In many real-world applications, deployed models encounter inputs that differ from the data seen during training. Out-of-distribution detection identifies whether an input stems from an unseen distribution, while open-world recognition…
The human visual system processes images with varied degrees of resolution, with the fovea, a small portion of the retina, capturing the highest acuity region, which gradually declines toward the field of view's periphery. However, the…
Attention mechanisms are becoming increasingly popular, being used in neural network models in multiple domains such as natural language processing (NLP) and vision applications, especially at the edge. However, attention layers are…
Powerful new multi-kiloton liquid scintillator neutrino detectors, including NOvA and LENA, will come on-line within the next decade. When these are coupled with a modest-power decay-at-rest (DAR) neutrino source at short-baseline, these…
Proteins are made of atoms constantly fluctuating, but can occasionally undergo large-scale changes. Such transitions are of biological interest, linking the structure of a protein to its function with a cell. Atomic-level simulations, such…
The NuMI Off-Axis $\nu_{e}$ Appearance (NO$\nu$A) is the currently running leading long-baseline neutrino oscillation experiment, whose main physics goal is to explore the current issues in the neutrino sector, such as determination of the…
Neutrino cross sections are a critical ingredient in experiments that depend on neutrino scattering to reconstruct event kinematics and infer neutrino characteristics, like NOvA and T2K. An opportunity exists to reduce the 5-10% broad…
In neutrino experiments, neutrino energy reconstruction is crucial because neutrino oscillations and differential cross-sections are functions of neutrino energy. It is also challenging due to the complexity in the detector response and…
We propose a novel-view augmentation (NOVA) strategy to train NeRFs for photo-realistic 3D composition of dynamic objects in a static scene. Compared to prior work, our framework significantly reduces blending artifacts when inserting…
ESA's PROBA-V Earth observation satellite enables us to monitor our planet at a large scale, studying the interaction between vegetation and climate and provides guidance for important decisions on our common global future. However, the…
A modern deep neural network (DNN) for image classification tasks typically consists of two parts: a backbone for feature extraction, and a head for feature encoding and class predication. We observe that the head structures of mainstream…
Applications in the Internet of Video Things (IoVT) domain have very tight constraints with respect to power and area. While neuromorphic vision sensors (NVS) may offer advantages over traditional imagers in this domain, the existing NVS…
Now that the NOvA experiment is approaching two years run time and has released some preliminary data, some constraints for the oscillation parameters can be inferred. Currently the best fits for NOvA are three separate results, the reason…
We present a deep learning approach for vertex reconstruction of neutrino-nucleus interaction events, a problem in the domain of high energy physics. In this approach, we combine both energy and timing data that are collected in the MINERvA…
NO$\nu$A is an accelerator-based neutrino oscillation experiment which has a great potential to measure the last unknown mixing angle $\theta_{13}$, the neutrino mass hierarchy, and the CP-violation phase in lepton sector with 1) 700 kW…
Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending…
Although deep convolutional networks have been widely studied for head and neck (HN) organs at risk (OAR) segmentation, their use for routine clinical treatment planning is limited by a lack of robustness to imaging artifacts, low soft…
Charged-current anti-neutrino interactions on hydrocarbon scintillator in the MINERvA detector are used to study activity from their final-state neutrons. To ensure that most of the neutrons are from the primary interaction, rather than…
The MINERvA collaboration is currently engaged in a broad program of neutrino-nucleus interaction measurements. Several recent measurements of interest to the accelerator-based oscillation community are presented. These include measurements…