Related papers: SDA-SNE: Spatial Discontinuity-Aware Surface Norma…
Multi-head self-attention (MSA) is a key component of Vision Transformers (ViTs), which have achieved great success in various vision tasks. However, their high computational cost and memory footprint hinder their deployment on…
In various applications, the multivariate time series often suffers from missing data. This issue can significantly disrupt systems that rely on the data. Spatial and temporal dependencies can be leveraged to impute the missing samples.…
Presenting a 3D scene from multiview images remains a core and long-standing challenge in computer vision and computer graphics. Two main requirements lie in rendering and reconstruction. Notably, SOTA rendering quality is usually achieved…
In this paper, we propose a novel deep architecture tailored for 3D point cloud applications, named as SPE-Net. The embedded ``Selective Position Encoding (SPE)'' procedure relies on an attention mechanism that can effectively attend to the…
Proximal gradient algorithms (PGA), while foundational for inverse problems like image reconstruction, often yield unstable convergence and suboptimal solutions by violating the critical non-negativity constraint. We identify the gradient…
Data assimilation addresses the problem of identifying plausible state trajectories of dynamical systems given noisy or incomplete observations. In geosciences, it presents challenges due to the high-dimensionality of geophysical dynamical…
Enterprise Networks, over the years, have become more and more complex trying to keep up with new requirements that challenge traditional solutions. Just to mention one out of many possible examples, technologies such as Virtual LANs…
Semantic segmentation plays an important role in intelligent vehicles, providing pixel-level semantic information about the environment. However, the labeling budget is expensive and time-consuming when semantic segmentation model is…
Recent advances in deep learning-based medical image segmentation studies achieve nearly human-level performance in fully supervised manner. However, acquiring pixel-level expert annotations is extremely expensive and laborious in medical…
This paper proposes a Spatially-Augmented Sequence-to-Sequence Neural Diarization (SA-S2SND) framework, which integrates direction-of-arrival (DOA) cues estimated by SRP-DNN into the S2SND backbone. A two-stage training strategy is adopted:…
Self-supervised depth estimation has drawn much attention in recent years as it does not require labeled data but image sequences. Moreover, it can be conveniently used in various applications, such as autonomous driving, robotics,…
How to improve generative modeling by better exploiting spatial regularities and coherence in images? We introduce a novel neural network for building image generators (decoders) and apply it to variational autoencoders (VAEs). In our…
RDMA is vital for efficient distributed training across datacenters, but millisecond-scale latencies complicate the design of its reliability layer. We show that depending on long-haul link characteristics, such as drop rate, distance and…
Semi-supervised domain adaptation (SSDA) aims to bridge source and target domain distributions, with a small number of target labels available, achieving better classification performance than unsupervised domain adaptation (UDA). However,…
Direction-of-Arrival (DOA) estimation in sensor arrays faces limitations under demanding conditions, including low signal-to-noise ratio, single-snapshot scenarios, coherent sources, and unknown source counts. Conventional beamforming…
Due to its robust and precise distance measurements, LiDAR plays an important role in scene understanding for autonomous driving. Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotations, which are…
Due to the difficulty in obtaining real samples and ground truth, the generalization performance and domain adaptation performance are critical for the feasibility of stereo matching methods in practical applications. However, there are…
Object detection is essential in space applications targeting Space Domain Awareness and also applications involving relative navigation scenarios. Current deep learning models for Object Detection in space applications are often trained on…
Children possess the ability to learn multiple cognitive tasks sequentially, which is a major challenge toward the long-term goal of artificial general intelligence. Existing continual learning frameworks are usually applicable to Deep…
Background: The generation of potential energy surfaces is a critical step in theoretical models aiming to understand and predict nuclear fission. Discontinuities frequently arise in these surfaces in unconstrained collective coordinates,…