Related papers: PLEIADES: Building Temporal Kernels with Orthogona…

We present a simple, yet effective, approach for self-supervised 3D human pose estimation. Unlike the prior work, we explore the temporal information next to the multi-view self-supervision. During training, we rely on triangulating 2D body…

A data-driven framework is proposed towards the end of predictive modeling of complex spatio-temporal dynamics, leveraging nested non-linear manifolds. Three levels of neural networks are used, with the goal of predicting the future state…

Quantifying predictive uncertainty of deep semantic segmentation networks is essential in safety-critical tasks. In applications like autonomous driving, where video data is available, convolutional long short-term memory networks are…

As deep learning continues to be driven by ever-larger datasets, understanding which examples are most important for generalization has become a critical question. While progress in data selection continues, emerging applications require…

Temporal heterogeneous networks (THNs) are evolving networks that characterize many real-world applications such as citation and events networks, recommender systems, and knowledge graphs. Although different Graph Neural Networks (GNNs)…

Deep generative models are rapidly gaining traction in medical imaging. Nonetheless, most generative architectures struggle to capture the underlying probability distributions of volumetric data, exhibit convergence problems, and offer no…

Systems of interacting particles or agents have wide applications in many disciplines such as Physics, Chemistry, Biology and Economics. These systems are governed by interaction laws, which are often unknown: estimating them from…

As the demand for enabling high-level autonomous driving has increased in recent years and visual perception is one of the critical features to enable fully autonomous driving, in this paper, we introduce an efficient approach for…

Approximations based on random Fourier features have recently emerged as an efficient and formally consistent methodology to design large-scale kernel machines. By expressing the kernel as a Fourier expansion, features are generated based…

One of the main factors that contributed to the large advances in autonomous driving is the advent of deep learning. For safer self-driving vehicles, one of the problems that has yet to be solved completely is lane detection. Since methods…

Semantic segmentation is a key technology for autonomous vehicles to understand the surrounding scenes. The appealing performances of contemporary models usually come at the expense of heavy computations and lengthy inference time, which is…

3D Convolution Neural Networks (CNNs) have been widely applied to 3D scene understanding, such as video analysis and volumetric image recognition. However, 3D networks can easily lead to over-parameterization which incurs expensive…

Multi-scale learning frameworks have been regarded as a capable class of models to boost semantic segmentation. The problem nevertheless is not trivial especially for the real-world deployments, which often demand high efficiency in…

Spatial self-attention layers, in the form of Non-Local blocks, introduce long-range dependencies in Convolutional Neural Networks by computing pairwise similarities among all possible positions. Such pairwise functions underpin the…

A surrogate model approximates the outputs of a solver of Partial Differential Equations (PDEs) with a low computational cost. In this article, we propose a method to build learning-based surrogates in the context of parameterized PDEs,…

State-of-the-art machine-learning methods for event cameras treat events as dense representations and process them with conventional deep neural networks. Thus, they fail to maintain the sparsity and asynchronous nature of event data,…

Event detection in time series is a challenging task due to the prevalence of imbalanced datasets, rare events, and time interval-defined events. Traditional supervised deep learning methods primarily employ binary classification, where…

We introduce a foundation model for event classification in high-energy physics, built on a Graph Neural Network architecture and trained on 120 million simulated proton-proton collision events spanning 12 distinct physics processes. The…

The separation of overlapping objects presents a significant challenge in scientific imaging. While deep learning segmentation-regression algorithms can predict pixel-wise intensities, they typically treat all regions equally rather than…

In recent years, deep learning (DL) approaches have demonstrated promising results in decoding hemodynamic responses captured by functional near-infrared spectroscopy (fNIRS), particularly in the context of brain-computer interface (BCI)…