Sorry, you need to enable JavaScript to visit this website.

We propose sandwiched video compression – a video compression
system that wraps neural networks around a standard video codec.
The sandwich framework consists of a neural pre- and post-processor
with a standard video codec between them. The networks are trained
jointly to optimize a rate-distortion loss function with the goal of significantly improving over the standard codec in various compression
scenarios. End-to-end training in this setting requires a differentiable
proxy for the standard video codec, which incorporates temporal

The importance of document digitization has increased due to recent technological advancements, including in the medical field. Digitization of medical records plays a vital role in the healthcare sector as it helps expedite emergency treatment. Due to the scarcity of published studies and public German textual resources, a medical records database with German handwriting was collected and digitized.

Most deep learning pipelines are built on real-valued operations to deal with real-valued inputs such as images, speech or music signals. However, a lot of applications naturally make use of complex-valued signals or images, such as MRI or remote sensing. Additionally the Fourier transform of signals is complex-valued and has numerous applications. We aim to make deep learning directly applicable to these complex-valued signals without using projections into R2 .

Seizure detection using machine learning is a critical problem for the timely intervention and management of epilepsy. We propose SeizFt, a robust seizure detection framework using EEG from a wearable device. It uses features paired with an ensemble of trees, thus enabling further interpretation of the model's results. The efficacy of the underlying augmentation and class-balancing strategy is also demonstrated. This study was performed for the Seizure Detection Challenge 2023, an ICASSP Grand Challenge.

The development of semi-supervised learning (SSL) has in recent years largely focused on the development of new consistency regularization or entropy minimization approaches, often resulting in models with complex training strategies to obtain the desired results. In this work, we instead propose a novel approach that explicitly incorporates the underlying clustering assumption in SSL through extending a recently proposed differentiable clustering module. Leveraging annotated data to guide the cluster centroids results in a simple end-to-end trainable deep SSL approach.

We propose a throughput-optimal biased backpressure (BP) algorithm for routing, where the bias is learned through a graph neural network that seeks to minimize end-to-end delay. Classical BP routing provides a simple yet powerful distributed solution for resource allocation in wireless multi-hop networks but has poor delay performance. A low-cost approach to improve this delay performance is to favor shorter paths by incorporating pre-defined biases in the BP computation, such as a bias based on the shortest path (hop) distance to the destination.

Recently, many studies have been conducted on automated epileptic seizures detection. However, few of these techniques are applied in clinical settings for several reasons. One of them is the imbalanced nature of the seizure detection task. Additionally, the current detection techniques do not really generalize to other patient populations. To address these issues, we present in this paper a hybrid CNN-LSTM model robust to cross-site variability. We investigate the use of data augmentation (DA) methods as an efficient tool to solve imbalanced training problems.

Recently, many studies have been conducted on automated epileptic seizures detection. However, few of these techniques are applied in clinical settings for several reasons. One of them is the imbalanced nature of the seizure detection task. Additionally, the current detection techniques do not really generalize to other patient populations. To address these issues, we present in this paper a hybrid CNN-LSTM model robust to cross-site variability. We investigate the use of data augmentation (DA) methods as an efficient tool to solve imbalanced training problems.

Vector-quantized autoencoders have recently gained interest in image compression, generation and self-supervised learning. However, as a neural compression method, they lack the possibility to allocate a variable number of bits to each image location, e.g. according to the semantic content or local saliency. In this paper, we address this limitation in a simple yet effective way. We adopt a product quantizer (PQ) that produces a set of discrete codes for each image patch rather than a single index.