Related papers: Temporal FiLM: Capturing Long-Range Sequence Depen…

Weather forecasting is crucial for public safety, disaster prevention and mitigation, agricultural production, and energy management, with global relevance. Although deep learning has significantly advanced weather prediction, current…

A novel and efficient end-to-end learning model for automatic modulation classification is proposed for wireless spectrum monitoring applications, which automatically learns from the time domain in-phase and quadrature data without…

We introduce a new neural architecture and an unsupervised algorithm for learning invariant representations from temporal sequence of images. The system uses two groups of complex cells whose outputs are combined multiplicatively: one that…

Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception. However, existing methods lack flexible adaptivity, leading to irreversible detail loss and…

While Large Language Models (LLMs) demonstrate strong performance across domains, their long-context capabilities are limited by transient neural activations causing information decay and unstructured feed-forward network (FFN) weights…

Learning representations for graph-structured data is essential for graph analytical tasks. While remarkable progress has been made on static graphs, researches on temporal graphs are still in its beginning stage. The bottleneck of the…

Speech dereverberation is often an important requirement in robust speech processing tasks. Supervised deep learning (DL) models give state-of-the-art performance for single-channel speech dereverberation. Temporal convolutional networks…

Neural Fields (NF) have gained prominence as a versatile framework for complex data representation. This work unveils a new problem setting termed \emph{Meta-Continual Learning of Neural Fields} (MCL-NF) and introduces a novel strategy that…

In recent years, advances in Artificial Intelligence have significantly impacted computer science, particularly in the field of computer vision, enabling solutions to complex problems such as video frame prediction. Video frame prediction…

Time series analysis faces significant challenges in handling variable-length data and achieving robust generalization. While Transformer-based models have advanced time series tasks, they often struggle with feature redundancy and limited…

Federated learning is a decentralized training approach that keeps data under stakeholder control while achieving superior performance over isolated training. While inter-institutional feature discrepancies pose a challenge in all federated…

Convolutional Neural Networks (CNNs) have been widely employed for image Super-Resolution (SR) in recent years. Various techniques enhance SR performance by altering CNN structures or incorporating improved self-attention mechanisms.…

We extend the recent latent recurrent modeling to sequential input streams. By interleaving fast, recurrent latent updates with self-organizational ability between slow observation updates, our method facilitates the learning of stable…

The performance of autonomous systems heavily relies on their ability to generate a robust representation of the environment. Deep neural networks have greatly improved vision-based perception systems but still fail in challenging…

Traditional convolutional layers extract features from patches of data by applying a non-linearity on an affine function of the input. We propose a model that enhances this feature extraction process for the case of sequential data, by…

Image segmentation is a fundamental task in computer vision, aimed at partitioning an image into semantically meaningful regions. Referring image segmentation extends this task by using natural language expressions to localize specific…

The goal of continuous emotion recognition is to assign an emotion value to every frame in a sequence of acoustic features. We show that incorporating long-term temporal dependencies is critical for continuous emotion recognition tasks. To…

Modeling long-term dependencies for audio signals is a particularly challenging problem, as even small-time scales yield on the order of a hundred thousand samples. With the recent advent of Transformers, neural architectures became good at…

Continual learning is an emerging topic in the field of deep learning, where a model is expected to learn continuously for new upcoming tasks without forgetting previous experiences. This field has witnessed numerous advancements, but few…

Empowering LLMs with the ability to precisely understand long contexts is crucial for many downstream applications. However, handling long contexts with conventional transformer architecture requires substantial training and inference…