Related papers: SAPE: Spatially-Adaptive Progressive Encoding for …
The Mixed Lebesgue space is a suitable tool for modelling and measuring signals living in time-space domains. And sampling in such spaces plays an important role for processing high-dimensional time-varying signals. In this paper, we first…
In today's ever-connected world, the demand for fast and widespread connectivity is insatiable, making multibeam satellite systems an indispensable pillar of modern telecommunications infrastructure. However, the evolving communication…
Sound field reproduction with undistorted sound quality and precise spatial localization is desirable for automotive audio systems. However, the complexity of automotive cabin acoustic environment often necessitates a trade-off between…
Structural coloration is commonly modeled using wave optics for reliable and photorealistic rendering of natural, quasi-periodic and complex nanostructures. Such models often rely on dense, preliminary or preprocessed data to accurately…
Traffic forecasting is a complex multivariate time-series regression task of paramount importance for traffic management and planning. However, existing approaches often struggle to model complex multi-range dependencies using local…
Recently, self-supervised Masked Autoencoders (MAE) have attracted unprecedented attention for their impressive representation learning ability. However, the pretext task, Masked Image Modeling (MIM), reconstructs the missing local patches,…
Spatial prediction of the radio propagation environment of a transmitter can assist and improve various aspects of wireless networks. The majority of research in this domain can be categorized as 'reactive' spatial prediction, where the…
Accelerated MRI protocols routinely involve a predefined sampling pattern that undersamples the k-space. Finding an optimal pattern can enhance the reconstruction quality, however this optimization is a challenging task. To address this…
Integrated sensing and communication (ISAC) is an encouraging wireless technology which can simultaneously perform both radar and communication functionalities by sharing the same transmit waveform, spectral resource, and hardware platform.…
Semantic segmentation networks are usually pre-trained once and not updated during deployment. As a consequence, misclassifications commonly occur if the distribution of the training data deviates from the one encountered during the robot's…
This paper explores enabling large language models (LLMs) to understand spatial information from multichannel audio, a skill currently lacking in auditory LLMs. By leveraging LLMs' advanced cognitive and inferential abilities, the aim is to…
Recent advances in implicit neural representations show great promise when it comes to generating numerical solutions to partial differential equations. Compared to conventional alternatives, such representations employ parameterized neural…
Deep neural networks often suffer from poor generalization due to complex and non-convex loss landscapes. Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of…
Scene Text Recognition requires modeling visual structures that evolve from coarse layouts to fine-grained character strokes. Training such models relies on large amounts of annotated data. Recent self-supervised approaches, such as Masked…
Motivated by the challenge of seamless cross-dataset transfer in EEG signal processing, this article presents an exploratory study on the use of Joint Embedding Predictive Architectures (JEPAs). In recent years, self-supervised learning has…
Multimodal large language models (MLLMs) have achieved strong performance on vision-language tasks, yet often suffer from inefficiencies due to redundant visual tokens. Existing token merging methods reduce sequence length but frequently…
In this paper, we propose a novel self-supervised representation learning by taking advantage of a neighborhood-relational encoding (NRE) among the training data. Conventional unsupervised learning methods only focused on training deep…
Self-supervised monocular depth estimation has achieved notable success under daytime conditions. However, its performance deteriorates markedly at night due to low visibility and varying illumination, e.g., insufficient light causes…
Recent general-purpose audio representations show state-of-the-art performance on various audio tasks. These representations are pre-trained by self-supervised learning methods that create training signals from the input. For example,…
Deep neural networks often suffer from poor generalization caused by complex and non-convex loss landscapes. One of the popular solutions is Sharpness-Aware Minimization (SAM), which smooths the loss landscape via minimizing the maximized…