Related papers: Exploring Frequency-Domain Feature Modeling for HR…
In the realm of deep learning, spatial attention mechanisms have emerged as a vital method for enhancing the performance of convolutional neural networks. However, these mechanisms possess inherent limitations that cannot be overlooked.…
From a machine learning perspective, the human ability localize sounds can be modeled as a non-parametric and non-linear regression problem between binaural spectral features of sound received at the ears (input) and their sound-source…
Head-related transfer functions (HRTFs) are important for immersive audio, and their spatial interpolation has been studied to upsample finite measurements. Recently, neural fields (NFs) which map from sound source direction to HRTF have…
This study investigates the approach of direction-dependent selection of Head-Related Transfer Functions (HRTFs) and its impact on sound localization accuracy. For applications such as virtual reality (VR) and teleconferencing, obtaining…
Deep functional map frameworks are widely employed for 3D shape matching. However, most existing deep functional map methods cannot adaptively capture important frequency information for functional map estimation in specific matching…
Image super-resolution (SR) is a technique to recover lost high-frequency information in low-resolution (LR) images. Spatial-domain information has been widely exploited to implement image SR, so a new trend is to involve frequency-domain…
In many signal processing applications, one wishes to acquire images that are sparse in transform domains such as spatial finite differences or wavelets using frequency domain samples. For such applications, overwhelming empirical evidence…
Self-supervised learning has demonstrated impressive performance in speech tasks, yet there remains ample opportunity for advancement in the realm of speech enhancement research. In addressing speech tasks, confining the attention mechanism…
Current artificial neural networks mainly conduct the learning process in the spatial domain but neglect the frequency domain learning. However, the learning course performed in the frequency domain can be more efficient than that in the…
Financial spillovers in interconnected systems, such as global banking networks, require tools that capture temporal and frequency dynamics, while incorporating the underlying network topology. While current network time series models are…
Neural rendering can be used to reconstruct implicit representations of shapes without 3D supervision. However, current neural surface reconstruction methods have difficulty learning high-frequency geometry details, so the reconstructed…
Diffusion models have become a leading paradigm for image super-resolution (SR), but existing methods struggle to guarantee both the high-frequency perceptual quality and the low-frequency structural fidelity of generated images. Although…
Many real-world time series exhibit strong periodic structures arising from physical laws, human routines, or seasonal cycles. However, modern deep forecasting models often fail to capture these recurring patterns due to spectral bias and a…
While deep learning has reduced the prevalence of manual feature extraction, transformation of data via feature engineering remains essential for improving model performance, particularly for underwater acoustic signals. The methods by…
Hyperspectral Image (HSI) classification is an important issue in remote sensing field with extensive applications in earth science. In recent years, a large number of deep learning-based HSI classification methods have been proposed.…
As a sub-field of object detection, moving infrared small target detection presents significant challenges due to tiny target sizes and low contrast against backgrounds. Currently-existing methods primarily rely on the features extracted…
Dynamic feature selection (DFS) is a machine learning framework in which features are acquired sequentially for individual samples under budget constraints. The exponential growth in the number of possible feature acquisition paths forces a…
Adapting vision transformer foundation models through parameter-efficient fine-tuning (PEFT) methods has become increasingly popular. These methods optimize a limited subset of parameters, enabling efficient adaptation without the need to…
With the increasing demand of capturing our environment in three-dimensions for AR/ VR applications and autonomous driving among others, the importance of high-resolution point clouds rises. As the capturing process is a complex task, point…
The individuality of head-related transfer functions (HRTFs) is a key issue for binaural synthesis. While, over the years, a lot of work has been accomplished to propose end-user-friendly solutions to HRTF personalization, it remains a…