Related papers: WaveFormer: Frequency-Time Decoupled Vision Modeli…

Accurate traffic forecasting is essential for intelligent transportation systems, supporting a wide range of real-world applications. However, it remains challenging due to two key factors:~(1) Traffic series contain heterogeneous temporal…

The recent works on Video Object Segmentation achieved remarkable results by matching dense semantic and instance-level features between the current and previous frames for long-time propagation. Nevertheless, global feature matching…

Interactive image editing allows users to modify images through visual interaction operations such as drawing, clicking, and dragging. Existing methods construct such supervision signals from videos, as they capture how objects change with…

Recent advances in vision transformers (ViTs) have achieved great performance in visual recognition tasks. Convolutional neural networks (CNNs) exploit spatial inductive bias to learn visual representations, but these networks are spatially…

Neural channel decoder, as a data-driven channel decoding strategy, has shown very promising improvement on error-correcting capability over the classical methods. However, the success of those deep learning-based decoder comes at the cost…

Speech emotion recognition is crucial to human-computer interaction. The temporal regions that represent different emotions scatter in different parts of the speech locally. Moreover, the temporal scales of important information may vary…

Starting from first principles of wave propagation, we consider a multiple-input multiple-output (MIMO) representation of a communication system between two spatially-continuous volumes. This is the concept of holographic MIMO…

Underwater images often exhibit poor quality, distorted color balance and low contrast due to the complex and intricate interplay of light, water, and objects. Despite the significant contributions of previous underwater enhancement…

We present a novel generative modeling framework,Wavelet-Fourier-Diffusion, which adapts the diffusion paradigm to hybrid frequency representations in order to synthesize high-quality, high-fidelity images with improved spatial…

Current Deep Learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio-temporal relationships within obtained sensor data. These approaches derive scene dynamics…

It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks. Nevertheless, the original Vision Transformer may lack of inductive biases of local neighborhoods and possess a high…

Orthogonal Frequency Division Multiplexing (OFDM) is the dominant waveform in modern wireless systems, but suffers performance degradation in high-mobility environments due to Doppler-induced inter-carrier interference and unreliable…

Time series forecasting plays a vital role across scientific, industrial, and environmental domains, especially when dealing with high-dimensional and nonlinear systems. While Transformer-based models have recently achieved state-of-the-art…

It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolution neural networks (CNNs) and vision transformers (ViTs) have…

Mesh denoising, aimed at removing noise from input meshes while preserving their feature structures, is a practical yet challenging task. Despite the remarkable progress in learning-based mesh denoising methodologies in recent years, their…

The wave operator model provides a framework for modeling wave propagation by encoding material parameter distributions into matrix-form operators. This paper extends this framework from lossless to lossy media. We present a derivation of…

Real-world problems often involve complex and unstructured sets of measurements, which occur when sensors are sparsely placed in either space or time. Being able to model this irregular spatiotemporal data and extract meaningful forecasts…

The recently developed transformer networks have achieved impressive performance in image denoising by exploiting the self-attention (SA) in images. However, the existing methods mostly use a relatively small window to compute SA due to the…

Although diffusion models are rising as a powerful solution for blind face restoration, they are criticized for two problems: 1) slow training and inference speed, and 2) failure in preserving identity and recovering fine-grained facial…

Transformer-based QA models use input-wide self-attention -- i.e. across both the question and the input passage -- at all layers, causing them to be slow and memory-intensive. It turns out that we can get by without input-wide…