Related papers: Hierarchical Separable Video Transformer for Snaps…
Spectral image reconstruction is an important task in snapshot compressed imaging. This paper aims to propose a new end-to-end framework with iterative capabilities similar to a deep unfolding network to improve reconstruction accuracy,…
Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they…
Snapshot compressive imaging (SCI) surges as a novel way of capturing hyperspectral images. It operates an optical encoder to compress the 3D data into a 2D measurement and adopts a software decoder for the signal reconstruction. Recently,…
State-of-the-art transformer-based video instance segmentation (VIS) approaches typically utilize either single-scale spatio-temporal features or per-frame multi-scale features during the attention computations. We argue that such an…
It has recently been demonstrated that spatial resolution adaptation can be integrated within video compression to improve overall coding performance by spatially down-sampling before encoding and super-resolving at the decoder. Significant…
Vision Transformers (ViT) have recently brought a new wave of research in the field of computer vision. These models have performed particularly well in image classification and segmentation. Research on semantic and instance segmentation…
High dynamic range (HDR) deghosting algorithms aim to generate ghost-free HDR images with realistic details. Restricted by the locality of the receptive field, existing CNN-based methods are typically prone to producing ghosting artifacts…
Contemporary models for generating images show remarkable quality and versatility. Swayed by these advantages, the research community repurposes them to generate videos. Since video content is highly redundant, we argue that naively…
Transformer has achieved satisfactory results in the field of hyperspectral image (HSI) classification. However, existing Transformer models face two key challenges when dealing with HSI scenes characterized by diverse land cover types and…
Vision Transformer (ViT) architectures represent images as collections of high-dimensional vectorized tokens, each corresponding to a rectangular non-overlapping patch. This representation trades spatial granularity for embedding…
Self-supervised pretrain techniques have been widely used to improve the downstream tasks' performance. However, real-world magnetic resonance (MR) studies usually consist of different sets of contrasts due to different acquisition…
Dataset distillation aims to synthesize compact yet informative datasets that allow models trained on them to achieve performance comparable to training on the full dataset. While this approach has shown promising results for image data,…
Video prediction is a pixel-wise dense prediction task to infer future frames based on past frames. Missing appearance details and motion blur are still two major problems for current predictive models, which lead to image distortion and…
Hyperspectral videos (HSVs), with their inherent spatial-spectral-temporal structure, offer distinct advantages in challenging tracking scenarios such as cluttered backgrounds and small objects. However, existing methods primarily focus on…
Both local details and global context are crucial in medical image segmentation, and effectively integrating them is essential for achieving high accuracy. However, existing mainstream methods based on CNN-Transformer hybrid architectures…
Satellite Image Time Series (SITS) representation learning is complex due to high spatiotemporal resolutions, irregular acquisition times, and intricate spatiotemporal interactions. These challenges result in specialized neural network…
Currently the semantic segmentation task of multispectral remotely sensed imagery (MSRSI) faces the following problems: 1) Usually, only single domain feature (i.e., space domain or frequency domain) is considered; 2) downsampling operation…
Vision Transformers have excelled in computer vision but their attention mechanisms operate independently across layers, limiting information flow and feature learning. We propose an effective cross-layer attention propagation method that…
In this paper, we consider the task of space-time video super-resolution (ST-VSR), namely, expanding a given source video to a higher frame rate and resolution simultaneously. However, most existing schemes either consider a fixed…
Vision Transformers (ViTs) have ushered in a new era in computer vision, showcasing unparalleled performance in many challenging tasks. However, their practical deployment in computational pathology has largely been constrained by the sheer…