Related papers: HRFormer: High-Resolution Transformer for Dense Pr…
Convolutional neural networks (CNNs) have been widely utilized in many computer vision tasks. However, CNNs have a fixed reception field and lack the ability of long-range perception, which is crucial to human pose estimation. Due to its…
The hybrid deep models of Vision Transformer (ViT) and Convolution Neural Network (CNN) have emerged as a powerful class of backbones for vision tasks. Scaling up the input resolution of such hybrid backbones naturally strengthes model…
Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…
The Resolution of feature maps is critical for medical image segmentation. Most of the existing Transformer-based networks for medical image segmentation are U-Net-like architecture that contains an encoder that utilizes a sequence of…
Image denoising is an important low-level computer vision task, which aims to reconstruct a noise-free and high-quality image from a noisy image. With the development of deep learning, convolutional neural network (CNN) has been gradually…
Depth completion aims to predict dense depth maps with sparse depth measurements from a depth sensor. Currently, Convolutional Neural Network (CNN) based models are the most popular methods applied to depth completion tasks. However,…
While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares…
Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual…
Dense prediction is a fundamental requirement for many medical vision tasks such as medical image restoration, registration, and segmentation. The most popular vision model, Convolutional Neural Networks (CNNs), has reached bottlenecks due…
Bottom-up human pose estimation methods have difficulties in predicting the correct pose for small persons due to challenges in scale variation. In this paper, we present HigherHRNet: a novel bottom-up human pose estimation method for…
Local feature matching is a computationally intensive task at the subpixel level. While detector-based methods coupled with feature descriptors struggle in low-texture scenes, CNN-based methods with a sequential extract-to-match pipeline,…
Human pose estimation in complicated situations has always been a challenging task. Many Transformer-based pose networks have been proposed recently, achieving encouraging progress in improving performance. However, the remarkable…
Hyperspectral image (HSI) classification (HSIC) requires effective modeling of complex spatial-spectral dependencies under limited labeled data and high dimensionality. While transformer-based models have shown strong capability in…
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…
Hyperspectral image has become increasingly crucial due to its abundant spectral information. However, It has poor spatial resolution with the limitation of the current imaging mechanism. Nowadays, many convolutional neural networks have…
In this work, we introduce SPFormer, a novel Vision Transformer enhanced by superpixel representation. Addressing the limitations of traditional Vision Transformers' fixed-size, non-adaptive patch partitioning, SPFormer employs superpixels…
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…
High-resolution representations are important for vision-based robotic grasping problems. Existing works generally encode the input images into low-resolution representations via sub-networks and then recover high-resolution…
We propose a novel method for joint estimation of shape and pose of rigid objects from their sequentially observed RGB-D images. In sharp contrast to past approaches that rely on complex non-linear optimization, we propose to formulate it…
Transformers have exhibited promising performance in computer vision tasks including image super-resolution (SR). However, popular transformer-based SR methods often employ window self-attention with quadratic computational complexity to…