Related papers: HRFormer: High-Resolution Transformer for Dense Pr…

Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks. Previous research has established that Vision…

In this paper, we present Uformer, an effective and efficient Transformer-based architecture for image restoration, in which we build a hierarchical encoder-decoder network using the Transformer block. In Uformer, there are two core…

We present CSWin Transformer, an efficient and effective Transformer-based backbone for general-purpose vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute whereas local…

The design choices in Transformer feed-forward neural networks have resulted in significant computational and parameter overhead. In this work, we emphasize the importance of hidden dimensions in designing lightweight FFNs, a factor often…

Human fashion understanding is one crucial computer vision task since it has comprehensive information for real-world applications. This focus on joint human fashion segmentation and attribute recognition. Contrary to the previous works…

Local feature matching between images remains a challenging task, especially in the presence of significant appearance variations, e.g., extreme viewpoint changes. In this work, we propose DeepMatcher, a deep Transformer-based network built…

We present a new self-supervised pre-training of Vision Transformers for dense prediction tasks. It is based on a contrastive loss across views that compares pixel-level representations to global image representations. This strategy…

Pre-trained Transformer language models (LM) have become go-to text representation encoders. Prior research fine-tunes deep LMs to encode text sequences such as sentences and passages into single dense vector representations for efficient…

Hyperspectral image classification (HSIC) has gained significant attention because of its potential in analyzing high-dimensional data with rich spectral and spatial information. In this work, we propose the Differential Spatial-Spectral…

Recently, vision transformers have shown great success in a set of human reconstruction tasks such as 2D human pose estimation (2D HPE), 3D human pose estimation (3D HPE), and human mesh reconstruction (HMR) tasks. In these tasks, feature…

High-resolution dense prediction enables many appealing real-world applications, such as computational photography, autonomous driving, etc. However, the vast computational cost makes deploying state-of-the-art high-resolution dense…

Pansharpening aims to fuse a registered high-resolution panchromatic image (PAN) with a low-resolution hyperspectral image (LR-HSI) to generate an enhanced HSI with high spectral and spatial resolution. Existing pansharpening approaches…

3D human pose estimation can be handled by encoding the geometric dependencies between the body parts and enforcing the kinematic constraints. Recently, Transformer has been adopted to encode the long-range dependencies between the joints…

This is an official pytorch implementation of Deep High-Resolution Representation Learning for Human Pose Estimation. In this work, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution…

Building height (BH) and footprint (BF) are fundamental urban morphological parameters required by climate modelling, disaster-risk assessment, and population mapping, yet globally consistent data remain scarce. In this work, we develop…

The CNN-based methods have achieved impressive results in medical image segmentation, but they failed to capture the long-range dependencies due to the inherent locality of the convolution operation. Transformer-based methods are recently…

Due to the difficulty of acquiring large-scale 3D human keypoint annotation, previous methods for 3D human pose estimation (HPE) have often relied on 2D image features and sequential 2D annotations. Furthermore, the training of these…

Humans can often count unfamiliar objects by observing visual repetition and composition, rather than relying only on object categories. However, many exemplar-free counting models struggle in such situations and may overcount when objects…

Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…

Transformer models have recently garnered significant attention in image restoration due to their ability to capture long-range pixel dependencies. However, long-range attention often results in computational overhead without practical…