Related papers: Efficient Human Pose Estimation by Maximizing Fusi…

Recent Vision Transformer~(ViT) models have demonstrated encouraging results across various computer vision tasks, thanks to their competence in modeling long-range dependencies of image patches or tokens via self-attention. These models,…

Recently, a series of works in computer vision have shown promising results on various image and video understanding tasks using self-attention. However, due to the quadratic computational and memory complexities of self-attention, these…

In multi-person pose estimation, the left/right joint type discrimination is always a hard problem because of the similar appearance. Traditionally, we solve this problem by stacking multiple refinement modules to increase network's…

This paper presents an end-to-end 3D convolutional network named attention-based multi-modal fusion network (AMFNet) for the semantic scene completion (SSC) task of inferring the occupancy and semantic labels of a volumetric 3D scene from…

Recently, CNN and Transformer hybrid networks demonstrated excellent performance in face super-resolution (FSR) tasks. Since numerous features at different scales in hybrid networks, how to fuse these multiscale features and promote their…

While Transformer networks benefit from a global receptive field, their quadratic cost relative to sequence length restricts their application to long sequences and high-resolution inputs. We introduce Fast Multipole Attention (FMA), a…

In this paper, we propose a two-stage fully 3D network, namely \textbf{DeepFuse}, to estimate human pose in 3D space by fusing body-worn Inertial Measurement Unit (IMU) data and multi-view images deeply. The first stage is designed for pure…

Factorization Machines (FMs) are a supervised learning approach that enhances the linear regression model by incorporating the second-order feature interactions. Despite effectiveness, FM can be hindered by its modelling of all feature…

Micro-expression recognition (MER) presents a significant challenge due to the transient and subtle nature of the motion changes involved. In recent years, deep learning methods based on attention mechanisms have made some breakthroughs in…

The performance of human pose estimation depends on the spatial accuracy of keypoint localization. Most existing methods pursue the spatial accuracy through learning the high-resolution (HR) representation from input images. By the…

Existing human pose estimation approaches often only consider how to improve the model generalisation performance, but putting aside the significant efficiency problem. This leads to the development of heavy models with poor scalability and…

3D human pose lifting is a promising research area that leverages estimated and ground-truth 2D human pose data for training. While existing approaches primarily aim to enhance the performance of estimated 2D poses, they often struggle when…

Feature fusion, the combination of features from different layers or branches, is an omnipresent part of modern network architectures. It is often implemented via simple operations, such as summation or concatenation, but this might not be…

Human pose estimation is an essential yet challenging task in computer vision. One of the reasons for this difficulty is that there are many redundant regions in the images. In this work, we proposed a convolutional network architecture…

Multi-frame human pose estimation in complicated situations is challenging. Although state-of-the-art human joints detectors have demonstrated remarkable results for static images, their performances come short when we apply these models to…

Depth map records distance between the viewpoint and objects in the scene, which plays a critical role in many real-world applications. However, depth map captured by consumer-grade RGB-D cameras suffers from low spatial resolution. Guided…

Multispectral (MS) and panchromatic (PAN) images describe the same land surface, so these images not only have their own advantages, but also have a lot of similar information. In order to separate these similar information and their…

Transformer-based methods have achieved remarkable results in image super-resolution tasks because they can capture non-local dependencies in low-quality input images. However, this feature-intensive modeling approach is computationally…

Currently, lightweight hybrid backbone networks have partially alleviated the issue of computational saturation, but the imbalance in computational efficiencys between convolutional neural networks (CNNs) and attention mechanisms is…

Recently, lightweight methods for single image super-resolution (SISR) have gained significant popularity and achieved impressive performance due to limited hardware resources. These methods demonstrate that adopting residual feature…