Related papers: BTranspose: Bottleneck Transformers for Human Pose…
While CNN-based models have made remarkable progress on human pose estimation, what spatial dependencies they capture to localize keypoints remains unclear. In this work, we propose a model called \textbf{TransPose}, which introduces…
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…
Making top-down human pose estimation method present both good performance and high efficiency is appealing. Mask RCNN can largely improve the efficiency by conducting person detection and pose estimation in a single framework, as the…
Human pose estimation deeply relies on visual clues and anatomical constraints between parts to locate keypoints. Most existing CNN-based methods do well in visual representation, however, lacking in the ability to explicitly learn the…
Human pose estimation aims at localizing human anatomical keypoints or body parts in the input data (e.g., images, videos, or signals). It forms a crucial component in enabling machines to have an insightful understanding of the behaviors…
Human pose estimation (i.e., locating the body parts / joints of a person) is a fundamental problem in human-computer interaction and multimedia applications. Significant progress has been made based on the development of depth sensors,…
The target of 2D human pose estimation is to locate the keypoints of body parts from input 2D images. State-of-the-art methods for pose estimation usually construct pixel-wise heatmaps from keypoints as labels for learning convolution…
Recently, human pose estimation mainly focuses on how to design a more effective and better deep network structure as human features extractor, and most designed feature extraction networks only introduce the position of each anatomical…
Human pose estimation (HPE) with convolutional neural networks (CNNs) for indoor monitoring is one of the major challenges in computer vision. In contrast to HPE in perspective views, an indoor monitoring system can consist of an…
We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transformer network. This network directly learns a regression…
Human pose estimation from image and video is a vital task in many multimedia applications. Previous methods achieve great performance but rarely take efficiency into consideration, which makes it difficult to implement the networks on…
Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have led to significant progress in 2D body pose estimation. However, achieving a good balance between accuracy, efficiency, and robustness remains a challenge. For…
In recent years, 2D human pose estimation has made significant progress on public benchmarks. However, many of these approaches face challenges of less applicability in the industrial community due to the large number of parametric…
Multi-person pose estimation (MPPE) estimates keypoints for all individuals present in an image. MPPE is a fundamental task for several applications in computer vision and virtual reality. Unfortunately, there are currently no…
The typical bottom-up human pose estimation framework includes two stages, keypoint detection and grouping. Most existing works focus on developing grouping algorithms, e.g., associative embedding, and pixel-wise keypoint regression that we…
Multi-person pose estimation generally follows top-down and bottom-up paradigms. Both of them use an extra stage ($\boldsymbol{e.g.,}$ human detection in top-down paradigm or grouping process in bottom-up paradigm) to build the relationship…
The task of human pose estimation (HPE) deals with the ill-posed problem of estimating the 3D position of human joints directly from images and videos. In recent literature, most of the works tackle the problem mostly by using convolutional…
We propose the Waterfall Transformer architecture for Pose estimation (WTPose), a single-pass, end-to-end trainable framework designed for multi-person pose estimation. Our framework leverages a transformer-based waterfall module that…
Human pose estimation - the process of recognizing human keypoints in a given image - is one of the most important tasks in computer vision and has a wide range of applications including movement diagnostics, surveillance, or self-driving…
In this paper, HeadPosr is proposed to predict the head poses using a single RGB image. \textit{HeadPosr} uses a novel architecture which includes a transformer encoder. In concrete, it consists of: (1) backbone; (2) connector; (3)…