Head pose estimation is a crucial problem for many tasks, such as driver attention, fatigue detection, and human behaviour analysis. It is well known that neural networks are better at handling classification problems than regression problems. It is an extremely nonlinear process to let the network output the angle value directly for optimization learning, and the weight constraint of the loss function will be relatively weak. This paper proposes a novel Bernoulli heatmap for head pose estimation from a single RGB image. Our method can achieve the positioning of the head area while estimating the angles of the head. The Bernoulli heatmap makes it possible to construct fully convolutional neural networks without fully connected layers and provides a new idea for the output form of head pose estimation. A deep convolutional neural network (CNN) structure with multiscale representations is adopted to maintain high-resolution information and low-resolution information in parallel. This kind of structure can maintain rich, high-resolution representations. In addition, channelwise fusion is adopted to make the fusion weights learnable instead of simple addition with equal weights. As a result, the estimation is spatially more precise and potentially more accurate. The effectiveness of the proposed method is empirically demonstrated by comparing it with other state-of-the-art methods on public datasets.
CAPE: A CLIP-Aware Pointing Ensemble of Complementary Heatmap Cues for Embodied Reference Understanding
Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Istanbul Technical University(伊斯坦布尔技术大学);Carnegie Mellon University(卡内基梅隆大学);KIT Campus Transfer GmbH (KCT)(KIT校园转移有限责任公司)
SGRNet: Spatially Guided Radiology Network for Structured Radiological Reporting of Head and Neck Cancer
University of Strasbourg(斯特拉斯堡大学);IHU Strasbourg(斯特拉斯堡大学医院研究所);Indian Institute of Technology (IIT) Madras(印度马德拉斯理工学院);All India Institute of Medical Sciences(全印度医学科学院)
mmEgoHand: Egocentric Hand Pose Estimation and Gesture Recognition with Head-mounted Millimeter-wave Radar and IMU
School of Software Engineering, Xi’an Jiaotong University(软件工程学院,西安交通大学);School of Cyber Science and Engineering, Xi’an Jiaotong University(网络科学与工程学院,西安交通大学);School of Computer Science and Technology, Xi’an Jiaotong University(计算机科学与技术学院,西安交通大学);College of Computer Science and Technology, Zhejiang University(计算机科学与技术学院,浙江大学)
YOLOPose: Transformer-based Multi-Object 6D Pose Estimation using Keypoint Regression
University of Bonn(波恩大学)
6D物体位姿估计是自主机器人操作应用的重要前提。用于姿态估计的现有技术模型是基于卷积神经网络(CNN)的。最近,最初为自然语言处理提出的架构Transformers也在许多计算机视觉任务中取得了最先进的成果。配备有多头自注意力机制,Transformers实现简单的单级端到端架构,用于联合学习目标检测和6D对象姿态估计。在这项工作中,我们提出了YOLOPose(You Only Look Once Pose Estimation的缩写),这是一种基于关键点回归的基于变换器的多对象6D姿态估计方法。与用于预测图像中关键点的标准热图相比,我们直接回归关键点。此外,我们采用了一个可学习的方向估计模块来预测的关键点的方向。与单独的翻译估计模块一起,我们的模型是端到端可微的。我们的方法适用于实时应用,并取得了与最先进的方法相当的结果。
MultiFormer: A Multi-Person Pose Estimation System Based on CSI and Attention Mechanism
University of Electronic Science and Technology of China(电子科技大学);School of Information and Communication Engineering(信息与通信工程学院);National Key Laboratory of Science and Technology on Communications(科学技术通信国家实验室)