Related papers: Rethinking the Heatmap Regression for Bottom-up Hu…

Human pose estimation on medium and small scales has long been a significant challenge in this field. Most existing methods focus on restoring high-resolution feature maps by stacking multiple costly deconvolutional layers or by…

Estimating human and camera trajectories with accurate scale in the world coordinate system from a monocular video is a highly desirable yet challenging and ill-posed problem. In this study, we aim to recover expressive parametric human…

Human Activity Recognition (HAR) is a key building block of many emerging applications such as intelligent mobility, sports analytics, ambient-assisted living and human-robot interaction. With robust HAR, systems will become more…

Heatmap is a common geovisualization method that interpolates and visualizes a set of point observations on a map surface. Most of online web mapping libraries implement a one-pass heatmap algorithm using HTML5 canvas or WebGL for efficient…

Accurate localization of cephalometric landmarks holds great importance in the fields of orthodontics and orthognathics due to its potential for automating key point labeling. In the context of landmark detection, particularly in…

We present EgoTAP, a heatmap-to-3D pose lifting method for highly accurate stereo egocentric 3D pose estimation. Severe self-occlusion and out-of-view limbs in egocentric camera views make accurate pose estimation a challenging problem. To…

Building large-scale, globally consistent maps is a challenging problem, made more difficult in environments with limited access, sparse features, or when using data collected by novice users. For such scenarios, where state-of-the-art…

Human Pose (HP) estimation is actively researched because of its wide range of applications. However, even estimators pre-trained on large datasets may not perform satisfactorily due to a domain gap between the training and test data. To…

The Rayleigh regression model was recently proposed for modeling amplitude values of synthetic aperture radar (SAR) image pixels. However, inferences from such model are based on the maximum likelihood estimators, which can be biased for…

Modern deep neural networks (DNNs) are highly accurate on many recognition tasks for overhead (e.g., satellite) imagery. However, visual domain shifts (e.g., statistical changes due to geography, sensor, or atmospheric conditions) remain a…

Deep learning approaches have been rapidly adopted across a wide range of fields because of their accuracy and flexibility, but require large labeled training datasets. This presents a fundamental problem for applications with limited,…

Reinforcement Learning from Human Feedback (RLHF) aims to align language models (LMs) with human values by training reward models (RMs) on binary preferences and using these RMs to fine-tune the base LMs. Despite its importance, the…

Reconstructing detailed 3D human meshes from a single in-the-wild image remains a fundamental challenge in computer vision. Existing SMPLX-based methods often suffer from slow inference, produce only coarse body poses, and exhibit…

For human-centric large-scale scenes, fine-grained modeling for 3D human global pose and shape is significant for scene understanding and can benefit many real-world applications. In this paper, we present LiveHPS, a novel…

R}easoning for Robust Human Pose and Shape Estimation), designed to estimate human body shape and pose from single-view images. ReBaR effectively addresses the challenges of occlusions and depth ambiguity by learning reference features for…

Current Transformer-based methods for small object detection continue emerging, yet they have still exhibited significant shortcomings. This paper introduces HeatMap Position Embedding (HMPE), a novel Transformer Optimization technique that…

This paper introduces a novel human pose estimation approach using sparse inertial sensors, addressing the shortcomings of previous methods reliant on synthetic data. It leverages a diverse array of real inertial motion capture data from…

Expressive Human Pose and Shape Estimation (EHPS) plays a crucial role in various AR/VR applications and has witnessed significant progress in recent years. However, current state-of-the-art methods still struggle with accurate parameter…

Radar-based indoor 3D human pose estimation typically relied on fine-grained 3D keypoint labels, which are costly to obtain especially in complex indoor settings involving clutter, occlusions, or multiple people. In this paper, we propose…

High-dimensional, heterogeneous data with complex feature interactions pose significant challenges for traditional predictive modeling approaches. While Projection to Latent Structures (PLS) remains a popular technique, it struggles to…