Related papers: WheelPose: Data Synthesis Techniques to Improve Po…

Human Pose Estimation (HPE) is one of the fundamental problems in computer vision. It has applications ranging from virtual reality, human behavior analysis, video surveillance, anomaly detection, self-driving to medical assistance. The…

Human pose estimation (HPE) has received increasing attention recently due to its wide application in motion analysis, virtual reality, healthcare, etc. However, it suffers from the lack of labeled diverse real-world datasets due to the…

Human motion analysis has seen drastic improvements recently, however, due to the lack of representative datasets, for clinical in-bed scenarios it is still lagging behind. To address this issue, we implemented BlanketGen, a pipeline that…

This work is a portable MetaVerse implementation, and we use 3D pose estimation with AI to make virtual avatars do synchronized actions and interact with the environment. The motivation is that we find it inconvenient to use joysticks and…

Generative models for audio-conditioned dance motion synthesis map music features to dance movements. Models are trained to associate motion patterns to audio patterns, usually without an explicit knowledge of the human body. This approach…

With the advent of generative modeling techniques, synthetic data and its use has penetrated across various domains from unstructured data such as image, text to structured dataset modeling healthcare outcome, risk decisioning in financial…

Accurate estimation of 3D human motion from monocular video requires modeling both kinematics (body motion without physical forces) and dynamics (motion with physical forces). To demonstrate this, we present SimPoE, a Simulation-based…

The growing popularity of remote fitness has increased the demand for highly accurate computer vision models that track human poses. However, the best methods still fail in many real-world fitness scenarios, suggesting that there is a…

We introduce the concept of a Visual Compiler that generates a scene specific pedestrian detector and pose estimator without any pedestrian observations. Given a single image and auxiliary scene information in the form of camera parameters…

We propose a novel generative approach for 3D human pose estimation. 3D human pose estimation poses several key challenges due to the complex geometry of the human body, self-occluding joints, and the requirement for large-scale real-world…

We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperbolic space $\mathbb{H}^d$ to natively preserve the hierarchical tree topology of the human…

Videos are an accessible form of media for analyzing sports postures and providing feedback to athletes. Existing sport-specific systems embed bespoke human pose attributes and thus can be hard to scale for new attributes, especially for…

Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving. Given the heavy reliance of current trajectory forecasting models on data-driven methodologies, we aim…

Recovering 3D human poses from a monocular camera view is a highly ill-posed problem due to the depth ambiguity. Earlier studies on 3D human pose lifting from 2D often contain incorrect-yet-overconfident 3D estimations. To mitigate the…

We propose an experimental method for measuring bias in face recognition systems. Existing methods to measure bias depend on benchmark datasets that are collected in the wild and annotated for protected (e.g., race, gender) and…

Deep learning-based methods for video pedestrian detection and tracking require large volumes of training data to achieve good performance. However, data acquisition in crowded public environments raises data privacy concerns -- we are not…

The main difficulty of person re-identification (ReID) lies in collecting annotated data and transferring the model across different domains. This paper presents UnrealPerson, a novel pipeline that makes full use of unreal image data to…

Movement synchrony reflects the coordination of body movements between interacting dyads. The estimation of movement synchrony has been automated by powerful deep learning models such as transformer networks. However, instead of designing a…

Recent work has shown the benefits of synthetic data for use in computer vision, with applications ranging from autonomous driving to face landmark detection and reconstruction. There are a number of benefits of using synthetic data from…

Synthetic data serves as an alternative in training machine learning models, particularly when real-world data is limited or inaccessible. However, ensuring that synthetic data mirrors the complex nuances of real-world data is a challenging…