-
Modec: Multimodal Decomposable Models for Human Pose Estimation
A dataset for human pose estimation that consists of images with annotated body parts. -
Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation
A dataset for human pose estimation that consists of images with annotated body parts. -
Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwis...
A graphical model for human pose estimation that exploits the fact that local image measurements can be used to detect parts and predict spatial relationships between them. -
InstaVariety
InstaVariety dataset is used for training the model, and it contains images of people performing various actions. -
VLOG-People
VLOG-People dataset is used for training the model, and it contains videos of people performing various actions. -
MPII Human Pose Dataset
Human pose estimation refers to the task of recognizing postures by localizing body keypoints (head, shoulders, elbows, wrists, knees, ankles, etc.) from images. -
MPII Pose Descriptions Dataset
The MPII Pose Descriptions Dataset is a dataset created in this paper, containing up to four pose descriptions for each annotated image. -
Image Text Pseudo-Pose (ITPP)
A large-scale dataset of human poses and their text descriptions extracted from large-scale image datasets. -
Simultaneously-collected multimodal lying pose dataset
Simultaneously-collected multimodal lying pose dataset for in-bed human pose monitoring under adverse vision conditions. -
Intelligent Carpet
Human pose estimation from ambiguous pressure data using a temporal adaptation of ViTPose. -
DPoser: Diffusion Model as Robust 3D Human Pose Prior
The DPoser dataset is used for human pose prior modeling, leveraging diffusion models. -
Vinkle Srivastav et al. dataset
A dataset for human pose estimation in low-resolution depth images. -
Convolutional pose machines
Convolutional pose machines -
DirectPose
DirectPose: Direct End-to-End Multi-Person Pose Estimation -
FlyingThings3D dataset
The FlyingThings3D dataset is a benchmark for stereo matching, consisting of a large collection of images and corresponding disparity maps. -
MPII Human Pose
The MPII Human Pose dataset contains around 25K images with full-body pose annotations. -
Lite-HRNet: A Lightweight High-Resolution Network
Human pose estimation requires high-resolution representation to achieve high performance. We present an efficient high-resolution network, Lite-HRNet, for human pose estimation.
