Pose Tracking
62 papers with code • 3 benchmarks • 10 datasets
Pose Tracking is the task of estimating multi-person human poses in videos and assigning unique instance IDs for each keypoint across frames. Accurate estimation of human keypoint-trajectories is useful for human action recognition, human interaction understanding, motion capture and animation.
Source: LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking
Benchmarks
These leaderboards are used to track progress in Pose Tracking
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Libraries
Use these libraries to find Pose Tracking models and implementationsDatasets
PoseTrack
10,000 People - Human Pose Recognition Data
HOI4D
VBR
VR-Folding
Drunkard's Dataset
InfiniteRep
Latest papers
AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing
In this paper, we present AvatarPoser, the first learning-based method that predicts full-body poses in world coordinates using only motion input from the user's head and hands.
Semantic-Aware Fine-Grained Correspondence
alxead/sfc
•
•
Establishing visual correspondence across images is a challenging and essential task.
MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior
irlab-therapeutics/mabe_2022
•
•
We introduce MABe22, a large-scale, multi-agent video and trajectory benchmark to assess the quality of learned behavior representations.
Structure PLP-SLAM: Efficient Sparse Mapping and Localization using Point, Line and Plane for Monocular, RGB-D and Stereo Cameras
One of the biggest challenges in parallel tracking and mapping with a monocular camera is to keep the scale consistent when reconstructing the geometric primitives.
Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty Estimation
We propose a single-stage, category-level 6-DoF pose estimation algorithm that simultaneously detects and tracks instances of objects within a known category.
HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction
leolyliu/HOI4D-Instructions
•
•
CVPR 2022
We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction.
HMD-EgoPose: Head-Mounted Display-Based Egocentric Marker-Less Tool and Hand Pose Estimation for Augmented Surgical Guidance
Further, we reveal the capacity of our HMD-EgoPose framework for performant 6DoF pose estimation on a commercially available optical see-through head-mounted display (OST-HMD) through a low-latency streaming approach.
You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration
The canonical object representation is learned solely in simulation and then used to parse a category-level, task trajectory from a single demonstration video.
PoseTrack21: A Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose Tracking
andoer/posetrack21
•
•
CVPR 2022
Current research evaluates person search, multi-object tracking and multi-person pose estimation as separate tasks and on different datasets although these tasks are very akin to each other and comprise similar sub-tasks, e. g. person detection or appearance-based association of detected persons.
Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space
gorilla-lab-scut/ss-conv
•
•
NeurIPS 2021
In this paper, we propose a novel design of Sparse Steerable Convolution (SS-Conv) to address the shortcoming; SS-Conv greatly accelerates steerable convolution with sparse tensors, while strictly preserving the property of SE(3)-equivariance.
