computer-vision-1

3D Human Pose Tracking

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in 3d-human-pose-tracking-1

Trend

Dataset

Best Model

Actions

Panoptic

Libraries

i

Use these libraries to find 3d-human-pose-tracking-1 models and implementations

Datasets

Panoptic

InfiniteRep

UNIPD-BPE

VIDIMU: Multimodal video and IMU kinematic dataset on daily life activities using affordable devices

Subtasks

No subtasks available.

Most implemented papers

Iterative Greedy Matching for 3D Human Pose Tracking from Multiple Views

Juergen Gall, Julian Tanke•Mon Sep 09 2019

This work builds upon a real-time 2D multi-person pose estimation system and greedily solves the association problem between multiple views as problems associated with greedy matching such as occlusion can be easily resolved in 3D.

28

Content

0

Paper Graph

Part-aware Measurement for Robust Multi-View Multi-Human 3D Pose Estimation and Tracking

Chu-Song Chen, Hau Chu, Jia-Hong Lee, Yao-Chih Lee, Ching-Hsien Hsu, Jia-Da Li•Mon May 31 2021

This paper introduces an approach for multi-human 3D pose estimation and tracking based on calibrated multiview that takes advantage of temporal consistency to match the 2D poses estimated with previously constructed 3D skeletons in every view.

29 0

Paper Graph

Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting

Wentao Bao, Zhong Li, Lele Chen, Libing Zeng, Junsong Yuan, Yubo Kong•Sun Jul 16 2023

An uncertainty-aware state space Transformer (USST) is proposed that takes the merits of the attention mechanism and aleatoric uncertainty within the framework of the classical state-space model and can be further enhanced by the velocity constraint and visual prompt tuning on large vision transformers.

30 0

Paper Graph

Adding a benchmark result helps the community track progress.