computer-vision

Multi-Person Pose forecasting

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 multi-person-pose-forecasting

Trend

Dataset

Best Model

Actions

Expi - common actions split

Expi - unseen actions split

Libraries

i

Use these libraries to find multi-person-pose-forecasting models and implementations

Datasets

Expi

Subtasks

No subtasks available.

Most implemented papers

Learning Trajectory Dependencies for Human Motion Prediction

Hongdong Li, M. Salzmann, Wei Mao, Miaomiao Liu•Wed Aug 14 2019

A simple feed-forward deep network for motion prediction, which takes into account both temporal smoothness and spatial dependencies among human body joints, and design a new graph convolutional network to learn graph connectivity automatically.

524

Content

0

Paper Graph

Multi-Person Extreme Motion Prediction

F. Moreno-Noguer, Xavier Alameda-Pineda, Wen Guo, Xiaoyu Bie•Mon May 17 2021

A novel cross interaction attention mechanism that exploits historical information of both persons, and learns to predict cross dependencies between the two pose sequences to predict the future motion of two interacted persons given two sequences of their past skeletons.

91 0

Paper Graph

Multi-Person 3D Motion Prediction with Multi-Range Transformers

Xiaolong Wang, Huazhe Xu, Jiashun Wang, Medhini Narasimhan•Mon Nov 22 2021

A Multi-Range Transformers model is introduced which contains of a local-range encoder for individual motion and a global-rangeEncoder for social interactions, which outperforms state-of-the-art methods on long-term 3D motion prediction, but also generates diverse social interactions.

93 0

Paper Graph

SoMoFormer: Multi-Person Pose Forecasting with Transformers

Hamid Rezatofighi, Edward Vendrow, Satyajit Kumar, Ehsan Adeli•Mon Aug 29 2022

SoMoFormer outperforms state-of-the-art methods for long-term motion prediction on the SoMoF benchmark as well as the CMU-Mocap and MuPoTS-3D datasets.

29 0

Paper Graph

Best Practices for 2-Body Pose Forecasting

Alessandro Flaborea, Alessio Sampieri, Fabio Galasso, Muhammad Rameez Ur Rahman, Luca Scofano, Edoardo De Matteis•Tue Apr 11 2023

This study confirms the positive impact of frequency input representations, space-time separable and fully-learnable interaction adjacencies for the encoding GCN and FC decoding and contributes a novel initialization procedure for the 2-body spatial interaction parameters of the encoder, which benefits performance and stability.

13 0

Paper Graph

Trajectory-Aware Body Interaction Transformer for Multi-Person Pose Forecasting

Xiaogang Peng, Zizhao Wu, Siyuan Mao•Wed Mar 08 2023

A novel Trajectory-Aware Body Interaction Transformer (TBIFormer) for multi-person pose forecasting via effectively modeling body part interactions and empirically evaluates the frame-work on CMU-Mocap, MuPoTS-3D as well as synthesized datasets, demonstrating that the method greatly outperforms the state-of-the-art methods.

37 0

Paper Graph

Adding a benchmark result helps the community track progress.