computer-vision

motion prediction

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 motion-prediction

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find motion-prediction models and implementations

sshaoshuai/mtr

3 papers 560

Datasets

UCY

Waymo Open Motion Dataset

Argoverse 2 Motion Forecasting

Expi

GTA-IM Dataset

Subtasks

OPD: Single-view 3D Openable Part Detection

Most implemented papers

On Human Motion Prediction Using Recurrent Neural Networks

Julieta Martinez, Michael J. Black, J. Romero•Fri May 05 2017

It is shown that, surprisingly, state of the art performance can be achieved by a simple baseline that does not attempt to model motion at all, and a simple and scalable RNN architecture is proposed that obtains state-of-the-art performance on human motion prediction.

997

Content

vita-epfl/unitraj

2 papers 42

SinD

NTU RGB+D 2D

Lyft Level 5 Prediction

VIENA2

CITR & DUT

0

Paper Graph

Tracking Without Bells and Whistles

L. Leal-Taixé, Philipp Bergmann, Tim Meinhardt•Tue Mar 12 2019

Overall, Tracktor yields superior tracking performance than any current tracking method and the analysis exposes remaining and unsolved tracking challenges to inspire future research directions.

1005 0

Paper Graph

GRIP++: Enhanced Graph-based Interaction-aware Trajectory Prediction for Autonomous Driving

Xin Li, Xiaowen Ying, Mooi Choo Choo Chuah•Tue Jul 16 2019

An improved scheme called GRIP++, which uses both fixed and dynamic graphs for trajectory predictions of different types of traffic agents and achieves better prediction accuracy than state-of-the-art schemes.

179 0

Paper Graph

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 0

Paper Graph

HP-GAN: Probabilistic 3D Human Motion Prediction via GAN

Zicheng Liu, E. Barsoum, J. Kender•Sun Nov 26 2017

A novel sequence-to-sequence model for probabilistic human motion prediction, trained with a modified version of improved Wasserstein generative adversarial networks (WGAN-GP), in which the model learns a probability density function of future human poses conditioned on previous poses.

362 0

Paper Graph

BiHMP-GAN: Bidirectional 3D Human Motion Prediction GAN

R. Venkatesh Babu, Jogendra Nath Kundu, Maharshi Gor•Wed Dec 05 2018

Outcomes of both qualitative and quantitative evaluations, on the probabilistic generations of the model, demonstrate the superiority of BiHMP-GAN over previously available methods.

156 0

Paper Graph

One Thousand and One Hours: Self-driving Motion Prediction Dataset

Ashesh Jain, V. Iglovikov, Sammy Omari, G. Zuidhof, J. Houston, Luca Bergamini, Yawei Ye, Peter Ondruska•Wed Jun 24 2020

This collection was collected by a fleet of 20 autonomous vehicles along a fixed route in Palo Alto, California over a four-month period and forms the largest, most complete and detailed dataset to date for the development of self-driving, machine learning tasks such as motion forecasting, planning and simulation.

439 0

Paper Graph

History Repeats Itself: Human Motion Prediction via Motion Attention

M. Salzmann, Wei Mao, Miaomiao Liu•Wed Jul 22 2020

An attention-based feed-forward network is introduced that explicitly leverages the observation that human motion tends to repeat itself to capture motion attention to capture the similarity between the current motion context and the historical motion sub-sequences.

344 0

Paper Graph

Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks

Y. Gal, Vatsal Raina, A. Malinin, Neil Band, German Chesnokov, M. Gales, A. Noskov, Andrey Ploskonosov, Liudmila Prokhorenkova, Ivan Provilkov, Vyas Raina, Mariya Shmatova, Panos Tigas, Boris Yangel•Wed Jul 14 2021

This work proposes the Shifts Dataset, a standardized large-scale dataset of tasks across a range of modalities affected by distributional shifts that will enable researchers to meaningfully evaluate the plethora of recently developed uncertainty quantification methods, as well as assessment criteria and state-of-the-art baselines.

148 0

Paper Graph

Scene Transformer: A unified architecture for predicting multiple agent trajectories

Jiquan Ngiam, Jonathon Shlens, Vijay Vasudevan, Jeffrey Ling, Benjamin Caine, Chenxi Liu, Benjamin Sapp, Zhifeng Chen, Zhengdong Zhang, H. Chiang, R. Roelofs, Alex Bewley, Ashish Venugopal, David J. Weiss•Mon Jun 14 2021

A model for predicting the behavior of all agents jointly, producing consistent futures that account for interactions between agents is formulated, and it is shown that the model can unify a variety of motion prediction tasks from joint motion predictions to conditioned prediction.

236 0

Paper Graph

Adding a benchmark result helps the community track progress.