Motion Forecasting

38 papers with code • 2 benchmarks • 6 datasets

Motion forecasting is the task of predicting the location of a tracked object in the future

Most implemented papers

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

agrimgupta92/sgan CVPR 2018

Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments.

Social NCE: Contrastive Learning of Socially-aware Motion Representations

vita-epfl/social-nce ICCV 2021

Learning socially-aware motion representations is at the core of recent advances in multi-agent problems, such as human motion forecasting and robot navigation in crowds.

Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data

StanfordASL/Trajectron-plus-plus ECCV 2020

Reasoning about human motion is an important prerequisite to safe and socially-aware robotic navigation.

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

wenkaip-1836890/pyromid_l5prediction 25 Jun 2020

Motivated by the impact of large-scale datasets on ML systems we present the largest self-driving dataset for motion prediction to date, containing over 1, 000 hours of data.

Peeking into the Future: Predicting Future Person Activities and Locations in Videos

google/next-prediction CVPR 2019

To facilitate the training, the network is learned with an auxiliary task of predicting future location in which the activity will happen.

Deep Predictive Motion Tracking in Magnetic Resonance Imaging: Application to Fetal Imaging

bchimagine/DeepPredictiveMotionTracking 25 Sep 2019

Nevertheless, visual monitoring of fetal motion based on displayed slices, and navigation at the level of stacks-of-slices is inefficient.

Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction

abduallahmohamed/Social-STGCNN CVPR 2020

Better machine understanding of pedestrian behaviors enables faster progress in modeling interactions between agents such as autonomous vehicles and humans.

Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

autonomousvision/transfuser CVPR 2021

How should representations from complementary sensors be integrated for autonomous driving?

DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets

Tsinghua-MARS-Lab/DenseTNT ICCV 2021

In this work, we propose an anchor-free and end-to-end trajectory prediction model, named DenseTNT, that directly outputs a set of trajectories from dense goal candidates.

Are socially-aware trajectory prediction models really socially-aware?

vita-epfl/s-attack 24 Aug 2021

An attack is a small yet carefully-crafted perturbations to fail predictors.