MediaBrain-SJTU/MemoNet

[CVPR2022] Remember Intentions: Retrospective-Memory-based Trajectory Prediction

34
/ 100
Emerging

This project helps predict where people or objects will move in the near future by analyzing their past movements and comparing them to a stored 'memory' of similar scenarios. You input a sequence of past locations, and it outputs a predicted future path, including the likely destination. It's designed for anyone needing to forecast movement, such as researchers in robotics, autonomous driving, or crowd analysis.

137 stars. No commits in the last 6 months.

Use this if you need to accurately predict the future trajectories of agents like pedestrians or vehicles, leveraging a system that learns from and recalls similar past events for improved accuracy and interpretability.

Not ideal if you're looking for a simple, out-of-the-box solution for non-trajectory prediction tasks or if your data doesn't involve sequential movement patterns.

trajectory-prediction robotics autonomous-vehicles human-behavior-analysis crowd-simulation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 16 / 25

How are scores calculated?

Stars

137

Forks

19

Language

Python

License

Last pushed

Sep 11, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MediaBrain-SJTU/MemoNet"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.