MediaBrain-SJTU/MemoNet
[CVPR2022] Remember Intentions: Retrospective-Memory-based Trajectory Prediction
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.
Stars
137
Forks
19
Language
Python
License
—
Category
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.
Higher-rated alternatives
StanfordASL/Trajectron
Code accompanying "The Trajectron: Probabilistic Multi-Agent Trajectory Modeling with Dynamic...
StanfordASL/Trajectron-plus-plus
Code accompanying the ECCV 2020 paper "Trajectron++: Dynamically-Feasible Trajectory Forecasting...
uber-research/LaneGCN
[ECCV2020 Oral] Learning Lane Graph Representations for Motion Forecasting
agrimgupta92/sgan
Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks",...
devendrachaplot/Neural-SLAM
Pytorch code for ICLR-20 Paper "Learning to Explore using Active Neural SLAM"