Erica Weng
ericaweng
Carnegie Mellon University Robotics Institute
Languages
Repos
18
Stars
10
Forks
1
Top Language
Python
Loading contributions...
Top Repositories
Code for the ICCV 2023 conference paper Joint Metrics Matter: A Better Standard for Trajectory Forecasting
PyTorch Lightning implementation of Joint AgentFormer from Joint Metrics Matter (https://arxiv.org/abs/2305.06292) and AgentFormer (https://arxiv.org/abs/2103.14023)
State-of-the-art methods for human trajectory forecasting. Contains code for papers published at ECCV 2020 and ICCV 2021.
There is an updated version of this repository here: https://github.com/ericaweng/Joint_AgentFormer
https://ericaweng.github.io
A unified interface to many trajectory forecasting datasets.
Repositories
18PyTorch Lightning implementation of Joint AgentFormer from Joint Metrics Matter (https://arxiv.org/abs/2305.06292) and AgentFormer (https://arxiv.org/abs/2103.14023)
https://ericaweng.github.io
A unified interface to many trajectory forecasting datasets.
No description provided.
StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.
No description provided.
Code for the ICCV 2023 conference paper Joint Metrics Matter: A Better Standard for Trajectory Forecasting
No description provided.
No description provided.
State-of-the-art methods for human trajectory forecasting. Contains code for papers published at ECCV 2020 and ICCV 2021.
There is an updated version of this repository here: https://github.com/ericaweng/Joint_AgentFormer
[ECCV2022] Official implementation of the paper "View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums"
[CVPR2022] Remember Intentions: Retrospective-Memory-based Trajectory Prediction
Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018
Code accompanying the ECCV 2020 paper "Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data" by Tim Salzmann*, Boris Ivanovic*, Punarjay Chakravarty, and Marco Pavone (* denotes equal contribution).
No description provided.
No description provided.
No description provided.