• Stars
    star
    105
  • Rank 328,134 (Top 7 %)
  • Language
    Python
  • License
    GNU Affero Genera...
  • Created over 3 years ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

[CVPR 2022] S-attack library. Official implementation of two papers "Vehicle trajectory prediction works, but not everywhere" and "Are socially-aware trajectory prediction models really socially-aware?".

S-attack library:
A library for evaluating trajectory prediction models

This library contains two research projects to assess the trajectory prediction models, Scene-attack which evaluates the scene-understanding of models and Social-attack which evaluates social understanding of them.


Vehicle trajectory prediction works, but not everywhere, CVPR 2022
M. Bahari, S. Saadatnejad, A. Rahimi, M. Shaverdikondori, A. Shahidzadeh, S. Moosavi-Dezfooli, A. Alahi
Website                 Paper                 Citation                 Code


Are socially-aware trajectory prediction models really socially-aware?, TR_C 2022
S. Saadatnejad, M. Bahari, P. Khorsandi, M. Saneian, S. Moosavi-Dezfooli, A. Alahi
Website                 Paper                 Citation                 Code


For citation:

@InProceedings{bahari2022sattack,
    author    = {Bahari, Mohammadhossein and Saadatnejad, Saeed and Rahimi, Ahmad and Shaverdikondori, Mohammad and Shahidzadeh, Amir-Hossein and Moosavi-Dezfooli, Seyed-Mohsen and Alahi, Alexandre},
    title     = {Vehicle trajectory prediction works, but not everywhere},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    year      = {2022},
}
@article{saadatnejad2022sattack,
     author = {Saeed Saadatnejad and Mohammadhossein Bahari and Pedram Khorsandi and Mohammad Saneian and Seyed-Mohsen Moosavi-Dezfooli and Alexandre Alahi},
     title = {Are socially-aware trajectory prediction models really socially-aware?},
     journal = {Transportation Research Part C: Emerging Technologies},
     volume = {141},
     pages = {103705},
     year = {2022},
     issn = {0968-090X},
     doi = {https://doi.org/10.1016/j.trc.2022.103705},
}

More Repositories

1

CrowdNav

[ICRA19] Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning
Python
583
star
2

monoloco

A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.
Python
420
star
3

trajnetplusplusbaselines

[ITS'21] Human Trajectory Forecasting in Crowds: A Deep Learning Perspective
Python
244
star
4

UniTraj

A Unified Framework for scalable Vehicle Trajectory Prediction, ECCV 2024
Python
166
star
5

social-nce

[ICCV21] Official implementation of the "Social NCE: Contrastive Learning of Socially-aware Motion Representations" in PyTorch.
Python
157
star
6

causalmotion

[CVPR22] Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective
Python
73
star
7

RRB

Official implementation of "Injecting Knowledge in Data-driven Vehicle Trajectory Predictors", Published in Transportation research part C.
Python
67
star
8

ttt-plus-plus

[NeurIPS21] TTT++: When Does Self-supervised Test-time Training Fail or Thrive?
Python
56
star
9

DePOSit

[ICRA 2023] Official implementation of "A generic diffusion-based approach for 3D human pose prediction in the wild".
Python
49
star
10

bounding-box-prediction

Bounding box prediction library. Official implementation of two papers on human 2D/3D bounding box prediction
Python
46
star
11

trajnetplusplustools

Tools for TrajNet++
Python
42
star
12

monstereo

MonoLoco++ and MonStereo for 3D localization, orientation, bounding box dimensions and social distancing from monocular and / or stereo images. PyTorch Official Implementation.
Python
39
star
13

social-transmotion

[ICLR 2024] Official implementation of "Social-Transmotion: Promptable Human Trajectory Prediction" in PyTorch.
Python
34
star
14

trajnetplusplusdata

Data for TrajNet++ Challenge
31
star
15

detection-attributes-fields

PyTorch implementation of "Detecting 32 Pedestrian Attributes for Autonomous Vehicles"
Python
31
star
16

looking

Python
30
star
17

trajnetplusplusdataset

Dataset Preparation for TrajNet++
Python
29
star
18

collaborative-gan-sampling

[AAAI20] TensorFlow implementation of the Collaborative Sampling in Generative Adversarial Networks
Python
24
star
19

decoupled-pose-prediction

Official implementation of "Learning Decoupled Representations for Human Pose Forecasting" in PyTorch
Python
19
star
20

Person-Re-Identification-with-Confidence

Python
18
star
21

motion-style-transfer

[CoRL22] Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecasting
Python
17
star
22

SVGNet

The official implementation of "SVG-Net: An SVG-based Trajectory Prediction Model"
17
star
23

CIM

Causal Imitative Model official code
Python
14
star
24

openpifpaf_wholebody

PifPaf extension to detect body, foot, face and hand keypoints.
Python
13
star
25

unposed

[RA-L 2024] Official implementation of "Toward Reliable Human Pose Forecasting with Uncertainty"
Python
13
star
26

rock-pytorch

A PyTorch implementation of "Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection"
Python
12
star
27

hybrid-feature-fusion

Python
11
star
28

butterflydetector

Python
9
star
29

pedestrian-transition-dataset

Jupyter Notebook
9
star
30

DLAV-2022

EPFL Deep Learning for Autonomous Vehicles, Spring 2022
Jupyter Notebook
9
star
31

SemDisc

Official implementation of "A Shared Representation for Photorealistic Driving Simulators" in PyTorch.
Python
9
star
32

JRDB-Traj

JRDB dataset: trajectory prediction baselines and data preprocessing
Python
8
star
33

introML-2021

EPFL Introduction to Machine Learning for Engineers, Spring 2021
Jupyter Notebook
7
star
34

SGG-CoRF

Python
7
star
35

CODE

Implementation of CODE: Confident Ordinary Differential Editing
Jupyter Notebook
6
star
36

IntroML-2024

Jupyter Notebook
6
star
37

DLAV-2023

Jupyter Notebook
5
star
38

introML-2023

Jupyter Notebook
5
star
39

Deep-Visual-Re-Identification-with-Confidence

Python
5
star
40

pose-action-recognition

Python
5
star
41

TIC-TAC

[ICML 2024] Code repository for "TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression". We address the problem of sub-optimal covariance estimation in deep heteroscedastic regression by proposing a new model and metric.
Python
5
star
42

openpifpaf-torchhub

Pretrained models for OpenPifPaf via torchhub.
4
star
43

openpifpaf_animalpose

Python
3
star
44

trajnetplusplus-model-zoo

TrajNet++ Model Zoo is a collection of pre-trained models on the TrajNet++ Benchmark
2
star
45

unitraj-DLAV

The UniTraj framework, developed by VITA, adjusted for the project of DLAV course.
Python
2
star
46

DLAV-2024

Jupyter Notebook
2
star
47

introML-2022

EPFL Introduction to Machine Learning for Engineers, Spring 2022
Jupyter Notebook
1
star
48

IncrementalHumanPose

Python
1
star
49

code_template

A repository displaying a possible code structure suitable for Slurm
Python
1
star