ChuhuaW

SGNet.pytorch

Pytorch Implementation for Stepwise Goal-Driven Networks for Trajectory Prediction (RA-L/ICRA2022)

Advlight

Code for "Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink" (CVPR 2021)

All-Hands-on-Desk

Hand Segmentation and Activity Localization in EgoHands Dataset

caffe

Caffe: a fast open framework for deep learning.

cpp_notakto

C_notakto

Ego-Exo

Code accompanying Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos (CVPR 2021)

Flight-Delay

flownet2-pytorch

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks

globi-IVMOOC

The interactions of creatures in tropical and temperate rainforests by using visualization methods and to examine whether the interactions differ between the biospheres.

long-short-term-transformer

Long Short-Term Transformer for Online Action Detection

Notakto_AlphaZero

A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4

Stealthy_Adversarial_Attacks.pytorch

optical_adversarial_attack

Code for "Engineering pupil function for optical adversarial attacks," Opt. Express 30, 6500-6518 (2022).

Q-learning-Tic-Tac-Toe

Reinforcement learning of the game of Tic Tac Toe in Python

reverse_tic_7x7

ShadowAttack

Code of our CVPR 2022 paper "Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon"

SiamFC-PyTorch

SiamFC PyTorch

SpaceNetExploration

A sample project demonstrating how to extract building footprints from satellite images using a semantic segmentation model. Data from the SpaceNet Challenge.

SQL_coursera

tad-IROS2019

Code of the Unsupervised Traffic Accident Detection paper in Pytorch.

tic-tac-GO_ZERO

Alpha Go Zero for 5x5 reverse tic-tac-toe

Trajectron-plus-plus

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).