JiazeWang

AgentFormer

[ICCV 2021] Official PyTorch Implementation of "AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting".

AutoBots_JZ

Autoformer

About Code release for "Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting" (NeurIPS 2021), https://arxiv.org/abs/2106.13008

chatgpt-demo

A demo repo based on OpenAI API (gpt-3.5-turbo)

CLIP

Contrastive Language-Image Pretraining

deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

dense_v2

DenseTNT

earth-forecasting-transformer

Official implementation of Earthformer

faceswap

Deepfakes Software For All

google-images-download

Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!

Hello-World-Github

Hello world project

Image-Downloader

Download images from Google, Bing, Baidu. 谷歌、百度、必应图片下载.

ImageMol

ImageMol is a molecular image-based pre-training deep learning framework for computational drug discovery.

kubric

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

LAV

(CVPR 2022) A minimalist, mapless, end-to-end self-driving stack for joint perception, prediction, planning and control.

MAE

PyTorch implementation of Masked Autoencoder

MAE-pytorch

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

mmTransformer

[CVPR 2021] "Multimodal Motion Prediction with Stacked Transformers": official code implementation and project page.

OpenSTL

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

PAConv

(CVPR 2021) PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

Point-MAE

[ECCV2022] Masked Autoencoders for Point Cloud Self-supervised Learning

PoseAug

[CVPR 2021] PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation, (Oral, Best Paper Candidate)

PoseTriplet

[CVPR 2022] PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision (Oral)

QCNet

[CVPR 2023] Query-Centric Trajectory Prediction

reagent

ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning

SP-GAN

tracking_wo_bnw

Implementation of "Tracking without bells and whistles” and the multi-object tracking "Tracktor"

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).

transfuser_jiaze

[CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving