Stars
An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.
Collect some World Models for Autonomous Driving (and Robotic) papers.
Image and Video Generation Weekly Paper Analysis
Segment-anything interactively in NeRF.
Code + pre-trained models for the paper Keeping Your Eye on the Ball Trajectory Attention in Video Transformers
Vision toolbox for video related tasks including action recognition, multi-object tracking.
PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)
PyTorch implementation of Contrastive Learning methods
Code for training temporal fully-connected CRF models in Torch
👾 Fast and simple video download library and CLI tool written in Go
Weakly Supervised Temporal Action Localization Using Deep Metric Learning
MSGAN: Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis (CVPR2019)
W-TALC: Weakly-supervised Temporal Activity Localization and Classification
Training code for the ACAM action detection model.
VideoX: a collection of video cross-modal models
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
StarGAN v2 - Official PyTorch Implementation (CVPR 2020)
A list of papers on Generative Adversarial (Neural) Networks
Ready to train Pytorch implementation of the CVPR'19 paper "Self-Supervised GANs via Auxiliary Rotation Loss"
Video Representation Learning by Dense Predictive Coding. Tengda Han, Weidi Xie, Andrew Zisserman.
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
Multi-mapping Image-to-Image Translation via Learning Disentanglement. NeurIPS2019
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Pytorch implementation of Self-Attention Generative Adversarial Networks (SAGAN)
[ICCV 2019] "AutoGAN: Neural Architecture Search for Generative Adversarial Networks" by Xinyu Gong, Shiyu Chang, Yifan Jiang and Zhangyang Wang