Pinned Repositories
LaViLa
Code release for "Learning Video Representations from Large Language Models"
mmaction
An open-source toolbox for action understanding based on PyTorch
action-detection
temporal action detection with SSN
AVION
[arXiv:2309.16669] Code release for "Training a Large Video Model on a Single Machine in a Day"
bsq-vit
[arXiv:2406.07548] Image and Video Tokenization with Binary Spherical Quantization
decord-dev
dense_flow
Tools to extract dense optical flow from videos, based on OpenCV
RecurrentConvNet-for-Speech
TeSTra
Code for ECCV2022 "Real-time Online Video Detection with Temporal Smoothing Transformers"
zhaoyue-zephyrus's Repositories
zhaoyue-zephyrus/AVION
[arXiv:2309.16669] Code release for "Training a Large Video Model on a Single Machine in a Day"
zhaoyue-zephyrus/bsq-vit
[arXiv:2406.07548] Image and Video Tokenization with Binary Spherical Quantization
zhaoyue-zephyrus/TeSTra
Code for ECCV2022 "Real-time Online Video Detection with Temporal Smoothing Transformers"
zhaoyue-zephyrus/decord-dev
zhaoyue-zephyrus/dense_flow
Tools to extract dense optical flow from videos, based on OpenCV
zhaoyue-zephyrus/denseflow
Extracting optical flow and frames
zhaoyue-zephyrus/ActivityNet
This repository is intended to host tools and demos for ActivityNet
zhaoyue-zephyrus/antialiased-cnns
pip install antialiased-cnns to improve stability and accuracy
zhaoyue-zephyrus/CLIP
Contrastive Language-Image Pretraining
zhaoyue-zephyrus/CompressAI
A PyTorch library and evaluation platform for end-to-end compression research
zhaoyue-zephyrus/compression
Data compression in TensorFlow
zhaoyue-zephyrus/CompressionData
The training data of learned image compression. The data is from flicker.com.
zhaoyue-zephyrus/Deformable-Convolution-V2-PyTorch
Deformable ConvNets V2 in PyTorch
zhaoyue-zephyrus/EfficientNet-PyTorch
A PyTorch implementation of EfficientNet
zhaoyue-zephyrus/FrozenBiLM
[NeurIPS 2022] Zero-Shot Video Question Answering via Frozen Bidirectional Language Models
zhaoyue-zephyrus/kinetics-i3d
Convolutional neural network model for video classification trained on the Kinetics dataset.
zhaoyue-zephyrus/LaViLa
Code release for "Learning Video Representations from Large Language Models"
zhaoyue-zephyrus/metaseq
Repo for external large-scale work
zhaoyue-zephyrus/mmaction
An open-source toolbox for action understanding based on PyTorch
zhaoyue-zephyrus/mmaction2
OpenMMLab's Next Generation Action Understanding Toolbox and Benchmark
zhaoyue-zephyrus/mmcv
Open MMLab Computer Vision Foundation
zhaoyue-zephyrus/mmdetection
Open MMLab Detection Toolbox with PyTorch 1.0
zhaoyue-zephyrus/opencv
Open Source Computer Vision Library
zhaoyue-zephyrus/opencv_extra
OpenCV extra data
zhaoyue-zephyrus/pytorch-distributed
A quickstart and benchmark for pytorch distributed training.
zhaoyue-zephyrus/reformer-pytorch
Reformer, the efficient Transformer, in Pytorch
zhaoyue-zephyrus/SlowFast
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.
zhaoyue-zephyrus/submitit
Python 3.6+ toolbox for submitting jobs to Slurm
zhaoyue-zephyrus/temporal-segment-networks
Code & Models for Temporal Segment Networks (TSN) in ECCV 2016
zhaoyue-zephyrus/video-long-term-feature-banks
Long-Term Feature Banks for Detailed Video Understanding