naraysa

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

DALL-E

PyTorch package for the discrete VAE used for DALL·E.

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

ImageBind

ImageBind One Embedding Space to Bind Them All

insanely-fast-whisper

SlowFast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

ConvNeXt

Code release for ConvNeXt model

pytorchvideo

A deep learning library for video understanding research.

Deformable-DETR

Deformable DETR: Deformable Transformers for End-to-End Object Detection.

video-nonlocal-net

Non-local Neural Networks for Video Classification

kinetics-i3d

Convolutional neural network model for video classification trained on the Kinetics dataset.

ViTPose

The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"

VMZ

VMZ: Model Zoo for Video Modeling

OWOD

(CVPR 2021 Oral) Open World Object Detection

PyTorch-Pretrained-ViT

Vision Transformer (ViT) in PyTorch

kinetics-dataset

PyVideoResearch

A repository of common methods, datasets, and tasks for video research

kinetics_i3d_pytorch

Inflated i3d network with inception backbone, weights transfered from tensorflow

DAB-DETR

[ICLR 2022] Official implementation of the paper "DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR"

gpu_flow

GPU based optical flow extraction in OpenCV

MinVIS

OW-DETR

[CVPR 2022] Official Pytorch code for OW-DETR: Open-world Detection Transformer

Motionformer

Code + pre-trained models for the paper Keeping Your Eye on the Ball Trajectory Attention in Video Transformers

Materials-Temporal-Action-Detection

temporal action detection: benchmark results, features download etc.

tfvaegan

[ECCV 2020] Official Pytorch implementation for "Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification". SOTA results for ZSL and GZSL

fishervector

Improved Fisher Vector Implementation- extracts Fisher Vector features from your data

strm

[CVPR 2022] Official Pytorch Implementation for "Spatio-temporal Relation Modeling for Few-shot Action Recognition". SOTA Results for Few-shot Action Recognition

BiAM

[ICCV 2021] Official Pytorch implementation for Discriminative Region-based Multi-Label Zero-Shot Learning SOTA results on NUS-WIDE and OpenImages

Generative_MLZSL

[TPAMI 2023] Generative Multi-Label Zero-Shot Learning

paper_summary

Write summaries of papers I've read in Japanese