Popular GitHub Repositories for Video Classification

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

Video classification tools using 3D ResNet

[ICLR2022] official implementation of UniFormer

Implementation of TimeSformer from Facebook AI, a pure attention-based solution for video classification

Explore Action Recognition

Implementation of STAM (Space Time Attention Model), a pure and simple attention model that reaches SOTA for video classification

Sign Language Recognition for Deaf People

Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks, debuted in ICLR 2022

Learning Video Representations from Correspondence Proposals (CVPR 2019 Oral)

Deepfakes Video classification via CNN, LSTM, C3D and triplets [IWBF'20]

[ICCV 2019 Oral] TA3N: https://github.com/cmhungsteve/TA3N (Most updated repo)

The notebook explains the various steps to obtain the results of publication: "Is Space-Time Attention All You Need for Video Understanding?"

Keras 3 Implementation of Video Swin Transformers for 3D Video Modeling

Human action classification for video, offline and natively on iOS via Core ML

[NeurIPS'22] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Python script to fine tune Open source Video Vision Transformer (ViVit) using HuggingFace Trainer Library

Action Recognition using Convolutional Neural Network (CNN)

Video Content-Based Advertisement Recommendation Using Text Classification

A simple and fun video classification/action recognition using VGG16 as a feature extractor and RNN.