OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
-
Updated
May 16, 2024 - Python
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
Code & Models for Temporal Segment Networks (TSN) in ECCV 2016
[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding
Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.
An open-source toolbox for action understanding based on PyTorch
Temporal Segment Networks (TSN) in PyTorch
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
temporal action detection with SSN
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Video Foundation Models & Data for Multimodal Understanding
ActionVLAD for video action classification (CVPR 2017)
Dataset, code and model for the CVPR'20 paper "The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction". And for the ECCV'20 SimAug paper.
The 2nd place Solution to the Youtube-8M Video Understanding Challenge by Team Monkeytyping (based on tensorflow)
[CVPR 2021] TDN: Temporal Difference Networks for Efficient Action Recognition
STEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)
[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
TensorFlow code for finetuning I3D model on UCF101.
Official code for MiniGPT4-video
Easily convert RGB video data (e.g. .avi) to the TensorFlow tfrecords file format for training e.g. a NN in TensorFlow. This implementation allows to limit the number of frames per video to be stored in the tfrecords.
[CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding
Add a description, image, and links to the video-understanding topic page so that developers can more easily learn about it.
To associate your repository with the video-understanding topic, visit your repo's landing page and select "manage topics."