mmaction2
by open-mmlab
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
AI summary
Video analysis toolkit
A comprehensive video understanding toolbox and benchmark with modular design, supporting various tasks such as action recognition, localization, and retrieval.
- stars
- 4.4K
- forks
- 1.3K
- watching
- 42
- awesome lists
- 3
Similar projects
Found by comparing what the projects do, not just their names.
Computer Vision Library
Provides a foundational library for computer vision research and training deep learning models with high-quality implementation of common CPU and CUDA ops.
Object detection toolkit
An object detection toolbox built on top of PyTorch, providing a modular framework for various tasks such as bounding box detection and instance segmentation.
3D detector
An open-source platform for general 3D object detection with support for multiple modalities and datasets.
Image segmentation framework
An open source toolbox for semantic segmentation in images and medical images.
Generative AI toolkit
A toolkit for building and experimenting with generative AI models for image and video generation, restoration, enhancement, and other tasks.
Model deployment tool
A toolset for deploying deep learning models on various devices and platforms
Action understanding tool
An open-source toolbox for action understanding from video data using PyTorch.
Pose estimator
A comprehensive toolbox for pose estimation tasks in computer vision
openmv/openmv2.4K
Machine vision platform
A platform for machine vision development with programmable cameras and extensive image processing capabilities
Deep learning trainer
Provides a flexible and configurable framework for training deep learning models with PyTorch.
Video foundation models
Develops general video foundation models and related datasets for multimodal understanding and generation through generative and discriminative learning.
Video generator
A deep learning framework for generating videos from text inputs and visual features.
Human model toolkit
Provides a modular framework and tools for working with 3D human parametric models in computer vision and graphics
openbmb/minicpm-v12.9K
Multimodal LLM
A multimodal language model designed to understand images, videos, and text inputs and generate high-quality text outputs.
Chart model trainer
Develops a large-scale dataset and benchmark for training multimodal chart understanding models using large language models.
Featured in 3 awesome lists
Each link jumps to the spot where the list mentions mmaction2.
