Build software better, together

open-mmlab / mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

benchmark deep-learning pytorch ava x3d action-recognition video-understanding video-classification tsm non-local i3d tsn slowfast temporal-action-localization spatial-temporal-action-detection openmmlab posec3d uniformerv2

Updated Mar 18, 2026
Python

EvolvingLMMs-Lab / lmms-eval

Star

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

benchmark evaluation agi video-understanding vlm multimodal large-language-models vision-language-model llm-evaluation audio-evaluation multimodal-evaluation

Updated Sep 5, 2026
Python

jinwchoi / awesome-action-recognition

Star

A curated list of action recognition and related area resources

awesome activity-recognition video-processing awesome-list object-recognition action-recognition video-understanding activity-understanding pose-estimation action-detection video-recognition action-classification

Updated May 13, 2023

OpenGVLab / Ask-Anything

Star

[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

chat video gradio big-model video-understanding captioning-videos video-question-answering foundation-models large-model large-language-models chatgpt langchain stablelm

Updated Jul 17, 2026
Python

zai-org / GLM-V

Star

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

video-understanding reasoning vlm image2text

Updated Sep 2, 2026
Python

OpenGVLab / InternVideo

Star

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

Updated Jul 2, 2026
Python

mit-han-lab / temporal-shift-module

Star

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

acceleration low-latency video-understanding tsm nvidia-jetson-nano efficient-model temporal-modeling

Updated Jul 11, 2024
Python

open-mmlab / mmaction

Star

An open-source toolbox for action understanding based on PyTorch

pytorch action-recognition video-understanding action-detection temporal-action-detection temporal-action-localization spatial-temporal-action-detection

Updated Apr 8, 2022
Python

HKUDS / VideoAgent

Star

[EMNLP2026] "VideoAgent: All-in-One Agentic Framework for Video Understanding and Editing, and Remaking"

podcast audio-editing agents video-editing video-understanding llm-agents notebooklm audio-understanding

Updated Jul 22, 2026
Python

NVIDIA-AI-Blueprints / video-search-and-summarization

Star

NVIDIA AI Blueprint for video search and summarization (VSS) is a GPU-accelerated reference architecture for building video analytics agents with real-time verified alerts, visual Q&A, and automated reporting. The VSS Blueprint uses vision language models (VLMs) such as NVIDIA Cosmos, LLMs such as NVIDIA Nemotron, RAG, and NVIDIA NIMs.

Updated Sep 6, 2026
Python

MCG-NJU / VideoMAE

Star

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

pytorch transformer action-recognition video-understanding mae video-analysis video-representation-learning self-supervised-learning masked-autoencoder vision-transformer video-transformer neurips-2022

Updated Dec 8, 2023
Python

PaddlePaddle / PaddleVideo

Star

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.