video-understanding 开源项目推荐（621 个）

open-mmlab /mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

EvolvingLMMs-Lab /lmms-eval

适用于文本、图像、视频和音频任务的通用多模态评估工具包

jinwchoi /awesome-action-recognition

A curated list of action recognition and related area resources

OpenGVLab /Ask-Anything

[CVPR 2024亮点][VideoChatGPT] ChatGPT具有视频理解！还有更多支持LM，例如miniGPT 4、StableLM和MOSS。

OpenGVLab /InternVideo

[ECCV2024] 面向多模态理解的视频基础模型与数据

zai-org /GLM-V

GLM-4.6V/4.5V/4.1V-Thinking：通过可扩展强化学习实现多功能多模式推理

mit-han-lab /temporal-shift-module

[ICCV TSM：用于高效视频理解的时间偏移模块

HKUDS /VideoAgent

VideoAgent：用于视频理解、编辑和重新制作的一体化学习框架

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

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.

open-mmlab /mmaction

An open-source toolbox for action understanding based on PyTorch

MCG-NJU /VideoMAE

[NeurIPS 2022聚焦] VideoMAE：屏蔽自动编码器是自我监督视频预训练的数据高效学习者

microsoft /Mage

该项目在 GitHub 上没有填写描述

PaddlePaddle /PaddleVideo

基于PaddlePaddle的精彩视频理解工具包。它支持视频数据注释工具、轻量级的Ruby和基于骨架的动作识别模型、视频标记和运动动作检测的实际应用。

yjxiong /temporal-segment-networks

ECCV 2016中的时间段网络（TSN）代码和模型

bytedance /SALMONN

SALMONN family: A suite of advanced multi-modal LLMs

bytedance /Lance

A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

TheShadow29 /awesome-grounding

awesome grounding: A curated list of research papers in visual grounding

yjxiong /tsn-pytorch

Temporal Segment Networks (TSN) in PyTorch

cuixing158 /Awesome-CV-MasterHub

🔥 🔥 🔥 A paper list of some recent Computer Vision(CV) works

PKU-YuanGroup /Chat-UniVi

[CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding