Git Stars Git Stars

#video-understanding Repositories

Discover 51 active open source GitHub repositories tagged with #video-understanding, accumulating 114,089 total stars (averaging 2,237 stars per project). Leading this topic is QwenLM/Qwen3-VL with 20,240 stars.

51
Total Repositories
114,089
Total Stars
2,237
Avg Stars/Repo
1
QwenLM/Qwen3-VL

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

QwenLM
โญ 20,240 Jupyter Notebook ๐Ÿ‘ค QwenLM Organization ๐Ÿ• Updated 2026-01-30 ๐Ÿ“… Created 2024-08-29
2
facebookresearch/SlowFast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

facebookresearch
โญ 7,447 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2026-03-16 ๐Ÿ“… Created 2019-08-20
3
LargeWorldModel/LWM

Large World Model -- Modeling Text and Video with Millions Context

LargeWorldModel
โญ 7,391 Python ๐Ÿ‘ค LargeWorldModel Organization ๐Ÿ• Updated 2024-10-19 ๐Ÿ“… Created 2024-02-08
4
open-mmlab/mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

open-mmlab
โญ 5,203 Python ๐Ÿ‘ค open-mmlab Organization ๐Ÿ• Updated 2026-03-18 ๐Ÿ“… Created 2020-07-11
5
facebookresearch/vjepa2

PyTorch code and models for VJEPA2 self-supervised learning from video.

facebookresearch
โญ 4,911 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2026-10-29 ๐Ÿ“… Created 2025-04-25
7
EvolvingLMMs-Lab/lmms-eval

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

EvolvingLMMs-Lab
โญ 4,501 Python ๐Ÿ‘ค EvolvingLMMs-Lab Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2024-03-07
8
NVlabs/VILA

VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

NVlabs
โญ 3,873 Python ๐Ÿ‘ค NVlabs Organization ๐Ÿ• Updated 2026-03-12 ๐Ÿ“… Created 2024-02-23
9
facebookresearch/pytorchvideo

A deep learning library for video understanding research.

facebookresearch
โญ 3,568 Python ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2026-10-16 ๐Ÿ“… Created 2021-03-09
10
OpenGVLab/Ask-Anything

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

OpenGVLab
โญ 3,361 Python ๐Ÿ‘ค OpenGVLab Organization ๐Ÿ• Updated 2026-07-17 ๐Ÿ“… Created 2023-04-19
11
yoloytang/Awesome-LLMs-for-Video-Understanding

๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅ [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.

yoloytang
โญ 3,310 ๐Ÿ‘ค yoloytang User ๐Ÿ• Updated 2026-11-11 ๐Ÿ“… Created 2023-07-16
12
google-research/kubric

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

google-research
โญ 2,859 Jupyter Notebook ๐Ÿ‘ค google-research Organization ๐Ÿ• Updated 2026-05-21 ๐Ÿ“… Created 2020-07-22
13
OpenGVLab/InternVideo

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

OpenGVLab
โญ 2,421 Python ๐Ÿ‘ค OpenGVLab Organization ๐Ÿ• Updated 2026-07-02 ๐Ÿ“… Created 2022-11-23
14
facebookresearch/perception_models

State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

facebookresearch
โญ 2,415 Jupyter Notebook ๐Ÿ‘ค facebookresearch Organization ๐Ÿ• Updated 2026-04-13 ๐Ÿ“… Created 2025-04-16
15
zai-org/GLM-V

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

zai-org
โญ 2,406 Python ๐Ÿ‘ค zai-org Organization ๐Ÿ• Updated 2026-11-06 ๐Ÿ“… Created 2025-06-28
16
mit-han-lab/temporal-shift-module

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

mit-han-lab
โญ 2,167 Python ๐Ÿ‘ค mit-han-lab Organization ๐Ÿ• Updated 2024-07-11 ๐Ÿ“… Created 2019-03-27
17
HKUDS/VideoAgent

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

HKUDS
โญ 2,059 Python ๐Ÿ‘ค HKUDS Organization ๐Ÿ• Updated 2026-07-22 ๐Ÿ“… Created 2025-07-16
18
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.

NVIDIA-AI-Blueprints
โญ 2,003 Python ๐Ÿ‘ค NVIDIA-AI-Blueprints Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2024-10-22
โญ 1,795 Python ๐Ÿ‘ค microsoft Organization ๐Ÿ• Updated 2026-11-02 ๐Ÿ“… Created 2026-06-15
20
PaddlePaddle/PaddleVideo

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.

PaddlePaddle
โญ 1,698 Python ๐Ÿ‘ค PaddlePaddle Organization ๐Ÿ• Updated 2025-02-12 ๐Ÿ“… Created 2020-11-12
21
bytedance/SALMONN

SALMONN family: A suite of advanced multi-modal LLMs

bytedance
โญ 1,576 ๐Ÿ‘ค bytedance Organization ๐Ÿ• Updated 2026-10-16 ๐Ÿ“… Created 2023-08-11
22
bytedance/Lance

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

bytedance
โญ 1,370 Python ๐Ÿ‘ค bytedance Organization ๐Ÿ• Updated 2026-07-14 ๐Ÿ“… Created 2026-05-15
23
DAMO-NLP-SG/VideoLLaMA3

Frontier Multimodal Foundation Models for Image and Video Understanding

DAMO-NLP-SG
โญ 1,174 Jupyter Notebook ๐Ÿ‘ค DAMO-NLP-SG Organization ๐Ÿ• Updated 2025-08-14 ๐Ÿ“… Created 2025-01-19
24
TheShadow29/awesome-grounding

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

TheShadow29
โญ 1,132 ๐Ÿ‘ค TheShadow29 User ๐Ÿ• Updated 2026-10-16 ๐Ÿ“… Created 2018-09-03
25
mit-han-lab/streaming-vlm

StreamingVLM: Real-Time Understanding for Infinite Video Streams

mit-han-lab
โญ 1,095 Python ๐Ÿ‘ค mit-han-lab Organization ๐Ÿ• Updated 2025-10-15 ๐Ÿ“… Created 2025-10-11
26
OpenGVLab/VideoMamba

[ECCV2024] VideoMamba: State Space Model for Efficient Video Understanding

OpenGVLab
โญ 1,052 Python ๐Ÿ‘ค OpenGVLab Organization ๐Ÿ• Updated 2024-07-06 ๐Ÿ“… Created 2024-03-11
27
cuixing158/Awesome-CV-MasterHub

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

cuixing158
โญ 986 ๐Ÿ‘ค cuixing158 User ๐Ÿ• Updated 2026-11-08 ๐Ÿ“… Created 2025-02-14
28
activitynet/ActivityNet

This repository is intended to host tools and demos for ActivityNet

activitynet
โญ 965 Jupyter Notebook ๐Ÿ‘ค activitynet Organization ๐Ÿ• Updated 2024-03-21 ๐Ÿ“… Created 2015-10-23
29
PKU-YuanGroup/Chat-UniVi

[CVPR 2024 Highlight๐Ÿ”ฅ] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

PKU-YuanGroup
โญ 943 Python ๐Ÿ‘ค PKU-YuanGroup Organization ๐Ÿ• Updated 2024-10-16 ๐Ÿ“… Created 2023-11-13
30
Valen-Team/Valen

Open multimodal decision models, 0.8B to 27B, for text, images and video. Decide with probabilities over your own candidates and locate with bounding boxes, in place of generated text. Free API, ONNX, GGUF, vLLM and SGLang; fine-tuning code included.

Valen-Team
โญ 932 Python ๐Ÿ‘ค Valen-Team Organization ๐Ÿ• Updated 2026-11-15 ๐Ÿ“… Created 2026-09-23
31
tulerfeng/Video-R1

Video-R1: Reinforcing Video Reasoning in MLLMs [๐Ÿ”ฅthe first paper to explore R1 for video]

tulerfeng
โญ 900 Python ๐Ÿ‘ค tulerfeng User ๐Ÿ• Updated 2025-12-14 ๐Ÿ“… Created 2025-02-22
32
DirtyHarryLYL/LLM-in-Vision

Recent LLM-based CV and related works. Welcome to comment/contribute!

DirtyHarryLYL
โญ 868 ๐Ÿ‘ค DirtyHarryLYL User ๐Ÿ• Updated 2025-03-08 ๐Ÿ“… Created 2023-03-10
33
dvlab-research/LLaMA-VID

LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models (ECCV 2024)

JIA-Lab-research
โญ 854 Python ๐Ÿ‘ค JIA-Lab-research Organization ๐Ÿ• Updated 2024-07-29 ๐Ÿ“… Created 2023-11-28
34
OpenMOSS/MOSS-VL

An open-weight 11B model series for long-form and real-time video understanding

OpenMOSS
โญ 838 C++ ๐Ÿ‘ค OpenMOSS Organization ๐Ÿ• Updated 2026-10-14 ๐Ÿ“… Created 2026-04-08
35
CodeGoat24/UnifiedReward

Official implementation of UnifiedReward & [NeurIPS 2025] UnifiedReward-Think & UnifiedReward-Flex

CodeGoat24
โญ 831 Python ๐Ÿ‘ค CodeGoat24 User ๐Ÿ• Updated 2026-06-18 ๐Ÿ“… Created 2025-03-04
37
vision-x-nyu/thinking-in-space

Official repo and evaluation implementation of VSI-Bench

vision-x-nyu
โญ 734 Python ๐Ÿ‘ค vision-x-nyu Organization ๐Ÿ• Updated 2025-08-05 ๐Ÿ“… Created 2024-12-14
38
OpenGVLab/VideoMAEv2

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

OpenGVLab
โญ 730 Python ๐Ÿ‘ค OpenGVLab Organization ๐Ÿ• Updated 2024-10-08 ๐Ÿ“… Created 2023-04-04
39
showlab/videollm-online

VideoLLM-online: Online Video Large Language Model for Streaming Video (CVPR 2024)

showlab
โญ 690 Python ๐Ÿ‘ค showlab Organization ๐Ÿ• Updated 2025-11-26 ๐Ÿ“… Created 2024-06-17
40
magic-research/PLLaVA

Official repository for the paper PLLaVA

magic-research
โญ 676 Python ๐Ÿ‘ค magic-research Organization ๐Ÿ• Updated 2024-07-28 ๐Ÿ“… Created 2024-04-18
41
bytedance/vidi

The official repo for "Vidi: Large Multimodal Models for Video Understanding and Editing"

bytedance
โญ 662 Python ๐Ÿ‘ค bytedance Organization ๐Ÿ• Updated 2026-08-03 ๐Ÿ“… Created 2025-02-08
43
Vision-CAIR/MiniGPT4-video

Official code for Goldfish model for long video understanding and MiniGPT4-video for short video understanding

Vision-CAIR
โญ 637 Python ๐Ÿ‘ค Vision-CAIR Organization ๐Ÿ• Updated 2024-12-10 ๐Ÿ“… Created 2024-03-23
44
jy0205/LaVIT

LaVIT: Empower the Large Language Model to Understand and Generate Visual Content

jy0205
โญ 601 Jupyter Notebook ๐Ÿ‘ค jy0205 User ๐Ÿ• Updated 2024-10-06 ๐Ÿ“… Created 2023-09-09
45
oxbshw/watch-skill

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio, and screen activity into searchable, timestamped evidence, and proves work with deterministic contractsโ€”not model opinions. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

oxbshw
โญ 599 Python ๐Ÿ‘ค oxbshw User ๐Ÿ• Updated 2026-11-16 ๐Ÿ“… Created 2026-07-05
46
lwpyh/Awesome-MLLM-Reasoning-Collection

A collection of multimodal reasoning papers, codes, datasets, benchmarks and resources.

lwpyh
โญ 598 ๐Ÿ‘ค lwpyh User ๐Ÿ• Updated 2026-04-01 ๐Ÿ“… Created 2025-03-16
47
zhenyingfang/Awesome-Temporal-Action-Detection-Temporal-Action-Proposal-Generation

Temporal Action Detection & Weakly Supervised Temporal Action Detection & Temporal Action Proposal Generation

zhenyingfang
โญ 597 ๐Ÿ‘ค zhenyingfang User ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2020-03-09
48
gokayfem/ComfyUI_VLM_nodes

ComfyUI nodes for vision-language models: Qwen3-VL, Moondream 3, Florence-2, SmolVLM2, InternVL, Gemma 3, MiniCPM-V. Plus open-vocabulary detection, SAM2/SAM3 segmentation, video temporal reasoning, GGUF via llama.cpp, and hosted LLM/VLM APIs.

gokayfem
โญ 592 Python ๐Ÿ‘ค gokayfem User ๐Ÿ• Updated 2026-08-08 ๐Ÿ“… Created 2024-01-24
49
SAOS-3624/dsh-video-storyboard

Scene-aware storyboard for DeepSeek Harness: 9โ€“16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.

SAOS-3624
โญ 585 JavaScript ๐Ÿ‘ค SAOS-3624 User ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-10-26
50
AssafSinger94/dino-tracker

Official Pytorch Implementation for โ€œDINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Videoโ€ (ECCV 2024)

AssafSinger94
โญ 543 Python ๐Ÿ‘ค AssafSinger94 User ๐Ÿ• Updated 2024-11-23 ๐Ÿ“… Created 2024-04-03

Frequently Asked Questions

1

What is the most popular #video-understanding repository on GitHub?

The top ranked open source #video-understanding project on GitHub is QwenLM/Qwen3-VL with 20,240 stars. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

2

Which programming languages are most used in #video-understanding repositories?

Among the top ranked #video-understanding projects on GitHub, the most common programming languages are Python, Jupyter Notebook, C++, JavaScript.

3

How is the #video-understanding repository ranking calculated?

We track 51 active open source repositories tagged with #video-understanding (500+ stars), totaling 114,089 stars with an average of 2,237 stars per repository. Rankings update daily from the GitHub API.