Repo AI đang lênCập nhật hằng ngày từ GitHub

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

A curated list of action recognition and related area resources

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

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

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

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

An open-source toolbox for action understanding based on PyTorch

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

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.

Code & Models for Temporal Segment Networks (TSN) in ECCV 2016

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

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

Temporal Segment Networks (TSN) in PyTorch

Data preparation and loader for AMASS

Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101

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

Real-time multi-person action recognition from OpenPose skeleton sequences, with tracking, feature extraction, model training, and inference pipelines for research and prototyping.

Using two stream architecture to implement a classic action recognition method on UCF101 dataset

Papers, code and datasets about deep learning and multi-modal learning for video analysis

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

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

A curated paper list of awesome skeleton-based action recognition.

A list of Human-Object Interaction Learning.

Skeleton-based Action Recognition

temporal action detection with SSN

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

PyTorch implementation of two-stream networks for video action recognition

Code release for ActionFormer (ECCV 2022)

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 contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.

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

[ICCV 2023 & TPAMI 2025] MeViS: A Large-scale Benchmark for Video Segmentation with Motion Expressions

Local Video-LLM powered AI Baby Monitor

SiamMOT: Siamese Multi-Object Tracking