[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
-
Updated
Dec 15, 2025 - Python
[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
⚡ Build structured YouTube datasets at scale — effortlessly fetch transcripts and rich metadata for NLP, ML, and AI workflows.
I3D implemetation in Keras + video preprocessing + visualization of results
The GMPHD filter based Online Multiple Object Tracker using Group Management and Relative Motion Analysis
Automatic Number Plate Recognition with YOLOv5 and PyTorch
Retrieve YouTube data from your Browser
Frame-differencing method: Automatic extraction of movement from video data
A simple YouTube Downloader.
Image and video data released into the public-domain
Object Recognition Prototype for Detection of Bell Peppers and Kiwis in Video Data (Deployed on NVIDIA Jetson Nano)
This annotation tool is build to clean and create video dataset.
Human gesture recognition from videos sequences.
This repository contains the material for learning Python, Bayesian statistics, and kinematics analysis of MLD study group.
YouTube search metadata scraper
vidWFT (video Wave Float Tracker) leverages opencv CSRT to track floats in water, deriving wave characteristics.
youtube scraping automation toolkit
Explore Vimeo video data with Bright Data API for content analysis and trends.
bilibili homepage data extractor
Bright Data API로 콘텐츠 분석 및 트렌드를 위해 Vimeo 비디오 데이터를 탐색합니다.
A React Native SDK to monitor, measure, and optimize video performance on Android and iOS.
Add a description, image, and links to the video-data topic page so that developers can more easily learn about it.
To associate your repository with the video-data topic, visit your repo's landing page and select "manage topics."