pathak22/unsupervised-video
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
This project helps computer vision researchers and practitioners automatically analyze video footage to understand how objects move. By using large amounts of unlabeled video as input, it produces models that can identify and track moving objects, making it easier to segment videos without manual annotation. It's designed for those who work with video analysis and need to extract insights from motion.
261 stars. No commits in the last 6 months.
Use this if you are a computer vision researcher or engineer needing pre-trained models for tasks like object tracking or motion segmentation in videos.
Not ideal if you need a consumer-ready application for video editing or general object detection without a focus on motion analysis.
Stars
261
Forks
51
Language
Lua
License
MIT
Category
Last pushed
Apr 25, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/pathak22/unsupervised-video"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
BR-IDL/PaddleViT
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
IBM/CrossViT
Official implementation of CrossViT. https://arxiv.org/abs/2103.14899
NVlabs/GCVit
[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
ViTAE-Transformer/ViTDet
Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object...
bytedance/SPTSv2
The official implementation of SPTS v2: Single-Point Text Spotting