Name: Zhengzhong Tu
Type: User
Company: @UTAustin @Google @Google-Research
Bio: Assistant Professor of CS at TAMU
Twitter: _vztu
Location: College Station, TX
Blog: https://vztu.github.io
Zhengzhong Tu's Projects
Deep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
TRIQ implementation
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
Video quality metrics, reference implementation in python: VIF, SSIM, PSNR, ...
[IEEE TIP'2021] "UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content", Zhengzhong Tu, Yilin Wang, Neil Birkbeck, Balu Adsumilli, Alan C. Bovik
Automatic downloader of videos from Vimeo.com
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
This is a GitHub copy of [ACM Multimedia'18] End-to-End Blind Quality Assessment of Compressed Videos Using Deep Neural Networks.
Quality Assessment of In-the-Wild Videos (ACM MM 2019)
My profile README
Person detection in YFCC100m dataset
Youtube-8m Videos, Frames and Ids Generator. Extract videos from youtube-8m. Extract frames from youtube-8m.
Kaggle Youtube 8M WILLOW approach