Lubomir Bourdev
YOU?
Author Swipe
View article: RU-AI: A Large Multimodal Dataset for Machine Generated Content Detection
RU-AI: A Large Multimodal Dataset for Machine Generated Content Detection Open
This repository contains all the collected and aligned data for RU-AI dataset. It is constructed based on three large publicly available datasets: Flickr8K, COCO, and Places205, by adding their corresponding machine-generated pairs from fi…
View article: PIM: Video Coding using Perceptual Importance Maps
PIM: Video Coding using Perceptual Importance Maps Open
Human perception is at the core of lossy video compression, with numerous approaches developed for perceptual quality assessment and improvement over the past two decades. In the determination of perceptual quality, different spatio-tempor…
View article: An Interactive Annotation Tool for Perceptual Video Compression
An Interactive Annotation Tool for Perceptual Video Compression Open
Human perception is at the core of lossy video compression and yet, it is challenging to collect data that is sufficiently dense to drive compression. In perceptual quality assessment, human feedback is typically collected as a single scal…
View article: ELF-VC: Efficient Learned Flexible-Rate Video Coding
ELF-VC: Efficient Learned Flexible-Rate Video Coding Open
While learned video codecs have demonstrated great promise, they have yet to achieve sufficient efficiency for practical deployment. In this work, we propose several novel ideas for learned video compression which allow for improved perfor…
View article: Learned Video Compression
Learned Video Compression Open
We present a new algorithm for video coding, learned end-to-end for the low-latency mode. In this setting, our approach outperforms all existing video codecs across nearly the entire bitrate range. To our knowledge, this is the first ML-ba…
View article: Real-Time Adaptive Image Compression
Real-Time Adaptive Image Compression Open
We present a machine learning-based approach to lossy image compression which outperforms all existing codecs, while running in real-time. Our algorithm typically produces files 2.5 times smaller than JPEG and JPEG 2000, 2 times smaller th…