Lai Zihang

Introducing our ICCV'21 Oral: Video Autoencoder. We disentangle the 3D structure and camera pose from a video on a static scene, in a self-supervised manner. The training objective is solely reconstructing the input video frames. page with code: zlai0.github.io/VideoAutoencod… (1/n

We are presenting our new paper at LUV2020 workshop today at 16:15 - 16:30pm. MAST: A Memory-Augmented Self-Supervised Tracker, by @LaiZihang, @erika_lu_, @Oxford_VGG. A strong tracking model trained with no manual annotation. Code: github.com/zlai0/MAST #VGGatCVPR2020

Check zlai0.github.io/CorrFlow/ We are excited to share code & model for Self-supervised Correspondence Flow (BMVC 2019 Oral) @bmvc2019, State-of-the-art performance on video segmentation and pose tracking. @Oxford_VGG

(1/4) Meet VGGers @bmvc2019! 1. Self-supervised Video Representation Learning for Correspondence Flow, @LaiZihang, @WeidiXie Poster: Session 1 #83 (Tuesday 14:00-16:15) Oral: Video Analysis (Thursday 13:00-13:15) Page: zlai0.github.io/CorrFlow/