A tiny milestone in my academic journey.

I know these metrics do not carry much significance in today's academic landscape.

Nevertheless, they serve as a personal gauge, allowing me to assess the papers' impact and reflect on if I've contributed something meaningful.

SAM + Optical Flow = FlowSAM

FlowSAM can discover and segment moving objects in a video and outperforms all previous approaches by a considerable margin in both single and multi-object benchmarks 🔥

robots.ox.ac.uk/~vgg/research/…

This originally aims to generate comic books for my daughter with diffusion models, i.e., continuous image sequences with consistent characters, storylines, etc. Well, I guess now we have #SORA 🤣.....

Still, it is good to get it accepted on #CVPR2024 , congrats the team !!

Still suffering from occlusion? Our recent work Amodal Ground Truth and Completion in the Wild (#CVPR2024) Visual Geometry Group (VGG) with Chuanxia Zheng Weidi Xie and Andrew Zisserman enables reconstruction of the entire shape of any occluded object to help you solve occlusion intrinsically.

Our #paper [Free3D] (Visual Geometry Group (VGG) with Andrea Vedaldi), [Amodal](with Guanqi Zhan, Weidi Xie, and Andrew Zisserman), [OneMoreStep] (@NTUsg with Minghui and Tat-Jen Cham) have been accepted to #CVPR2024 ! Congratulations to the team. The project pages and codes have been released.