Come and chat with us in today's paper session 4!

Honoured to be on the list with many other colleagues, It's a pleasure to review so many high-quality papers this year and I am glad that they all got in:)

Come and say hi at #ICCV2023 I am in Paris this week to present our recent work: "Helping Hands: An Object-Aware Ego-Centric Video Recognition Model" Thursday 5th 2:30-4:30 PM @ Room Nord Arxiv: arxiv.org/abs/2308.07918

Come Tuesday morning to the 1st Perception Test Challenge workshop at ICCV at S04. We have cool talks from Derek Hoiem and Rohit Girdhar + challenge winners. We will also give away our brand new PT tshirts to anyone asking a question / giving a comment.

We are looking for a student researcher to work on 4d scene reconstruction in London (google.com/about/careers/…). Apply and/or get in touch if you feel it may be a good fit.

Student researcher position applications are open at Google Deepmind! I'm hosting a SR in the intersection of bias and generative models. If you're an interested PhD student please reach out! google.com/about/careers/…

Most text-image alignment evaluations rely on small non-balanced datasets with sparse human ratings. We introduce Gecko🦎: offering (1) a more balanced and comprehensive text prompt benchmark with (2) richer human ratings, and (3) a more accurate auto-eval metric in one paper⬇️

We're excited to release TAPVid-3D: an evaluation benchmark of 4,000+ real world videos and 2.1 million metric 3D point trajectories, for the task of Tracking Any Point in 3D!

We are looking for a student researcher to work on video understanding plus 3D, in Google DeepMind London. DM/Email me or pass it to someone if you feel it may be a good fit!