[1/4] Current 3D human pose reconstruction models are very impressive, but which model should you pick for your application? Introducing the Caltech Tennis Dataset (CalTennis), a large-scale video benchmark for evaluating monocular-to-3D pose estimation in the wild. CalTennis

[1/8] Introducing TaskNPoint! TLDR: A simple, tuning-free recipe for teaching humanoid to perform dynamic skills from a handful of iPhone videos of human demonstrations, trained in under 1 hour on a single GPU.

1/9 Videos of the real world are chaotic: filled with occlusions, abrupt motions, and non-rigid deformations. How well can current tracking models handle these difficulties? In our NeurIPS paper we answer this question with ITTO, a challenging new benchmark suite for evaluating

Posing w/ my poster on poseing at the

AI institute in dynamic systems workshop on ML for science in engineering this week 🤗🤸‍♂️!