Yi Yang (杨亿)

I believe solely in Jesus. 我独信耶稣。

I am currently a Research Scientist at Google DeepMind, where my research focuses on self-supervised visual representation learning for robotics.

Previously, I was a Research Scientist at Baidu Research from 2013 to 2018. I received my Ph.D. from UC Irvine in 2013 under the supervision of Prof. Deva Ramanan. During my graduate studies, I completed summer internships at Microsoft Research (2011) and Google (2012). I finished my master study at the Hong Kong University of Science and Technology in 2008 and bachelor study at Tsinghua University in 2006.

Full publications: Google Scholar

Yi Yang

Selected Publications

TAPNext: Tracking Any Point (TAP) as Next Token Prediction
ICCV 2025

TAPVid-3D: A Benchmark for Tracking Any Point in 3D
NeurIPS 2024

RoboTAP: Tracking Arbitrary Points for Few-Shot Visual Imitation
ICRA 2024

TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement
ICCV 2023

TAP-Vid: A Benchmark for Tracking Any Point in a Video
NeurIPS 2022

UnOS: Unified Unsupervised Optical-flow and Stereo-depth Estimation by Watching Videos
CVPR 2019

Occlusion Aware Unsupervised Learning of Optical Flow
CVPR 2018

Attention to Scale: Scale-aware Semantic Image Segmentation
CVPR 2016

Deep Captioning with Multimodal Recurrent Neural Networks
ICLR 2015

Recognizing Proxemics in Personal Photos
CVPR 2012

Articulated Pose Estimation with Flexible Mixtures of Parts
CVPR 2011

Layered Object Detection for Multi-Class Segmentation
CVPR 2010