Understanding hand-object manipulation by modeling the contextual relationship between actions, grasp types and object attributes

Minjie Cai, Kris Kitani, Yoichi Sato

GroundNet: Monocular Ground Plane Normal Estimation with Geometric Consistency

Yunze Man, Xinshuo Weng, Xi Li +1

The paper introduces GroundNet, a monocular model that jointly predicts depth, surface normals, and ground segmentation to estimate the 3D orientation of the ground plane, using a…

Visual Compiler: Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator

Namhoon Lee, Xinshuo Weng, Vishnu Naresh Boddeti +4

Ego-Pose Estimation and Forecasting as Real-Time PD Control

Ye Yuan, Kris Kitani

Personalized Dynamics Models for Adaptive Assistive Navigation Systems

Eshed Ohn-Bar, Kris Kitani, Chieko Asakawa

Incremental Class Discovery for Semantic Segmentation with RGBD Sensing

Yoshikatsu Nakajima, Byeongkeun Kang, Hideo Saito +1

Learning Spatio-Temporal Features with Two-Stream Deep 3D CNNs for Lipreading

Xinshuo Weng, Kris Kitani