Recent Publications

Mutual Context Network for Jointly Estimating Egocentric Gaze and Action

In this work, we address two coupled tasks of gaze prediction and action recognition in egocentric videos by exploring their mutual …

Generalizing Hand Segmentation in Egocentric Videos With Uncertainty-Guided Model Adaptation

Although the performance of hand segmentation in egocentric videos has been significantly improved by using CNNs, it still remains a …

Improving Action Segmentation via Graph Based Temporal Reasoning

Temporal relations among multiple action segments play an important role in action segmentation especially when observations are …

An ego-vision system for discovering human joint attention

Joint attention often happens during social interactions, in which individuals share focus on the same object. This work proposes an …

Support Strategies for Remote Guides in Assisting People with Visual Impairments for Effective Indoor Navigation

People with visual impairments often require mobility assistance of sighted guides but they are not always available. Recent …

Gaze Estimation by Exploring Two-Eye Asymmetry

Eye gaze estimation is increasingly demanded by recent intelligent systems to facilitate a range of interactive applications. …

Investigating audio data visualization for interactive sound recognition

Interactive machine learning techniques have a great potential to personalize media recognition models for each individual user by …

Light Structure from Pin Motion: Geometric Point Light Source Calibration

We present a method for geometric point light source calibration. Unlike prior works that use Lambertian spheres, mirror spheres, or …

InvisibleEye: Fully Embedded Mobile Eye Tracking Using Appearance-Based Gaze Estimation

Despite their potential for a range of exciting new applications, mobile eye trackers suffer from several fundamental usability …

Manipulation-Skill Assessment from Videos with Spatial Attention Network

Recent advances in computer vision have made it possible to automatically assess from videos the manipulation skills of humans in …