Search Results - "Shi, Bertram E."

Towards High Performance Low Complexity Calibration in Appearance Based Gaze Estimation by Chen, Zhaokang, Shi, Bertram E.

“…Appearance-based gaze estimation from RGB images provides relatively unconstrained gaze tracking from commonly available hardware. The accuracy of…”
Get full text

Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks by Lin Sun, Kui Jia, Dit-Yan Yeung, Shi, Bertram E.

“…Human actions in video sequences are three-dimensional (3D) spatio-temporal signals characterizing both the visual appearance and motion dynamics of the…”
Get full text

Active head rolls enhance sonar-based auditory localization performance by Wijesinghe, Lakshitha P, Wohlgemuth, Melville J, So, Richard H Y, Triesch, Jochen, Moss, Cynthia F, Shi, Bertram E

“…Animals utilize a variety of active sensing mechanisms to perceive the world around them. Echolocating bats are an excellent model for the study of active…”
Get full text

Expandable Networks for Neuromorphic Chips by Merolla, P.A., Arthur, J.V., Shi, B.E., Boahen, K.A.

“…We have developed a grid network that broadcasts spikes (all-or-none events) in a multichip neuromorphic system by relaying them from chip to chip. The grid is…”
Get full text

HOTS: A Hierarchy of Event-Based Time-Surfaces for Pattern Recognition by Lagorce, Xavier, Orchard, Garrick, Galluppi, Francesco, Shi, Bertram E., Benosman, Ryad B.

“…This paper describes novel event-based spatio-temporal features called time-surfaces and how they can be used to create a hierarchical event-based pattern…”
Get full text

Joint Learning of Binocularly Driven Saccades and Vergence by Active Efficient Coding by Zhu, Qingpeng, Triesch, Jochen, Shi, Bertram E

“…This paper investigates two types of eye movements: vergence and saccades. Vergence eye movements are responsible for bringing the images of the two eyes into…”
Get full text

Robot End Effector Tracking Using Predictive Multisensory Integration by Wijesinghe, Lakshitha P, Triesch, Jochen, Shi, Bertram E

“…We propose a biologically inspired model that enables a humanoid robot to learn how to track its end effector by integrating visual and proprioceptive cues as…”
Get full text

Autonomous Development of Active Binocular and Motion Vision Through Active Efficient Coding by Lelais, Alexander, Mahn, Jonas, Narayan, Vikram, Zhang, Chong, Shi, Bertram E, Triesch, Jochen

“…We present a model for the autonomous and simultaneous learning of active binocular and motion vision. The model is based on the Active Efficient Coding (AEC)…”
Get full text

Robot Navigation in Crowds by Graph Convolutional Networks With Attention Learned From Human Gaze by Chen, Yuying, Liu, Congcong, Shi, Bertram E., Liu, Ming

“…Safe and efficient crowd navigation for mobile robot is a crucial yet challenging task. Previous work has shown the power of deep reinforcement learning…”
Get full text

Active efficient coding explains the development of binocular vision and its failure in amblyopia by Eckmann, Samuel, Klimmasch, Lukas, Shi, Bertram E., Triesch, Jochen

“…The development of vision during the first months of life is an active process that comprises the learning of appropriate neural representations and the…”
Get full text

Robust active binocular vision through intrinsically motivated learning by Lonini, Luca, Forestier, Sébastien, Teulière, Céline, Zhao, Yu, Shi, Bertram E, Triesch, Jochen

“…The efficient coding hypothesis posits that sensory systems of animals strive to encode sensory signals efficiently by taking into account the redundancies in…”
Get full text

Iterative Distillation for Better Uncertainty Estimates in Multitask Emotion Recognition by Deng, Didan, Wu, Liang, Shi, Bertram E.

“…When recognizing emotions, subtle nuances in displays of emotion generate ambiguity or uncertainty in emotion perception. Emotion uncertainty has been…”
Get full text

Using Eye Gaze to Enhance Generalization of Imitation Networks to Unseen Environments by Liu, Congcong, Chen, Yuying, Liu, Ming, Shi, Bertram E.

“…Vision-based autonomous driving through imitation learning mimics the behavior of human drivers by mapping driver view images to driving actions. This article…”
Get full text

Using Variable Dwell Time to Accelerate Gaze-Based Web Browsing with Two-Step Selection by Chen, Zhaokang, Shi, Bertram E.

“…In order to avoid the "Midas Touch" problem, gaze-based interfaces for selection often introduce a dwell time: a fixed amount of time the user must fixate upon…”
Get full text

Dynamic Bayesian Adjustment of Dwell Time for Faster Eye Typing by Pi, Jimin, Koljonen, Paul A., Hu, Yong, Shi, Bertram E.

“…Eye typing is a hands-free method of human computer interaction, which is especially useful for people with upper limb disabilities. Users select a desired key…”
Get full text

Offset Calibration for Appearance-Based Gaze Estimation via Gaze Decomposition by Chen, Zhaokang, Shi, Bertram E.

“…Appearance-based gaze estimation provides relatively unconstrained gaze tracking. However, subject-independent models achieve limited accuracy partly due to…”
Get full text

Laplacian Auto-Encoders: An explicit learning of nonlinear data manifold by Jia, Kui, Sun, Lin, Gao, Shenghua, Song, Zhan, Shi, Bertram E.

“…A key factor contributing to the success of many auto-encoders based deep learning techniques is the implicit consideration of the underlying data manifold in…”
Get full text

An Event-by-Event Approach for Velocity Estimation and Object Tracking With an Active Event Camera by Zhu, Qingpeng, Triesch, Jochen, Shi, Bertram E.

“…An event-based camera has independent pixels that quickly respond to relative brightness changes and report them asynchronously with high temporal resolution…”
Get full text

An active-efficient-coding model of optokinetic nystagmus by Zhang, Chong, Triesch, Jochen, Shi, Bertram E

“…Optokinetic nystagmus (OKN) is an involuntary eye movement responsible for stabilizing retinal images in the presence of relative motion between an observer…”
Get full text

Neural population models for perception of motion in depth by Peng, Qiuyan, Shi, Bertram E.

“…•We propose two models of motion in depth perception built from neurally plausible operators.•Surprisingly, models cannot be distinguished by breaking input…”
Get full text