Publications

A Practical Method for Fully Automatic Intrinsic Camera Calibration Using Directionally Encoded Light

• July 22, 2017

• Mahdi Abbaspour Tehrani (University of California Irvine)
• Thabo Beeler
• Anselm Grundhöfer

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017

Learning Video Object Segmentation from Static Images

• July 22, 2017

• Federico Perazzi
• Anna Khoreva (Max Planck Institute for Informatics)
• Rodrigo Benenson (Max Planck Institute for Informatics)
• Bernt Schiele (Max Planck Institute for Informatics)
• Alexander Sorkine-Hornung

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017

One-Shot Metric Learning for Person Re-identification

• July 22, 2017

• Slawomir Bak
• Peter Carr

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017

Weakly-Supervised Visual Grounding of Phrases with Linguistic Structures

• July 21, 2017

• Fanyi Xiao (University of California Davis)
• Leonid Sigal
• Yong Jae Lee (University of California Davis)

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017

• Press Release:  Computers using linguistic clues to deduce photo content

Factorized Variational Autoencoders for Modeling Audience Reactions to Movies

• July 21, 2017

• Zhiwei Deng (Simon Fraser University)
• Rajitha Navarathna
• Peter Carr
• Stephan Mandt
• Yisong Yue (Caltech)
• Iain Matthews
• Greg Mori (Simon Fraser University)

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017

• Press Release:  Neural nets model audience reactions to movies

Joint Optimization of Robot Design and Motion Parameters using the Implicit Function Theorem

• July 12, 2017

• Sehoon Ha
• Stelian Coros (Carnegie Mellon University)
• Alexander Alspach
• Joohyung Kim
• Katsu Yamane

• Robotics: Science and Systems 2017

IRIDiuM+: Deep Media Storytelling with Non-Linear Light Field Video

• July 10, 2017

• Maggie Kosek
• Charalampos Koniaris
• David Sinclair
• Dessy Markova
• Fraser Rothnie
• Lanny Smoot
• Kenny Mitchell

• ACM SIGGRAPH 2017

Kernel-Predicting Convolutional Networks for Denoising Monte Carlo Renderings

• July 10, 2017

• Steve Bako (University of California, Santa Barbara)
• Thijs Vogels (ETH Zurich, Disney Research Zurich)
• Brian McWilliams
• Mark Meyer (Pixar Animation Studios)
• Jan Novák
• Alex Harvill (Pixar Animation Studios)
• Pradeep Sen (University of California, Santa Barbara)
• Tony DeRose
• Fabrice Rousselle

• ACM SIGGRAPH 2017

• Press Release:  Disney Research, Pixar Animation Studios and UCSB accelerate rendering with AI

Active Vertical Stabilization Mechanism for Lightweight Handheld Cameras

• July 3, 2017

• Utku Pehlivan
• Günter Niemeyer

• IEEE International Conference on Advanced Intelligent Mechatronics 2017

Collaborative Storytelling between Robot and Child: A Feasibility Study

• June 27, 2017

• Ming Sun
• Iolanda Leite
• Jill F. Lehman
• Boyang Albert Li

• Interaction Design and Children (IDC) 2017

• Press Release:  When kids talk to robots: Enhancing engagement and learning

Investigating the Effects of Interactive Features for Preschool Television Programming

• June 27, 2017

• Liz Carter
• Jennifer Hyde (Disney Research Pittsburgh)
• Jessica Hodgins

• Interaction Design and Children (IDC) 2017

• Press Release:  When kids talk to robots: Enhancing engagement and learning

Persistent Memory in Repeated Child-Robot Conversations

• June 27, 2017

• Iolanda Leite
• André Pereira
• Jill F. Lehman

• Interaction Design and Children (IDC) 2017

• Press Release:  When kids talk to robots: Enhancing engagement and learning