Demos

Live demonstrations of excellent computer vision systems or work in progress are an increasingly important way to show the real performance of algorithms and to increase the impact of research work. At CVPR 2016 we aim to have a program of outstanding live demos to be displayed alongside the main scientific paper presentations.

Please contact Demo Chair Andrew Davison with any queries.

Demo Schedule

Monday, June 27th

10:30AM - 12:30PM Interactive Session 1-1

Amplitude Modulated Video Camera – Light Separation for Dynamic Scenes


Amir Kolaman, Rami Hagege, Hugo Guterman (Ben-Gurion University of the Negev)

FANNG: Fast Approximate Nearest Neighbour Graphs


Ben Harwood and Tom Drummond (Monash University)

DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving


Chenyi Chen, Ari Seff, Alain L. Kornhauser, Jianxiong Xiao (Princeton University)

VL-SLAM: Real-Time Visual-Inertial Navigation and Semantic Mapping


Jingming Dong, Xiaohan Fei, Nikolaos Karianakis, Konstantine Tsotsos, Stefano Soatto (UCLA)

4:45PM - 7:00PM Interactive Session 1-2

Live Prediction of Age, Gender and Facial Attractiveness


Rasmus Rothe, Radu Timofte, Luc van Gool (ETH Zurich)

A Real-Time RGB-NIR Imaging System Using a Single Image Sensor


Kazunori Yoshizaki, Munenori Fukunishi, Yasuhiro Komiya, Yusuke Monno, Masayuki Tanaka, Masatoshi Okutomi, Steven Lansel (Olympus R&D Group, Tokyo Institute of Technology, Olympus Communication Technology of America)

The Menpo Project


Epameinondas Antonakos, James Booth, Patrick Snape, George Trigeorgis (Imperial College London)

Real-time 3D Object Detection and Tracking


David Joseph Tan, Federico Tombari, Nassir Navab (TU Munich, University of Bologna, Johns Hopkins University)

Tuesday, June 28th

10:30AM - 12:30PM Interactive Session 2-1

Live Demo for Semantic Image Segmentation


Shuai Zheng, Sadeep Jayasumana, Bernardina Romera-Paredes, Philip H. S. Torr (University of Oxford)

Big Data Analytics for Intelligent Farming: i-EKBase


Ritaban Dutta, Aaron Zimmermann, Heiko Mueller, Michelle Nic Raghnaill (DATA61 CSIRO, Australia)

Photo-realistic Virtual Worlds to Boost Video Understanding and Autonomous Driving: Introducing SYNTHIA & Virtual KITTI


Adrien Gaidon, German Ros, Antonio M. Lopez, Eleonora Vig, David Vázquez, Qiao Wang (Xerox Research Center Europe, Computer Vision Center at Universitat Autonoma de Barcelona)

Monocular Real-Time Surface Reconstruction using Dynamic Level of Detail


Jacek Zienkiewicz, Stefan Leutenegger (Imperial College London)

4:45PM - 7:00PM Interactive Session 2-2

Don't Think, Just Sketch - Deep Sketch-Based Fine-Grained Retrieval


Yi-Zhe Song, Timothy Hospedales, Tao Xiang (Queen Mary, University of London)

Staple: Complementary Learners for Real-Time Tracking


Luca Bertinetto, Jack Valmadre, Stuart Golodetz, Ondrej Miksik, Philip H.S. Torr (University of Oxford)

EmotioNet: An Accurate, Real-Time Algorithm for the Automatic Annotation of Half a Million Facial Expressions in the Wild


Aleix M. Martinez, Fabian Benitez-Quiroz (The Ohio State University)

Grounding Natural Language Phrases in Images with Bounding Boxes and Segmentation Masks


Anna Rohrbach, Ronghang Hu, Marcus Rohrbach, Bernt Schiele, Trevor Darrell (Max Planck Institute for Informatics, UC Berkley, ICSI)

Wednesday, June 29th

10:30AM - 12:30PM Interactive Session 3-1

Face2Face


Justus Thies, Michael Zollhoefer, Christian Theobalt, Marc Stamminger, Matthias Niessner (University of Erlangen-Nuremberg, Max Planck Institute for Informatics, Stanford University)

AntiCrime: A System for Suspect Retrieval and Loitering Discovery in Large Scale Surveillance Videos


Jianquan Liu, Shoji Nishimura, and Takuya Araki (NEC Corporation)

3D Semantic Parsing of Large-Scale Indoor Spaces


Iro Armeni, Ozan Sener, Amir R. Zamir, Silvio Savarese (Stanford University, Cornell University)

Robust Spatial Layout Estimation for Cluttered Indoor Scenes on Mobile Devices


Kuan Fang, Kevin Chen, Silvio Savarese (Stanford University)

4:45PM - 7:00PM Interactive Session 3-2

3D Object Tracking from Monocular Images using Stable Parts


Alberto Crivellaro, Mahdi Rad, Yannick Verdie, Kwang Moo Yi, Pascal Fua, Vincent Lepetit (EPFL, Graz University of Technology, NCam-Tech)

Real-Time Image and Video Super-Resolution on Mobile, Desktop and in the Browser


Wenzhe Shi, Jose Caballero, Andrew Aitken, Zehan Wang (Magic Pony Technology)

CloudCV Visual Question Answering (VQA)


Harsh Agrawal, Aishwarya Agrawal, Jiasen Lu, Deshraj Yadav, Akrit Mohapatra, Devi Parikh, Dhruv Batra (Virginia Tech)

Convolutional Pose Machines


Shih-En Wei, Varun Ramakrishna, Yaser Sheikh (CMU, Uber Advanced Technologies Center)

Thursday, June 30th

10:30AM - 12:30PM Interactive Session 4-1

SemanticPaint: Mobile Interactive Segmentation of 3D Worlds


Michael Sapienza, Stuart Golodetz, Olaf Kahler, Victor A. Prisacariu, Philip H. S. Torr (University of Oxford)

Real-Time Human Segmentation using Deep Fully Convolutional Encoder-Decoder Network


Ping-Lin Chang, Tingfan Wu and Shawn Guan (Umbo CV)

Glass-Enabled Contextual Interactions through Video-Based Guidance


Dima Damen, Davide Moltisanti, Teesid Leelasawassuk and Walterio Mayol-Cuevas (University of Bristol)

Mobile 3D Scanner


Olivier Saurer, Ioannis Mariggis, Petri Tanskanen, Marc Pollefeys (ETH Zurich)

4:45PM - 7:00PM Interactive Session 4-2

Pairwise Conditional Random Forests for Facial Expression Recognition


Arnaud Dapogny (Universite Pierre et Marie Curie)

A Storyline-based Query-Answering Benchmark for Understanding Scenes and Events from a Network of Cameras


Qi Hang, Tianfu Wu, Mun-Wai Lee, Song-Chun Zhu (UCLA)

Vision-aided Inertial Navigation for Virtual Reality Applications


Ryan DuToit, Georgios Georgiou, Kejian Wu, Chao Guo, Stergios Roumeliotis (University of Minnesota)

Robust Keyframe-based Monocular SLAM for Augmented Reality


Haomin Liu, Guofeng Zhang, Hujun Bao (Zhejiang University)