Event Sold Out

We have over 100 people registered for this exciting meeting and over 30 people on the waiting list, if you are unable to attend this meeting please email me and i can refund yourself and release a ticket to another person

Andrew a.gilbert@surrey.ac.uk

One Day BMVA symposium in London, UK on Friday 8th July, 2016

Chairs: Kai Arulkumaran & Anil Bharath
Keynote speakers: Andrea Vedaldi (University of Oxford), Ben Graham (University of Warwick), Nicolas Koumchatzky (Twitter Cortex), Samim Winiger (Samim.io), Sander Dieleman (Google DeepMind), Soumith Chintala (Facebook AI Research), Nick Kingsbury (University of Cambridge)

www.bmva.org/meetings

Introduction

The aim of the workshop is to explore not just the areas of computer vision that deep learning can advance, but also how the investigation of different areas in computer vision has led to advances in deep learning. We will be hosting a range of speakers from both academia and industry, talking about varied topics within this area. In addition, we will have a number of poster sessions to allow for other researchers to present their work in this exciting field.

Programme

0845-0915 Coffee / Registration

0915-0925 Introduction

0925-0945 Alison Lowndes NVIDIA Deep Learning Platform Update

0945-1015 Sander Dieleman Classifying Galaxies and Plankton with Deep Neural Networks

1015-1115 Coffee / Poster Session 1

1115-1145 Nick Kingsbury Can Scatternets Help Deep Networks to Learn and be More Comprehensible?

1145-1215 Samim Winiger New Patterns for Creation - Applying Machine Learning to Creativity

1215-1315 Lunch

1315-1345 Nicolas Koumchatzky Live Video Classification at Twitter

1345-1415 Andrea Vedaldi Understanding Visual Representations

1415-1515 Coffee / Poster Session 2

1515-1545 Ben Graham Spatially Sparse Convolutional Neural Networks

1545-1615 Soumith Chintala Hybrid Deep Adversarial Networks for Unsupervised Vision

1615-1645 Panel Discussion

1645-1700 Conclusion

After the meeting, we will move to a local pub for further discussion.

Posters

Adeline Paiement - Skeleton-free Body Pose Estimation from Depth Images for Movement Analysis

Qiyang Zhao - Suppressing the Unusual: Towards Robust CNNs Using Symmetric Activation Functions

Wenzhe Shi - Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network

Adrian Carrio - Convolutional Neural Networks for Electric Tower Detection

Heba Sailem - Convolutional Networks in Biological Imaging: from Learning to Discovery

Victor Podlozhnyuk - Optimised CNNs on Mobile Devices

Anurag Arnab - Higher Order Conditional Random Fields in Deep Neural Networks

Edward Johns - Pairwise Decomposition of Image Sequences for Active Multi-View Recognition

Gaurav Kaul - Near Memory Acceleration for Deep Learning Systems

Nicolas Jaccard - Classification of X-ray Transmission Images of Cargo Containers Using Convolutional Neural Networks

Antonia Creswell - Adversarial Training For Generating Sketches

Tu Bui - Learning Photo-sketch Mapping with Convolutional Neural Networks

The best poster prize is sponsored by NVIDIA