Generative Networks In Computer Vision and Machine Learning

One Day Meeting: Generative Networks In Computer Vision and Machine Learning

Wednesday 27 November 2019

Chairs: Nathan Olliverre

Keynote Speakers

Thomas Kustner, Guang Yang, Emanuele Sansone

Programme

Generative networks have been at the forefront of research in Computer Vision and Machine Learning in the last couple of years. Generative Networks have achieved impressive results for many real-world applications. As an active research topic, many GAN variants have emerged with improvements in sample quality and training stability. These novel techniques in synthesising have come to the fore and have been used for image generation, image processing, image synthesis from captions, image editing, visual domain adaptation, data generation for visual recognition, and many other applications, often leading to state of the art results. This BMVA Symposium brought together those who have a focus or interest in Generative network such as GANs and VAEs for a day of talks previewing novel and exciting research in the area.

Meeting Report

After the meeting the organisers prepared a short summary of the meeting.

This can be found here

Videos of Talks

On our BMVA YouTube channel there are recorded talks of the slides and speaker from the day here

Programme

09:30 - 10:20 - Keynote: Thomas Kustner (Imperial College London)

10:20 - 10:40 - Generative System to Assist the Artist in the Choice of 3D Composition for a Still Life Painting - Guido Salimbeni

10:40 - 11:00 - AI & Auto Colourisation - Black & White to Colour with Generative Adversarial Networks - Marc Górriz Blanch

11:00 - 11:20 - Coffee Break

11:20 - 11:50 - Keynote: Guang Yang (Imperial College London)

11:50 - 12:10 - Nonparametric Models and Uncertainty Propagation in Generative Deep Networks - Neill Campbell

12:10 - 12:30 - HoloGAN: Unsupervised learning of 3D representations from natural images - Thu Nguyen-Phuoc

12:30 - 13:30 - Lunch

13:30 - 13:50 - Gated Variational AutoEncoders: Incorporating Weak Supervision to Encourage Disentanglement - Matthew J. Vowels

13:50 - 14:40 - Keynote: Alison Lowdnes (Nvidia)

14:40 - 15:00 -Learning Human Reconstruction from Synthetic Dataset - Akin Caliskan

15:00 - 15:20 - Coffee Break

15:20 - 15:40 - Learning Generative 3D Face Models with Deep Disentangled Representations - Victoria Fernandez Abrevaya

15:40 - 16:00 - SymbolGAN and Deep Style Transfer - Chaozheng Wang

16:00 - 17:00 - Keynote: Emanuele Sansone (Huawei Technologies)

Meeting Location

The BCS has moved, the meeting will take place at:

British Computer Society (BCS), 25 Copthall Avenue, London EC2R 7BP

Registration

Please register using the options below (scroll for more options):

Meeting Location

The BCS has moved, the meeting will take place at:

British Computer Society (BCS), 25 Copthall Avenue, London EC2R 7BP