BMVA Symposium: Transfer Learning (TL) in Computer Vision (CV) - TLCV

Weds 25th Jan 2017, London

Chairs:

Dr Dima Damen (Bristol), Dr Gabriela Csurka (Xerox) and Dr Timothy Hospedales (QMUL)

Keynotes Speakers:

Prof Massimiliano Pontil (Istituto Italiano di Tecnologia and UCL – *TL Methodologies,

Prof Peter Hall (Bath) – *TL across Visual Domains – From Images to Sketches

Invited Speakers:

Dr Michel Valstar (University of Nottingham) –TL for Facial Action Unit Detection,

Dr Teo de Campos (University of Surrey) – Transductive TL for Activity recognition,

Dr Adrien Gaidon (XRCE) – *TL from Gaming Environments to Real Images

Call for Papers

The Computer Vision community is in need of moving beyond dataset or task-specific methods towards those that can efficiently adapt to new tasks or domains in a supervised, semi-supervised or unsupervised manner. We aim in this technical meeting to bring together leading researchers, at various levels in their career, with expertise or strong interest in TL for Computer Vision problems, in order to discuss current challenges and propose future directions including potentially establishing a continuous forum or a workshop series.

We are inviting researchers to present short talks and posters that address the motivation, methodologies, challenges and applications of using TL in Computer Vision. These could include ongoing or recently published works, relevant but not limited to:

• TL for a specific computer vision task (e.g. object/event/activity detection, recognition, retrieval, tracking)
• Cross-Dataset or Cross-Annotations TL
• Cross-Domain TL
• Cross-Task TL
• Cross-Modality or Cross-Sensor TL
• Unsupervised and Incremental TL
• Datasets, Challenges and Protocols for Evaluating TL Methods

Call for Participation:

All those interested in presenting at this meeting are invited to submit a summary of their talk http://goo.gl/forms/AkAByVlRIH0qxen42 by 1st Nov 2016 [firm deadline].