[Elsnet-list] V&L Net Workshop on Vision and Language: Call for Participation

Frank Keller keller at inf.ed.ac.uk
Sat Aug 27 23:13:42 CEST 2011

V&L Net Workshop on Vision and Language


Endorsed by BMVA (the British Machine Vision Association) and EACL (the European Chapter of the Association for Computational Linguistics)

Date: Thursday, 15 September 2011
Venue: Huxley Building, University of Brighton

Invited Speakers:
Yiannis Aloimonos, University of Maryland
Ted Briscoe, University of Cambridge
Roy Davies, Royal Holloway, University of London
Khurshid Ahmad, Trinity College Dublin

Accepted Posters: see below

The EPSRC Network on Vision and Language (V&L Net)

The EPSRC Network on Vision and Language (V&L Net) is a forum for researchers from the fields of Computer Vision and Language Processing to meet, exchange ideas, expertise and technology, and form new partnerships. Our aim is to create a lasting interdisciplinary research community situated at the language-vision interface, jointly working towards solutions for some of today's toughest computational challenges, including image and video search, description of visual content and text-to-image generation.

Workshop Aims

The Vision and Language Workshop is chiefly intended to be a networking and community building event for the computer vision and language processing communities.  It will give us an opportunity to meet and get to know each other.  This process will be supported by an informal approach characterised by diverse networking activities and a large number of brief oral presentations combined with poster presentations. 

The Vision and Language Workshop is free for full V&L Net members.  V&L Net will furthermore cover the cost of one night's accommodation in Brighton and economy-class travel within the UK for full V&L Net members presenting an accepted poster.  Full details can be found on the workshop page on the V&L Net website (for contact details see below).

Call for Participation

The Vision & Language Workshop organisers invite researchers with an interest in computer vision and language processing to register for the workshop by sending an email to vl-net at brighton.ac.uk
giving name, affiliation and primary research interests.

Mini-posters for WLTM Notice Board

Delegates are furthermore encouraged to bring along to the workshop A3-sized mini-posters for our would-like-to-meet notice board.  The idea is for mini-posters to describe collaborations sought, profile research groups, advertise publications, and similar items.

Outline Programme

09:00-13:00 Morning Session

Introduction and Welcome

Invited Talks:
Yiannis Aloimonos, University of Maryland: Robots need language: A computational model for the integration of vision, action and language
Ted Briscoe, University of Cambridge: Integrating textual information extraction and visual similarity search for biomedical research papers

Invited CV Overview Talk: Roy Davies, Royal Holloway, University of London
Invited NLP Overview Talk: Khurshid Ahmad, Trinity College Dublin

13:00-14:00 Lunch Break 

14:00-18:00 Afternoon Session

Teaser Presentations for Posters (accepted posters see below)
Poster Session
Would-like-to-meet Notice Board
Evening Drinks

Accepted Posters:

Amjad Altadmri and Amr Ahmed: Automatic Semantic Video Annotation in Wide Domain Videos Based on Similarity and Commonsense Knowledge Bases

Andrew J. Anderson, Elia Bruni, Brian Murphy, Marco Baroni and Massimo Poesio: fMRI Analyses of semantic structure using joint text and image models

Mark Andrews and Gabriella Vigliocco: Augmenting Distributional Statistics with Experiential Data

Marco Baroni, Elia Bruni and Giang Binh Tran: Multimodal distributional semantics

Moreno I. Coco, George L. Malcolm and Frank Keller: The Interplay of Bottom-Up and Top-Down Mechanisms in Visual Guidance during Object Naming

N. T. Crook, S. Pulman, P. Blunsom: Automatic generation of natural language descriptions of visual scenes

Simon Dobnik: From situated descriptions of spatial scenes to situated dialogue

Jordi Gonzalez, Josep M. Gonfaus, F. Xavier Roca: Exploiting Natural-Language Interaction in Video Surveillance Systems

Lewis D Griffin, M Husni Wahab and Andrew J Newell: Extrapolation of visual appearance on the basis of semantic relatedness

Margaret Mitchell: From an Image to a Description

Joanna Isabelle Olszewska: Spatio-Temporal Visual Ontology

Paul Piwek: Computational Modelling of Reference in Visually-shared Domains of Conversation

Massimo Poesio, Andrew Anderson, Marco Baroni, Sonja Eisenbeiss, Carol Rennie and Alessandro Lenci: BabyExp: From Data Collection to Analysis

Daniel R. Saunders and Russell L. Woods: Development of an Objective, Language-Based Measure of Perceived Video Quality

Niels Schutte, John Kelleher, and Brian Mac Namee: Using Dialogue to Improve Robot Perception

Marietta Sionti, Leonardo Claudino, Carolyn Penstein Rose, Stella Markantonatou and Yiannis Aloimonos: Comparing linguistic classifications with sensorimotor data of English and Greek verbs of motion

David Windridge: Cross-Modal Bootstrapping of Rule-Salient Audio-Visual Representations for Sports Video Annotation


Anja Belz, University of Brighton
Darren Cosker, University of Bath
Frank Keller, University of Edinburgh
Dimitrios Makris, Kingston University


vl-net at brighton.ac.uk

The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.

More information about the Elsnet-list mailing list