Language 2017 - Workshop on Closing the Loop between Vision and Language

The scope of this workshop lies at the intersection of Computer Vision and Natural Language Processing, which has received increasing interest in recent years. Researches have addressed several interesting tasks including generating text descriptions for images and videos, learning language embeddings of images, and predicting visual classifiers from unstructured text. More recent works further extend the scope of this area to combine videos and language, learning to solve non-visual tasks using visual cues, and question answering by visual verification of relation phrases. In this workshop, we aim to cover all these interesting aspects which benefit from jointly modelling visual and semantic concepts, and discuss its future and impact. We will also have a panel discussion focused on how to develop useful datasets and benchmarks that are suitable to the various tasks in this area.
The program of this workshop will include three to four invited talks by leading researchers in this area covering its diverse aspects and contributed submissions. Below is a call for extended abstracts. We welcome ongoing work as well as recently published works including paper to be presented at the main conference (ICCV 2017) in this area.
General Track Organizers (morning)
Mohamed Elhoseiny, Facebook Research
Devi Parikh, Assistant Professor at Georgia Tech
Leonid Sigal, Senior Research Scientist at Disney Research
Manohar Paluri, Facebook Research
Ahmed Elgammal, Professor at Rutgers University
Visual Storytelling Challenge Organizers (afternoon)
Ishan Misra, CMU, ishanmisra-AT-gmail.com
Justin Johnson, Stanford, jcjohns-AT-cs.stanford.edu
Ting-Hao Kenneth Huang, CMU, windx0303-AT-gmail.com
Frank O Ferraro, JHU, fferraro-AT-gmail.com
Margaret Mitchell, Google Research, margarmitchell-AT-gmail.com
Workshop Website
https://sites.google.com/site/clvlworkshopiccv17/