All presenters are limited to 20 minutes for both presentation and discussion. Please prepare a 15-minute talk and allow 5 minutes for setup/discussion. All session rooms are equipped with a computer and a projector. Presenters can make use of the conference computer or connect their own laptop. You should aim to copy your presentations over, or connect your laptops before the session begins to avoid any delays.

We require that at least one author registers and attends the workshop. If you have not registered yet, please do so before the 15th of September, and share your ECCV/Workshop registration information with us at: iwrr2016@cvc.uab.es.



0850 – 0900    Welcome

0900 – 1000    Invited Talk 1

               Deep Learning and Synthetic Data for Text Spotting
               Dr Max Jaderberg (Google Deep Mind, UK)

1000 – 1030    Coffee Break

1030 – 1130    Oral Session 1

10:30       Robust Text Detection with Vertically-Regressed Proposal Network        
               Donglai Xiang, Qiang Guo, Yan Xia

10:50       Scene Text Detection with Adaptive Line Clustering
               Xinxu Qiao, He Zhu, Weiping Li

11:10       From text detection to text segmentation: a unified evaluation scheme
               Stefania Calarasanu, Jonathan Fabrizio, Séverine Dubuisson

1130 – 1230    Invited Talk 2

               COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images              
               Dr Serge Belongie (Cornell Tech, USA)

1230 – 1330    Lunch

1330 – 1450    Oral Session 2

13:30       Efficient exploration of text regions in natural scene images using adaptive image sampling
               Ismet Zeki Yalniz, Douglas Gray, R. Manmatha

13:50       Dynamic Lexicon Generation for Natural Scene Images
               Yash Patel, Lluis Gomez, Maral Rusiol, Dimosthenis Karatzas

14:10       End-to-End Interpretation of the French Street Name Signs Dataset
               Raymond Smith, Chunhui Gu, Dar-Shyang Lee, Huiyi Hu, Ranjith Unnikrishnan, Julian Ibarz, Sacha Arnoud, Sophia Lin

14:30       Downtown Osaka Scene Text Dataset
               Masakazu Iwamura, Takahiro Matsuda, Naoyuki Morimoto, Hitomi Sato, Yuki Ikeda, Koichi Kise

1450 – 1520    Coffee Break

1520 – 1620    Invited Talk 3

               Robust Reading in Mobile Apps        
               Prof R. Manmatha (A9/Amazon, Palo Alto, CA)

1620 – 1720    Panel Discussion

1720 – 1730    Closing Remarks