Chalearn LAP Inpainting Competition Track 2 - Video decaptioning Forum

Go back to competition Back to thread list Post in this thread

> Competition and ECCV news, including proceedings and TPAMI SI!

Dear participants, we are happy to provide you further news! given our ECCV Satellite event and associated Springer proceedings and TPAMI SI, now we have time to extend the period of the competition so that you can provide with a better solution to the challenge and be able to publish and present your work both at ECCV satellite event proceedings and IEEE TPAMI SI!!! :) Please look detail information next and lets us know anydoubts. thx for your contribution and good luck!
-----
Call for Participation: ChaLearn Looking at People Inpainting and Denoising events:
Challenge and ECCV 2018 Satellite Event - Registration FREE
Associated Springer book chapter publication of best works and IEEE TPAMI Special Issue
Sponsoring: prizes from Google, Disney Research, Amazon, and ChaLearn

***********************************************************************
CALL FOR PARTICIPATION
ChaLearn Looking at People Inpainting Challenge 2018
ECCV Satellite Event
Sep. 9th 2018, Munich, https://www.hi-hotel-muenchen.de/en/munich-conference-hotel/, 130m from main ECCV venue.
Competition webpage: http://chalearnlap.cvc.uab.es/challenge/26/description/
Satellite event webpage: http://chalearnlap.cvc.uab.es/workshop/29/description/
IEEE TPAMI Special Issue webpage: http://chalearnlap.cvc.uab.es/special-issue/30/description/
************************************************************************

We are organizing an academic competition and ECCV 2018 Satellite event in the context of inpainting of images and video sequences. Inpainting refers to replacing missing parts in an image (or video). The problem of dealing with missing data or incomplete data in machine learning and computer vision arises in many applications. Recent strategies make use of generative models to impute missing or corrupted data. Advances in computer vision using deep generative models have found applications in image/video processing, such as denoising, restoration, super-resolution, or inpainting. We focus on image and video inpainting tasks, that might benefit from novel methods such as Generative Adversarial Networks (GANs) or Residual connections. Solutions to the inpainting problem may be useful in a wide variety of computer vision tasks.

We propose a challenge that aims at compiling the latest efforts and research advances from the computational intelligence community in creating fast and accurate inpainting algorithms. The methods will be evaluated on large, newly collected and annotated datasets related to three realistic scenarios in visual inpainting:

Track 1. Image inpainting to recover missing parts of human body
https://competitions.codalab.org/competitions/18423
Track 2. Video inpainting to remove overlayed text in video clips
https://competitions.codalab.org/competitions/18421
Track 3. Image denoising and inpainting for fingerprint verification
https://competitions.codalab.org/competitions/18426

In all cases, the main goal is to generate the visually best possible set of pixels to obtain a complete image or video clip.

The challenges are running in the CodaLab platform (http://codalab.org/), and results will be presented at ECCV 2018 Satellite event, 9th Sep. 2018, Munich, with Springer post-event proceedings. Participants obtaining the best results will be invited to present their results at this event and extended versions of best papers to a dedicated Special Issue at IEEE TPAMI. There will be travel grants and AWS credits for top ranked participants sponsored by Google, Amazon, Disney Research and ChaLearn.

Sponsors: ChaLearn (http://chalearnlap.cvc.uab.es/ http://www.chalearn.org/), Google (www.google.com), Amazon (https://www.amazon.com/), Disney Research (https://www.disneyresearch.com/)

******************************
Important dates (tentative)
******************************
- Competitions schedule: http://chalearnlap.cvc.uab.es/challenge/26/schedule/
- ECCV Satellite event submission schedule: http://chalearnlap.cvc.uab.es/workshop/29/schedule/
- Special issue schedule: http://chalearnlap.cvc.uab.es/special-issue/30/schedule/

***********************
Organizing team
***********************
Sergio Escalera (sergio.escalera.guerrero@gmail.com), Computer Vision Center & University of Barcelona, Barcelona, Spain
Stephane Ayache, AMU/LIF, France
Jun Wan, Institute of Automation, Chinese Academy of Science (CASIA), Beijing, China
Florin Popescu, Fraunhofer Institute FOKUS in Berlin, Germany
Umut Güçlü, Radboud University, Nijmegen, Netherlands
Yağmur Güçlütürk, Radboud University, Nijmegen, Netherlands
Marti Soler, Universitat de Barcelona, Barcelona, Spain
Meysam Madadi, Computer Vision Center, Barcelona, Spain
Xavier Baró, Universitat Oberta de Catalunya, Barcelona, Spain
Isabelle Guyon, ChaLearn, USA, University Paris-Saclay, Paris, France
Ondřej Kanich, Faculty of Information Technology, BUT, Czech Republic
Jan Svoboda, Lugano, Switzerland
Martin Drahansky, Brno University of Technology, Czech Republic
Hugo Jair Escalante, ChaLearn, USA, INAOE, Mexico

Posted by: sergio.escalera.guerrero @ April 16, 2018, 8:16 a.m.
Post in this thread