Chalearn Satellite Workshop on Image and Video Inpainting @ECCV18
Call for Participation: ChaLearn Looking at People Inpainting and Denoising in the Deep Learning Age events:
Challenge and ECCV 2018 Satellite Event - Registration FREE
Associated Springer book chapter publication and IEEE TPAMI Special Issue
Sponsoring: prizes from Google, Disney Research, Amazon, and ChaLearn
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/
ECCV 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/
Aims and scope: The problem of dealing with missing data or incomplete data in machine learning 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 [4,5]. We focus on image and video inpainting tasks, that might benefit from novel methods such as Generative Adversarial Networks (GANs) [6,7] or Residual connections [8,9]. Solutions to the inpainting problem may be useful in a wide variety of computer vision tasks. We chose three examples: human pose estimation and video de-captioning and fingerprint denoising.
1- Human pose estimation: it is challenging to perform human pose recognition in images containing occlusions; since tackling human pose recognition is a prerequisite for human behaviour analysis in many applications, replacing occluded parts may help the whole processing chain.
2- video de-captioning: in the context of news media and video entertainment, broadcasting programs from various languages, such as news, series or documentaries, there are frequently text captions or encrusted commercials or subtitles, which reduce visual attention and occlude parts of frames that may decrease the performance of automatic understanding systems. Despite recent advances in machine learning, it is still challenging to aim at fast (real time) and accurate automatic text removal in video sequences.
3- fingerprint denoising: biometrics play an increasingly important role in security to ensure privacy and identity verification, as evidenced by the increasing prevalence of fingerprint sensors on mobile devices. Fingerprint retrieval keeps also being an important law enforcement tool used in forensics. However, much remains to be done to improve the accuracy of verification, both in terms of false negatives (in part due to poor image quality when fingers are wet or dirty) and in terms of false positives due to the ease of forgery.
As one of the important branches in image and video analysis of humans (named Looking at People), understanding and inpainting occluded parts have become a research area of great interest as it has many potential applications domains including human behavior analysis, augmented reality and biometry recognition. We propose a satellite workshop on image and video inpainting. This session aims at compiling the latest efforts and research advances from the scientific community in enhancing traditional computer vision and pattern recognition algorithms with human image inpainting, video decaptioning and fingerprint denoising at both the learning and prediction stages.
Workshop topics and guidelines: The scope of the workshop comprises all aspects of image and video inpainting and denoising. Including but not limited to the following topics:
- 2D/3D human pose recovery under occlusion,
- human inpainting,
- human retexturing,
- video decaptioning,
- temporal occlusion recovery,
- object recognition under occlusion,
- fingerprint recognition,
- fingerprint denoising,
- future frame video prediction,
- unsupervised learning for missing data recovery and/or denoising,
- new data and applications of inpainting and/or denoising.
Abstract submissions for presentation in the workshop can be done through CMT web page: https://cmt3.research.microsoft.com/INPAINTING2018/. The abstract papers must have maximum 4 pages length plus references. Authors have to use this template. Contributions will be published within a volume in this series: http://www.springer.com/series/15602. Accepted papers will present their results in the satellite workshop and extended versions will be published within CIML volume. We organize a TPAMI Special Issue on the topic and extended versions of best satellite event papers will be invited to contribute.
The workshop is a FREE-REGISTRATION EVENT, open to everyone, and take place at Holiday Inn Munich – City Centre, Hochstrasse 3, 81669 München, Germany, at just 130m of main ECCV venue. You can check the place in google map here.
 V. Jain and S. Seung, “Natural image denoising with convolutional networks,” in Advances in Neural Information Processing Systems, 2009, pp. 769–776.
 L. Xu, J. S. Ren, C. Liu, and J. Jia, “Deep convolutional neural network for image deconvolution,” in Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger, Eds. Curran Associates, Inc., 2014, pp. 1790–1798.
 C. Dong, C. C. Loy, K. He, and X. Tang, “Image super-resolution using deep convolutional networks,” IEEE transactions on pattern analysis and machine intelligence, vol. 38, no. 2, pp. 295–307, 2016.
 J. Xie, L. Xu, and E. Chen, “Image denoising and inpainting with deep neural networks,” in Advances in Neural Information Processing Systems, 2012, pp. 341–349.
 A. Newson, A. Almansa, M. Fradet, Y. Gousseau, and P. P´erez, “Video inpainting of complex scenes,” SIAM Journal on Imaging Sciences, vol. 7, no. 4, pp. 1993–2019, 2014.
 I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” in Advances in neural information processing systems, 2014, pp. 2672–2680.
 D. Pathak, P. Kr¨ahenb¨uhl, J. Donahue, T. Darrell, and A. Efros, “Context encoders: Feature learning by inpainting,” in Computer Vision and Pattern Recognition (CVPR), 2016.
 K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016.
 X.-J. Mao, C. Shen, and Y.-B. Yang, “Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections,” ArXiv e-prints, Jun. 2016.