Timezone: »

Competition track
Sergio Escalera · Markus Weimer

Fri Dec 08 08:00 AM -- 08:45 PM (PST) @ 103 A+B
Event URL: https://nips.cc/Conferences/2017/CompetitionTrack »

This is the first NIPS edition on "NIPS Competitions". We received 23 competition proposals related to data-driven and live competitions on different aspects of NIPS. Proposals were reviewed by several qualified researchers and experts in challenge organization. Five top-scored competitions were accepted to be run and present their results during the NIPS 2017 Competition track day. Evaluation was based on the quality of data, problem interest and impact, promoting the design of new models, and a proper schedule and managing procedure. Below, you can find the five accepted competitions. Organizers and participants in these competitions will be invited to present their work to this workshop, to be held on December 8th.

Accepted competitions:
The Conversational Intelligence Challenge Webpage: http://convai.io
Classifying Clinically Actionable Genetic Mutations Webpage: https://www.kaggle.com/c/msk-redefining-cancer-treatment
Learning to Run Webpage: https://www.crowdai.org/challenges/nips-2017-learning-to-run
Human-Computer Question Answering Competition Webpage: http://sites.google.com/view/hcqa/
Adversarial Attacks and Defences Webpage: https://www.kaggle.com/nips-2017-adversarial-learning-competition

Fri 8:15 a.m. - 8:30 a.m.
Opening (Talk)
Sergio Escalera, Markus Weimer
Fri 8:30 a.m. - 9:00 a.m.
  • Overview of the Challenge
  • Overview of top 10 competitors
  • Presentation by top 2 competitors
  • Winners recognition on stage
  • Keynote: XPRIZE scientific Advisor
Amir Banifatemi, rania khalaf, Sean McGregor
Fri 9:00 a.m. - 10:00 a.m.
  • Introduction into adversarial examples. Invited speaker, Dawn Song
    • Overview of the competition, Alexey Kurakin, Ian Goodfellow
    • Winner of attack competition, Yinpeng Dong, Fangzhou Liao, Tianyu Pang
    • Winner of defense competition, Yinpeng Dong, Fangzhou Liao, Tianyu Pang
    • 2nd place defense competition, Cihang Xie
Alexey Kurakin, Ian Goodfellow, Samy Bengio, Yao Zhao, Yinpeng Dong, Tianyu Pang, Fangzhou Liao, Cihang Xie, Adithya Ganesh, Oguz Elibol
Fri 10:00 a.m. - 10:30 a.m.
Coffee Break and Competition I: Adversarial Attacks and Defenses posters (Break)
Fri 10:30 a.m. - 12:15 p.m.
  • Overview of the Challenge
  • Keynote: Carmichael Ong
  • Challenge logistics (CrowdAI platform)
  • Run top submissions on the final test environment
  • Talks from top participants
  • AWS & NVIDIA sponsored prize ceremony
  • Keynote: Sergey Levine
Łukasz Kidziński, Carmichael Ong, Sharada Mohanty, Jason Fries, Jennifer Hicks, Zhuobin Zheng, Chun Yuan, Sergey Plis
Fri 12:15 p.m. - 1:30 p.m.
Lunch (Break)
Fri 1:15 p.m. - 1:30 p.m.

Competition review, results, and award ceremony

Alexander Ecker, Leon A Gatys, Matthias Bethge
Fri 1:30 p.m. - 3:00 p.m.
  • Overview of the Challenge
  • Awarding prize
  • Short presentation by winning team
  • Inspirational talk: Alexander Rudnicky Abstract: Current automatic systems use limited models of conversation with humans. Historically research in dialog systems has focused on goal-directed interaction for which objective measures of success could be defined. More recently attention has turned to so-called open-domain conversation chatbots, similar to social exchanges between people but for which measures of success are not yet agreed upon. On reflection, natural human communication is mostly a combination of task, social and likely other levels. The challenge is to understand how to manage such communication in a way that reflects human capabilities.
  • Panel Discussion. Moderated by Julian Serban. Panelists: Alexander Rudnicky, Dilek Hakkani-Tur, Jianfeng Gao and Joelle Pineau.
Mikhail Burtsev, Ryan Lowe, Iulian Vlad Serban, Yoshua Bengio, Alex Rudnicky, Alan W Black, Shrimai Prabhumoye, Artem Rodichev, Nikita Smetanin, Denis Fedorenko, CheongAn Lee, EUNMI HONG, Hwaran Lee, Geonmin Kim, Nicolas Gontier, Atsushi Saito, Andrey Gershfeld, Artem Burachenok
Fri 3:00 p.m. - 3:30 p.m.
Coffee break and Competition III: The Conversational Intelligence Challenge posters (Poster)
Fri 3:30 p.m. - 5:15 p.m.
Competition IV: Classifying Clinically Actionable Genetic Mutations (Talk) Maged Macgari, Alex Grigorenko, Anasuya Das, Leifur Thorbergsson, Wendy Kan, Xi Zhang, Dandi Chen, Lezhi Li, Nishant Kumar, JJ Gao
Fri 5:15 p.m. - 5:45 p.m.
Fri 5:45 p.m. - 7:15 p.m.
  • Overview of the Challenge
  • Talks from participants
  • Competition against human team
  • Q&A with organizers, experts, developers
Jordan Boyd-Graber, Hal Daumé III, He He, Mohit Iyyer, Pedro Rodriguez
Fri 7:30 p.m. - 7:40 p.m.
Closing (Talk)
Sergio Escalera, Markus Weimer
Fri 7:30 p.m. - 9:00 p.m.
Dinner (Break)

Author Information

Sergio Escalera (University of Barcelona and Computer Vision Center)

Sergio Escalera obtained the P.h.D. degree on Multi-class visual categorization systems at Computer Vision Center, UAB. He obtained the 2008 best Thesis award on Computer Science at Universitat Autònoma de Barcelona. He leads the Human Pose Recovery and Behavior Analysis Group at UB, CVC, and the Barcelona Graduate School of Mathematics. He is an associate professor at the Department of Mathematics and Informatics, Universitat de Barcelona. He is an adjunct professor at Universitat Oberta de Catalunya, Aalborg University, and Dalhousie University. He has been visiting professor at TU Delft and Aalborg Universities. He is a member of the Visual and Computational Learning consolidated research group of Catalonia. He is also a member of the Computer Vision Center at Campus UAB. He is Editor-in-Chief of American Journal of Intelligent Systems and editorial board member of more than 5 international journals. He is advisor, director, and vice-president of ChaLearn Challenges in Machine Learning, leading ChaLearn Looking at People events. He is co-founder of PhysicalTech and Care Respite companies. He is also member of the AERFAI Spanish Association on Pattern Recognition, ACIA Catalan Association of Artificial Intelligence, and he is vice-chair of IAPR TC-12: Multimedia and visual information systems. He has different patents and registered models. He has published more than 150 research papers and participated in the organization of scientific events, including CCIA04, CCIA14, ICCV11, AMDO2016, FG2017, and workshops at ICCV11, ICMI13, ECCV14, CVPR15, ICCV15, CVPR16, ECCV16, ICPR16, NIPS16. He has been guest editor at JMLR, TPAMI, IJCV, TAC, and Neural Comp. and App. He has been area chair at WACV16, NIPS16, and FG17. His research interests include, between others, statistical pattern recognition, visual object recognition, and HCI systems, with special interest in human pose recovery and behavior analysis from multi-modal data.

Markus Weimer (Microsoft)

More from the Same Authors