Timezone: »

 
Workshop
Competition Track Friday
Hugo Jair Escalante · Katja Hofmann

Fri Dec 11 08:00 AM -- 05:45 PM (PST) @ None
Event URL: https://neurips.cc/Conferences/2020/CompetitionTrack »

First session for the competition program at NeurIPS2020.

Machine learning competitions have grown in popularity and impact over the last decade, emerging as an effective means to advance the state of the art by posing well-structured, relevant, and challenging problems to the community at large. Motivated by a reward or merely the satisfaction of seeing their machine learning algorithm reach the top of a leaderboard, practitioners innovate, improve, and tune their approach before evaluating on a held-out dataset or environment. The competition track of NeurIPS has matured in 2020, its fourth year, with a considerable increase in both the number of challenges and the diversity of domains and topics. A total of 16 competitions are featured this year as part of the track, with 8 competitions associated to each of the two days. The list of competitions that ar part of the program are available here:

https://neurips.cc/Conferences/2020/CompetitionTrack

Fri 8:00 a.m. - 8:15 a.m.
Opening - Competition Track Session (Intro) Video
Katja Hofmann, Hugo Jair Escalante
Fri 8:15 a.m. - 8:35 a.m.
3D+texture garment reconstruction challenge design (data, metrics, tracks, etc) (Live oral presentation)
Hugo Bertiche
Fri 8:35 a.m. - 9:00 a.m.
3D+texture garment reconstruction challenge results (Live oral presentation)
Meysam Madadi
Fri 9:00 a.m. - 9:03 a.m.
Opening the L2RPN challenge @ NeurIPS2020 (Intro)
Antoine Marot
Fri 9:03 a.m. - 9:13 a.m.
Winning the L2RPN challenge (Oral presentation) Video
Antoine Marot
Fri 9:13 a.m. - 9:23 a.m.
A L2RPN Winning approach (Oral presentation) Video
Jixiang LU
Fri 9:23 a.m. - 9:33 a.m.
The Best L2RPN wining approach (Oral presentation) Video
Bo Zhou
Fri 9:33 a.m. - 9:40 a.m.
L2RPN Post Challenge open questions (Oral presentation) Video
Antoine Marot
Fri 9:40 a.m. - 9:45 a.m.
Closing and ceremony award (Outro)
Antoine Marot
Fri 10:00 a.m. - 10:03 a.m.
Introducing the Hide-and-Seek privacy challenge (Intro)
James Jordon
Fri 10:03 a.m. - 10:18 a.m.
The importance of synthetic data (Oral presentation) Video
James Jordon
Fri 10:18 a.m. - 10:28 a.m.
Synthetic data in the healthcare setting (Oral presentation) Video
James Jordon
Fri 10:28 a.m. - 10:38 a.m.
What we learned from the Hide-and-Seek privacy challenge (Oral presentation)
James Jordon
Fri 10:38 a.m. - 10:43 a.m.
Closing remarks (Outro)
James Jordon
Fri 11:00 a.m. - 11:16 a.m.
Background on black box optimization (BBO) (Oral presentation) Video
Ryan Turner
Fri 11:16 a.m. - 11:27 a.m.
BBO challenge platform with Valohai (Oral presentation) Video
Juha Kiili
Fri 11:27 a.m. - 11:32 a.m.
Spotlight for 1st place (BBO challenge) (Oral presentation) Video
Ryan Turner, Alexander Cowen-Rivers
Fri 11:32 a.m. - 11:37 a.m.
Spotlight for 2nd place (BBO challenge) (Oral presentation)
Ryan Turner, Jiwei Liu
Fri 11:37 a.m. - 11:42 a.m.
Spotlight for 3rd place (BBO challenge) (Oral presentation) Video
Ryan Turner, Mikita Sazanovich
Fri 2:00 p.m. - 2:07 p.m.
Opening the SpaceNet 7 Challenge @ NeurIPS2020 (Oral presentation)
Adam Van Etten
Fri 2:07 p.m. - 2:15 p.m.
Introduction to SpaceNet (Oral presentation)
Jake Shermeyer
Fri 2:15 p.m. - 2:25 p.m.
The SpaceNet 7 Dataset (Oral presentation)
Jesus Martinez-Manso
Fri 2:25 p.m. - 2:30 p.m.
The SpaceNet 7 Metric (Oral presentation)
Adam Van Etten
Fri 2:30 p.m. - 2:40 p.m.
The Winners of SpaceNet 7 (Oral presentation)
Adam Van Etten
Fri 2:40 p.m. - 2:45 p.m.
SpaceNet 7 Closing and Future Plans (Oral presentation)
Adam Van Etten
Fri 3:00 p.m. - 3:05 p.m.
introduction to the 2020 NeurIPS education challenge (Oral presentation) Video
Angus Lamb
Fri 3:05 p.m. - 3:20 p.m.
Competition overview: motivation, impact, dataset, tasks (Oral presentation) Video
Angus Lamb
Fri 3:20 p.m. - 3:30 p.m.
Competition results and insights (Oral presentation) Video
Jack Wang
Fri 3:30 p.m. - 3:35 p.m.
Beyond the competition: what's next? (Oral presentation) Video
Jack Wang
Fri 3:35 p.m. - 3:45 p.m.
Q&A and discussion (Outro)
Jack Wang, Angus Lamb
Fri 4:00 p.m. - 4:05 p.m.
Traffic Map Movies - An Introduction to the Traffic4cast Challenge (Oral presentation) Video
Sepp Hochreiter
Fri 4:05 p.m. - 4:10 p.m.
The Traffic4cast Competition Design and Data (Oral presentation) Video
Michael Kopp
Fri 4:10 p.m. - 4:12 p.m.
The Best Traffic4Cast Submissions (Intro)
D Kreil
Fri 4:12 p.m. - 4:17 p.m.
1st prize: Utilizing UNet for the Future Traffic Map Prediction - Traffic4cast highlight talk (Oral presentation) Video
Sungbin Choi
Fri 4:17 p.m. - 4:22 p.m.
2nd prize: TLab: Traffic Map Movie Forecasting Based on HR-NET - Traffic4cast highlight talk (Oral presentation) Video
Fanyou Wu
Fri 4:22 p.m. - 4:27 p.m.
3rd prize: Towards Good Practices of U-Net for Traffic Forecasting - Traffic4cast highlight talk (Oral presentation) Video
Jingwei Xu
Fri 4:27 p.m. - 4:32 p.m.
Graph Ensemble Net and the Importance of Feature & Loss Function Design for Traffic Prediction - Traffic4cast highlight talk (Oral presentation) Video
Qi Qi
Fri 4:32 p.m. - 4:37 p.m.
Uncertainty Intervals for Graph-based Spatio-Temporal Traffic Prediction - Traffic4cast highlight talk (Oral presentation) Video
tijs Maas
Fri 4:37 p.m. - 4:45 p.m.
Traffic4cast Award Ceremony, Outlook, and Follow Up Challenges (Discussion panel)
D Kreil
Fri 5:00 p.m. - 5:15 p.m.
The Hateful Memes Challenge: Competition Overview (Oral presentation) Video
Douwe Kiela
Fri 5:15 p.m. - 5:45 p.m.
The Hateful Memes Challenge: Live award ceremony and winner presentations (Discussion panel)
Douwe Kiela

Author Information

Hugo Jair Escalante (INAOE)
Katja Hofmann (Microsoft Research)

Dr. Katja Hofmann is a Principal Researcher at the [Game Intelligence](http://aka.ms/gameintelligence/) group at [Microsoft Research Cambridge, UK](https://www.microsoft.com/en-us/research/lab/microsoft-research-cambridge/). There, she leads a research team that focuses on reinforcement learning with applications in modern video games. She and her team strongly believe that modern video games will drive a transformation of how we interact with AI technology. One of the projects developed by her team is [Project Malmo](https://www.microsoft.com/en-us/research/project/project-malmo/), which uses the popular game Minecraft as an experimentation platform for developing intelligent technology. Katja's long-term goal is to develop AI systems that learn to collaborate with people, to empower their users and help solve complex real-world problems. Before joining Microsoft Research, Katja completed her PhD in Computer Science as part of the [ILPS](https://ilps.science.uva.nl/) group at the [University of Amsterdam](https://www.uva.nl/en). She worked with Maarten de Rijke and Shimon Whiteson on interactive machine learning algorithms for search engines.

More from the Same Authors