ICCV 2019 and CoRL 2019 Announce Best Papers; DeepMind AlphaStar Reaches ‘Grandmaster Level’
ICCV 2019 Best Papers Announced
ICCV 2019 today announced its Best Paper Awards in three categories. The ICCV (IEEE International Conference on Computer Vision) is a top international biannual computer vision gathering comprising a main conference and several co-located workshops and tutorials. ICCV 2019 received 4,303 papers — more than twice the number submitted to ICCV 2017 — and accepted 1,075, for a reception rate of roughly 25 percent.
(Synced)
ICCV 2019 | Best Paper Award (Marr Prize):SinGAN: Learning a Generative Model from a Single Natural Image
ICCV 2019 | Best Student Paper Award:PLMP — Point-Line Minimal Problems in Complete Multi-View Visibility
ICCV 2019 | Best Paper Honorable Mentions
Paper: Asynchronous Single-Photon 3D Imaging
Paper: Specifying Object Attributes and Relations in Interactive Scene Generation
Google AI Beats Top Human Players at Strategy Game StarCraft II
Players of the science-fiction video game StarCraft II faced an unusual opponent this summer. An artificial intelligence (AI) known as AlphaStar — which was built by Google’s AI firm DeepMind — achieved a grandmaster rating after it was unleashed on the game’s European servers, placing within the top 0.15% of the region’s 90,000 players.
(Nature) / (Paper) / (DeepMind Blog)/ (Watch the video)
CoRL 2019 Announces Best Paper Awards
The Conference on Robot Learning (CoRL) is a new annual international conference focusing on the intersection of robotics and machine learning.
CoRL 2019 | Best Paper Award
A Divergence Minimization Perspective on Imitation Learning Methods
CoRL 2019 | Best System Paper Award
Learning to Manipulate Object Collections Using Grounded State Representations
Technology
Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning
Researchers present relay policy learning, a method for imitation and reinforcement learning that can solve multi-stage, long-horizon robotic tasks. This general and universally-applicable, two-phase approach consists of an imitation learning stage resulting in goal-conditioned hierarchical policies that can be easily improved using fine-tuning via reinforcement learning in the subsequent phase.
(Google Brain)
Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation
The fundamental challenge of planning for multi-step manipulation is to find effective and plausible action sequences that lead to the task goal. Researchers present Cascaded Variational Inference (CAVIN) Planner, a model-based method that hierarchically generates plans by sampling from latent spaces.
(Stanford University & Nvidia &University of Toronto & Vector Institute)
Prescribed Generative Adversarial Networks
In this paper, researchers develop the prescribed GAN (PresGAN) to address these shortcomings. PresGANs add noise to the output of a density network and optimize an entropy-regularized adversarial loss. The added noise renders tractable approximations of the predictive log-likelihood and stabilizes the training procedure.
(Columbia University & University of Cambridge & DeepMind)
You May Also Like
Google Introduces Huge Universal Language Translation Model: 103 Languages Trained on Over 25 Billion Examples
A Google AI research team recently proposed a universal neural machine translation (NMT) system trained on over 25 billion examples that can handle 103 languages. Synced invited Graham Neubig, an Assistant Professor from Carnegie Mellon University to share his thoughts on the universal neural machine translation (NMT) system.
(Synced)
Can a Smart Light Bulb Steal Your Personal Data?
In a new paper, researchers from the University of Texas at San Antonio (UTSA) design and implement attacks that leverage characteristics of the light emitted by modern smart bulbs to “steal” users’ private data and preferences from other nearby devices.
(Synced)
Global AI Events
November 3–7: Empirical Methods in Natural Language Processing in Hong Kong, China
November 4–8: Microsoft Ignite in Orlando, United States
November 8: MLconf in San Francisco, United States
November 13–14: AI & Big Data Expo in Santa Clara, United States
Global AI Opportunities
Research Scientist, Google Brain Toronto
OpenAI Seeking Software Engineers and Deep Learning Researchers
DeepMind Scholarship: Access to Science
We know you don’t want to miss any stories. Subscribe to our popular Synced Global AI Weekly to get weekly AI updates.
Need a comprehensive review of the past, present and future of modern AI research development? Trends of AI Technology Development Report is out!
2018 Fortune Global 500 Public Company AI Adaptivity Report is out!
Purchase a Kindle-formatted report on Amazon.
Apply for Insight Partner Program to get a complimentary full PDF report.
