Natural Questions: a New Corpus and Challenge for Question Answering Research
To help spur research advances in QA, we are excited to announce Natural Questions (NQ), a new, large-scale corpus for training and evaluating open-domain question answering systems, and the first to replicate the end-to-end process in which people find answers to questions.
(Google AI) / (Paper)
Facebook Open Sources
Zero-shot Transfer across 93 Languages: Open-sourcing Enhanced LASER library
Binary Image Selection (BISON): Interpretable Evaluation of Visual Grounding / (GitHub)
A New Predictive Model for More Accurate Electrical Grid Mapping / (GitHub)
Announcing CheXpert, Large Dataset of Chest X-rays Co-released with MIT’s MIMIC-CXR Dataset
CheXpert is a large dataset of chest X-rays and competition for automated chest x-ray interpretation, which features uncertainty labels and radiologist-labeled reference standard evaluation sets.
(Stanford Machine Learning Group) / (Paper)
AlphaStar: Mastering the Real-Time Strategy Game StarCraft II
Now, we introduce our StarCraft II program AlphaStar, the first Artificial Intelligence to defeat a top professional player. In a series of test matches held on 19 December, AlphaStar decisively beat Team Liquid’s Grzegorz “MaNa” Komincz, one of the world’s strongest professional StarCraft players, 5-0, following a successful benchmark match against his team-mate Dario “TLO” Wünsch. The matches took place under professional match conditions on a competitive ladder map and without any game restrictions.
(DeepMind) / (Synced)
Filling Holes: Adobe Proposes Foreground-Aware Image Inpainting
Existing image inpainting methods fill holes by borrowing information from surrounding image regions. These methods however produce unsatisfactory results if holes overlap with foreground objects, suffering from a “lack of information about the actual extent of foreground and background regions with the holes.”
3D Human Pose Machines with Self-supervised Learning
This paper proposes a simple yet effective self-supervised correction mechanism to learn all intrinsic structures of human poses from abundant images. Specifically, the proposed mechanism involves two dual learning tasks, i.e., the 2D-to-3D pose transformation and 3D-to-2D pose projection, to serve as a bridge between 3D and 2D human poses in a type of “free” self-supervision for accurate 3D human pose estimation.
(Sun Yat-sen University & SenseTime Group)
You May Also Like
World First: Huawei Unveils Groundbreaking 5G Chipset “Tiangang”
President of Huawei’s Carrier Business Group Ryan Ding says the chip makes breakthroughs in integration, computing capability and spectral bandwidth. The Tiangang chip’s computing capability is 2.5 times more powerful than previous chips, and it supports the 200 MHz high spectral bandwidth that will be required for future network deployment.
You Can’t Keep an RL-Powered ANYmal Down
ANYmal does not have an easy life. One of the four-legged robot’s main tasks is to learn how to stand up again — no matter how many times it is kicked, pushed or otherwise tumbles to the ground.
Global AI Events
Jan 27 – Feb 1, 2019 AAAI 2019: Association for the Advancement of Artificial Intelligence. Hawaii, United State
March 17 – 20, ACM IUI. Los Angeles, United States
Global AI Opportunities