Week Ending 09.29.19

September 30, 2019 Craig Smith

RESEARCH WATCH: 09.29.19

Over the past week, 811 new papers were published in "Computer Science".

The paper discussed most in the news over the past week was "Can WhatsApp Counter Misinformation by Limiting Message Forwarding?" by Philipe de Freitas Melo et al (Sep 2019), which was referenced 27 times, including in the article WhatsApp Was Extensively Abused For Spreading Misinformation During 2019 Elections In India in Indiatimes. The paper author, Kiran Garimella (Aalto University), was quoted saying "I’m from India and through the current election, individuals have been saying that the forwarding restrict wasn’t serving to a lot".
Leading researcher Yoshua Bengio (Université de Montréal) came out with "GraphMix: Regularized Training of Graph Neural Networks for Semi-Supervised Learning", which has 0 shares on Twitter so far.

Over the past week, 84 new papers were published in "Computer Science - Artificial Intelligence".

The paper discussed most in the news over the past week was by a team at Allen Institute for Artiﬁcial Intelligence: "From F to A on the N.Y. Regents Science Exams: An Overview of the Aristo Project" by Peter Clark et al (Sep 2019), which was referenced 15 times, including in the article Why Understanding AI Misleading Terms Is Key To Understanding AI Breakthroughs And Limitations in Forbes.com. The paper author, Oren Etzioni (Allen Institute for Artiﬁcial Intelligence), was quoted saying "If I could go back to 1956 [when the field of AI was launched], I would choose a different terminology". The paper got social media traction with 140 shares. A user, @peterjansen_ai, tweeted "Here is the paper describing AI2's system that achieves 90% accuracy on the 8th grade standardized science exams. It's truly incredible to see how much of this comes from contextualized embeddings -- I never thought they would do that well on this complex inference task".
Leading researcher Yoshua Bengio (Université de Montréal) published "Recurrent Independent Mechanisms" @nasim_rahaman tweeted "New paper from et al. about “factorizing” RNNs in to independent mechanisms that sparsely interact! Check it out".
The paper shared the most on social media this week is by a team at Google: "Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?" by Ofir Nachum et al (Sep 2019) with 63 shares.

Over the past week, 171 new papers were published in "Computer Science - Computer Vision and Pattern Recognition".

The paper discussed most in the news over the past week was "DeepPrivacy: A Generative Adversarial Network for Face Anonymization" by Håkon Hukkelås et al (Sep 2019), which was referenced 14 times, including in the article DeepPrivacy Aims to Anonymize People While Retaining Their Facial Expressions in Beebom. The paper got social media traction with 293 shares. A Twitter user, @fenbielding, said "Scramble suits in the next 5 years?", while @RD_Partners observed "Adding features and emotions back into anonymized faces may seem counter-intuitive, but researchers have developed a technique that attempts to do just that, and it could be the key to clearer incognito communication. Read more".
Leading researcher Dhruv Batra (Georgia Institute of Technology) came out with "Improving Generative Visual Dialog by Answering Diverse Questions".

Over the past week, 11 new papers were published in "Computer Science - Computers and Society".

Over the past week, 18 new papers were published in "Computer Science - Human-Computer Interaction".

The paper discussed most in the news over the past week was by a team at Arizona State University: "Multimodal Dataset of Human-Robot Hugging Interaction" by Kunal Bagewadi et al (Sep 2019), which was referenced 1 time, including in the article Free (Robot) Hugs! An Embracing Multimodal Dataset in SyncedReview.com. The paper got social media traction with 5 shares.

This week was very active for "Computer Science - Learning", with 296 new papers.

The paper discussed most in the news over the past week was "DeepPrivacy: A Generative Adversarial Network for Face Anonymization" by Håkon Hukkelås et al (Sep 2019),
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Avoidance Learning Using Observational Reinforcement Learning".
The paper shared the most on social media this week is by a team at Google: "Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?" by Ofir Nachum et al (Sep 2019)

Over the past week, 16 new papers were published in "Computer Science - Multiagent Systems".

Over the past week, 18 new papers were published in "Computer Science - Neural and Evolutionary Computing".

The paper discussed most in the news over the past week was by a team at University of Waterloo: "Human-Machine Collaborative Design for Accelerated Design of Compact Deep Neural Networks for Autonomous Driving" by Mohammad Javad Shafiee et al (Sep 2019), which was referenced 4 times, including in the article AI Builds AI: Startup’s AI Generates Compact Neural Networks in NVIDIA Newsroom. The paper got social media traction with 12 shares.
The paper shared the most on social media this week is by a team at The University of Tokyo: "HumanGAN: generative adversarial network with human-based discriminator and its evaluation in speech perception modeling" by Kazuki Fujii et al (Sep 2019) with 59 shares. @fakufakurevenge (Robin Scheibler) tweeted "Human acting as discriminator function in GAN! Very cool!".

This week was very active for "Computer Science - Robotics", with 67 new papers.

The paper discussed most in the news over the past week was "Nailed It: Autonomous Roofing with a Nailgun-Equipped Octocopter" by Matthew Romano et al (Sep 2019), which was referenced 26 times, including in the article Nailed It: Autonomous Roofing Drone Takes Off in DroneLife. The paper author, Ella Atkins (University of Michigan), was quoted saying "For me, the biggest excitement of this work is in recognizing that autonomous, useful, physical interaction and construction tasks are possible with drones". The paper was shared 1 time in social media. The authors present the first demonstration of autonomous roofing with a multicopter.
Leading researcher Sergey Levine (University of California, Berkeley) came out with "Deep Dynamics Models for Learning Dexterous Manipulation".