Week Ending 06.23.19
RESEARCH WATCH: 06.23.19
Over the past week, 938 new papers were published in "Computer Science".
The paper discussed most in the news over the past week was by a team at Samsung: "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models" by Egor Zakharov et al (May 2019), which was referenced 187 times, including in the article New Deepfake Software Only Needs One Image to Make You Sing in Interesting Engineering. The paper author, Egor Zakharov (Samsung), was quoted saying "Effectively, the learned model serves as a realistic avatar of a person". The paper also got the most social media traction with 61373 shares. On Twitter, @catovitch said "I wonder if this can/will be used with video compression. If it can be done in real time, the decoder could just be told "build a face our of this frame, then rotate it to these 3D positions for the next 5 frames"".
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Unsupervised State Representation Learning in Atari" @arshtvk tweeted "Great work, Ankesh".
The paper shared the most on social media this week is by a team at Carnegie Mellon University: "XLNet: Generalized Autoregressive Pretraining for Language Understanding"by Zhilin Yang et al (Jun 2019) with 1425 shares. @mark_riedl (Mark Riedl 🚀 Mars (Moon)) tweeted "RIP BERT The problem is naming models after Sesame Street characters is that it artificially adds significance to then models. And then they will be cast aside when something better comes along in a few months".
Over the past week, 77 new papers were published in "Computer Science - Artificial Intelligence".
The paper discussed most in the news over the past week was "ARCHANGEL: Tamper-proofing Video Archives using Temporal Content Hashes on the Blockchain" by Tu Buiet al (Apr 2019), which was referenced 24 times, including in the article Can Anything Protect Us From Deepfakes? in PCMag Australia. The paper author, John Sheridan(Monash University), was quoted saying "Exploring blockchain technology together with some of the world's leading archives, the ARCHANGEL project has shown, for real, how archives might combine forces to protect and assure vital digital evidence for the future. ARCHANGEL has been an outstanding partnership that has delivered ground breaking research into the practicalities of using blockchain to assure trust in large scale digital archives." The paper got social media traction with 43 shares. A Twitter user, @JCollomosse, said "ARCHANGEL fuses Blockchain and AI to help secure the integrity of National Archives around the world Check our talk at the CVPR Blockchain workshop (June 17). Project page".
Leading researcher Sergey Levine (University of California, Berkeley) published "When to Trust Your Model: Model-Based Policy Optimization" The investigators study the role of model usage in policy optimization both theoretically and empirically.
Over the past week, 174 new papers were published in "Computer Science - Computer Vision and Pattern Recognition".
The paper discussed most in the news over the past week was by a team at Samsung: "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models" by Egor Zakharov et al (May 2019)
Leading researcher Abhinav Gupta (Carnegie Mellon University) came out with "PyRobot: An Open-source Robotics Framework for Research and Benchmarking" The investigators introduce PyRobot, an open - source robotics framework for research and benchmarking. @MolloyLaurence tweeted "Hmmm... Interesting... #PiWars2020 who want to give this a spin?".
The paper shared the most on social media this week is by a team at University of Oxford: "Stacked Capsule Autoencoders" by Adam R. Kosiorek et al (Jun 2019) with 251 shares. @jgvfwstone (James V Stone) tweeted "Stacked Capsule Autoencoders Adam R. Kosiorek, Sara Sabour, Yee Whye Teh, Geoffrey E. Hinton, June 2019. This is reminiscent of sound ideas on "instantiation parameters" in Hinton's earliest papers, but with 21st century computational power".
Over the past week, 24 new papers were published in "Computer Science - Computers and Society".
The paper discussed most in the news over the past week was by a team at Allen Institute for Artificial Intelligence: "Gender trends in computer science authorship" by Lucy Lu Wang et al (Jun 2019), which was referenced 14 times, including in the article Computer Science Research Gender Gap Won’t Close for 100 Years in New York Times. The paper author, Oren Etzioni (Allen Institute for Artificial Intelligence), was quoted saying "We were hoping for a positive result, because we all had the sense that the number of women authors was growing". The paper got social media traction with 17 shares. On Twitter, @nicklocatelli posted "👩🏼🔬#⃣👨🏼🔬💻 A comprehensive and up-to-date analysis of Computer Science literature (2.87 million papers through 2018) reveals that, if current trends continue, parity between the number of male and female authors will not be reached in this century".
The paper shared the most on social media this week is "Gender gaps in urban mobility" by Laetitia Gauvin et al (Jun 2019) with 59 shares. The researchers present recent results on urban mobility from a gendered perspective by uniquely combining a wide range of datasets, including commercial sources of telecom and open data. @MarbleData (Marble Data) tweeted "So proud of this work!🚗🚕🚌🚎🚲🚶🏻♀️cities are not designed in a neutral way. Without putting the spotlight on these disparities, change cannot happen and cities are not inclusive #gender #mobility".
Over the past week, 21 new papers were published in "Computer Science - Human-Computer Interaction".
This week was very active for "Computer Science - Learning", with 358 new papers.
The paper discussed most in the news over the past week was by a team at Samsung: "Few-Shot Adversarial Learning of Realistic Neural Talking Head Models" by Egor Zakharov et al (May 2019)
Leading researcher Yoshua Bengio (Université de Montréal) published "Unsupervised State Representation Learning in Atari"
The paper shared the most on social media this week is by a team at Carnegie Mellon University: "XLNet: Generalized Autoregressive Pretraining for Language Understanding"by Zhilin Yang et al (Jun 2019)
Over the past week, 12 new papers were published in "Computer Science - Multiagent Systems".
Over the past week, 15 new papers were published in "Computer Science - Neural and Evolutionary Computing".
The paper discussed most in the news over the past week was "The trade-off between long-term memory and smoothness for recurrent networks" by Antônio H. Ribeiro et al (Jun 2019), which was referenced 2 times, including in the article RNNs: The Trade-Off Between Long-Term Memory and Smoothness in Medium.com. The paper got social media traction with 7 shares. A user, @arXiv__ml, tweeted "#machinelearning Training recurrent neural networks (RNNs) that possess long-term memory is challenging. We provide insight into th".
Leading researcher Yoshua Bengio (Université de Montréal) came out with "Conditional Computation for Continual Learning" The investigators analyze parameter sharing under the conditional computation framework where the parameters of a neural network are conditioned on each input example. @iandanforth tweeted "Good paper taking on catastrophic forgetting in a principled way. One issue though is thinking that fully disjoint networks (one per input) is the end of the spectrum".
The paper shared the most on social media this week is by a team at University of Oxford: "Stacked Capsule Autoencoders" by Adam R. Kosiorek et al (Jun 2019)
This week was active for "Computer Science - Robotics", with 53 new papers.
The paper discussed most in the news over the past week was by a team at Carnegie Mellon University: "PyRobot: An Open-source Robotics Framework for Research and Benchmarking" by Adithyavairavan Murali et al (Jun 2019)