Google Announced The Release of BodyPix 2.0 – Real-time Person Segmentation In The Browser

19 November 2019

Google Announced The Release of BodyPix 2.0 – Real-time Person Segmentation In The Browser

Google announced the release of BodyPix 2.0 – an update of Google’s open-source machine learning model for a real-time person and body-part segmentation in the browser. The first version of…

SPICE: New Self-Supervised Method For Sound Pitch Estimation

16 November 2019

SPICE: New Self-Supervised Method For Sound Pitch Estimation

Google researchers have published a novel deep learning-based approach for sound pitch estimation. The novel method is in fact, the first one to be able to perform sound pitch estimation…

Neural Network Learns and Respects Basic Physics Laws

16 November 2019

Neural Network Learns and Respects Basic Physics Laws

A group of researchers from Google Brain, PetCube and Uber has proposed a neural network model that learns and respects laws of physics. In their novel paper – “Hamiltonian Neural…

Researchers Improve State-of-the-Art in Image Recognition By 1% Using New Training Method

14 November 2019

Researchers Improve State-of-the-Art in Image Recognition By 1% Using New Training Method

Researchers from Google Brain and Carnegie Mellon University have proposed a novel training method that improves ImageNet classification accuracy by 1%. The new state-of-the-art image classification model is built using…

Dance-to-music: Researchers Train A Model To Generate Music-Driven Coreography

11 November 2019

Dance-to-music: Researchers Train A Model To Generate Music-Driven Coreography

A group of researchers from the University of California and NVIDIA has published a method for modeling the dance-to-music process of humans. Their model is able to learn how to…

Adversarial T-Shirts: Researchers Designed T-Shirts That Can Fool Object Detectors

10 November 2019

Adversarial T-Shirts: Researchers Designed T-Shirts That Can Fool Object Detectors

Researchers from Northeastern University, MIT and IBM have invented adversarial T-shirts – a form of physical adversarial attack for evading people detectors. In their novel paper, named “Evading Real-Time Person…

Deezer Released Spleeter: A Sound Source Separation Library

7 November 2019

Deezer Released Spleeter: A Sound Source Separation Library

Deezer, the French online music streaming service has announced that it is releasing Spleeter – an open-source library for sound source separation. Sound source separation is an important task in…

Deepfakes Detection Challenge Preview Dataset Was Released

2 November 2019

Deepfakes Detection Challenge Preview Dataset Was Released

The Deepfake Detection Challenge is a competition where participants compete to find the best ways of detecting and preventing manipulated media. This includes mostly images and videos, where the so-called…

DeepMind’s AlphaStar Is Now Better Than 99.8% of Human Players

1 November 2019

DeepMind’s AlphaStar Is Now Better Than 99.8% of Human Players

Deepmind researchers, part of the Deepmind’s AlphaStar team, have announced that their artificial intelligence agents have reached grandmaster level in the popular, real-time strategy game Starcraft II. At the beginning…

PresGANs: Researchers Proposed New Generative Adversarial Network Model

1 November 2019

PresGANs: Researchers Proposed New Generative Adversarial Network Model

A group of researchers from Columbia University, the University of Cambridge and Google DeepMind, has proposed a novel type of Generative Adversarial Networks (GANs) – Prescribed Generative Adversarial Networks. The…

MIT Scientists Can Detect Where People are Looking in Videos

31 October 2019

MIT Scientists Can Detect Where People are Looking in Videos

Researchers from the Massachusetts Institute of Technology (MIT) and the Toyota Research Institute have proposed a new method that can detect where people are looking in videos. In their novel…

Google’s Live Caption Uses Deep Neural Networks to Transcribe Video and Audio in Real-time

31 October 2019

Google’s Live Caption Uses Deep Neural Networks to Transcribe Video and Audio in Real-time

Google has announced a new feature for Google Pixel and Android called Live Caption. The novel feature can automatically caption media playing on the phone in real-time. It leverages advances…

Google Researchers Released New State-of-the-art Method For Depth Estimation from Single Image

30 October 2019

Google Researchers Released New State-of-the-art Method For Depth Estimation from Single Image

Researchers from Google AI have proposed a new state-of-the-art method for unsupervised depth estimation from images, that works without using any additional input. The novel method, which in fact is…

Video-to-Video Synthesis Using Only Few Example Images

29 October 2019

Video-to-Video Synthesis Using Only Few Example Images

A group of researchers from NVIDIA has proposed a new method that learns to synthesize videos of unseen objects by using only a few example images of those objects. The…

Semi-weakly Supervised Learning: Increasing Classification Accuracy with Billion-scale Unlabeled Images

27 October 2019

Semi-weakly Supervised Learning: Increasing Classification Accuracy with Billion-scale Unlabeled Images

Researchers from Facebook AI Research (FAIR) have announced their work on a new concept in deep learning called Semi-weakly Supervised Learning. The new approach that the researchers propose, in fact,…

Learning To Smell: Google Researchers Have Trained A Neural Network to Predict Smell

24 October 2019

Learning To Smell: Google Researchers Have Trained A Neural Network to Predict Smell

A group of researchers from Google AI has published their work in learning odor descriptors as perceptual representations of small molecules. In the latest Google AI blog post, Alexander B.…

t-SNE CUDA: Visualizing High-Dimensional Data With GPU Accelerated t-SNE

23 October 2019

t-SNE CUDA: Visualizing High-Dimensional Data With GPU Accelerated t-SNE

t-SNE (t-distributed Stochastic Neighbor Embedding) is a popular method for exploring high-dimensional data proposed by Hinton and van der Maaten in 2008. The technique has become widespread in the machine…

Trident Networks: Novel State-of-the-art Model for Object Detection

23 October 2019

Trident Networks: Novel State-of-the-art Model for Object Detection

Researchers from the University of Chinese Academy of Sciences have proposed a new state-of-the-art object detection method based on scale-aware deep neural networks. In their novel paper, named “Scale-aware Trident…

Deep Learning Helps Historians Restore Damaged Ancient Greek Texts

21 October 2019

Deep Learning Helps Historians Restore Damaged Ancient Greek Texts

A group of researchers from Google’s Deepmind has published their most recent work on restoring ancient text using deep learning. In their novel paper named, “Restoring ancient text using deep…

New Method Allows Users To Draw Together with a Neural Network

19 October 2019

New Method Allows Users To Draw Together with a Neural Network

A group of researchers from the University of Oxford, Adobe Research and UC Berkeley, has proposed an interactive method for sketch-to-image translation based on Generative Adversarial Networks. The whole approach…

OpenAI’s Robot Hand Learned How To Solve Rubik’s Cube

17 October 2019

OpenAI’s Robot Hand Learned How To Solve Rubik’s Cube

Researchers from OpenAI announced that they have developed a human-like robot hand that can solve Rubik’s Cube. In OpenAI’s latest blog post, the group of researchers explains their efforts for…