Neural Networks

In a novel paper, “Unifying Deep Local and Global Features for Image Search”, researchers from Google proposed a new method for image searching that unifies local and global features, enabling…

In recent work, researchers from Microsoft have proposed a new method for measuring dataset similarity based on optimal transport (OT) techniques. Measuring dataset similarity is a non-trivial problem that has…

A group of researchers from several universities have joined forces on developing a new method for old image restoration using deep learning. In their paper, “Old Photo Restoration via Deep…

A group of researchers from Baidu has proposed and developed a novel ultra-lightweight optical character recognition system (OCR). Their, so-called PP-OCR is based on lightweight deep neural networks with several…

The Tiny Object Detection (TOD) Challenge was designed in order to foster research in the direction of tiny object detection in images. The main focus of the challenge was the…

Researchers from Google AI have proposed a new way of training sparse neural networks that overcomes the typical issues found in existing dense-to-sparse methods. Past research has shown that deep…

A group of researchers from Google AI has developed a new imitation learning method called Primal Wasserstein Imitation Learning (PWIL). The newly proposed method for imitation learning does not rely…

Researchers from Baidu in a collaboration with several universities and research institutes have developed an intelligent framework for the exploration of UI design solutions using collective machine learning. The new…

A new, large-scale product image dataset was recently published by researchers from JD AI Research. Motivated by the lack of precise and large-scale datasets of product images, researchers have started…

A group of researchers from the University of Science and Technology, ETRI from Korea have developed a method for learning speech gesture generation using online speech videos. In their latest…

A group of researchers from several research institutes and universities has collaborated together on a project to develop a road damage detection model that works well in multiple countries. Considering…

A group of researchers has developed and released a novel deep neural network that can convert a video and audio signal into a lip-synced video. In their recent paper, the…

In their recent paper, researchers from Google AI have proposed a new state-of-the-art model for panoptic and semantic segmentation. The new model comes as an improvement over the series of…

In another research project from Google AI, researchers have developed a machine learning method that helps doctors increase coverage in colonoscopy screenings. Colonoscopy as a procedure for detecting polyps and…

Researchers from Google have developed and released a new tool that helps developers to easily write TensorFlow code. Basically, the new tool called TensorFlow Coder which is part of Tensorflow…

Researchers from MIT University have conducted a research project where their goal was to understand what makes deepfakes detectable. With the numerous advances in image generation in the past decade,…

Researchers from the Carnegie Mellon University, Facebook AI Research, Argo AI, and the University of California have developed a method that successfully extracts 3D humans and objects along with their…

WebDataset is a novel Python library that allows efficient data access and overcomes most challenges introduced by working with very large datasets. The library was developed in order to overcome…

In a 2-year-old collaboration project, researchers from Facebook AI and New York University Langone Health, have developed a new way to accelerate MRI scanning procedures by leveraging AI technologies. The…

Researchers from Shandong Normal University and the Chinese Academy of Sciences have collected and published a large-scale logo detection dataset. In the context of branding and brand management, logo detection…

In a novel paper, researchers from the Seoul National University in Korea have proposed an accurate method for 3D human pose and mesh estimation from a single image. Typically human…