Posted by AJ Piergiovanni and Anelia Angelova, Research Scientists, Google Research, Brain Team Video is an ubiquitous source of media content that touches on many aspects of people’s day-to-day lives. Increasingly, real-world video applications, such as video captioning, video content…
Scientists have developed a small robot to understand how ants teach one another. Read More
Researchers have developed an AI pilot that enables autonomous aircraft to navigate a crowded airspace. The artificial intelligence can safely avoid collisions, predict the intent of other aircraft, track aircraft and coordinate with their actions, and communicate over the radio…
Posted by Bingyi Cao, Software Engineer, Google Research, and Mário Lipovský, Software Engineer, Google Lens Computer vision models see daily application for a wide variety of tasks, ranging from object recognition to image-based 3D object reconstruction. One challenging type of…
Researchers have successfully applied a computer-based natural language processing model to protein research. Read More
Posted by Qifei Wang, Senior Software Engineer, and Feng Yang, Senior Staff Software Engineer, Google Research Deep learning models for visual tasks (e.g., image classification) are usually trained end-to-end with data from a single visual domain (e.g., natural images or…
Posted by Arun Kandoor, Software Engineer, Google Research The increasing demand for machine learning (ML) model inference on-device (for mobile devices, tablets, etc.) is driven by the rise of compute-intensive applications, the need to keep certain data on device for…
A new computer vision system watches the 3D printing process and adjusts velocity and printing path to avoid errors. Training the system in simulation, researchers avoid the costly trial-and-error associated with setting 3D printing parameters for new materials. Read More
Artificial vision systems are implemented in motion sensing, object detection, and self-driving vehicles. However, they are not suitable for changing external environments and are limited to a hemispherical field-of-view (FOV). Addressing this issue, researchers have now developed a novel artificial…
Posted by Ehsan Amid, Research Scientist, and Rohan Anil, Principal Engineer, Google Research, Brain Team While model design and training data are key ingredients in a deep neural network’s (DNN’s) success, less-often discussed is the specific optimization method used for…