The proposed project seeks to develop a Machine Learning-based software solution that accurately measures the capacity, State of Health (SoH), State of Charge (SoC), and cycle count of non-smart batteries utilized in mobile fleets. The project’s primary objective is to bridge the gap between smart and non-smart batteries by monitoring non-smart battery capacity and other […]

The goal is to develop a system that can rapidly detect and report emerging disease outbreaks worldwide by analyzing clusters of news articles using Large Language Models. The objective is to create an efficient and effective way of identifying “disease events” that can alert public health officials to take prompt action.

Streaming Cameras have become ubiquitous in the urban and industrial landscape. This research project aims to improve the AI-based action recognition capability of consumer-class home camera streams, which often have limited bandwidth and degraded video quality. The project proposes to develop a network-aware, video-action recognition AI pipeline that pushes key operations of traditional action recognition […]

Layer 6 powers the AI use cases for a variety of banking and financial applications at TD Bank. The goal of the research project is to improve the AI engine by having the training more efficient and distributed among a variety of clusters. The AI engine will allow models to be trained faster and with […]

Facial landmark detection is a computer vision problem where the goal is to predict the location of specific points on a face, like the eyes, nose, and mouth. This is useful for things like facial recognition and 3D modeling. To train a model to do this, we need a lot of images with those points […]

High-fidelity 3D face reconstruction from monocular images aims to obtain a 3D representation of the subject from a single or multiple input image. Recently, self-supervised deep-based methods have demonstrated impressive performance in 3D face reconstruction. These methods are efficient and produce plausible face reconstruction. However, for AAA production (games and movies), they do not yet […]

Geotab‘s dash cams deliver a clear and complete picture of harsh driving events and provide crucial video evidence in the case of collisions and insurance disputes. It is essential to ensure the dashcams work well and capture high quality footage. The object of this project is to automatically detect dash cam installation faulty and monitor […]

SpassMed’s ShockRanger is a primary product that utilizes vital signs from patient monitors to provide healthcare providers with meaningful signals for clinical decision-making. SpassMed is seeking one or more methods that can accurately forecast shocks, particularly Septic shock, among patients in ICUs. In addition, SpassMed aims to develop models for effectively classifying patients into their […]

Road safety affects everyone. In an effort to reduce accidents, we need to understand both the driving behavioural patterns that are predictive of accidents, and the environmental factors involved. In order to analysis risks, at first, collect a rich set of data: including Latitude/Longitude, engine RPM, accelerometer data in the X, Y, and Z plane, […]

The task of predicting salaries for a given job title and seniority in a specific region is challenging due to the complexity of various factors as well as the sensitivity of salary data. It’s hard to get an accurate sense of what people are getting paid in many regions in the world and getting harder […]

Smoking and all other forms of tobacco exposure are known to cause extremely detrimental health effects. It is the leading cause of preventable morbidity and mortality worldwide, and quitting smoking can increase life expectancy by as much 10 years. Tobacco is associated with poor reproductive health outcomes, cardiovascular disease, lung cancer, diabetes, blindness, and much […]

Ecomtent focuses on developing vertical-specific generative AI models for e-commerce brands, offering a self-service tool to allow customers to generate an unlimited number of high-quality images in any scenario. To this end, we leverage a textto- image model which will be trained to recontextualize any image via a simple text prompt. In particular, we seek […]