MSR Speaking Qualifier

work, we address the problem of goal-directed cloth manipulation, a challenging task due to the deformability of cloth. Our insight is that optical flow, a technique normally used for motion estimation in video, can also provide an effective representation for corresponding cloth poses across observation and goal images. We introduce FabricFlowNet (FFN), a cloth manipulation [...]

Title: Towards Practical Ultrasound AI Across Real-World Patient Diversity Abstract: In the case of high-tempo, traumatic scenarios on the battlefield, real-time ultrasound (US) imaging serves as an enabler for countless possible robotic interventions. Having the ability to automatically segment anatomical landmarks in the body, such as arteries, veins, ligaments, and veins, for percutaneous procedures remains [...]

Title: Audiovisual ontology and robust representations via cross-modal fusion   Abstract: The shrill of an ambulance siren and flashing lights, the hum of an accelerating car — important events often come to us simultaneously through sight and sound. We first consider the problem of identifying these events from raw, unlabeled audiovisual data of agents interacting with [...]

Title: T-HTN: Timeline Based HTN Planning for Multi-Agent Robots   Abstract: Planning in mission-critical systems like deep-space habitats with onboard robotic systems must be robust to unforeseen circumstances. Such systems are expected to complete a set of goals with different deadlines each day for routine maintenance while also accounting for emergencies. With the presence of [...]

Title: Towards Self-supervised Object Discovery and Tracking   Abstract: Object discovery and multiple object tracking (MOT) are two highly interrelated tasks that are known to be fundamental problems in computer vision, and are crucial for video understanding. Most existing methods rely on supervised training with human annotations, which is laborious and expensive. In this thesis, [...]

Title: Towards Object-generic 6D Pose Estimation Abstract: Pose estimation is a basic module in many robot manipulation pipelines. Estimating the pose of objects in the environment can be useful for grasping, motion planning, or manipulation. However, current state-of-the-art methods for pose estimation either rely on large annotated training sets or simulated data. Further, the long [...]

Title: End-to-End Deep Stereo Layout Estimation   Abstract: Accurate layout estimation is crucial for planning and navigation in robotics applications, such as self-driving. In this paper, we introduce the Stereo Bird's Eye ViewNetwork (SBEVNet), a novel supervised end-to-end framework for estimation of bird's eye view layout from a pair of stereo images. Although our network [...]

Title: Design of a Multimodal System for Social Emotional Learning in Early Childhood Classrooms   Abstract: As the prevalence of mobile and touch-based devices continues to expand in society, so too does its impact on young children. With educational technologies also on the rise, young children benefit most from those technologies that are designed to [...]

Title: End-to-End Methods for Autonomous Driving in Simulation   Abstract: Fully autonomous driving is considered one of the grand challenges of modern technology and a variety of approaches have emerged for creating and evaluating autonomous driving agents. The self-driving industry typically adopts a modular software architecture and uses large fleets of autonomous vehicles for data [...]

Title: Retrieval-based Novel Activity Detection in Untrimmed Videos   Abstract: Accurately detecting activities in untrimmed videos is a challenging task as systems need to handle variance in object scales, multiple viewpoints, and multiple types of activities. Furthermore, in a real-world scenario, activity detectors are often required to detect novel kinds of activities when the need [...]