Learning to Learn and Structure Learning in Model Spaces for Small Sample Visual Recognition
Yuxiong Wang Carnegie Mellon University Abstract Understanding how to recognize novel categories from few examples for both humans and machines remains a fundamental challenge. Humans are remarkably able to grasp a new category and make meaningful generalization to novel instances from just few examples. By contrast, state-of-the-art machine learning techniques and visual recognition systems typically [...]
The lifetime of an object – an object’s perspective onto interactions
Event Location: Newell Simon Hall 1507Bio: Lecturer (Assistant Professor) in Computer Vision at the University of Bristol. Received her PhD from the University of Leeds (2009). Dima's research interests are in the automatic understanding of object interactions, actions and activities using static and wearable visual (and depth) sensors. Dima co-chaired BMVC 2013, is area chair [...]
The lifetime of an object – an object’s perspective onto interactions
Dima Damen Assistant Professor, University of Bristol, United Kingdom April 10, 2017, 3:00-4:00 p.m., Newell Simon Hall 1507 Abstract As opposed to the traditional notion of actions and activities in computer vision, where the motion (e.g. jumping) or the goal (e.g. cooking) is the focus, I will argue for an object-centred perspective onto actions and [...]
Safe, Efficient, and Robust Predictive Control of Constrained Nonlinear Systems
Vishnu R. Desaraju Carnegie Mellon University April 12, 2017, 2:00 p.m., NSH 1305 Abstract As autonomous systems are deployed in increasingly complex and uncertain environments, safe, accurate, and robust feedback control techniques are required to ensure reliable operation. Accurate trajectory tracking is essential to complete a variety of tasks, but this may be difficult if [...]
Computer Vision @ Scale
Manohar Paluri Research Lead, Facebook Abstract Over the past 5 years the community has made significant strides in the field of Computer Vision. Thanks to large scale datasets, specialized computing in form of GPUs and many breakthroughs in modeling better convnet architectures Computer Vision systems in the wild at scale are becoming a reality. At [...]
“Ensuring Safe Human-Robot Co-Existence by Reachability Analysis”
Matthias Althoff Technische Universität München Abstract Modern manufacturing companies are expected to quickly and efficiently adapt to production changes, and robotics has long been known as the candidate solution for the required flexibility. To improve such flexibility, future working environments will be populated by both humans and robot manipulators, sharing the same workspace. This scenario [...]
Towards scaling video understanding
Serena Yeung Ph.D. Student, Stanford University Abstract The quantity of video data is vast, yet our capabilities for visual recognition and understanding in videos lags significantly behind that for images. In this talk, I will discuss the challenges of scale in labeling, modeling, and inference behind this gap. I will then present three works addressing [...]
Harnessing Task Mechanics for Robotic Manipulation: Modeling, Uncertainty Reduction and Control
Jiaji Zhou Carnegie Mellon University Abstract A high-fidelity and tractable mechanics model of the physical interaction is essential for autonomous robotic manipulation in complex and uncertain environments. Nonetheless, task mechanics are often ignored or nullified in most robotic manipulation systems. This thesis proposal addresses three aspects of harnessing task mechanics: mechanics model learning, uncertainty reduction [...]
Teruko Yata Memorial Lecture in Robotics
Event Location: Rashid Auditorium - 4401 Gates and Hillman CentersAbstract: SPEAKER: Chris Urmson, CEO & co-founder Aurora Title: Perspectives on Self-Driving Cars Abstract: Self-driving vehicles will save millions of lives, make cities more liveable, save resources, and transform transportation to be more accessible and enjoyable for everyone. Despite a decade of rapid advancement in the [...]