Seminar
Deep Robotic Learning
Sergey Levine Assistant Professor, UC Berkeley Abstract Deep learning methods have provided us with remarkably powerful, flexible, and robust solutions in a wide range of passive perception areas: computer vision, speech recognition, and natural language processing. However, active decision making domains such as robotic control present a number of additional challenges, standard supervised learning methods [...]
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 [...]
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 [...]
Chris Urmson: Perspectives on Self-Driving Cars – Teruko Yata Memorial Lecture in Robotics
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 state-of-the-art, perception of the technology still lands somewhere between solved [...]
Visual Analysis of Dense Crowds
Event Location: Newell Simon Hall 1507Bio: Haroon Idrees is a postdoctoral researcher in the Center for Research in Computer Vision (CRCV) at the University of Central Florida (UCF). He is interested in machine vision and learning, with focus on crowd analysis, action recognition, multi-camera and airborne surveillance, as well as deep learning and multimedia content [...]
Haroon Idrees: Visual Analysis of Dense Crowds
Haroon Idrees Post Doc Associate, Center for Research in Computer Vision, University of Central Florida (UCF) Abstract Automated analysis of dense crowds is a challenging problem with far-reaching applications in crowd safety and management, as well as gauging political significance of protests and demonstrations. In this talk, I will first describe a counting approach which [...]