Category: AIR Seminars

AIR Weekly Seminar: Reasoning about Complex Media from Weak Multi-modal Supervision

The Hariri Institute of Computing has organized a “Reasoning about Complex Media from Weak Multi-modal Supervision” seminar on Monday, November 30th, 11:00am- 12:00pm as a part of its AIR Weekly Seminar series. The speaker for this event is Adriana Kovashka, Professor in Computer Science at the University of Pittsburgh. The AIR seminar will address the […]

Understanding and Anticipating Activities

Last week, Professor Dr. Juergen Gall led a talk about the aspects of video understanding. He began speaking about holistic video understanding, where a video can be categorized by the activity as well as other tags that can describe scenes or attributes of video. He goes on to describe a multi-stage temporal convolutional network, which […]

Two Speakers Share Automating AI Vision Analysis

AIR Seminar Series Talk 1: “D-RISE” Deep neural networks are being used increasingly to automate data analysis and decision making, yet their decision-making process is largely unclear and is difficult to explain to the end-users. Vitali Petsiuk, Ph.D Student, Computer Science, Boston University Talk 2: “Tracking with NL-RPN” A novel natural language region proposal network (NL-RPN) […]

Blurring Structure and Learning for Adaptive Local Recognition

AIR Distinguished Speaker Series Speaker: Evan Shelhamer, Research Scientist at Adobe, Visiting Researcher at MIT When: Monday, April 6, 2020 Time: 11:00am-12:30pm ZOOM Info: https://bostonu.zoom.us/j/815792639?pwd=cWxMNG1FbytWQzB6ZE5EbWtVbmR2QT09 Meeting ID: 815 792 639  Password: 457178 Abstract: The visual world is vast and varied, but there is nevertheless ubiquitous structure. In this talk, I will focus on incorporating locality and scale structure into […]

Multi-Modal Embodied Visual Learning

Kristen Grauman, Professor, Department of Computer Science, University of Texas at Austin When: 10:30am – 11:00am Networking & refreshments 11:00am – 12:00pm Talk Where: Kilachand Center, Colloquium Room 101 610 Commonwealth Ave,  Boston, MA 02215 Abstract: Computer vision has seen major success in learning to recognize objects from massive “disembodied” Web photo collections labeled by […]

Representations for Learning Scene Layout and Inferring Geometric Context from Images

Charless Fowlkes, Professor & Chancellor’s Fellow, Computer Science, University of California, Irvine When: Monday, March 16, 2020 12:30pm – 1:30pm Where: Metcalf Trustee Ballroom (9th floor) 1 Silber Way, Boston, MA 02215 Abstract: The content of an image can be understood in many ways, from inferring low-level descriptions of surface shape and material properties, to high-level […]

Maria-Florina Balcan Gives Talk about Machine Learning

Yesterday, Maria-Florina Balcan, Carnegie Mellon University Associate Professor of Computer Science, gave a talk on her research titled “Machine Learning: New Challenges and Connections.” This talk is part of the Cyber Alliance Distinguished Speaker Series and was held at the Kilachand building. In her presentation, she spoke machine learning’s far-reaching influences. Machine learning is now doing tasks for […]

“Machine Learning: New Challenges and Connections”

AIR Distinguished Speaker Series Maria-Florina Balcan, Assoc. Prof., Computer Science, Carnegie Mellon Univ. When: Monday, December 2, 2019 10:30am-11:00am networking and reception, 11:00am-12:00pm talk Where: Kilachand Center, 610 Commonwealth Ave, Colloquium Room 101 ABSTRACT: Over the past decades, machine learning has evolved into a highly successful discipline that has significantly influenced several fields, including vision, information […]

Learning to Learn More with Less

AIR Speaker Series Yuxiong Wang, Postdoctoral Fellow, Robotics Institute, Carnegie Mellon University When: Monday, November 18, 2019 12:00pm-1:00pm Where: Hariri Institute for Computing, Seminar Room MCS 157, 111 Cummington Mall, Boston, MA Abstract: Understanding how humans and machines learn from a few examples remains a fundamental challenge. Humans are remarkably capable of grasping new concepts from […]

Individual Freedom Versus the Hidden Persuaders: Preserving Individual Freedom in an Age of Socio-Technical Control via Algorithmic Rewards and Punishments

When: Wednesday, September 11, 2019 Event Start Time: 10:00 am Event End Time: 6:00 pm Where: Hillel House, 213 Bay State Road, Boston, MA Abstract: Consequences of computer network-based monitoring and control reach into everyone’s lives, with implications for individual rights and autonomy. Bringing together internationally recognized scholars, the conference investigates this growing problem and […]