University of Cambridge > Talks.cam > Microsoft Research Cambridge, public talks > Activity recognition in naturalistic environments

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Activity recognition in naturalistic environments

Download to your calendar using vCal

If you have a question about this talk, please contact .

Please be aware that this event may be recorded. Microsoft will own the copyright of any recording and reserves the right to distribute it as required.

The development of automated systems for the analysis of human movement and behaviour is a major aim of ubiquitous computing. While the untapped potential especially for medical and lifestyle applications is huge, so far, there are barely any systems sufficiently robust to be useful under real-life conditions. In this talk I will discuss some of the reasons for this lack of in-the-wild deployments, how deep learning can address some of the emerging issues, and how practitioners in ubicomp / machine learning need to adapt study designs and evaluation approaches for naturalistic settings like the private home.

This talk is part of the Microsoft Research Cambridge, public talks series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

SS03, William Gates Building. Zoom link: https://cl-cam-ac-uk.zoom.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&from=addon Pfizer Lecture Theatre, Chemistry, Department of Senior Parlour, Gonville & Caius College

Other talks

Rothschild Public Lecture | Forty years of causal inference: Report of a great-grandfather Title to be confirmed: CMS Cultural evolution creates language-like structure: from humans to humpback whales and beyond Pancreatic cancer - the clinical challenge;  Why the microenvironment matters during pancreatic cancer progression and treatment Title to be confirmed Title to follow
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity