Please select the desired project time frame:

• July 2026
• January 2026
• July 2025
• January 2025
• July 2024
• January 2024
• July 2023
• January 2023
• July 2022
• January 2022
• July 2021
• January 2021
• July 2020
• January 2020
• July 2019
• January 2019
• July 2018
• January 2018
• July 2017
• January 2017
• July 2016
• January 2016
• July 2015
• January 2015
• July 2014
• January 2014
• July 2013
• January 2013
• July 2012
• January 2012
• July 2011
• January 2011
• July 2010
• January 2010
• July 2009
• January 2009
• July 2008
• January 2008
• July 2007
• January 2007
• July 2006
• January 2006
• July 2005
• January 2005
• July 2004
• January 2004
• July 2003
• January 2003
• July 2002
• January 2002
• July 2001
• January 2001

Start of funding 01.07.2016

Webly-Supervised Deep Learning for Large-Scale Human Activity Recognition in Videos

---

There are an estimated 3.5 trillion photographs in the world. Facebook alone reports 6 billion photo uploads per month. Every minute, 72 hours of video are uploaded to YouTube. Cisco estimates that in the next few years, visual data (images and video) will account for over 85% of total internet traffic. Yet, we still lack effective computational methods to analyze big visual data. In the joint project, we focus on developing a new approach for human activity recognition in large-scale video collections. Our main idea is to take advantage of the large amount of data already available on the web in a weakly supervised scenario, thus it does not require manual labelling. To this end, we will design a deep learning architecture that incrementally learns the model by starting from the images retrieved from a search engine (e.g. Google). Then, these images will be enriched with “confident” frames extracted videos, and so the initial weak classifier is incrementally adapted to the video domain.