Show simple item record

dc.contributor.authorLaptev, Ivan
dc.descriptionPresented on September 30, 2016 at 12:00 p.m. in the Marcus Nanotechnology Building, Room 1116en_US
dc.descriptionIvan Laptev is a research director at INRIA Paris, France. Laptev’s main research interests include visual recognition of human actions, objects, and interactions.en_US
dc.descriptionRuntime: 56:30 minutesen_US
dc.description.abstractRecent progress in visual recognition goes hand-in-hand with the supervised learning and large-scale training data. While the amount of existing images and videos is huge, their detailed annotation is expensive and often ambiguous. To address these problems, in this talk we will focus on weakly-supervised learning methods using incomplete and noisy supervision for training. In the first part I will discuss recognition from still images and will describe our work on weakly-supervised convolutional networks for recognizing and localizing objects and human actions. The second part of the talk will focus on the learning of human actions from videos. In particular we will consider understanding specific tasks from YouTube instruction videos and corresponding narrations. We will conclude with future challenges and opportunities of visual recognition.en_US
dc.format.extent00:00 minutes
dc.format.extent56:30 minutes
dc.relation.ispartofseriesIRIM Seminar Seriesen_US
dc.subjectActivity understandingen_US
dc.subjectComputer visionen_US
dc.subjectObject recognitionen_US
dc.titleWeakly Supervised Learning from Images and Videoen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Institute for Robotics and Intelligent Machineen_US

Files in this item


This item appears in the following Collection(s)

  • IRIM Seminar Series [116]
    Each semester a core seminar series is announced featuring guest speakers from around the world and from varying backgrounds in robotics.

Show simple item record