Sharing Knowledge for Large Scale Visual Recognition

Speaker:  Lamberto Ballan - Università di Padova
  Thursday, March 22, 2018 at 11:00 AM - Sala verde
This talk overviews my recent research activities in computer vision, pattern recognition and multimedia for understanding big visual
data. I will focus on two models for "sharing" prior and contextual knowledge for solving large scale visual recognition problems. In the
first part of the talk, I'll show that images that are very difficult to recognize on their own may become more clear in the context of a
neighborhood of related images with similar social-network metadata. Our model uses image metadata non-parametrically to generate neighborhoods of related images, then uses a deep neural network to blend visual information from the image and its neighbors. In the second part of the talk, I'll present our recent work on knowledge transfer for scene-specific motion prediction. When given a single frame of a video, humans can not only interpret the content of the scene, but also they are able to forecast the near future. This ability is driven by their rich prior knowledge about the visual world, both in terms of the dynamics of moving agents, as well as the semantic of the scene. We
exploit the interplay between these two key elements to predict scene-specific motion patterns on a novel large dataset collected from UAV.

Contact person: Marco Cristani

Contact person

Publication date
February 7, 2018

Studying