Sharing Knowledge for Large Scale Visual Recognition

Lamberto Ballan

In this talk Lamberto Ballan will present two models for “sharing” prior and contextual knowledge for solving large scale visual recognition problems.

Lecture date and venue: Thursday, October 6 in Aula Anfiteatro, MICC, Viale Morgagni 65 at 2.30PM

In the first part of the talk, Lamberto Ballan will 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. This intuition is used to improve multi-label image annotation and show state-of-the-art results on the NUS-WIDE dataset. The model uses image metadata nonparametrically 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, he’ll present his 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 mostly 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. The interplay between these two key elements is exploited to predict scene-specific motion patterns on a novel large dataset collected from UAV on the Stanford campus.

Filippo Mameli, Marco Bertini, Leonardo Galteri, Alberto Del Bimbo, Image and video restoration and compression artefact removal using a NoGAN approach

ACM MM 2020 Demo Paper

Image and video restoration and compression

Marie Curie

Lamberto Ballan Fellow of the week

Best Poster ACM ICMR 2020

Image Retrieval Using Multi-Scale CNN Feature Pooling