[May 10th 2018] LabMeeting: DBox: Deep Learning for Bounding Box Supervision in Semantic Segmentation

Simone Bonechi (DIISM, University of Siena) May 10, 2018 – 9:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Most of the leading convolutional neural networks for semantic segmentation exploit a large number of pixel–level annotations. Such human based labelling require a considerable effort that complicate the creation of large–scale datasets. In this […]

Read More »

[May 3rd 2018] LabMeeting: Modeling stylized character expression via deep learning

Lisa Graziani (DIISM, University of Siena) May 3, 2018 – 9:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description DeepExpr is a perceptual model that allows an accurate retrieval of stylized character expressions given a human expression query. It can be helpful in animation to create desired character expressions driven by human facial […]

Read More »

[April 12th 2018] LabMeeting: Synthetic data generation for semantic segmentation

Paolo Andreini(DIISM, University of Siena) April 12, 2018 – 9:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description In recent years, deep learning techniques have push the state of the art in many visual recognition tasks, based on fully annotated data by human experts. Nevertheless, this annotation procedure is inherently difficult and costly, […]

Read More »

[April 5th 2018] LabMeeting: Convolutional Networks in Visual Environments

Alessandro Betti (DIISM, University of Siena) April 5, 2018 – 9:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description The puzzle of computer vision might find new challenging solutions when we realize that most successful methods are working at image level, which is remarkably more difficult than processing directly visual streams. In this […]

Read More »

[March 29th 2018] LabMeeting: LogSCM – Logical Support Constraint Machines

Francesco Giannini (DIISM, University of Siena) March 29, 2018 – 9:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description The success of support vector machines lies in the fact that only a small portion of data are significant to determine the maximum margin hyperplane separating two opposite class of labeled examples, namely the […]

Read More »

[March 22nd 2018] LabMeeting Extra: Excursus in the State of the art of object detection – Deep learning models, performance, practical tests

Matteo Tiezzi (DIISM, University of Siena) March 22, 2018 – 10:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description In image classification an image with a single object is the focus and the task is to say what it contains. But when we look at the world around us, we carry out far […]

Read More »

[April 3rd, 2018] Trust your data or not – Standard remains Standard (QP); implications for robust clustering in social networks

Immanuel Bomze (VCOR/ISOR and DataScience@UniWien) based upon joint work with Michael Kahr, Markus Leitner, Werner Schachinger and Reinhard Ullrich (all Univ.Wien) April 3, 2018 – 11:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description In a Standard Quadratic Optimization Problem (StQP), a possibly indefinite quadratic form (the simplest nonlinear function) is extremized over […]

Read More »

[March 22nd 2018] LabMeeting: Dialogue Generation from Structured Knowledge

Andrea Zugarini (DIISM, University of Siena) March 22, 2018 – 9:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description Current task-oriented dialogue systems are limited to operate in a pre-defined domain. They provide good performances, but they lack of generalization capabilities because of their bound with the specific task. On the other hand, […]

Read More »

[March 15th, 2018] CLARE: a Constrained Learning And Reasoning Environment

Giuseppe Marra (DIISM, University of Siena) March 15th, 2018 – 9:30 AM DIISM, Artificial Intelligence laboratory (room 201), Siena SI Description In spite of the amazing results of deep learning in many applications, a real intelligent behavior of an agent, acting in a complex environment, is likely to require some kind of higher-level symbolic inference. […]

Read More »