1. Lecca, Michela,
    Retinex-inspired Image Enhancement: the Sampling-based Milano Retinex Approaches [Talk in "Mathematics for Computer Vision", February 15-16, 2018],
    Talk in the Workshop MCV 2018, FBK, Feb 15-16 2018, Trento, IT,
    2018
  2. Lecca, Michela; Da Pos, Osvaldo,
    2018
  3. Podestà, Federico,
    2018
  4. Claudia Meroni, Elena; Piazzalunga, Daniela; Pronzato, Chiara,
    In this paper, we study the effects of extra-school activities on children’s non-cognitive development, using data from the Millennium Cohort Study (UK) and focusing on children aged 7-11 years old. We classify the time spent out of school into six homogenous groups of activities, using principal component analysis, and estimate the relationship thereof with five behavioural dimensions drawn from the Strength and Difficulties questionnaire, exploiting the panel structure of the data. Results show the beneficial effects on children’s behaviour of sports, school-related activities, time with parents and household chores, while a small detrimental effect of video-screen time is detected. We test the robustness of our estimates against omitted variable bias, and the results are confirmed. We also observe that children from more advantaged backgrounds have easier access to more beneficial activities. Overall, our results suggest that different uses of time may reinforce inequalities across children from different backgrounds.,
    2018
  5. Sierminksa, Eva; Piazzalunga, Daniela; Grabka, Markus,
    2018
  6. Cimatti, Alessandro; Delong, Rance; Stojic, Ivan; Tonetta, Stefano,
    2018
  7. Azzolini, Davide; Martini, Alberto; Rettore, Enrico; Romano, Barbara; Schizzerotto, Antonio; Vergolini, Loris,
    Testing a Social Innovation in Financial Aid for Low-Income Students: Experimental Evidence from Italy,
    2018
  8. Donadello, Ivan,
    Semantic Image Interpretation (SII) is the process of generating a structured description of the content of an input image. This description is encoded as a labelled direct graph where nodes correspond to objects in the image and edges to semantic relations between objects. Such a detailed structure allows a more accurate searching and retrieval of images. In this thesis, we propose two well-founded methods for SII. Both methods exploit background knowledge, in the form of logical constraints of a knowledge base, about the domain of the images. The first method formalizes the SII as the extraction of a partial model of a knowledge base. Partial models are built with a clustering and reasoning algorithm that considers both low-level and semantic features of images. The second method uses the framework Logic Tensor Networks to build the labelled direct graph of an image. This framework is able to learn from data in presence of the logical constraints of the knowledge base. Therefore, the graph construction is performed by predicting the labels of the nodes and the relations according to the logical constraints and the features of the objects in the image. These methods improve the state-of-the-art by introducing two well-founded methodologies that integrate low-level and semantic features of images with logical knowledge. Indeed, other methods, do not deal with low-level features or use only statistical knowledge coming from training sets or corpora. Moreover, the second method overcomes the performance of the state-of-the-art on the standard task of visual relationship detection.,
    2018
  9. Lecca, Michela; Da Pos, Osvaldo,
    2018
  10. Jumaah, Ahmed Salih Fadhil,
    2018