no code implementations • 12 Mar 2024 • Andreas Damianou, Francesco Fabbri, Paul Gigioli, Marco De Nadai, Alice Wang, Enrico Palumbo, Mounia Lalmas
In the realm of personalization, integrating diverse information sources such as consumption signals and content-based representations is becoming increasingly critical to build state-of-the-art solutions.
no code implementations • 8 Mar 2024 • Marco De Nadai, Francesco Fabbri, Paul Gigioli, Alice Wang, Ang Li, Fabrizio Silvestri, Laura Kim, Shawn Lin, Vladan Radosavljevic, Sandeep Ghael, David Nyhan, Hugues Bouchard, Mounia Lalmas-Roelleke, Andreas Damianou
While promising, this move presents significant challenges for personalized recommendations.
1 code implementation • 3 Oct 2022 • Yahui Liu, Enver Sangineto, Yajing Chen, Linchao Bao, Haoxian Zhang, Nicu Sebe, Bruno Lepri, Marco De Nadai
Multi-domain image-to-image (I2I) translations can transform a source image according to the style of a target domain.
1 code implementation • 9 Jun 2022 • Elia Peruzzo, Enver Sangineto, Yahui Liu, Marco De Nadai, Wei Bi, Bruno Lepri, Nicu Sebe
In this work, we propose a different and complementary direction, in which a local bias is introduced using an auxiliary self-supervised task, performed jointly with standard supervised training.
1 code implementation • 26 Sep 2021 • Yahui Liu, Yajing Chen, Linchao Bao, Nicu Sebe, Bruno Lepri, Marco De Nadai
The ISF manipulates the semantics of an input latent code to make the image generated from it lying in the desired visual domain.
1 code implementation • ICCV 2021 • Pierfrancesco Ardino, Marco De Nadai, Bruno Lepri, Elisa Ricci, Stéphane Lathuilière
This paper introduces Click to Move (C2M), a novel framework for video generation where the user can control the motion of the synthesized video through mouse clicks specifying simple object trajectories of the key objects in the scene.
no code implementations • CVPR 2021 • Yahui Liu, Enver Sangineto, Yajing Chen, Linchao Bao, Haoxian Zhang, Nicu Sebe, Bruno Lepri, Wei Wang, Marco De Nadai
In this paper, we propose a new training protocol based on three specific losses which help a translation network to learn a smooth and disentangled latent style space in which: 1) Both intra- and inter-domain interpolations correspond to gradual changes in the generated images and 2) The content of the source image is better preserved during the translation.
1 code implementation • NeurIPS 2021 • Yahui Liu, Enver Sangineto, Wei Bi, Nicu Sebe, Bruno Lepri, Marco De Nadai
This task encourages the VTs to learn spatial relations within an image and makes the VT training much more robust when training data are scarce.
1 code implementation • 19 Oct 2020 • Pierfrancesco Ardino, Yahui Liu, Elisa Ricci, Bruno Lepri, Marco De Nadai
Inspired by recent works on image inpainting, our proposed method leverages the semantic segmentation to model the content and structure of the image, and learn the best shape and location of the object to insert.
1 code implementation • 11 Aug 2020 • Raul Gomez, Yahui Liu, Marco De Nadai, Dimosthenis Karatzas, Bruno Lepri, Nicu Sebe
In this paper we propose the use of an image retrieval system to assist the image-to-image translation task.
1 code implementation • 10 Aug 2020 • Yahui Liu, Marco De Nadai, Deng Cai, Huayang Li, Xavier Alameda-Pineda, Nicu Sebe, Bruno Lepri
Our proposed model disentangles the image content from the visual attributes, and it learns to modify the latter using the textual description, before generating a new image from the content and the modified attribute representation.
1 code implementation • 11 Jun 2020 • Emanuele Strano, Filippo Simini, Marco De Nadai, Thomas Esch, Mattia Marconcini
To explain the observed spatial patterns, we also propose a model that combines two agglomeration forces and simulates human settlements' historical growth.
Physics and Society
1 code implementation • 15 Mar 2020 • Yahui Liu, Marco De Nadai, Jian Yao, Nicu Sebe, Bruno Lepri, Xavier Alameda-Pineda
Unsupervised image-to-image translation (UNIT) aims at learning a mapping between several visual domains by using unpaired training images.
1 code implementation • 12 Jul 2019 • Yahui Liu, Marco De Nadai, Gloria Zen, Nicu Sebe, Bruno Lepri
In this work, we propose a novel GAN architecture that decouples the required annotations into a category label - that specifies the gesture type - and a simple-to-draw category-independent conditional map - that expresses the location, rotation and size of the hand gesture.
1 code implementation • 7 Aug 2018 • Marco De Nadai, Bruno Lepri
In this paper, we use multiple sources of data to entangle the economic contribution of the neighborhood's characteristics such as walkability and security perception.
Computers and Society
1 code implementation • 1 Aug 2016 • Marco De Nadai, Radu L. Vieriu, Gloria Zen, Stefan Dragicevic, Nikhil Naik, Michele Caraviello, Cesar A. Hidalgo, Nicu Sebe, Bruno Lepri
But in a world where the preference for safe looking neighborhoods is small, the connection between the perception of safety and liveliness will be either weak or nonexistent.
Computers and Society Social and Information Networks Physics and Society
1 code implementation • 13 Mar 2016 • Marco De Nadai, Jacopo Staiano, Roberto Larcher, Nicu Sebe, Daniele Quercia, Bruno Lepri
This is mainly because it is hard to collect data about "city life".
Computers and Society Social and Information Networks Physics and Society