Invited Speakers

Workshop Program

24 May 2022
Room "Sala d'Arte"

09.00 - 09.15: Welcome

09.15 - 09.45: Toward an Understanding of People from First Person Vision (Prof. Giovanni Maria Farinella)

09.45 - 10.15: Regular Papers

• Generating High-Resolution 3D Faces using VQ-VAE-2 with PixelSNAIL Networks
  Alessio Gallucci (Eindhoven University of Technology), Dmitry Znamenskiy (Philips), Nicola Pezzotti (Philips), Milan Petkovic (Philips)

• Recognition of complex gestures for real-time emoji assignment
  Rosa Zuccarà (Università di Catania), Alessandro Ortis (University of Catania), Sebastiano Battiato (Università di Catania)

• StyleTrendGAN: a deep learning generative framework for fashion bag generation
  Emanuele Balloni (University of Macerata), Laura Della Sciucca (Università Politecnica delle Marche), Marco Mameli (Università Politecnica delle Marche), Emanuele Frontoni (University of Macerata), Primo Zingaretti (Università Politecnica delle Marche), Marina Paolanti (University of Macerata)

10.15 - 10.45: Fashion compatibility modeling towards clothing matching (Prof. Xuemen Song)

Break

11.00 - 11.20: Regular Papers

• Effect of Gender, Pose and Camera Distance on Human Body Dimensions Estimation
  Yansel Gonzalez Tejeda (Paris Lodron University of Salzburg), Helmut A. Mayer (Paris Lodron University of Salzburg)

• Gender Recognition from 3D Shape Parameters
  Giulia Martinelli (University of Trento), Nicola Garau (University of Trento), Nicola Conci (University of Trento)

11.20 - 11.50: Learning Visio-linguistic Embeddings for Interactive Fashion Product Retrieval (Loris Bazzani)

11.50 - 12.20: Presentation Papers

• SimBa: a Pose Estimation Dataset for Safe Human-Robot Interaction
  Alessandro Simoni (University of Modena and Reggio Emilia), Stefano Pini (University of Modena and Reggio Emilia), Matteo Fincato (University of Modena and Reggio Emilia)

• On the Importance of Appearance and Interaction Feature Representations for Person Re-identification
  Richard Blythman (Huawei), Andrea Zunino (Leonardo), Christopher J Murray (Huawei), Vittorio Murino (Istituto Italiano di Tecnologia)

• First Steps Towards 3D Pedestrian Detection and Tracking from Single Image
  Gianluca Mancusi (University of Modena and Reggio Emilia), Matteo Fabbri (University of Modena and Reggio Emilia), Sara Egidi (Tetra Pak Packaging Solutions S.P.A.), Mattia Verasani (Tetra Pak Packaging Solutions S.P.A.), Paolo Scarabelli (Tetra Pak Packaging Solutions S.P.A.), Simone Calderara (University of Modena and Reggio Emilia), Rita Cucchiara (University of Modena and Reggio Emilia)

12.20 - 12.30: Best Paper Award (sponsored by MDPI Sensors)