We introduce the first learning-based method for recovering shapes from Laplacian spectra. Our model consists of a cycle-consistent module that maps between learned latent vectors of an auto-encoder and sequences of eigenvalues.
3-dimensional (3D) audio is the new frontier in audio technology and it is quickly taking place in many applications, from cinema to virtual reality, audio surveillance and video games. The large amount of data requires fast and compact solutions for signal processing. With this aim in view, research is moving towards the exploration of hypercomplex algebras in order to find a non-redundant and compact form for the representation of 3D audio sound fields without the loss of information.
Hand gesture recognition is still a topic of great interest for the computer vision community. In particular, sign language and semaphoric hand gestures are two foremost areas of interest due to their importance in Human-Human Communication (HHC) and Human-Computer Interaction (HCI), respectively. Any hand gesture can be represented by sets of feature vectors that change over time. Recurrent Neural Networks (RNNs) are suited to analyse this type of sets thanks to their ability to model the long term contextual information of temporal sequences.
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma
