In recent years, Speech Emotion Recognition (SER) has been investigated mainly transforming the speech signal into spectrograms that are then classified using Convolutional Neural Networks pretrained on generic images and fine tuned with spectrograms. In this paper, we start from the general idea above and develop a new learning solution for SER, which is based on Compact Convolutional Transformers (CCTs) combined with a speaker embedding. With CCTs, the learning power of Vision Transformers (ViT) is combined with a diminished need for large volume of data as made possible by the convolution. This is important in SER, where large corpora of data are usually not available. The speaker embedding allows the network to extract an identity representation of the speaker, which is then integrated by means of a self-attention mechanism with the features that the CCT extracts from the spectrogram. Overall, the solution is capable of operating in real-time showing promising results in a cross-corpus scenario, where training and test datasets are kept separate. Experiments have been performed on several benchmarks in a cross-corpus setting as rarely used in the literature, with results that are comparable or superior to those obtained with state-of-the-art network architectures. Our code is available at https://github.com/JabuMlDev/Speaker-VGG-CCT.
In this paper, we introduce a new approach for retrieval and classification of 3D models that directly performs in the Computer-Aided Design (CAD) format without any conversion to other representations like point clouds or meshes, thus avoiding any loss of information. Among the various CAD formats, we consider the widely used STEP extension, which represents a standard for product manufacturing information. This particular format represents a 3D model as a set of primitive elements such as surfaces and vertices linked together. In our approach, we exploit the linked structure of STEP files to create a graph in which the nodes are the primitive elements and the arcs are the connections between them. We then use Graph Neural Networks (GNNs) to solve the problem of model classification. Finally, we created two datasets of 3D models in native CAD format, respectively, by collecting data from the Traceparts model library and from the Configurators software modeling company. We used these datasets to test and compare our approach with respect to state-of-the-art methods that consider other 3D formats. Our code is available at https://github.com/divanoLetto/3D_STEP_Classification
Human facial expressions change dynamically, so their recognition / analysis should be conducted by accounting for the temporal evolution of face deformations either in 2D or 3D. While abundant 2D video data do exist, this is not the case in 3D, where few 3D dynamic (4D) datasets were released for public use. The negative consequence of this scarcity of data is amplified by current deep learning based-methods for facial expression analysis that require large quantities of variegate samples to be effectively trained. With the aim of smoothing such limitations, in this paper we propose a large dataset, named Florence 4D, composed of dynamic sequences of 3D face models, where a combination of synthetic and real identities exhibit an unprecedented variety of 4D facial expressions, with variations that include the classical neutral-apex transition, but generalize to expression-to-expression. All these characteristics are not exposed by any of the existing 4D datasets and they cannot even be obtained by combining more than one dataset. We strongly believe that making such a data corpora publicly available to the community will allow designing and experimenting new applications that were not possible to investigate till now. To show at some extent the difficulty of our data in terms of different identities and varying expressions, we also report a baseline experimentation on the proposed dataset that can be used as baseline.