Stefano Pini

Heavy metals in sediments from canals for water supplying and drainage: mobilization and control strategies.

One of the most critical aspects of the maintenance of canals for water supplying and drainage is the managing of deposited sediments, which must be periodically removed. Deposited sediments, if containing anthropogenic pollutants with a concentration exceeding specific law limits, must be stored as industrial wastes, thus raising additional economic and logistic problems to deal with. Our research considers polluted sediments from an area close to the south side of Po river, in order to characterize heavy metals associated with different mineral species, thus defining effective treatments for their inertization, and suggesting a possible process for their recycle. Our results demonstrate that the composition of these sediments is suitable for the production of tiles and bricks. Several tests were thus performed to optimize sample treatment and other process parameters, finally giving very encouraging results. Releasing tests on fired products reveal that all the heavy metals are well retained.

Modeling multimodal cues in a deep learning-based framework for emotion recognition in the wild

In this paper, we propose a multimodal deep learning architecture for emotion recognition in video regarding our participation to the audio-video based sub-challenge of the Emotion Recognition in the Wild 2017 challenge. Our model combines cues from multiple video modalities, including static facial features, motion patterns related to the evolution of the human expression over time, and audio information. Specifically, it is composed of three sub-networks trained separately: the first and second ones extract static visual features and dynamic patterns through 2D and 3D Convolutional Neural Networks (CNN), while the third one consists in a pretrained audio network which is used to extract useful deep acoustic signals from video. In the audio branch, we also apply Long Short Term Memory (LSTM) networks in order to capture the temporal evolution of the audio features. To identify and exploit possible relationships among different modalities, we propose a fusion network that merges cues from the different modalities in one representation. The proposed architecture outperforms the challenge baselines (38.81 % and 40.47 %): we achieve an accuracy of 50.39 % and 49.92 % respectively on the validation and the testing data.

Towards Video Captioning with Naming: A Novel Dataset and a Multi-modal Approach

Current approaches for movie description lack the ability to name characters with their proper names, and can only indicate people with a generic “someone” tag. In this paper we present two contributions towards the development of video description architectures with naming capabilities: firstly, we collect and release an extension of the popular Montreal Video Annotation Dataset in which the visual appearance of each character is linked both through time and to textual mentions in captions. We annotate, in a semi-automatic manner, a total of 53k face tracks and 29k textual mentions on 92 movies. Moreover, to underline and quantify the challenges of the task of generating captions with names, we present different multi-modal approaches to solve the problem on already generated captions.

Automatic Image Cropping and Selection Using Saliency: An Application to Historical Manuscripts

Automatic image cropping techniques are particularly important to improve the visual quality of cropped images and can be applied to a wide range of applications such as photo-editing, image compression, and thumbnail selection. In this paper, we propose a saliency-based image cropping method which produces significant cropped images by only relying on the corresponding saliency maps. Experiments on standard image cropping datasets demonstrate the benefit of the proposed solution with respect to other cropping methods. Moreover, we present an image selection method that can be effectively applied to automatically select the most representative pages of historical manuscripts thus improving the navigation of historical digital libraries.