Professor

In this work, given a piece of a dialog, we addressed the problem of predicting the subjective emotional response of the upcoming utterances (i.e. the emotion that will be expressed by the next speaker when the speaker talks). For that, we also take into account, as input, the personality trait of the next speaker. (PDF)

The task of video object segmentation with referring expressions (language-guided VOS) is to, given a linguistic phrase and a video, generate binary masks for the object to which the phrase refers. We propose a new architecture (RefVOS) to address this task and we show that the major challenges are related to understanding motion and static actions. (PDF)

In this work we address the subjectivity problem in the task of the recognition of the emotions evoked by videos. Instead of modeling the aggregated value, we jointly model the emotions experienced by each viewer and the aggregated value using a multi-task learning approach (PDF). A journal extension can also be found here.

In this work we propose a Recurrent network for multiple object Video Object Segmentation (RVOS) that is fully end-to-end trainable. Our model incorporates recurrence on two different domains: (i) the spatial, which allows to discover the different object instances within a frame, and (ii) the temporal, which allows to keep the coherence of the segmented objects along time. (PDF)

This paper tackles the task of estimating the topology of filamentary networks such as retinal vessels. Using a previous proposed CNN model that predicts the local connectivity among the central pixel of an input patch and its border points, we perform a qualitative and quantitative evaluation on retinal veins and arteries topology extraction on DRIVE dataset. (PDF)

This paper tackles the task of estimating the topology of road networks from aerial images. We design a CNN that predicts the local connectivity among the central pixel of an input patch and its border points. By iterating this local connectivity we sweep the whole image and infer the global topology of the road network. (PDF)

This paper addresses the problem of automatically inferring personality traits of people talking to a camera. It presents a deep study on understanding why CNN models are performing surprisingly well by using techniques on CNN model interpretability, combined with face detection and Action Unit (AUs) recognition systems. (PDF)