Publications by Rita Cucchiara

Image captioning has been recently gaining a lot of attention thanks to the impressive achievements shown by deep captioning architectures, which combine Convolutional Neural Networks to extract image representations, and Recurrent Neural Networks to generate the corresponding captions. At the same time, a significant research effort has been dedicated to the development of saliency prediction models, which can predict human eye fixations. Despite saliency information could be useful to condition an image captioning architecture, by providing an indication of what is salient and what is not, no model has yet succeeded in effectively incorporating these two techniques. In this work, we propose an image captioning approach in which a generative recurrent neural network can focus on different parts of the input image during the generation of the caption, by exploiting the conditioning given by a saliency prediction model on which parts of the image are salient and which are contextual. We demonstrate, through extensive quantitative and qualitative experiments on large scale datasets, that our model achieves superior performances with respect to different image captioning baselines with and without saliency. Finally, we also show that the trained model can focus on salient and contextual regions during the generation of the caption in an appropriate way.

Data-driven saliency has recently gained a lot of attention thanks to the use of Convolutional Neural Networks for predicting gaze fixations. In this paper we go beyond standard approaches to saliency prediction, in which gaze maps are computed with a feed-forward network, and present a novel model which can predict accurate saliency maps by incorporating neural attentive mechanisms. The core of our solution is a Convolutional LSTM that focuses on the most salient regions of the input image to iteratively refine the predicted saliency map. Additionally, to tackle the center bias typical of human eye fixations, our model can learn a set of prior maps generated with Gaussian functions. We show, through an extensive evaluation, that the proposed architecture outperforms the current state of the art on public saliency prediction datasets. We further study the contribution of each key component to demonstrate their robustness on different scenarios.

The prediction of human eye fixations has been recently gaining a lot of attention thanks to the improvements shown by deep architectures. In our work, we go beyond classical feed-forward networks to predict saliency maps and propose a Saliency Attentive Model which incorporates neural attention mechanisms to iteratively refine predictions. Experiments demonstrate that the proposed strategy overcomes by a considerable margin the state of the art on the largest dataset available for saliency prediction. Here, we provide experimental results on other popular saliency datasets to confirm the effectiveness and the generalization capabilities of our model, which enable us to reach the state of the art on all considered datasets.

Vehicle re-identification plays a major role in modern smart surveillance systems. Specifically, the task requires the capability to predict the identity of a given vehicle, given a dataset of known associations, collected from different views and surveillance cameras. Generally, it can be cast as a ranking problem: given a probe image of a vehicle, the model needs to rank all database images based on their similarities w.r.t the probe image. In line with recent research, we devise a metric learning model that employs a supervision based on local constraints. In particular, we leverage pairwise and triplet constraints for training a network capable of assigning a high degree of similarity to samples sharing the same identity, while keeping different identities distant in feature space. Eventually, we show how vehicle tracking can be exploited to automatically generate a weakly labelled dataset that can be used to train the deep network for the task of vehicle re-identification. Learning and evaluation is carried out on the NVIDIA AI city challenge videos.

A long tradition in social psychology focused on nonverbal behaviour displayed during dyadic interactions generally relying on evaluations from external coders. However, in addition to the fact that external coders may be biased, they may not capture certain type of behavioural indices. We designed three studies examining explicit and implicit prejudice as predictors of nonberval behaviour as reflected in objective indices provided by Kinect cameras. In the first study, we considered White-Black relations from the perspective of 36 White participants. Results revealed that implicit prejudice was associated with a reduction in interpersonal distance and in the volume of space between Whites and Blacks (vs. Whites and Whites), which in turn were associated with evaluations by collaborators taking part in the interaction. In the second study, 37 non-HIV participants interacted with HIV individuals. We found that implicit prejudice was associated with reduced volume of space between interactants over time (a process of bias overcorrection) only when they tried hard to control their behaviour (as captured by a stroop test). In the third study 35 non-disabled children interacted with disabled children. Results revealed that implicit prejudice was associated with reduced interpersonal distance over time.

We examined predictors and consequences of intergroup nonverbal behaviour by relying on new technologies and new objective indices. In three studies, both in the laboratory and in the field with children, behaviour was a function of implicit prejudice.

We present a novel video browsing and retrieval system for edited videos, in which videos are automatically decomposed into meaningful and storytelling parts (i.e. scenes) and tagged according to their transcript. The system relies on a Triplet Deep Neural Network which exploits multimodal features, and has been implemented as a set of extensions to the eXo Platform Enterprise Content Management System (ECMS). This set of extensions enable the interactive visualization of a video, its automatic and semi-automatic annotation, as well as a keyword-based search inside the video collection. The platform also allows a natural integration with third-party add-ons, so that automatic annotations can be exploited outside the proposed platform.

Game science has become a research field, which attracts industry attention due to a worldwide rich sell-market. To understand the player experience, concepts like flow or boredom mental states require formalization and empirical investigation, taking advantage of the objective data that psychophysiological methods like electroencephalography (EEG) can provide. This work studies the affective ludology and shows two different game levels for Neverwinter Nights 2 developed with the aim to manipulate emotions; two sets of affective design guidelines are presented, with a rigorous formalization that considers the characteristics of role-playing genre and its specific gameplay. An empirical investigation with a brain–computer interface headset has been conducted: by extracting numerical data features, machine learning techniques classify the different activities of the gaming sessions (task and events) to verify if their design differentiation coincides with the affective one. The observed results, also supported by subjective questionnaires data, confirm the goodness of the proposed guidelines, suggesting that this evaluation methodology could be extended to other evaluation tasks.

Estimating the focus of attention of a person looking at an image or a video is a crucial step which can enhance many vision-based inference mechanisms: image segmentation and annotation, video captioning, autonomous driving are some examples. The early stages of the attentive behavior are typically bottom-up; reproducing the same mechanism means to find the saliency embodied in the images, i.e. which parts of an image pop out of a visual scene. This process has been studied for decades in neuroscience and in terms of computational models for reproducing the human cortical process. In the last few years, early models have been replaced by deep learning architectures, that outperform any early approach compared against public datasets. In this paper, we propose a discussion on why convolutional neural networks (CNNs) are so accurate in saliency prediction. We present our DL architectures which combine both bottom-up cues and higher-level semantics, and incorporate the concept of time in the attentional process through LSTM recurrent architectures. Eventually, we present a video-specific architecture based on the C3D network, which can extracts spatio-temporal features by means of 3D convolutions to model task-driven attentive behaviors. The merit of this work is to show how these deep networks are not mere brute-force methods tuned on massive amount of data, but represent well-defined architectures which recall very closely the early saliency models, although improved with the semantics learned by human ground-thuth.