Publications by Marcella Cornia

Visual-semantic embeddings have been extensively used as a powerful model for cross-modal retrieval of images and sentences. In this setting, data coming from different modalities can be projected in a common embedding space, in which distances can be used to infer the similarity between pairs of images and sentences. While this approach has shown impressive performances on fully supervised settings, its application to semi-supervised scenarios has been rarely investigated. In this paper we propose a domain adaptation model for cross-modal retrieval, in which the knowledge learned from a supervised dataset can be transferred on a target dataset in which the pairing between images and sentences is not known, or not useful for training due to the limited size of the set. Experiments are performed on two target unsupervised scenarios, respectively related to the fashion and cultural heritage domain. Results show that our model is able to effectively transfer the knowledge learned on ordinary visual-semantic datasets, achieving promising results. As an additional contribution, we collect and release the dataset used for the cultural heritage domain.

State of the art Computer Vision techniques exploit the availability of large-scale datasets, most of which consist of images captured from the world as it is. This brings to an incompatibility between such methods and digital data from the artistic domain, on which current techniques under-perform. A possible solution is to reduce the domain shift at the pixel level, thus translating artistic images to realistic copies. In this paper, we present a model capable of translating paintings to photo-realistic images, trained without paired examples. The idea is to enforce a patch level similarity between real and generated images, aiming to reproduce photo-realistic details from a memory bank of real images. This is subsequently adopted in the context of an unpaired image-to-image translation framework, mapping each image from one distribution to a new one belonging to the other distribution. Qualitative and quantitative results are presented on Monet, Cezanne and Van Gogh paintings translation tasks, showing that our approach increases the realism of generated images with respect to the CycleGAN approach.

While several approaches to bring vision and language together are emerging, none of them has yet addressed the digital humanities domain, which, nevertheless, is a rich source of visual and textual data. To foster research in this direction, we investigate the learning of visual-semantic embeddings for historical document illustrations, devising both supervised and semi-supervised approaches. We exploit the joint visual-semantic embeddings to automatically align illustrations and textual elements, thus providing an automatic annotation of the visual content of a manuscript. Experiments are performed on the Borso d'Este Holy Bible, one of the most sophisticated illuminated manuscript from the Renaissance, which we manually annotate aligning every illustration with textual commentaries written by experts. Experimental results quantify the domain shift between ordinary visual-semantic datasets and the proposed one, validate the proposed strategies, and devise future works on the same line.

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 both 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 discuss the effectiveness of convolutional neural networks (CNNs) models in saliency prediction. We present a set of Deep Learning architectures developed by us, which can combine both bottom-up cues and higher-level semantics, and extract spatio-temporal features by means of 3D convolutions to model task-driven attentive behaviors. We will show how these deep networks closely recall the early saliency models, although improved with the semantics learned from the human ground-truth. Eventually, we will present a use-case in which saliency prediction is used to improve the automatic description of images.

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.

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.

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.

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.