Publications by Lorenzo Baraldi

Cross-modal retrieval has been recently becoming an hot-spot research, thanks to the development of deeply-learnable architectures. Such architectures generally learn a joint multi-modal embedding space in which text and images could be projected and compared. Here we investigate a different approach, and reformulate the problem of cross-modal retrieval as that of learning a translation between the textual and visual domain. In particular, we propose an end-to-end trainable model which can translate text into image features and vice versa, and regularizes this mapping with a cycle-consistency criterion. Preliminary experimental evaluations show promising results with respect to ordinary visual-semantic models.

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.

Video captioning has picked up a considerable measure of attention thanks to the use of Recurrent Neural Networks, since they can be utilized to both encode the input video and to create the corresponding description. In this paper, we present a recurrent video encoding scheme which can find and exploit the layered structure of the video. Differently from the established encoder-decoder approach, in which a video is encoded continuously by a recurrent layer, we propose to employ Quasi-Recurrent Neural Networks, further extending their basic cell with a boundary detector which can recognize discontinuity points between frames or segments and likewise modify the temporal connections of the encoding layer. We assess our approach on a large scale dataset, the Montreal Video Annotation dataset. Experiments demonstrate that our approach can find suitable levels of representation of the input information, while reducing the computational requirements.

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.

In this paper we introduce a new Connected Components Labeling (CCL) algorithm which exploits a novel approach to model decision problems as Directed Acyclic Graphs with a root, which will be called Directed Rooted Acyclic Graphs (DRAGs). This structure supports the use of sets of equivalent actions, as required by CCL, and optimally leverages these equivalences to reduce the number of nodes (decision points). The advantage of this representation is that a DRAG, differently from decision trees usually exploited by the state-of-the-art algorithms, will contain only the minimum number of nodes required to reach the leaf corresponding to a set of condition values. This combines the benefits of using binary decision trees with a reduction of the machine code size. Experiments show a consistent improvement of the execution time when the model is applied to CCL.

This paper considers a learnable approach for comparing and aligning videos. Our architecture builds upon and revisits temporal match kernels within neural networks: we propose a new temporal layer that finds temporal alignments by maximizing the scores between two sequences of vectors, according to a time-sensitive similarity metric parametrized in the Fourier domain. We learn this layer with a temporal proposal strategy, in which we minimize a triplet loss that takes into account both the localization accuracy and the recognition rate. We evaluate our approach on video alignment, copy detection and event retrieval. Our approach outperforms the state on the art on temporal video alignment and video copy detection datasets in comparable setups. It also attains the best reported results for particular event search, while precisely aligning videos.

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.