Nuova ricerca

MARCELLA CORNIA

Ricercatore t.d. art. 24 c. 3 lett. B
Dipartimento Educazione e Scienze Umane


Home | Curriculum(pdf) | Didattica |


Pubblicazioni

2024 - Generating More Pertinent Captions by Leveraging Semantics and Style on Multi-Source Datasets [Articolo su rivista]
Cornia, Marcella; Baraldi, Lorenzo; Fiameni, Giuseppe; Cucchiara, Rita
abstract


2023 - Embodied Agents for Efficient Exploration and Smart Scene Description [Relazione in Atti di Convegno]
Bigazzi, Roberto; Cornia, Marcella; Cascianelli, Silvia; Baraldi, Lorenzo; Cucchiara, Rita
abstract


2023 - Fashion-Oriented Image Captioning with External Knowledge Retrieval and Fully Attentive Gates [Articolo su rivista]
Moratelli, Nicholas; Barraco, Manuele; Morelli, Davide; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

Research related to fashion and e-commerce domains is gaining attention in computer vision and multimedia communities. Following this trend, this article tackles the task of generating fine-grained and accurate natural language descriptions of fashion items, a recently-proposed and under-explored challenge that is still far from being solved. To overcome the limitations of previous approaches, a transformer-based captioning model was designed with the integration of external textual memory that could be accessed through k-nearest neighbor (kNN) searches. From an architectural point of view, the proposed transformer model can read and retrieve items from the external memory through cross-attention operations, and tune the flow of information coming from the external memory thanks to a novel fully attentive gate. Experimental analyses were carried out on the fashion captioning dataset (FACAD) for fashion image captioning, which contains more than 130k fine-grained descriptions, validating the effectiveness of the proposed approach and the proposed architectural strategies in comparison with carefully designed baselines and state-of-the-art approaches. The presented method constantly outperforms all compared approaches, demonstrating its effectiveness for fashion image captioning.


2023 - Fully-Attentive Iterative Networks for Region-based Controllable Image and Video Captioning [Articolo su rivista]
Cornia, Marcella; Baraldi, Lorenzo; Ayellet, Tal; Cucchiara, Rita
abstract


2023 - LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On [Relazione in Atti di Convegno]
Morelli, Davide; Baldrati, Alberto; Cartella, Giuseppe; Cornia, Marcella; Bertini, Marco; Cucchiara, Rita
abstract

The rapidly evolving fields of e-commerce and metaverse continue to seek innovative approaches to enhance the consumer experience. At the same time, recent advancements in the development of diffusion models have enabled generative networks to create remarkably realistic images. In this context, image-based virtual try-on, which consists in generating a novel image of a target model wearing a given in-shop garment, has yet to capitalize on the potential of these powerful generative solutions. This work introduces LaDI-VTON, the first Latent Diffusion textual Inversion-enhanced model for the Virtual Try-ON task. The proposed architecture relies on a latent diffusion model extended with a novel additional autoencoder module that exploits learnable skip connections to enhance the generation process preserving the model's characteristics. To effectively maintain the texture and details of the in-shop garment, we propose a textual inversion component that can map the visual features of the garment to the CLIP token embedding space and thus generate a set of pseudo-word token embeddings capable of conditioning the generation process. Experimental results on Dress Code and VITON-HD datasets demonstrate that our approach outperforms the competitors by a consistent margin, achieving a significant milestone for the task.


2023 - Multimodal Garment Designer: Human-Centric Latent Diffusion Models for Fashion Image Editing [Relazione in Atti di Convegno]
Baldrati, Alberto; Morelli, Davide; Cartella, Giuseppe; Cornia, Marcella; Bertini, Marco; Cucchiara, Rita
abstract


2023 - OpenFashionCLIP: Vision-and-Language Contrastive Learning with Open-Source Fashion Data [Relazione in Atti di Convegno]
Cartella, Giuseppe; Baldrati, Alberto; Morelli, Davide; Cornia, Marcella; Bertini, Marco; Cucchiara, Rita
abstract

The inexorable growth of online shopping and e-commerce demands scalable and robust machine learning-based solutions to accommodate customer requirements. In the context of automatic tagging classification and multimodal retrieval, prior works either defined a low generalizable supervised learning approach or more reusable CLIP-based techniques while, however, training on closed source data. In this work, we propose OpenFashionCLIP, a vision-and-language contrastive learning method that only adopts open-source fashion data stemming from diverse domains, and characterized by varying degrees of specificity. Our approach is extensively validated across several tasks and benchmarks, and experimental results highlight a significant out-of-domain generalization capability and consistent improvements over state-of-the-art methods both in terms of accuracy and recall. Source code and trained models are publicly available at: https://github.com/aimagelab/open-fashion-clip.


2023 - Positive-Augmented Constrastive Learning for Image and Video Captioning Evaluation [Relazione in Atti di Convegno]
Sarto, Sara; Barraco, Manuele; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

The CLIP model has been recently proven to be very effective for a variety of cross-modal tasks, including the evaluation of captions generated from vision-and-language models. In this paper, we propose a new recipe for a contrastive-based evaluation metric for image captioning, namely Positive-Augmented Contrastive learning Score (PAC-S), that in a novel way unifies the learning of a contrastive visual-semantic space with the addition of generated images and text on curated data. Experiments spanning several datasets demonstrate that our new metric achieves the highest correlation with human judgments on both images and videos, outperforming existing reference-based metrics like CIDEr and SPICE and reference-free metrics like CLIP-Score. Finally, we test the system-level correlation of the proposed metric when considering popular image captioning approaches, and assess the impact of employing different cross-modal features. We publicly release our source code and trained models.


2023 - SynthCap: Augmenting Transformers with Synthetic Data for Image Captioning [Relazione in Atti di Convegno]
Caffagni, Davide; Barraco, Manuele; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

Image captioning is a challenging task that combines Computer Vision and Natural Language Processing to generate descriptive and accurate textual descriptions for input images. Research efforts in this field mainly focus on developing novel architectural components to extend image captioning models and using large-scale image-text datasets crawled from the web to boost final performance. In this work, we explore an alternative to web-crawled data and augment the training dataset with synthetic images generated by a latent diffusion model. In particular, we propose a simple yet effective synthetic data augmentation framework that is capable of significantly improving the quality of captions generated by a standard Transformer-based model, leading to competitive results on the COCO dataset.


2023 - Towards Explainable Navigation and Recounting [Relazione in Atti di Convegno]
Poppi, Samuele; Rawal, Niyati; Bigazzi, Roberto; Cornia, Marcella; Cascianelli, Silvia; Baraldi, Lorenzo; Cucchiara, Rita
abstract

Explainability and interpretability of deep neural networks have become of crucial importance over the years in Computer Vision, concurrently with the need to understand increasingly complex models. This necessity has fostered research on approaches that facilitate human comprehension of neural methods. In this work, we propose an explainable setting for visual navigation, in which an autonomous agent needs to explore an unseen indoor environment while portraying and explaining interesting scenes with natural language descriptions. We combine recent advances in ongoing research fields, employing an explainability method on images generated through agent-environment interaction. Our approach uses explainable maps to visualize model predictions and highlight the correlation between the observed entities and the generated words, to focus on prominent objects encountered during the environment exploration. The experimental section demonstrates that our approach can identify the regions of the images that the agent concentrates on to describe its point of view, improving explainability.


2023 - Unveiling the Impact of Image Transformations on Deepfake Detection: An Experimental Analysis [Relazione in Atti di Convegno]
Cocchi, Federico; Baraldi, Lorenzo; Poppi, Samuele; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

With the recent explosion of interest in visual Generative AI, the field of deepfake detection has gained a lot of attention. In fact, deepfake detection might be the only measure to counter the potential proliferation of generated media in support of fake news and its consequences. While many of the available works limit the detection to a pure and direct classification of fake versus real, this does not translate well to a real-world scenario. Indeed, malevolent users can easily apply post-processing techniques to generated content, changing the underlying distribution of fake data. In this work, we provide an in-depth analysis of the robustness of a deepfake detection pipeline, considering different image augmentations, transformations, and other pre-processing steps. These transformations are only applied in the evaluation phase, thus simulating a practical situation in which the detector is not trained on all the possible augmentations that can be used by the attacker. In particular, we analyze the performance of a k-NN and a linear probe detector on the COCOFake dataset, using image features extracted from pre-trained models, like CLIP and DINO. Our results demonstrate that while the CLIP visual backbone outperforms DINO in deepfake detection with no augmentation, its performance varies significantly in presence of any transformation, favoring the robustness of DINO.


2023 - Video Surveillance and Privacy: A Solvable Paradox? [Articolo su rivista]
Cucchiara, Rita; Baraldi, Lorenzo; Cornia, Marcella; Sarto, Sara
abstract


2023 - With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning [Relazione in Atti di Convegno]
Barraco, Manuele; Sarto, Sara; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract


2022 - ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval [Relazione in Atti di Convegno]
Messina, Nicola; Stefanini, Matteo; Cornia, Marcella; Baraldi, Lorenzo; Falchi, Fabrizio; Amato, Giuseppe; Cucchiara, Rita
abstract


2022 - Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions [Articolo su rivista]
Cascianelli, Silvia; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

Handwritten Text Recognition (HTR) in free-layout pages is a challenging image understanding task that can provide a relevant boost to the digitization of handwritten documents and reuse of their content. The task becomes even more challenging when dealing with historical documents due to the variability of the writing style and degradation of the page quality. State-of-the-art HTR approaches typically couple recurrent structures for sequence modeling with Convolutional Neural Networks for visual feature extraction. Since convolutional kernels are defined on fixed grids and focus on all input pixels independently while moving over the input image, this strategy disregards the fact that handwritten characters can vary in shape, scale, and orientation even within the same document and that the ink pixels are more relevant than the background ones. To cope with these specific HTR difficulties, we propose to adopt deformable convolutions, which can deform depending on the input at hand and better adapt to the geometric variations of the text. We design two deformable architectures and conduct extensive experiments on both modern and historical datasets. Experimental results confirm the suitability of deformable convolutions for the HTR task.


2022 - CaMEL: Mean Teacher Learning for Image Captioning [Relazione in Atti di Convegno]
Barraco, Manuele; Stefanini, Matteo; Cornia, Marcella; Cascianelli, Silvia; Baraldi, Lorenzo; Cucchiara, Rita
abstract


2022 - Dress Code: High-Resolution Multi-Category Virtual Try-On [Relazione in Atti di Convegno]
Morelli, Davide; Fincato, Matteo; Cornia, Marcella; Landi, Federico; Cesari, Fabio; Cucchiara, Rita
abstract

Image-based virtual try-on strives to transfer the appearance of a clothing item onto the image of a target person. Existing literature focuses mainly on upper-body clothes (e.g. t-shirts, shirts, and tops) and neglects full-body or lower-body items. This shortcoming arises from a main factor: current publicly available datasets for image-based virtual try-on do not account for this variety, thus limiting progress in the field. In this research activity, we introduce Dress Code, a novel dataset which contains images of multi-category clothes. Dress Code is more than 3x larger than publicly available datasets for image-based virtual try-on and features high-resolution paired images (1024 x 768) with front-view, full-body reference models. To generate HD try-on images with high visual quality and rich in details, we propose to learn fine-grained discriminating features. Specifically, we leverage a semantic-aware discriminator that makes predictions at pixel-level instead of image- or patch-level. The Dress Code dataset is publicly available at https://github.com/aimagelab/dress-code.


2022 - Dress Code: High-Resolution Multi-Category Virtual Try-On [Relazione in Atti di Convegno]
Morelli, Davide; Fincato, Matteo; Cornia, Marcella; Landi, Federico; Cesari, Fabio; Cucchiara, Rita
abstract


2022 - Dual-Branch Collaborative Transformer for Virtual Try-On [Relazione in Atti di Convegno]
Fenocchi, Emanuele; Morelli, Davide; Cornia, Marcella; Baraldi, Lorenzo; Cesari, Fabio; Cucchiara, Rita
abstract

Image-based virtual try-on has recently gained a lot of attention in both the scientific and fashion industry communities due to its challenging setting and practical real-world applications. While pure convolutional approaches have been explored to solve the task, Transformer-based architectures have not received significant attention yet. Following the intuition that self- and cross-attention operators can deal with long-range dependencies and hence improve the generation, in this paper we extend a Transformer-based virtual try-on model by adding a dual-branch collaborative module that can exploit cross-modal information at generation time. We perform experiments on the VITON dataset, which is the standard benchmark for the task, and on a recently collected virtual try-on dataset with multi-category clothing, Dress Code. Experimental results demonstrate the effectiveness of our solution over previous methods and show that Transformer-based architectures can be a viable alternative for virtual try-on.


2022 - Embodied Navigation at the Art Gallery [Relazione in Atti di Convegno]
Bigazzi, Roberto; Landi, Federico; Cascianelli, Silvia; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

Embodied agents, trained to explore and navigate indoor photorealistic environments, have achieved impressive results on standard datasets and benchmarks. So far, experiments and evaluations have involved domestic and working scenes like offices, flats, and houses. In this paper, we build and release a new 3D space with unique characteristics: the one of a complete art museum. We name this environment ArtGallery3D (AG3D). Compared with existing 3D scenes, the collected space is ampler, richer in visual features, and provides very sparse occupancy information. This feature is challenging for occupancy-based agents which are usually trained in crowded domestic environments with plenty of occupancy information. Additionally, we annotate the coordinates of the main points of interest inside the museum, such as paintings, statues, and other items. Thanks to this manual process, we deliver a new benchmark for PointGoal navigation inside this new space. Trajectories in this dataset are far more complex and lengthy than existing ground-truth paths for navigation in Gibson and Matterport3D. We carry on extensive experimental evaluation using our new space for evaluation and prove that existing methods hardly adapt to this scenario. As such, we believe that the availability of this 3D model will foster future research and help improve existing solutions.


2022 - Explaining Transformer-based Image Captioning Models: An Empirical Analysis [Articolo su rivista]
Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract


2022 - Focus on Impact: Indoor Exploration with Intrinsic Motivation [Articolo su rivista]
Bigazzi, Roberto; Landi, Federico; Cascianelli, Silvia; Baraldi, Lorenzo; Cornia, Marcella; Cucchiara, Rita
abstract


2022 - From Show to Tell: A Survey on Deep Learning-based Image Captioning [Articolo su rivista]
Stefanini, Matteo; Cornia, Marcella; Baraldi, Lorenzo; Cascianelli, Silvia; Fiameni, Giuseppe; Cucchiara, Rita
abstract


2022 - Investigating Bidimensional Downsampling in Vision Transformer Models [Relazione in Atti di Convegno]
Bruno, Paolo; Amoroso, Roberto; Cornia, Marcella; Cascianelli, Silvia; Baraldi, Lorenzo; Cucchiara, Rita
abstract

Vision Transformers (ViT) and other Transformer-based architectures for image classification have achieved promising performances in the last two years. However, ViT-based models require large datasets, memory, and computational power to obtain state-of-the-art results compared to more traditional architectures. The generic ViT model, indeed, maintains a full-length patch sequence during inference, which is redundant and lacks hierarchical representation. With the goal of increasing the efficiency of Transformer-based models, we explore the application of a 2D max-pooling operator on the outputs of Transformer encoders. We conduct extensive experiments on the CIFAR-100 dataset and the large ImageNet dataset and consider both accuracy and efficiency metrics, with the final goal of reducing the token sequence length without affecting the classification performance. Experimental results show that bidimensional downsampling can outperform previous classification approaches while requiring relatively limited computation resources.


2022 - Matching Faces and Attributes Between the Artistic and the Real Domain: the PersonArt Approach [Articolo su rivista]
Cornia, Marcella; Tomei, Matteo; Baraldi, Lorenzo; Cucchiara, Rita
abstract


2022 - Retrieval-Augmented Transformer for Image Captioning [Relazione in Atti di Convegno]
Sarto, Sara; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract


2022 - Spot the Difference: A Novel Task for Embodied Agents in Changing Environments [Relazione in Atti di Convegno]
Landi, Federico; Bigazzi, Roberto; Cornia, Marcella; Cascianelli, Silvia; Baraldi, Lorenzo; Cucchiara, Rita
abstract


2022 - The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition [Relazione in Atti di Convegno]
Cascianelli, Silvia; Pippi, Vittorio; Maarand, Martin; Cornia, Marcella; Baraldi, Lorenzo; Kermorvant, Christopher; Cucchiara, Rita
abstract


2022 - The Unreasonable Effectiveness of CLIP features for Image Captioning: an Experimental Analysis [Relazione in Atti di Convegno]
Barraco, Manuele; Cornia, Marcella; Cascianelli, Silvia; Baraldi, Lorenzo; Cucchiara, Rita
abstract


2022 - Transform, Warp, and Dress: A New Transformation-Guided Model for Virtual Try-On [Articolo su rivista]
Fincato, Matteo; Cornia, Marcella; Landi, Federico; Cesari, Fabio; Cucchiara, Rita
abstract

Virtual try-on has recently emerged in computer vision and multimedia communities with the development of architectures that can generate realistic images of a target person wearing a custom garment. This research interest is motivated by the large role played by e-commerce and online shopping in our society. Indeed, the virtual try-on task can offer many opportunities to improve the efficiency of preparing fashion catalogs and to enhance the online user experience. The problem is far to be solved: current architectures do not reach sufficient accuracy with respect to manually generated images and can only be trained on image pairs with a limited variety. Existing virtual try-on datasets have two main limits: they contain only female models, and all the images are available only in low resolution. This not only affects the generalization capabilities of the trained architectures but makes the deployment to real applications impractical. To overcome these issues, we present Dress Code, a new dataset for virtual try-on that contains high-resolution images of a large variety of upper-body clothes and both male and female models. Leveraging this enriched dataset, we propose a new model for virtual try-on capable of generating high-quality and photo-realistic images using a three-stage pipeline. The first two stages perform two different geometric transformations to warp the desired garment and make it fit into the target person's body pose and shape. Then, we generate the new image of that same person wearing the try-on garment using a generative network. We test the proposed solution on the most widely used dataset for this task as well as on our newly collected dataset and demonstrate its effectiveness when compared to current state-of-the-art methods. Through extensive analyses on our Dress Code dataset, we show the adaptability of our model, which can generate try-on images even with a higher resolution.


2021 - FashionSearch++: Improving Consumer-to-Shop Clothes Retrieval with Hard Negatives [Relazione in Atti di Convegno]
Morelli, Davide; Cornia, Marcella; Cucchiara, Rita
abstract

Consumer-to-shop clothes retrieval has recently emerged in computer vision and multimedia communities with the development of architectures that can find similar in-shop clothing images given a query photo. Due to its nature, the main challenge lies in the domain gap between user-acquired and in-shop images. In this paper, we follow the most recent successful research in this area employing convolutional neural networks as feature extractors and propose to enhance the training supervision through a modified triplet loss that takes into account hard negative examples. We test the proposed approach on the Street2Shop dataset, achieving results comparable to state-of-the-art solutions and demonstrating good generalization properties when dealing with different settings and clothing categories.


2021 - Learning to Read L'Infinito: Handwritten Text Recognition with Synthetic Training Data [Relazione in Atti di Convegno]
Cascianelli, Silvia; Cornia, Marcella; Baraldi, Lorenzo; Piazzi, Maria Ludovica; Schiuma, Rosiana; Cucchiara, Rita
abstract

Deep learning-based approaches to Handwritten Text Recognition (HTR) have shown remarkable results on publicly available large datasets, both modern and historical. However, it is often the case that historical manuscripts are preserved in small collections, most of the time with unique characteristics in terms of paper support, author handwriting style, and language. State-of-the-art HTR approaches struggle to obtain good performance on such small manuscript collections, for which few training samples are available. In this paper, we focus on HTR on small historical datasets and propose a new historical dataset, which we call Leopardi, with the typical characteristics of small manuscript collections, consisting of letters by the poet Giacomo Leopardi, and devise strategies to deal with the training data scarcity scenario. In particular, we explore the use of carefully designed but cost-effective synthetic data for pre-training HTR models to be applied to small single-author manuscripts. Extensive experiments validate the suitability of the proposed approach, and both the Leopardi dataset and synthetic data will be available to favor further research in this direction.


2021 - Learning to Select: A Fully Attentive Approach for Novel Object Captioning [Relazione in Atti di Convegno]
Cagrandi, Marco; Cornia, Marcella; Stefanini, Matteo; Baraldi, Lorenzo; Cucchiara, Rita
abstract


2021 - Multimodal Attention Networks for Low-Level Vision-and-Language Navigation [Articolo su rivista]
Landi, Federico; Baraldi, Lorenzo; Cornia, Marcella; Corsini, Massimiliano; Cucchiara, Rita
abstract

Vision-and-Language Navigation (VLN) is a challenging task in which an agent needs to follow a language-specified path to reach a target destination. The goal gets even harder as the actions available to the agent get simpler and move towards low-level, atomic interactions with the environment. This setting takes the name of low-level VLN. In this paper, we strive for the creation of an agent able to tackle three key issues: multi-modality, long-term dependencies, and adaptability towards different locomotive settings. To that end, we devise "Perceive, Transform, and Act" (PTA): a fully-attentive VLN architecture that leaves the recurrent approach behind and the first Transformer-like architecture incorporating three different modalities -- natural language, images, and low-level actions for the agent control. In particular, we adopt an early fusion strategy to merge lingual and visual information efficiently in our encoder. We then propose to refine the decoding phase with a late fusion extension between the agent's history of actions and the perceptual modalities. We experimentally validate our model on two datasets: PTA achieves promising results in low-level VLN on R2R and achieves good performance in the recently proposed R4R benchmark. Our code is publicly available at https://github.com/aimagelab/perceive-transform-and-act.


2021 - Out of the Box: Embodied Navigation in the Real World [Relazione in Atti di Convegno]
Bigazzi, Roberto; Landi, Federico; Cornia, Marcella; Cascianelli, Silvia; Baraldi, Lorenzo; Cucchiara, Rita
abstract

The research field of Embodied AI has witnessed substantial progress in visual navigation and exploration thanks to powerful simulating platforms and the availability of 3D data of indoor and photorealistic environments. These two factors have opened the doors to a new generation of intelligent agents capable of achieving nearly perfect PointGoal Navigation. However, such architectures are commonly trained with millions, if not billions, of frames and tested in simulation. Together with great enthusiasm, these results yield a question: how many researchers will effectively benefit from these advances? In this work, we detail how to transfer the knowledge acquired in simulation into the real world. To that end, we describe the architectural discrepancies that damage the Sim2Real adaptation ability of models trained on the Habitat simulator and propose a novel solution tailored towards the deployment in real-world scenarios. We then deploy our models on a LoCoBot, a Low-Cost Robot equipped with a single Intel RealSense camera. Different from previous work, our testing scene is unavailable to the agent in simulation. The environment is also inaccessible to the agent beforehand, so it cannot count on scene-specific semantic priors. In this way, we reproduce a setting in which a research group (potentially from other fields) needs to employ the agent visual navigation capabilities as-a-Service. Our experiments indicate that it is possible to achieve satisfying results when deploying the obtained model in the real world.


2021 - Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis [Relazione in Atti di Convegno]
Poppi, Samuele; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract


2021 - Working Memory Connections for LSTM [Articolo su rivista]
Landi, Federico; Baraldi, Lorenzo; Cornia, Marcella; Cucchiara, Rita
abstract


2020 - A Novel Attention-based Aggregation Function to Combine Vision and Language [Relazione in Atti di Convegno]
Stefanini, Matteo; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

The joint understanding of vision and language has been recently gaining a lot of attention in both the Computer Vision and Natural Language Processing communities, with the emergence of tasks such as image captioning, image-text matching, and visual question answering. As both images and text can be encoded as sets or sequences of elements - like regions and words - proper reduction functions are needed to transform a set of encoded elements into a single response, like a classification or similarity score. In this paper, we propose a novel fully-attentive reduction method for vision and language. Specifically, our approach computes a set of scores for each element of each modality employing a novel variant of cross-attention, and performs a learnable and cross-modal reduction, which can be used for both classification and ranking. We test our approach on image-text matching and visual question answering, building fair comparisons with other reduction choices, on both COCO and VQA 2.0 datasets. Experimentally, we demonstrate that our approach leads to a performance increase on both tasks. Further, we conduct ablation studies to validate the role of each component of the approach.


2020 - A Unified Cycle-Consistent Neural Model for Text and Image Retrieval [Articolo su rivista]
Cornia, Marcella; Baraldi, Lorenzo; Tavakoli, Hamed R.; Cucchiara, Rita
abstract


2020 - Explaining Digital Humanities by Aligning Images and Textual Descriptions [Articolo su rivista]
Cornia, Marcella; Stefanini, Matteo; Baraldi, Lorenzo; Corsini, Massimiliano; Cucchiara, Rita
abstract

Replicating the human ability to connect Vision and Language has recently been gaining a lot of attention in the Computer Vision and the Natural Language Processing communities. This research effort has resulted in algorithms that can retrieve images from textual descriptions and vice versa, when realistic images and sentences with simple semantics are employed and when paired training data is provided. In this paper, we go beyond these limitations and tackle the design of visual-semantic algorithms in the domain of the Digital Humanities. This setting not only advertises more complex visual and semantic structures but also features a significant lack of training data which makes the use of fully-supervised approaches infeasible. With this aim, we propose a joint visual-semantic embedding that can automatically align illustrations and textual elements without paired supervision. This is achieved by transferring the knowledge learned on ordinary visual-semantic datasets to the artistic domain. Experiments, performed on two datasets specifically designed for this domain, validate the proposed strategies and quantify the domain shift between natural images and artworks.


2020 - Explore and Explain: Self-supervised Navigation and Recounting [Relazione in Atti di Convegno]
Bigazzi, Roberto; Landi, Federico; Cornia, Marcella; Cascianelli, Silvia; Baraldi, Lorenzo; Cucchiara, Rita
abstract

Embodied AI has been recently gaining attention as it aims to foster the development of autonomous and intelligent agents. In this paper, we devise a novel embodied setting in which an agent needs to explore a previously unknown environment while recounting what it sees during the path. In this context, the agent needs to navigate the environment driven by an exploration goal, select proper moments for description, and output natural language descriptions of relevant objects and scenes. Our model integrates a novel self-supervised exploration module with penalty, and a fully-attentive captioning model for explanation. Also, we investigate different policies for selecting proper moments for explanation, driven by information coming from both the environment and the navigation. Experiments are conducted on photorealistic environments from the Matterport3D dataset and investigate the navigation and explanation capabilities of the agent as well as the role of their interactions.


2020 - Meshed-Memory Transformer for Image Captioning [Relazione in Atti di Convegno]
Cornia, Marcella; Stefanini, Matteo; Baraldi, Lorenzo; Cucchiara, Rita
abstract

Transformer-based architectures represent the state of the art in sequence modeling tasks like machine translation and language understanding. Their applicability to multi-modal contexts like image captioning, however, is still largely under-explored. With the aim of filling this gap, we present M² - a Meshed Transformer with Memory for Image Captioning. The architecture improves both the image encoding and the language generation steps: it learns a multi-level representation of the relationships between image regions integrating learned a priori knowledge, and uses a mesh-like connectivity at decoding stage to exploit low- and high-level features. Experimentally, we investigate the performance of the M² Transformer and different fully-attentive models in comparison with recurrent ones. When tested on COCO, our proposal achieves a new state of the art in single-model and ensemble configurations on the "Karpathy" test split and on the online test server. We also assess its performances when describing objects unseen in the training set. Trained models and code for reproducing the experiments are publicly available at :https://github.com/aimagelab/meshed-memory-transformer.


2020 - SMArT: Training Shallow Memory-aware Transformers for Robotic Explainability [Relazione in Atti di Convegno]
Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract


2020 - VITON-GT: An Image-based Virtual Try-On Model with Geometric Transformations [Relazione in Atti di Convegno]
Fincato, Matteo; Landi, Federico; Cornia, Marcella; Cesari, Fabio; Cucchiara, Rita
abstract


2019 - Artpedia: A New Visual-Semantic Dataset with Visual and Contextual Sentences in the Artistic Domain [Relazione in Atti di Convegno]
Stefanini, Matteo; Cornia, Marcella; Baraldi, Lorenzo; Corsini, Massimiliano; Cucchiara, Rita
abstract

As vision and language techniques are widely applied to realistic images, there is a growing interest in designing visual-semantic models suitable for more complex and challenging scenarios. In this paper, we address the problem of cross-modal retrieval of images and sentences coming from the artistic domain. To this aim, we collect and manually annotate the Artpedia dataset that contains paintings and textual sentences describing both the visual content of the paintings and other contextual information. Thus, the problem is not only to match images and sentences, but also to identify which sentences actually describe the visual content of a given image. To this end, we devise a visual-semantic model that jointly addresses these two challenges by exploiting the latent alignment between visual and textual chunks. Experimental evaluations, obtained by comparing our model to different baselines, demonstrate the effectiveness of our solution and highlight the challenges of the proposed dataset. The Artpedia dataset is publicly available at: http://aimagelab.ing.unimore.it/artpedia.


2019 - Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-to-Image Translation [Relazione in Atti di Convegno]
Tomei, Matteo; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

The applicability of computer vision to real paintings and artworks has been rarely investigated, even though a vast heritage would greatly benefit from techniques which can understand and process data from the artistic domain. This is partially due to the small amount of annotated artistic data, which is not even comparable to that of natural images captured by cameras. In this paper, we propose a semantic-aware architecture which can translate artworks to photo-realistic visualizations, thus reducing the gap between visual features of artistic and realistic data. Our architecture can generate natural images by retrieving and learning details from real photos through a similarity matching strategy which leverages a weakly-supervised semantic understanding of the scene. Experimental results show that the proposed technique leads to increased realism and to a reduction in domain shift, which improves the performance of pre-trained architectures for classification, detection, and segmentation. Code is publicly available at: https://github.com/aimagelab/art2real.


2019 - Image-to-Image Translation to Unfold the Reality of Artworks: an Empirical Analysis [Relazione in Atti di Convegno]
Tomei, Matteo; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

State-of-the-art Computer Vision pipelines show poor performances on artworks and data coming from the artistic domain, thus limiting the applicability of current architectures to the automatic understanding of the cultural heritage. This is mainly due to the difference in texture and low-level feature distribution between artistic and real images, on which state-of-the-art approaches are usually trained. To enhance the applicability of pre-trained architectures on artistic data, we have recently proposed an unpaired domain translation approach which can translate artworks to photo-realistic visualizations. Our approach leverages semantically-aware memory banks of real patches, which are used to drive the generation of the translated image while improving its realism. In this paper, we provide additional analyses and experimental results which demonstrate the effectiveness of our approach. In particular, we evaluate the quality of generated results in the case of the translation of landscapes, portraits and of paintings coming from four different styles using automatic distance metrics. Also, we analyze the response of pre-trained architecture for classification, detection and segmentation both in terms of feature distribution and entropy of prediction, and show that our approach effectively reduces the domain shift of paintings. As an additional contribution, we also provide a qualitative analysis of the reduction of the domain shift for detection, segmentation and image captioning.


2019 - M-VAD Names: a Dataset for Video Captioning with Naming [Articolo su rivista]
Pini, Stefano; Cornia, Marcella; Bolelli, Federico; Baraldi, Lorenzo; Cucchiara, Rita
abstract

Current movie captioning architectures are not capable of mentioning characters with their proper name, replacing them with a generic "someone" tag. The lack of movie description datasets with characters' visual annotations surely plays a relevant role in this shortage. Recently, we proposed to extend the M-VAD dataset by introducing such information. In this paper, we present an improved version of the dataset, namely M-VAD Names, and its semi-automatic annotation procedure. The resulting dataset contains 63k visual tracks and 34k textual mentions, all associated with character identities. To showcase the features of the dataset and quantify the complexity of the naming task, we investigate multimodal architectures to replace the "someone" tags with proper character names in existing video captions. The evaluation is further extended by testing this application on videos outside of the M-VAD Names dataset.


2019 - Recognizing social relationships from an egocentric vision perspective [Capitolo/Saggio]
Alletto, Stefano; Cornia, Marcella; Baraldi, Lorenzo; Serra, Giuseppe; Cucchiara, Rita
abstract

In this chapter we address the problem of partitioning social gatherings into interacting groups in egocentric scenarios. People in the scene are tracked, their head pose and 3D location are estimated. Following the formalism of the f-formation, we define with the orientation and distance an inherently social pairwise feature capable of describing how two people stand in relation to one another. We present a Structural SVM based approach to learn how to weight each component of the feature vector depending on the social situation is applied to. To better understand the social dynamics, we also estimate what we call social relevance of each subject in a group using a saliency attentive model. Extensive tests on two publicly available datasets show that our solution achieves encouraging results when detecting social groups and their relevant subjects in the challenging egocentric scenarios.


2019 - Show, Control and Tell: A Framework for Generating Controllable and Grounded Captions [Relazione in Atti di Convegno]
Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at hand, a higher degree of controllability is needed to apply captioning algorithms in complex scenarios. In this paper, we introduce a novel framework for image captioning which can generate diverse descriptions by allowing both grounding and controllability. Given a control signal in the form of a sequence or set of image regions, we generate the corresponding caption through a recurrent architecture which predicts textual chunks explicitly grounded on regions, following the constraints of the given control. Experiments are conducted on Flickr30k Entities and on COCO Entities, an extended version of COCO in which we add grounding annotations collected in a semi-automatic manner. Results demonstrate that our method achieves state of the art performances on controllable image captioning, in terms of caption quality and diversity. Code and annotations are publicly available at: https://github.com/aimagelab/show-control-and-tell.


2019 - Towards Cycle-Consistent Models for Text and Image Retrieval [Relazione in Atti di Convegno]
Cornia, Marcella; Baraldi, Lorenzo; Rezazadegan Tavakoli, Hamed; Cucchiara, Rita
abstract

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.


2019 - Visual-Semantic Alignment Across Domains Using a Semi-Supervised Approach [Relazione in Atti di Convegno]
Carraggi, Angelo; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

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.


2019 - What was Monet seeing while painting? Translating artworks to photo-realistic images [Relazione in Atti di Convegno]
Tomei, Matteo; Baraldi, Lorenzo; Cornia, Marcella; Cucchiara, Rita
abstract

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.


2018 - Aligning Text and Document Illustrations: towards Visually Explainable Digital Humanities [Relazione in Atti di Convegno]
Baraldi, Lorenzo; Cornia, Marcella; Grana, Costantino; Cucchiara, Rita
abstract

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.


2018 - Attentive Models in Vision: Computing Saliency Maps in the Deep Learning Era [Articolo su rivista]
Cornia, Marcella; Abati, Davide; Baraldi, Lorenzo; Palazzi, Andrea; Calderara, Simone; Cucchiara, Rita
abstract

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.


2018 - Automatic Image Cropping and Selection using Saliency: an Application to Historical Manuscripts [Relazione in Atti di Convegno]
Cornia, Marcella; Pini, Stefano; Baraldi, Lorenzo; Cucchiara, Rita
abstract

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.


2018 - Paying More Attention to Saliency: Image Captioning with Saliency and Context Attention [Articolo su rivista]
Cornia, Marcella; Baraldi, Lorenzo; Serra, Giuseppe; Cucchiara, Rita
abstract

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.


2018 - Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model [Articolo su rivista]
Cornia, Marcella; Baraldi, Lorenzo; Serra, Giuseppe; Cucchiara, Rita
abstract

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.


2018 - SAM: Pushing the Limits of Saliency Prediction Models [Relazione in Atti di Convegno]
Cornia, Marcella; Baraldi, Lorenzo; Serra, Giuseppe; Cucchiara, Rita
abstract

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.


2017 - Attentive Models in Vision: Computing Saliency Maps in the Deep Learning Era [Relazione in Atti di Convegno]
Cornia, Marcella; Abati, Davide; Baraldi, Lorenzo; Palazzi, Andrea; Calderara, Simone; Cucchiara, Rita
abstract

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.


2017 - Modeling Multimodal Cues in a Deep Learning-based Framework for Emotion Recognition in the Wild [Relazione in Atti di Convegno]
Pini, Stefano; Ben Ahmed, Olfa; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita; Huet, Benoit
abstract

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.


2017 - Towards Video Captioning with Naming: a Novel Dataset and a Multi-Modal Approach [Relazione in Atti di Convegno]
Pini, Stefano; Cornia, Marcella; Baraldi, Lorenzo; Cucchiara, Rita
abstract

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.


2017 - Visual Saliency for Image Captioning in New Multimedia Services [Relazione in Atti di Convegno]
Cornia, Marcella; Baraldi, Lorenzo; Serra, Giuseppe; Cucchiara, Rita
abstract

Image and video captioning are important tasks in visual data analytics, as they concern the capability of describing visual content in natural language. They are the pillars of query answering systems, improve indexing and search and allow a natural form of human-machine interaction. Even though promising deep learning strategies are becoming popular, the heterogeneity of large image archives makes this task still far from being solved. In this paper we explore how visual saliency prediction can support image captioning. Recently, some forms of unsupervised machine attention mechanisms have been spreading, but the role of human attention prediction has never been examined extensively for captioning. We propose a machine attention model driven by saliency prediction to provide captions in images, which can be exploited for many services on cloud and on multimedia data. Experimental evaluations are conducted on the SALICON dataset, which provides groundtruths for both saliency and captioning, and on the large Microsoft COCO dataset, the most widely used for image captioning.


2016 - A Deep Multi-Level Network for Saliency Prediction [Relazione in Atti di Convegno]
Cornia, Marcella; Baraldi, Lorenzo; Serra, Giuseppe; Cucchiara, Rita
abstract

This paper presents a novel deep architecture for saliency prediction. Current state of the art models for saliency prediction employ Fully Convolutional networks that perform a non-linear combination of features extracted from the last convolutional layer to predict saliency maps. We propose an architecture which, instead, combines features extracted at different levels of a Convolutional Neural Network (CNN). Our model is composed of three main blocks: a feature extraction CNN, a feature encoding network, that weights low and high level feature maps, and a prior learning network. We compare our solution with state of the art saliency models on two public benchmarks datasets. Results show that our model outperforms under all evaluation metrics on the SALICON dataset, which is currently the largest public dataset for saliency prediction, and achieves competitive results on the MIT300 benchmark.


2016 - Multi-Level Net: a Visual Saliency Prediction Model [Relazione in Atti di Convegno]
Cornia, Marcella; Baraldi, Lorenzo; Serra, Giuseppe; Cucchiara, Rita
abstract

State of the art approaches for saliency prediction are based on Full Convolutional Networks, in which saliency maps are built using the last layer. In contrast, we here present a novel model that predicts saliency maps exploiting a non-linear combination of features coming from different layers of the network. We also present a new loss function to deal with the imbalance issue on saliency masks. Extensive results on three public datasets demonstrate the robustness of our solution. Our model outperforms the state of the art on SALICON, which is the largest and unconstrained dataset available, and obtains competitive results on MIT300 and CAT2000 benchmarks.