1 code implementation • ECCV 2020 • My Kieu, Andrew D. Bagdanov, Marco Bertini, Alberto del Bimbo
Despite its broad application and interest, it remains a challenging problem in part due to the vast range of conditions under which it must be robust.
2 code implementations • 5 May 2024 • Lorenzo Agnolucci, Alberto Baldrati, Marco Bertini, Alberto del Bimbo
Given a query consisting of a reference image and a relative caption, Composed Image Retrieval (CIR) aims to retrieve target images visually similar to the reference one while incorporating the changes specified in the relative caption.
1 code implementation • 4 May 2024 • Niccolò Biondi, Federico Pernici, Simone Ricci, Alberto del Bimbo
This is particularly relevant in search and retrieval systems where it is crucial to avoid reprocessing of the gallery images with the updated model.
no code implementations • 18 Feb 2024 • Federico Becattini, Xiaolin Chen, Andrea Puccia, Haokun Wen, Xuemeng Song, Liqiang Nie, Alberto del Bimbo
Recommending fashion items often leverages rich user profiles and makes targeted suggestions based on past history and previous purchases.
no code implementations • 18 Feb 2024 • Federico Becattini, Lorenzo Berlincioni, Luca Cultrera, Alberto del Bimbo
Neuromorphic sensors, also known as event cameras, are a class of imaging devices mimicking the function of biological visual systems.
no code implementations • 29 Jan 2024 • Lorenzo Berlincioni, Luca Cultrera, Federico Becattini, Alberto del Bimbo
Recognizing faces and their underlying emotions is an important aspect of biometrics.
1 code implementation • 7 Nov 2023 • Lorenzo Agnolucci, Leonardo Galteri, Marco Bertini, Alberto del Bimbo
In this paper, we present a system to restore analog videos of historical archives.
Ranked #2 on Analog Video Restoration on TAPE
1 code implementation • 7 Nov 2023 • Lorenzo Agnolucci, Leonardo Galteri, Marco Bertini, Alberto del Bimbo
Given that, in this context, the speaker is typically in front of the camera and remains the same for the entire duration of the transmission, we can maintain a set of reference keyframes of the person from the higher-quality I-frames that are transmitted within the video stream and exploit them to guide the visual quality improvement; a novel aspect of this approach is the update policy that maintains and updates a compact and effective set of reference keyframes.
no code implementations • 31 Oct 2023 • Luca Cultrera, Federico Becattini, Lorenzo Seidenari, Pietro Pala, Alberto del Bimbo
We feed the state of the vehicle along with the representation of the environment as a special token of the transformer and propagate it throughout the network.
no code implementations • 31 Oct 2023 • Andrea Ciamarra, Federico Becattini, Lorenzo Seidenari, Alberto del Bimbo
We train the proposed model to also perform predictions for several timesteps in the future.
no code implementations • 31 Oct 2023 • Andrea Ciamarra, Roberto Caldelli, Federico Becattini, Lorenzo Seidenari, Alberto del Bimbo
In particular, when an image (video) is captured the overall geometry of the scene (e. g. surfaces) and the acquisition process (e. g. illumination) determine a univocal environment that is directly represented by the image pixel values; all these intrinsic relations are possibly changed by the deepfake generation process.
1 code implementation • 20 Oct 2023 • Lorenzo Agnolucci, Leonardo Galteri, Marco Bertini, Alberto del Bimbo
In this work, we propose a self-supervised approach named ARNIQA (leArning distoRtion maNifold for Image Quality Assessment) for modeling the image distortion manifold to obtain quality representations in an intrinsic manner.
Ranked #2 on No-Reference Image Quality Assessment on CSIQ
Blind Image Quality Assessment No-Reference Image Quality Assessment +1
2 code implementations • 20 Oct 2023 • Lorenzo Agnolucci, Leonardo Galteri, Marco Bertini, Alberto del Bimbo
We design a transformer-based Swin-UNet network that exploits both neighboring and reference frames via our Multi-Reference Spatial Feature Fusion (MRSFF) blocks.
Ranked #1 on Analog Video Restoration on TAPE
1 code implementation • 12 Oct 2023 • Giovanni Burbi, Alberto Baldrati, Lorenzo Agnolucci, Marco Bertini, Alberto del Bimbo
Multimodal image-text memes are prevalent on the internet, serving as a unique form of communication that combines visual and textual elements to convey humor, ideas, or emotions.
Ranked #1 on Hateful Meme Classification on HarMeme
no code implementations • 21 Sep 2023 • Alberto Baldrati, Marco Bertini, Tiberio Uricchio, Alberto del Bimbo
Given the recent advances in multimodal image pretraining where visual models trained with semantically dense textual supervision tend to have better generalization capabilities than those trained using categorical attributes or through unsupervised techniques, in this work we investigate how recent CLIP model can be applied in several tasks in artwork domain.
1 code implementation • 7 Sep 2023 • Hondamunige Prasanna Silva, Lorenzo Seidenari, Alberto del Bimbo
This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any modifications to the classifiers themselves.
no code implementations • 24 Aug 2023 • Alessandro Simoni, Francesco Marchetti, Guido Borghi, Federico Becattini, Lorenzo Seidenari, Roberto Vezzani, Alberto del Bimbo
Technologies to enable safe and effective collaboration and coexistence between humans and robots have gained significant importance in the last few years.
1 code implementation • 22 Aug 2023 • Alberto Baldrati, Marco Bertini, Tiberio Uricchio, Alberto del Bimbo
Given a query composed of a reference image and a relative caption, the Composed Image Retrieval goal is to retrieve images visually similar to the reference one that integrates the modifications expressed by the caption.
Ranked #6 on Image Retrieval on CIRR
1 code implementation • 14 Aug 2023 • Dario Cioni, Lorenzo Berlincioni, Federico Becattini, Alberto del Bimbo
Cultural heritage applications and advanced machine learning models are creating a fruitful synergy to provide effective and accessible ways of interacting with artworks.
no code implementations • 26 Jul 2023 • Lorenzo Agnolucci, Alberto Baldrati, Francesco Todino, Federico Becattini, Marco Bertini, Alberto del Bimbo
Among these, the CLIP model has shown remarkable capabilities for zero-shot transfer by matching an image and a custom textual prompt in its latent space.
no code implementations • 1 Jun 2023 • Lorenzo Berlincioni, Stefano Berretti, Marco Bertini, Alberto del Bimbo
Time varying sequences of 3D point clouds, or 4D point clouds, are now being acquired at an increasing pace in several applications (e. g., LiDAR in autonomous or assisted driving).
no code implementations • 17 Apr 2023 • Federico Becattini, Federico Maria Teotini, Alberto del Bimbo
We attempt to bridge the gap between outfit recommendation and generation by leveraging a graph-based representation of items in a collection.
1 code implementation • 13 Apr 2023 • Lorenzo Berlincioni, Luca Cultrera, Chiara Albisani, Lisa Cresti, Andrea Leonardo, Sara Picchioni, Federico Becattini, Alberto del Bimbo
Recently, event cameras have shown large applicability in several computer vision fields especially concerning tasks that require high temporal resolution.
2 code implementations • 2 Apr 2023 • Roberto Amoroso, Davide Morelli, Marcella Cornia, Lorenzo Baraldi, Alberto del Bimbo, Rita Cucchiara
Recent advancements in diffusion models have enabled the generation of realistic deepfakes from textual prompts in natural language.
2 code implementations • ICCV 2023 • Alberto Baldrati, Lorenzo Agnolucci, Marco Bertini, Alberto del Bimbo
Composed Image Retrieval (CIR) aims to retrieve a target image based on a query composed of a reference image and a relative caption that describes the difference between the two images.
1 code implementation • 15 Jan 2023 • Federico Pernici, Matteo Bruni, Claudio Baecchi, Alberto del Bimbo
Convolutional Neural Networks (CNNs) trained with the Softmax loss are widely used classification models for several vision tasks.
1 code implementation • 16 Nov 2022 • Niccolo Biondi, Federico Pernici, Matteo Bruni, Daniele Mugnai, Alberto del Bimbo
We identify stationarity as the property that the feature representation is required to hold to achieve compatibility and propose a novel training procedure that encourages local and global stationarity on the learned representation.
no code implementations • 15 Nov 2022 • Andrea Ciamarra, Federico Becattini, Lorenzo Seidenari, Alberto del Bimbo
For an autonomous vehicle it is essential to observe the ongoing dynamics of a scene and consequently predict imminent future scenarios to ensure safety to itself and others.
1 code implementation • ICIAP 2022 • Simone Ricci, Tiberio Uricchio, Alberto del Bimbo
In this paper, we introduced the novel concept of advisor network to address the problem of noisy labels in image classification.
Ranked #6 on Image Classification on Clothing1M (using extra training data)
no code implementations • 5 Sep 2022 • Benjamin Szczapa, Mohamed Daoudi, Stefano Berretti, Pietro Pala, Alberto del Bimbo, Zakia Hammal
We compared our method to the state-of-the-art on both datasets using different testing protocols, showing the competitiveness of the proposed approach.
1 code implementation • 1 Aug 2022 • Federico Becattini, Lavinia De Divitiis, Claudio Baecchi, Alberto del Bimbo
Overall, we integrate in a state of the art garment recommendation framework a style classifier and an event classifier in order to condition recommendation on a given query.
no code implementations • 29 Jul 2022 • Naima Otberdout, Claudio Ferrari, Mohamed Daoudi, Stefano Berretti, Alberto del Bimbo
We thus propose a new model that generates transitions between different expressions, and synthesizes long and composed 4D expressions.
no code implementations • 25 Jul 2022 • Pietro Bongini, Federico Becattini, Alberto del Bimbo
The use of Deep Learning and Computer Vision in the Cultural Heritage domain is becoming highly relevant in the last few years with lots of applications about audio smart guides, interactive museums and augmented reality.
1 code implementation • 23 Jun 2022 • Claudio Ferrari, Matteo Serpentoni, Stefano Berretti, Alberto del Bimbo
Deep learning advanced face recognition to an unprecedented accuracy.
2 code implementations • CVPRW 2022 • Alberto Baldrati, Marco Bertini, Tiberio Uricchio, Alberto del Bimbo
The proposed method is based on an initial training stage where a simple combination of visual and textual features is used, to fine-tune the CLIP text encoder.
Ranked #3 on Image Retrieval on LaSCo
Composed Image Retrieval (CoIR) Content-Based Image Retrieval +2
no code implementations • 7 Jun 2022 • Alessandra Alfani, Federico Becattini, Lorenzo Seidenari, Alberto del Bimbo
Several unsupervised and self-supervised approaches have been developed in recent years to learn visual features from large-scale unlabeled datasets.
1 code implementation • 11 May 2022 • Tommaso Barletti, Niccolo' Biondi, Federico Pernici, Matteo Bruni, Alberto del Bimbo
In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks.
no code implementations • 23 Mar 2022 • Francesco Marchetti, Federico Becattini, Lorenzo Seidenari, Alberto del Bimbo
Effective modeling of human interactions is of utmost importance when forecasting behaviors such as future trajectories.
Ranked #5 on Trajectory Prediction on Stanford Drone
1 code implementation • 25 Feb 2022 • Yangyang Guo, Liqiang Nie, Harry Cheng, Zhiyong Cheng, Mohan Kankanhalli, Alberto del Bimbo
From the results on four datasets regarding the above three tasks, our method yields remarkable performance improvements compared with the baselines, demonstrating its superiority on reducing the modality bias problem.
2 code implementations • CVPR 2022 • Alberto Baldrati, Marco Bertini, Tiberio Uricchio, Alberto del Bimbo
the visual content of the query image.
Ranked #9 on Image Retrieval on CIRR
1 code implementation • 15 Nov 2021 • Niccolo Biondi, Federico Pernici, Matteo Bruni, Alberto del Bimbo
Compatible features enable the direct comparison of old and new learned features allowing to use them interchangeably over time.
no code implementations • 12 Oct 2021 • Daniele Mugnai, Federico Pernici, Francesco Turchini, Alberto del Bimbo
Our approach leverages unlabeled data with an adversarial optimization strategy in which the internal features representation is obtained with a second-order pooling model.
no code implementations • 25 Jun 2021 • Francesco Bongini, Lorenzo Berlincioni, Marco Bertini, Alberto del Bimbo
In this paper we propose a novel data augmentation approach for visual content domains that have scarce training datasets, compositing synthetic 3D objects within real scenes.
no code implementations • CVPR 2022 • Naima Otberdout, Claudio Ferrari, Mohamed Daoudi, Stefano Berretti, Alberto del Bimbo
This allows us to learn how the motion of a sparse set of landmarks influences the deformation of the overall face surface, independently from the identity.
1 code implementation • 14 May 2021 • Fabio Zappardino, Tiberio Uricchio, Lorenzo Seidenari, Alberto del Bimbo
To understand human behavior we must not just recognize individual actions but model possibly complex group activity and interactions.
Ranked #8 on Group Activity Recognition on Volleyball
1 code implementation • 5 May 2021 • Yangyang Guo, Liqiang Nie, Zhiyong Cheng, Feng Ji, Ji Zhang, Alberto del Bimbo
Experimental results demonstrate that our adapted margin cosine loss can greatly enhance the baseline models with an absolute performance gain of 15\% on average, strongly verifying the potential of tackling the language prior problem in VQA from the angle of the answer feature space learning.
1 code implementation • IEEE Transactions on Neural Networks and Learning Systems 2021 • Federico Pernici, Matteo Bruni, Claudio Baecchi, Alberto del Bimbo
Typically, a learnable transformation (i. e. the classifier) is placed at the end of such models returning a value for each class used for classification.
no code implementations • 3 Feb 2021 • My Kieu, Lorenzo Berlincioni, Leonardo Galteri, Marco Bertini, Andrew D. Bagdanov, Alberto del Bimbo
Experimental results demonstrate the effectiveness of our approach: using less than 50\% of available real thermal training data, and relying on synthesized data generated by our model in the domain adaptation phase, our detector achieves state-of-the-art results on the KAIST Multispectral Pedestrian Detection Benchmark; even if more real thermal data is available adding GAN generated images to the training data results in improved performance, thus showing that these images act as an effective form of data augmentation.
no code implementations • 11 Dec 2020 • Lavinia De Divitiis, Federico Becattini, Claudio Baecchi, Alberto del Bimbo
In particular, we aim at retrieving a variety of modalities in which a certain garment can be combined.
1 code implementation • 18 Oct 2020 • Simone Undri Innocenti, Federico Becattini, Federico Pernici, Alberto del Bimbo
In this paper we present an event aggregation strategy to convert the output of an event camera into frames processable by traditional Computer Vision algorithms.
Ranked #4 on Gesture Recognition on DVS128 Gesture (using extra training data)
no code implementations • 18 Oct 2020 • Lorenzo Berlincioni, Federico Becattini, Lorenzo Seidenari, Alberto del Bimbo
Trajectory prediction is an important task, especially in autonomous driving.
1 code implementation • 16 Oct 2020 • Federico Pernici, Matteo Bruni, Claudio Baecchi, Francesco Turchini, Alberto del Bimbo
Contrarily to the standard expanding classifier, this allows: (a) the output nodes of future unseen classes to firstly see negative samples since the beginning of learning together with the positive samples that incrementally arrive; (b) to learn features that do not change their geometric configuration as novel classes are incorporated in the learning model.
no code implementations • 27 Aug 2020 • Claudio Ferrari, Lorenzo Berlincioni, Marco Bertini, Alberto del Bimbo
As additional contribution, we enrich the original dataset by using the annotated landmarks to deform and project the 3DMM onto the images.
no code implementations • 24 Jun 2020 • Benjamin Szczapa, Mohamed Daoudi, Stefano Berretti, Pietro Pala, Alberto del Bimbo, Zakia Hammal
For each video, pain intensity was measured using the dynamics of facial movement using 66 facial points.
no code implementations • 24 Jun 2020 • Ettore Maria Celozzi, Luca Ciabini, Luca Cultrera, Pietro Pala, Stefano Berretti, Mohamed Daoudi, Alberto del Bimbo
In this paper, a model is presented to extract statistical summaries to characterize the repetition of a cyclic body action, for instance a gym exercise, for the purpose of checking the compliance of the observed action to a template one and highlighting the parts of the action that are not correctly executed (if any).
1 code implementation • 6 Jun 2020 • Claudio Ferrari, Stefano Berretti, Pietro Pala, Alberto del Bimbo
The 3D Morphable Model (3DMM) is a powerful statistical tool for representing 3D face shapes.
1 code implementation • CVPR 2020 • Francesco Marchetti, Federico Becattini, Lorenzo Seidenari, Alberto del Bimbo
Autonomous vehicles are expected to drive in complex scenarios with several independent non cooperating agents.
no code implementations • 5 Jun 2020 • Luca Cultrera, Lorenzo Seidenari, Federico Becattini, Pietro Pala, Alberto del Bimbo
Current deep learning based autonomous driving approaches yield impressive results also leading to in-production deployment in certain controlled scenarios.
no code implementations • 21 Apr 2020 • Federico Vaccaro, Marco Bertini, Tiberio Uricchio, Alberto del Bimbo
In this paper, we address the problem of image retrieval by learning images representation based on the activations of a Convolutional Neural Network.
no code implementations • 22 Mar 2020 • Pietro Bongini, Federico Becattini, Andrew D. Bagdanov, Alberto del Bimbo
This will turn the classic audio guide into a smart personal instructor with which the visitor can interact by asking for explanations focused on specific interests.
no code implementations • 9 Oct 2019 • Marco Menardi, Alex Falcon, Saida S. Mohamed, Lorenzo Seidenari, Giuseppe Serra, Alberto del Bimbo, Carlo Tasso
To address this issue, in this paper we propose an approach capable of generating images starting from a given text using conditional GANs trained on uncaptioned images dataset.
no code implementations • 1 Aug 2019 • Benjamin Szczapa, Mohamed Daoudi, Stefano Berretti, Alberto Del Bimbo, Pietro Pala, Estelle Massart
In this paper, we tackle the problem of action recognition using body skeletons extracted from video sequences.
no code implementations • 27 Feb 2019 • Federico Pernici, Matteo Bruni, Claudio Baecchi, Alberto del Bimbo
Typically, a learnable transformation (i. e. the classifier) is placed at the end of such models returning a value for each class used for classification.
no code implementations • 11 Feb 2019 • Claudio Ferrari, Stefano Berretti, Alberto del Bimbo
In this report, we provide additional and corrected results for the paper "Extended YouTube Faces: a Dataset for Heterogeneous Open-Set Face Identification".
no code implementations • 29 May 2018 • Lorenzo Berlincioni, Federico Becattini, Leonardo Galteri, Lorenzo Seidenari, Alberto del Bimbo
Autonomous driving is becoming a reality, yet vehicles still need to rely on complex sensor fusion to understand the scene they act in.
no code implementations • CVPR 2018 • Federico Pernici, Federico Bartoli, Matteo Bruni, Alberto del Bimbo
It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams.
no code implementations • 11 Aug 2017 • Federico Pernici, Alberto del Bimbo
We present a novel unsupervised method for face identity learning from video sequences.
no code implementations • ICCV 2017 • Giuseppe Lisanti, Niki Martinel, Alberto del Bimbo, Gian Luca Foresti
First, a dictionary of sparse atoms is learned using patches extracted from single person images.
no code implementations • 22 Jul 2017 • Mohamed Daoudi, Stefano Berretti, Pietro Pala, Yvonne Delevoye, Alberto del Bimbo
Emotion recognition is attracting great interest for its potential application in a multitude of real-life situations.
no code implementations • 6 May 2017 • Federico Bartoli, Giuseppe Lisanti, Lamberto Ballan, Alberto del Bimbo
To this end, we propose a "context-aware" recurrent neural network LSTM model, which can learn and predict human motion in crowded spaces such as a sidewalk, a museum or a shopping mall.
1 code implementation • 4 May 2017 • Federico Becattini, Tiberio Uricchio, Lorenzo Seidenari, Lamberto Ballan, Alberto del Bimbo
In this paper we deal with the problem of predicting action progress in videos.
no code implementations • ICCV 2017 • Leonardo Galteri, Lorenzo Seidenari, Marco Bertini, Alberto del Bimbo
Moreover we show that our approach can be used as a pre-processing step for object detection in case images are degraded by compression to a point that state-of-the art detectors fail.
no code implementations • 1 Sep 2016 • Giovanni Cuffaro, Federico Becattini, Claudio Baecchi, Lorenzo Seidenari, Alberto del Bimbo
In this paper we present a simple yet effective approach to extend without supervision any object proposal from static images to videos.
no code implementations • 16 May 2016 • Tiberio Uricchio, Lamberto Ballan, Lorenzo Seidenari, Alberto del Bimbo
Automatic image annotation is among the fundamental problems in computer vision and pattern recognition, and it is becoming increasingly important in order to develop algorithms that are able to search and browse large-scale image collections.
no code implementations • 10 May 2016 • Simone Ercoli, Marco Bertini, Alberto del Bimbo
In this paper we present an efficient method for visual descriptors retrieval based on compact hash codes computed using a multiple k-means assignment.
no code implementations • 28 Jul 2015 • Giuseppe Lisanti, Svebor Karaman, Daniele Pezzatini, Alberto del Bimbo
In this paper we present a machine vision system to efficiently monitor, analyze and present visual data acquired with a railway overhead gantry equipped with multiple cameras.
no code implementations • CVPR 2015 • Naoufel Werghi, Claudio Tortorici, Stefano Berretti, Alberto del Bimbo
In this paper, we present and experiment a novel approach for representing texture of 3D mesh manifolds using local binary patterns (LBP).
1 code implementation • 28 Mar 2015 • Xirong Li, Tiberio Uricchio, Lamberto Ballan, Marco Bertini, Cees G. M. Snoek, Alberto del Bimbo
Where previous reviews on content-based image retrieval emphasize on what can be seen in an image to bridge the semantic gap, this survey considers what people tag about an image.
no code implementations • 2 Jul 2014 • Lamberto Ballan, Marco Bertini, Giuseppe Serra, Alberto del Bimbo
Our approach exploits collective knowledge embedded in user-generated tags and web sources, and visual similarity of keyframes and images uploaded to social sites like YouTube and Flickr, as well as web sources like Google and Bing.
no code implementations • 26 Jan 2014 • Giuseppe Lisanti, Iacopo Masi, Federico Pernici, Alberto del Bimbo
Pan-tilt-zoom (PTZ) cameras are powerful to support object identification and recognition in far-field scenes.