Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works200 from public data
- Benchmark Analysis of Representative Deep Neural Network Architectures831
An in-depth analysis of the majority of the deep neural networks (DNNs) proposed in the state of the art for image recognition, with a complete view of what solutions have been explored so far and in which research directions are worth exploring in the future.
- On the use of deep learning for blind image quality assessment369
The best proposal, named DeepBIQ, estimates the image quality by average-pooling the scores predicted on multiple subregions of the original image, having a linear correlation coefficient with human subjective scores of almost 0.91.
- Color constancy using CNNs232
Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most previous methods to accurately predict the scene illumination.
- 189
- Evaluating the Performance of Structure from Motion Pipelines186
A comparison of different state-of-the-art SfM pipelines in terms of their ability to reconstruct different scenes is reported and an evaluation procedure is proposed that considers both the reconstruction errors as well as the estimation errors of the camera poses used in the reconstruction.
- Single and Multiple Illuminant Estimation Using Convolutional Neural Networks168
An extensive comparison with both local and global illuminant estimation methods in the state of the art, on standard data sets with single and multiple illuminants, proves the effectiveness of this three-stage method.
- 166
- 150
- Deep learning for logo recognition126
The proposed recognition pipeline is composed of a logo region proposal followed by a Convolutional Neural Network specifically trained for logo classification, even if they are not precisely localized.
- How Far Can You Get by Combining Change Detection Algorithms?121
Results demonstrate that starting from simple algorithms the proposed IUTIS combination strategy can achieve comparable results with respect to more complex state-of-the-art change detection algorithms, while keeping the computational complexity affordable for real-time applications.
- Automatic color constancy algorithm selection and combination119
This work investigates how illuminant estimation techniques can be improved taking into account intrinsic, low level properties of the images, and shows how these properties can be used to drive the selection of the best algorithm for a given image.
- 110
- An interactive tool for manual, semi-automatic and automatic video annotation108
Results demonstrate that the use of the semi-automatic, as well as the automatic, modality drastically reduces the human effort while preserving the quality of the annotations.
- An introduction to quantum machine learning: from quantum logic to quantum deep learning98
The most notable scientific literature about quantum machine learning is presented, starting from the basics of quantum logic to some specific elements and algorithms of quantum computing (such as QRAM, Grover and HHL), in order to allow a better understanding of latest quantumMachine learning techniques.
- 98
- Large Age-Gap face verification by feature injection in deep networks90
A new method for face verification across large age gaps and also a dataset containing variations of age in the wild, the Large Age-Gap (LAG) dataset, with images ranging from child/young to adult/old is introduced.
- 83
- 68
- Image Analysis and Processing – ICIAP 200967
This book constitutes the refereed proceedings of the 15th International Conference on Image Analysis and Processing, ICIAP 2009, held in Vietri sul Mare, Italy, in September 2009.
- Automated Pruning for Deep Neural Network Compression60
This is the first study where the generalization capabilities in transfer learning tasks of the features extracted by a pruned network are analyzed, and it is shown that the representations learned using the proposed pruning methodology maintain the same effectiveness and generality of those learned by the corresponding non-compressed network on a set of different recognition tasks.
- 60
- Multitask painting categorization by deep multibranch neural network58
Among the different variants of the proposed network, the best method achieves accuracy levels of 56.5%, 57.2%, and 63.6% on the MultitaskPainting100k dataset for the tasks of artist, style and genre prediction respectively.
- NTIRE 2024 Quality Assessment of AI-Generated Content Challenge54
This challenge is to address a major challenge in the field of image and video processing, namely, Image Quality Assessment (IQA) and Video Quality Assessment (VQA) for AI-Generated Content (AIGC).
- Rehabilitating the ColorChecker Dataset for Illuminant Estimation50
A new 'recommended' set of ground-truth is re-generated based on the calculation methodology described by Shi and Funt and it is found that the difference in how algorithms perform can be large, with many local rankings of algorithms being reversed.
- Consensus-based framework for illuminant chromaticity estimation50
It is confirmed that the best and the worst algorithms do not exist at all among the state-of-the-art ones and show that simple combining strategies improve the illuminant estimation.
- 49
- Logo Recognition Using CNN Features49
This paper proposes a method for logo recognition based on Convolutional Neural Networks, instead of the commonly used keypoint-based approaches, which involves the selection of candidate subwindows using an unsupervised segmentation algorithm and the SVM-based classification of such candidate regions using features computed by a CNN.
- Artistic photo filter removal using convolutional neural networks48
The method uses a convolutional neural network for the prediction of the coefficients of local polynomial transformations that are applied to the input image and shows that the quality of the restoration performed by the method is clearly superior to that of traditional color balancing and restoration procedures.
- 48
- Biometric Recognition Using Multimodal Physiological Signals45
The proposed method consists of a convolutional neural network that exploits mono-dimensional convolutions (1D-CNN) and takes as input a window of the raw signals stacked along the channel dimension and the architecture and training hyperparameters are automatically optimized with the sequential model-based optimization.
- Video restoration based on deep learning: a comprehensive survey43
This paper provides a comprehensive review of the main features of existing video restoration methods based on deep learning, focusing on the main architectural components, strategies for motion handling, and loss functions.
- Color correction pipeline optimization for digital cameras43
Experimental results show that exploiting the cross-talks between the modules of the pipeline can lead to a higher color-rendition accuracy.
- 42
- Local detectors and compact descriptors for visual search: A quantitative comparison42
This work extends the previous analysis using the MPEG CDVS Test Model framework to consider additional detectors and the use of color descriptors to achieve interoperability between different implementations of clients and servers.
- Predicting Image Aesthetics with Deep Learning41
A canonical CNN architecture, originally trained to classify objects and scenes, is fine-tune by casting the image aesthetic prediction as a regression problem, which outperforms the best solution in the state of the art by almost 17 % in terms of Mean Residual Sum of Squares Error (MRSSE).
- 40
- Improving CNN-Based Texture Classification by Color Balancing40
It is shown how suitable color balancing models allow for a significant improvement in the accuracy in recognizing textures for many CNN architectures.
- The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report39
This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution, emphasizing groundbreaking advancements in state-of-the-art single-image ESR techniques.
- Designing an AI-Based Virtual Try-On Web Application39
This paper proposes an eyewear virtual try-on experience based on a framework that leverages advanced deep learning-based computer vision techniques, and considers actual glasses and face sizes to provide a realistic fit estimation using a markerless approach.
- 38
- Color space transformations for digital photography exploiting information about the illuminant estimation process38
It is demonstrated that incorporating knowledge about the illuminant estimation behavior in the optimization of the color correction matrix makes it possible to alleviate the error amplification.
- Reflectance spectra recovery from tristimulus values by adaptive estimation with metameric shape correction38
A local optimization-based method that is able to recover the reflectance spectra with the desired tristimulus values, choosing the metamer with the most similar shape to the reflectances available in the training set, is proposed.
- Two new von Kries based chromatic adaptation transforms found by numerical optimization37
Experimental results report several statistics to prove the effectiveness of the proposed von Kries based chromatic adaptation transforms with respect to the state-of-the-art.
- Improving image captioning descriptiveness by ranking and LLM-based fusion35
A novel approach to generate richer and more informative image captions by combining the captions generated from different SoTA captioning models, which requires no additional model training and enables the generation of more suitable captions for the training of both vision-language and captioning models.
- Semi-supervised cross-lingual speech emotion recognition33
A Semi-Supervised Learning (SSL) method for cross-lingual emotion recognition when only few labeled examples in the target domain are available, based on a Transformer, which adapts to the new domain by exploiting a pseudo-labeling strategy on the unlabeled utterances.
- 32
- 31
- 28
- A Smart Mirror for Emotion Monitoring in Home Environments27
This paper presents a general-purpose smart mirror that integrates several functionalities, standard and advanced, to support users in their everyday life and exploits a deep learning technique to develop most of the smart functionalities.
- Multimodal Car Driver Stress Recognition27
Experiments show that the best recognition results are obtained feeding the classifiers with the concatenation of the features of all the signals considered, reaching a micro average accuracy of 77.25% and 65.09% in the two experimental setups respectively.
- 27
- Combining strategies for white balance27
This work considers six methods for automatic white balance available in the literature and considers a consensus decision that takes into account the compendium of the responses of all the considered algorithms.
- 25
- Deep Multibranch Neural Network for Painting Categorization25
To automatically predict painting’s artist and style, a novel deep multibranch neural network is proposed, where the different branches process the input image at different scales to jointly model the fine and coarse features of the painting.
- Karate moves recognition from skeletal motion25
This work proposes a solution taking as input sequences of skeletal motions that can derive from both motion capture hardware or consumer-level, off the shelf, depth sensing systems.
- Polynomial modeling and optimization for colorimetric characterization of scanners25
Different computational strategies for colorimetric characterization of scanners using multidimensional polynomials are presented, and it is shown how genetic programming could be used to generate the best polynomial.
- 24
- Disentangling Image distortions in deep feature space24
This work analyzes the capability of deep visual representations to intrinsically characterize different types of image distortions and observes that a dimension-reduced representation of the features extracted from a given layer permits to efficiently separate types of distortions in the feature space.
- Visual RAG: Expanding MLLM visual knowledge without fine-tuning23
This paper introduces a novel approach, Visual RAG, that synergically combines the MLLMs capability to learn from the context, with a retrieval mechanism that greatly reduces the computational costs for improving the model image classification performance, and augments the model knowledge to new visual domains and tasks it was not trained for.
- Neural architecture search for image saliency fusion23
Extensive experimental evaluations show that the proposed saliency fusion approach outperforms the state-of-the-art on the MSRAB dataset and it is able to generalize to unseen data of different benchmark datasets.
- Image quality assessment by preprocessing and full reference model combination23
This paper investigates the hypothesis that combining error images with a visual attention model could allow a better fit of the psycho-visual data of the LIVE Image Quality assessment Database Release 2.0 and shows that the proposed quality assessment metric better correlates with the experimental data.
- 22
- Robust smile detection using convolutional neural networks21
Experimental results show that the fully automated approach for smile detection outperforms state-of-the-art methods on both high- and low-quality images.
- Learning Parametric Functions for Color Image Enhancement20
A novel CNN-based method for image enhancement that simulates an expert retoucher that is fast and accurate at the same time thanks to the decoupling between the inference of the parameters and the color transformation.
- Cooking Action Recognition with iVAT: An Interactive Video Annotation Tool20
The iVAT interactive video annotation tool is developed to support manual, semi-automatic and automatic annotations obtained on the basis of the interaction of the user with various detection algorithms.
- 19
- 18
- User Preferences Modeling and Learning for Pleasing Photo Collage Generation18
The results shows that the proposed framework allows to learn a novel computational model which effectively encodes an inter-user definition of pleasantness and generalizes well to new photo datasets of different themes and sizes not used in the learning.
- Color Coding for Data Visualization18
How a color scale should be designed to effectively represent both qualitative and quantitative information is discussed to critically discuss.
- Providing a Single Ground-Truth for Illuminant Estimation for the ColorChecker Dataset17
This short correspondence presents some of the background as to why the 3 existing ground-truths are different and goes on to make a new single and recommended set of correct answers for ColorChecker.
- An analysis of spectral similarity measures16
This paper divides the most used measures for the assessment of spectral similarity of reflectance and radiance signals into five groups on the basis of the type of errors they measure and analyzes the behaviour of the selected metrics with respect to two different color properties.
- ARC: Angle-Retaining Chromaticity diagram for color constancy error analysis16
This work proposes an Angle-Retaining Chromaticity diagram (ARC) for the visual analysis of the estimated illuminants and the corresponding errors, and provides both quantitative and qualitative proof of the superiority of ARC in preserving angular distances compared to other chromaticity diagrams.
- Color Target Localization under Varying Illumination Conditions16
The experimental results on a public dataset of RAW images containing the Macbeth ColorChecker CC target and acquired in uncontrolled environments, showed that all the descriptors considered benefited from the hypothesis validation introduced.
- 16
- Unified Framework for Identity and Imagined Action Recognition From EEG Patterns12
This work presents a unified deep learning framework for the recognition of user identity andThe recognition of imagined actions, based on electroencephalography (EEG) signals, for application as a brain–computer interface, and achieves accuracy levels above 90% both for action and user classification tasks.
- Fine-Grained Face Annotation Using Deep Multi-Task CNN12
A multi-task learning-based convolutional neural network (MTL-CNN) able to estimate multiple tags describing face images simultaneously and taking into account the correlation among face attributes is presented.
- Multiscale fully convolutional network for image saliency12
Despite training the model on binary ground truths only, the method is able to output a continuous-valued confidence map, which represents the probability of each image pixel being salient, which proves to be very effective in a comparison with the state-of-the-art.
- 11
- 11
- IVL-SYNTHSFM-v2: A synthetic dataset with exact ground truth for the evaluation of 3D reconstruction pipelines11
A dataset with 4000 synthetic images portraying five 3D models from different viewpoints under varying lighting conditions to allow evaluation and comparison of different solutions for 3D reconstruction of objects starting from a set of images taken under different realistic acquisition setups.
- A unifying representation for pixel-precise distance estimation11
Using the proposed representation, datasets acquired with different devices can be effortlessly combined to build more powerful models, and monocular distance estimation can be performed on images acquired from devices that were never used during training.
- 10
- 10
- 10
- Aesthetics Assessment of Images Containing Faces10
This paper exploits three different Convolutional Neural Networks to encode information regarding perceptual quality, global image aesthetics, and facial attributes; then, a model is trained to combine these features to explicitly predict the aesthetics of images containing faces.
- Error-Tolerant Color Rendering for Digital Cameras10
This work designs extended color correction pipelines which exploit the crosstalks between their modules to lead to a higher color rendition accuracy.
- Sensor placement optimization in buildings10
This work proposes an algorithm based on Direct Search, which is able to approach the global optimal solution within reasonable time and memory consumption, and is extended to work also on continuous solution spaces, and 3D problems.
- 9
- CURL: Image Classification using co-training and Unsupervised Representation Learning9
A strategy for semi-supervised image classification that leverages unsupervised representation learning and co-training, called CURL, that iteratively builds two classifiers on two different views of the data that clearly outperforms other supervised and semi- supervised learning methods in the state of the art.
- A semi-automatic annotation tool for cooking video9
This work presents an interactive, semi-automatic tool for the annotation of cooking videos that integrates computer vision techniques under the supervision of the user and the accuracy is increased, the human effort is reduced and the performance and usability are evaluated.
- High Contrast Color Sets under Multiple Illuminants9
This work compares four different heuristics for the selection of sets of colors with fixed cardinality and maximum dissimilarity using ΔE76 euclidean metrics on the perceptually uniform CIE L*a*b* space.
- 8
- Consensus-driven illuminant estimation with GANs8
A method is presented that exploits a generative adversarial network architecture to generate a spatially-varying illuminant map, which is then transformed by consensus into a global illuminants estimation, in the form of a single RGB triplet.
- Turning a Digital Camera into an Absolute 2D Tele‐Colorimeter8
A simple and effective technique for absolute colorimetric camera characterization, invariant to changes in exposure/aperture and scene irradiance, suitable in a wide range of applications including image‐based reflectance measurements, spectral pre‐filtering and spectral upsampling for rendering, to improve colour accuracy in high dynamic range imaging.
- On the Robustness of Color Texture Descriptors across Illuminants8
This paper recovered the spectral reflectances of 1360 texture images from the Outex 13 data set and rendered them as if they were taken under 33 different illuminants, measuring the classification performance of the texture features considered.
- Computational Strategies for Skin Detection8
A high-level computational strategy, which uses a face detector in the pre-processing step, and two different implementations of it are proposed: one relies on an adaptive single gaussian model, the other a fixed threshold skin cluster detector on an illuminant-independent image representation.
- Classification-Based Color Constancy8
This work has designed a strategy for the selection of the most appropriate algorithm on the basis of the classification results, and tested it on a subset of the widely used Funt and Ciurea dataset.
- 7
- 7
- 7
- Reliability and Stability of Mean Opinion Score for Image Aesthetic Quality Assessment Obtained Through Crowdsourcing6
Experimental results confirm the reliability and stability of the crowdsourced subjective IQA for the problem in question, and several images and styles are selected and defined, and the obtained scores are numerically analyzed.
- 6
- Image Memorability Using Diverse Visual Features and Soft Attention6
The proposed solution exploits feature maps extracted from two Convolutional Neural Networks pre-trained for object recognition and memorability estimation respectively that are enhanced using a soft attention mechanism in order to let the model focus on highly informative image regions for memorable estimation.
- 6
- Artistic Photo Filtering Recognition Using CNNs6
This paper proposes an approach based on deep Convolutional Neural Networks to recognize artistic photo filters applied to images, and shows that not only it is possible to reliably determine whether or not one of these filters has been applied, but also which one.
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- Region-Based Illuminant Estimation for Effective Color Correction5
A region-based color constancy algorithm able to automatically select (and/or blend) among different color corrections, including a conservative do nothing strategy.
- Generative AI in Healthcare4
The dissertation underscores the need for patient-centered AI development and outlines strategies to mitigate risks related to data integrity, model transparency, and system integration, as well as providing a structured framework for organizational readiness, governance principles, and key performance metrics.
- 4
- 4
- 4
- Unsupervised color coding for visualizing image classification results4
A general purpose system that, given as input a segmented/classified image, automatically provides different visual outputs exploiting solid colors, color boundaries, and transparent colors and places a textual label in the less salient sub-region of the corresponding class if the names of the classes are given.
- On the usefulness of hyperspectral imaging for face recognition4
This paper investigates whether the performance of hyperspectral face recognition algorithms can be improved by considering single and multiple one-dimensional projections of the whole spectral data along the spectral dimension, and finds three different projections investigated and found by optimization.
- Scoring recognizability of faces for security applications4
The system implements features filtering scheme combined with a skin-based face detection to improve its the robustness to false positives and cartoon-like faces and takes into account the recognizability trend over a customizable sliding time window to allow a high level analysis of the subject behaviour.
- 4
- Color Constancy Algorithm Selection Using CART4
This work investigates how illuminant estimation techniques can be improved taking into account intrinsic, low level properties of the images, and shows how these properties can be used to drive the selection of the best algorithm for a given image.
- An Evolutionary Framework for Colorimetric Characterization of Scanners4
This work presents an evolutionary framework for colorimetric characterization of scanners that uses genetic programming for assessing a characterizing polynomial and genetic algorithms to assess suitable coefficients of that polynometric.
- Enhancing Direction-of-Arrival Estimation with Multi-Task Learning3
This article presents a multi-task Convolutional Neural Network capable of simultaneously estimating both the NOS and the DOA of the signal, which surpasses the performance of state-of-the-art methods.
- 3
- 3
- Shallow camera pipeline for night photography rendering3
A camera pipeline for rendering visually pleasing photographs in low light conditions, characterized by a shallow structure and by a low parameter count, is introduced, which reached the fifth place in the NTIRE2022 Night Photography Rendering challenge.
- 3
- 3
- Can Linear Data Projection Improve Hyperspectral Face Recognition?3
This paper investigates if the performance of hyperspectral face recognition algorithms can be improved by considering 1D projections of the whole spectral data along the spectral dimension: single spectral band selection, non-negative spectral band combination, and unbounded spectralBand combination.
- On the use of MKL for cooking action recognition3
This paper investigates the use of the Multiple Kernel Learning (MKL) algorithm to adaptive search for the best linear relation among the considered features and proves the validity of the approach by considering a descriptor composed of multiple features aligned with dense trajectories.
- Absolute colorimetric characterization of a DSLR camera3
A simple but effective technique for absolute colorimetric camera characterization that offers a large dynamic range requiring just a single, off-the-shelf target and a commonly available controllable light source for the characterization.
- Face-Based Illuminant Estimation3
This work uses a face detector to find faces in the scene, and the corresponding skin colors to estimate the chromaticity of the illuminant, based on two observations: first, skin colors tend to form a cluster in the color space, making it a cue to estimates the Illuminant in thescene.
- Genetic Algorithms for Training Data and Polynomial Optimization in Colorimetric Characterization of Scanners3
A framework based on Genetic Algorithms to select training samples from large datasets and has the ability to optimize the training samples and the characterizing polynomial’s coefficients at the same time.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- CNN-based Rain Reduction in Street View Images2
Experimental results show that the Convolutional Neural Network model presented is able to outperform the state of the art in terms of two commonly used image quality metrics, and that it is capable to improve the performances of an OCR model to detect and recognise text in the wild.
- Combining Saliency Estimation Methods2
This work defines a general scheme, which is then specialize to perform dataset-specific and image-specific recombination, based on either linear weight regression, or method selection, to address the task of image saliency estimation through proper recombination of existing methods.
- 2
- A Fully Convolutional Network for Salient Object Detection2
A solution is proposed that exploits intermediate activations of a Fully Convolutional Neural Network previously trained for the recognition of 1,000 object classes, in order to gather generic object information at different levels of resolution by using both convolution and convolution-transpose layers.
- Object detection using feature-based template matching2
This work presents a fast technique for template matching, able to use histogram-based similarity measures on complex descriptors, and focuses on Color Histograms (CH), Histograms of Oriented Gradients (HOG), and Bag of visual Words histograms (BOW).
- Color Constancy Using Single Colors2
This work investigates if the von Kries adaptation can be generalized to deal with single colored patches and couples of colors, and the analysis of the characteristics of the colors forming the couples is carried out.
- Multiscale RGB-Guided Fusion for Hyperspectral Image Super-Resolution1
CGNet, a color-guided hyperspectral super-resolution network that leverages complementary information from low-resolution hyperspectral inputs and high-resolution RGB images, achieves higher PSNR and SSIM, lower SAM, and reduced ΔE00, confirming its ability to recover sharp spatial structures while preserving spectral fidelity.
- Illuminant-Adaptive 3D Lookup Tables for Camera Color Correction1
This work proposes a color correction framework based on illuminant-adaptive three-dimensional lookup tables (LUTs), which it calls Color Correction LUT (C$^2$LUT), which combines a chromaticity-aware illuminant representation with a non-linear color transformation, enabling accurate correction under illuminants spanning a wide range of chromaticities and spectral complexities.
- Decoupling spatial and spectral features for efficient hyperspectral image super-resolution1
The proposed Efficient Spatial-Spectral Processing Network (ESSPN) is a lightweight deep learning architecture designed to address the challenges of HSI-SR in a computationally efficient way and shows strong generalization across hyperspectral cameras with varying spectral responses, and across radiometric domains.
- DEAR: Dataset for Evaluating the Aesthetics of Rendering1
DEAR is the first dataset to systematically address image aesthetics of rendering assessment grounded in subjective human preferences, enabling the development and evaluation of models that go beyond traditional distortion-based IQA, focusing on a new task: Evaluation of Aesthetics of Rendering (EAR).
- Scalable Residual Laplacian Network for HEVC-compressed Video Restoration1
A novel Convolutional Neural Network that exploits the Laplacian decomposition technique, which is typically used in traditional image processing, to restore videos compressed with the High-Efficiency Video Coding (HEVC) algorithm with a lower model complexity and shorter runtime with respect to existing methods.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Getting the most of few data for neonatal pain assessment1
This paper develops two solutions based on the generative adversarial network (GAN) framework in order to improve discriminator power by transforming it into a multitask classifier and by training it with a combination of real and synthetic samples.
- DIY absolute tele-colorimeter using a camera-projector system1
A novel approach for colorimetric camera characterization is presented, which exploits a commonly available projector as controllable light source, and accurately relates the camera sensor response to the known reflected radiance.
- RGB-D-λ: 3D Multispectral Acquisition with Stereo RGB Cameras1
The main criteria defined by COSCH Working Group 1 and used by the authors to help Digital Cultural Heritage users to have a deepen knowledge and understanding of the constraints, preconditions and practical aspects related to the use of a multi-spectral acquisition system are summarized.
- Audio stream classification for multimedia database search1
A CART-based (Classification And Regression Tree [1]) classification framework for audio streams belonging to multimedia databases, which is mainly composed of popular songs and other audio records describing the popular traditions handed down generation by generation.
- 1
- 1
- Matrixing, number of color channels, and color gamut of camera devices1
The relationship between matrixing methods, the number of filters adopted and the size of the color gamut of a digital camera is investigated and an original method developed by the authors is considered.
- –
- –
- –
- Face anonymization preserving facial expressions and photometric realism–
This work proposes a feature-preserving anonymization framework that extends DeepPrivacy by incorporating dense facial landmarks to better retain expressions, and by introducing lightweight post-processing modules that ensure consistency in lighting direction and skin color.
- –
- –
- –
- –
- Acquisition and Modeling of Material Appearance Using a Portable, Low Cost, Device–
The rationale behind the design of the device using consumer-grade hardware components is presented and the accuracy of the acquisition process is comprehensively evaluated both quantitatively and qualitatively.
- Common issues and human intervention in object detection from handcrafted features to deep learning: discussion–
This work analyzes the object detection recipe, and shows that these two approaches actually present three common issues that require human supervision and ad hoc procedures to be addressed: the design of an object model suitable for the context, devices, and task at hand; the achievement of detection robustness against several factors like noise, image quality, changes in geometry, and light variations.
- –
- –
- –
- –
- –
- –
- –
- Image understanding for color constancy and vice versa–
This article chronologically review the color constancy algorithms that exploit results and techniques borrowed from the image understanding research field in order to exploit assumptions that could be met in a larger number of images.
- –
- –
- Special Section Guest Editorial: Computational Color Imaging–
This guest editorial introduces the JEI Special Section on Computational Color Imaging and its applications in medicine, education, and research.
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.