Carlos HinojosaKing Abdullah University of Science and Technology | KAUST · Center of Excellence on Generative AI
Carlos Hinojosa
PhD in Computer Science
Computer scientist working on computer vision and computational imaging. Currently looking for job opportunities.
About
42
Publications
4,606
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
396
Citations
Publications
Publications (42)
The SoccerNet 2024 challenges represent the fourth annual video understanding challenges organized by the SoccerNet team. These challenges aim to advance research across multiple themes in football, including broadcast video understanding, field understanding, and player understanding. This year, the challenges encompass four vision-based tasks. (1...
Chronic wounds pose an ongoing health concern globally, largely due to the prevalence of conditions such as diabetes and leprosy's disease. The standard method of monitoring these wounds involves visual inspection by healthcare professionals, a practice that could present challenges for patients in remote areas with inadequate transportation and he...
Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of the pretext task and learn richer visual representations, existing works have focused on replacing standard random masking with more sophisticated strategies, such as ad...
The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurrin...
Scene captioning consists of accurately describing the visual information using text, leveraging the capabilities of computer vision and natural language processing. However, current image captioning methods are trained on high-resolution images that may contain private information about individuals within the scene, such as facial attributes or se...
The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurrin...
Data augmentation is classically used to improve the overall performance of deep learning models. It is, however, challenging in the case of medical applications, and in particular for multiparametric datasets. For example, traditional geometric transformations used in several applications to generate synthetic images can modify in a non-realistic...
In recent years, fast technological advancements have led to the development of high-quality software and hardware, revolutionizing various industries such as the economy, health, industry, and agriculture. Specifically, applying information and communication technology (ICT) tools and the Internet of Things (IoT) in agriculture has improved produc...
Spectral microscopy suffers from axial chromatic aberrations (ACA). Deep optics is here used to design the PSF of a snapshot multispectral microscope based on a deformable mirror, to overcome ACA-related artifacts in the recovered data.
The accelerated use of digital cameras prompts an increasing concern about privacy and security, particularly in applications such as action recognition. In this paper, we propose an optimizing framework to provide robust visual privacy protection along the human action recognition pipeline. Our framework parameterizes the camera lens to successful...
Recent advances in deep learning led to several algorithms for the accurate diagnosis of pneumonia from chest X-rays. However, these models require large training medical datasets, which are sparse, isolated, and generally private. Furthermore, these models in medical imaging are known to over-fit to a particular data domain source, i.e., these alg...
The accelerated use of digital cameras prompts an increasing concern about privacy and security, particularly in applications such as action recognition. In this paper, we propose an optimizing framework to provide robust visual privacy protection along the human action recognition pipeline. Our framework parameterizes the camera lens to successful...
In recent years, compressive spectral imaging (CSI) has emerged as a new acquisition technique that acquires coded projections of the spectral scene, reducing considerably storage and transmission costs. Among several CSI devices, the single-pixel camera (SPC) architecture excels due to its low implementation cost when acquiring a large number of s...
The widespread use of always-connected digital cameras in our everyday life has led to increasing concerns about the users' privacy and security. How to develop privacy-preserving computer vision systems? In particular, we want to prevent the camera from obtaining detailed visual data that may contain private information. However, we also want the...
Accurate unsupervised classification of hyperspectral images (HSIs) is challenging and has drawn widespread attention in remote sensing due to its inherent complexity. Although significant efforts have been made to develop a variety of methods, most of them rely on supervised strategies. Subspace clustering methods, such as Sparse Subspace Clusteri...
The unsupervised classification of hyperspectral images (HSIs) draws attention in the remote sensing community due to its inherent complexity and the lack of labeled data. Among unsupervised methods, sparse subspace clustering (SSC) achieves high clustering accuracy by constructing a sparse affinity matrix. However, SSC has limitations when cluster...
Accurate land cover segmentation of spectral images is challenging and has drawn widespread attention in remote sensing due to its inherent complexity. Although significant efforts have been made for developing a variety of methods, most of them rely on supervised strategies. Subspace clustering methods, such as Sparse Subspace Clustering (SSC), ha...
Accurate land cover segmentation of spectral images is challenging and has drawn widespread attention in remote sensing due to its inherent complexity. Although significant efforts have been made for developing a variety of methods, most of them rely on supervised strategies. Subspace clustering methods, such as Sparse Subspace Clustering (SSC), ha...
The accurate segmentation of remotely sensed hyperspectral images has widespread attention in the Earth observation and remote sensing communities. In the past decade, most of the efforts focus on the development of different supervised methods for hyperspectral image classification. Recently, the computer vision community is developing unsupervise...
In a CSI classification task, it is necessary to a reconstruction process in most cases. In contrast, an approach for classification tasks of SPC avoiding the reconstruction process is presented with an accuracy of 97.72%.
Imaging spectroscopy collects the spectral information of a scene by sensing all the spatial information across the electromagnetic wavelengths and are useful for applications in surveillance, agriculture, and medicine, etc. In contrast, compressive spectral imaging (CSI) systems capture compressed projections of the scene, which are then used to r...
The low spatial resolution of hyperspectral (HS) images generally limits the classification accuracy. Therefore, different multiresolution data fusion techniques have been proposed in the literature. In this paper, a method for supervised classification of spectral images from data fusion measurements is proposed. Specifically, the proposed approac...
Compressive spectral imaging (CSI) acquires compressed observations of a spectral scene by applying different coding patterns at each spatial location and then performing a spectral-wise integration. Relying on compressive sensing, spectral image reconstruction is achieved by using nonlinear and relatively expensive optimization-based algorithms. I...
This paper proposes a classification method that fuses superpixels-segmentation information from an RGB image with a hyperspectral image without estimating the high spatial-spectral resolution cube. This methodology improves the classification accuracy while boosting the performance.
This paper proposes a spectral image clustering approach that uses a 3-D Gaussian filter to incorporate the spatial information of the scene in the Sparse Subspace Clustering model obtaining a more accurate representation coefficient matrix.
This paper proposes a new hyperspectral image subspace clustering framework which adds a total variation denoising constraint in order to improve the similarity between data points from the same subspace.
The snapshot colored compressive spectral imager (SCCSI) is a recent compressive spectral imaging (CSI) architecture that senses the spatial and spectral information of a scene in a single snapshot by means of a colored mosaic FPA detector and a dispersive element. Commonly, CSI architectures allow multiple snapshot acquisition, yielding improved r...
Compressive spectral imaging (CSI) captures coded and dispersed projections of the spatio-spectral source rather than direct measurements of the voxels. Using the coded projections, an l1 minimization reconstruction algorithm is then used to reconstruct the underlying scene. An architecture known as the snapshot colored compressive spectral imager...