The rapid advancement of deep learning and computer vision technologies is transforming sports analytics, enabling more precise performance analysis and motion tracking. However, accurately estimating hammer throw distances without physical measurements remains a challenge due to the complexity of the motion and the high speed of the projectile. The ability to accurately predict hammer throw distances would be particularly useful in indoor training settings, where the hammer’s trajectory is stopped by safety nets or mattresses from a short distance. To address this challenge, we introduce a deep learning-based method that combines object detection with physics-based modeling to estimate motion outcomes. Our methodology employs a dual-camera setup to capture side and back views of the throw, applies advanced object detection to track the hammer’s position frame by frame, and reconstructs 3D trajectory points to estimate the release speed, angle, and height that allow predicting the throw distance. By enabling quantitative assessment of performance without relying on physical landing measurements, the proposed approach supports objective training feedback on the release parameters and distance estimation in typical training environments where traditional distance-based evaluation is not feasible. Our approach enables accurate performance evaluation in spatially constrained settings. Experimental results demonstrate that our approach achieves an average error of less than three meters ( ∼ 4 %) in estimating the distances compared to ground truth measurements. Our codes and trained models will be made publicly available once the paper is published at https://github.com/AhmedEH28/Hammer-Throw-Distance-Estimation .

Autoencoders (AEs) are a type of unsupervised neural networks, which can be used to solve various tasks, e.g., dimensionality reduction, image compression, and image denoising. An AE has two goals: (i) compress the original input to a low-dimensional space at the bottleneck of the network topology using an encoder, (ii) reconstruct the input from the representation at the bottleneck using a decoder. Both encoder and decoder are optimized jointly by minimizing a distortion-based loss which implicitly forces the model to keep only the information in input data required to reconstruct them and to reduce redundancies. In this paper, we propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. To this end, we propose an additional loss term, based on the pairwise covariances of the network units, which complements the data reconstruction loss forcing the encoder to learn a more diverse and richer representation of the input. We tested our approach across different tasks, namely dimensionality reduction, image compression, and image denoising. Experimental results show that the proposed loss leads consistently to superior performance compared to using the standard AE loss.

Neural networks are composed of multiple layers arranged in a hierarchical structure jointly trained with a gradient-based optimization, where the errors are back-propagated from the last layer back to the first one. At each optimization step, neurons at a given layer receive feedback from neurons belonging to higher layers of the hierarchy. In this paper, we propose to complement this traditional 'between-layer' feedback with additional 'within-layer' feedback to encourage the diversity of the activations within the same layer. To this end, we measure the pairwise similarity between the outputs of the neurons and use it to model the layer's overall diversity. We present an extensive empirical study confirming that the proposed approach enhances the performance of several state-of-the-art neural network models in multiple tasks. The code is publically available at https://github.com/firasl/AAAI-23-WLD-Reg.

In this paper, we propose a novel subspace learning framework for one-class classification. The proposed framework presents the problem in the form of graph embedding. It includes the previously proposed subspace one-class techniques as its special cases and provides further insight on what these techniques actually optimize. The framework allows to incorporate other meaningful optimization goals via the graph preserving criterion and reveals a spectral solution and a spectral regression-based solution as alternatives to the previously used gradient-based technique. We combine the subspace learning framework iteratively with Support Vector Data Description applied in the subspace to formulate Graph-Embedded Subspace Support Vector Data Description. We experimentally analyzed the performance of newly proposed different variants. We demonstrate improved performance against the baselines and the recently proposed subspace learning methods for one-class classification.

In this paper, we formulate a new generalized reference kernel hoping to improve the original base kernel using a set of reference vectors. Depending on the selected reference vectors, our formulation shows similarities to approximate kernels, random mappings, and Non-linear Projection Trick. Focusing on small-scale one-class classification, our analysis and experimental results show that the new formulation provides approaches to regularize, adjust the rank, and incorporate additional information into the kernel itself, leading to improved one-class classification accuracy.

Linear discriminant analysis (LDA) is a classical statistical machine-learning method, which aims to find a linear data transformation increasing class discrimination in an optimal discriminant subspace. Traditional LDA sets assumptions related to the Gaussian class distributions and single-label data annotations. In this article, we propose a new variant of LDA to be used in multilabel classification tasks for dimensionality reduction on original data to enhance the subsequent performance of any multilabel classifier. A probabilistic class saliency estimation approach is introduced for computing saliency-based weights for all instances. We use the weights to redefine the between-class and within-class scatter matrices needed for calculating the projection matrix. We formulate six different variants of the proposed saliency-based multilabel LDA (SMLDA) based on different prior information on the importance of each instance for their class(es) extracted from labels and features. Our experiments show that the proposed SMLDA leads to performance improvements in various multilabel classification problems compared to several competing dimensionality reduction methods.

In this paper, we propose a method for ensembling the outputs of multiple object detectors for improving detection performance and precision of bounding boxes on image data. We further extend it to video data by proposing a two-stage tracking-based scheme for detection refinement. The proposed method can be used as a standalone approach for improving object detection performance, or as a part of a framework for faster bounding box annotation in unseen datasets, assuming that the objects of interest are those present in some common public datasets.

Privacy concerns in healthcare have gained interest recently via GDPR, with a rising need for privacy-preserving data collection methods that keep personal information hidden in otherwise usable data. Sometimes data needs to be encrypted for several authentication levels, where a semi-authorized user gains access to data stripped of personal or sensitive information, while a fully-authorized user can recover the full signal. In this paper, we propose a compressive sensing based multi-level encryption to ECG signals to mask possible heartbeat anomalies from semi-authorized users, while preserving the beat structure for heart rate monitoring. Masking is performed both in time and frequency domains. Masking effectiveness is validated using 1D convolutional neural networks for heartbeat anomaly classification, while masked signal usefulness is validated comparing heartbeat detection accuracy between masked and recovered signals. The proposed multi-level encryption method can decrease classification accuracy of heartbeat anomalies by up to 50%, while maintaining a fairly high R-peak detection accuracy.

Computational color constancy is a preprocessing step used in many camera systems. The main aim is to discount the effect of the illumination on the colors in the scene and restore the original colors of the objects. Recently, several deep learning-based approaches have been proposed to solve this problem and they often led to state-of-the-art performance in terms of average errors. However, for extreme samples, these methods fail and lead to high errors. In this paper, we address this limitation by proposing to aggregate different deep learning methods according to their output uncertainty. We estimate the relative uncertainty of each approach using Monte Carlo dropout and the final illumination estimate is obtained as the sum of the different model estimates weighted by the log-inverse of their corresponding uncertainties. The proposed framework leads to state-of-the-art performance on INTEL-TAU dataset.

Automatic classification of speech commands has revolutionized human computer interactions in robotic applications. However, employed recognition models usually follow the methodology of deep learning with complicated networks which are memory and energy hungry. So, there is a need to either squeeze these complicated models or use more efficient lightweight models in order to be able to implement the resulting classifiers on embedded devices. In this paper, we pick the second approach and propose a network layer to enhance the speech command recognition capability of a lightweight network and demonstrate the result via experiments. The employed method borrows the ideas of Taylor expansion and quadratic forms to construct a better representation of features in both input and hidden layers. This richer representation results in recognition accuracy improvement as shown by extensive experiments on Google speech commands (GSC) and synthetic speech commands (SSC) datasets.

Main characters in images are the most important humans that catch the viewer’s attention upon first look, and they are emphasized by properties such as size, position, color saturation, and sharpness of focus. Identifying the main character in images plays an important role in traditional photographic studies and media analysis, but the task is performed manually and is, thus, slow and laborious. Furthermore, selection of main characters can be sometimes subjective. In this paper, we analyze the feasibility of solving the main character recognition needed for photographic studies automatically and propose a method for identifying the main characters. The proposed method uses machine learning based human pose estimation along with traditional computer vision approaches for this task. We approach the task as a binary classification problem where each detected human is classified either as a main character or not. To evaluate both the subjectivity of the task and the performance of our method, we collected a dataset of 300 varying images from multiple sources and asked five people, a photographic researcher and four other persons, to annotate the main characters. Our analysis showed a relatively high agreement between different annotators. The proposed method achieved a promising F1 score of 0.83 on the full image set and 0.96 on a subset evaluated as most clear and important cases by the photographic researcher.

In this paper, we propose a speed-up approach for subclass discriminant analysis and formulate a novel efficient multi-view solution to it. The speed-up approach is developed based on graph embedding and spectral regression approaches that involve eigendecomposition of the corresponding Laplacian matrix and regression to its eigenvectors. We show that by exploiting the structure of the between-class Laplacian matrix, the eigendecomposition step can be substituted with a much faster process. Furthermore, we formulate a novel criterion for multi-view subclass discriminant analysis and show that an efficient solution to it can be obtained in a similar manner to the single-view case. We evaluate the proposed methods on nine single-view and nine multi-view datasets and compare them with related existing approaches. Experimental results show that the proposed solutions achieve competitive performance, often outperforming the existing methods. At the same time, they significantly decrease the training time.

In this paper, we propose a novel method for projecting data from multiple modalities to a new subspace optimized for one-class classification. The proposed method iteratively transforms the data from the original feature space of each modality to a new common feature space along with finding a joint compact description of data coming from all the modalities. For data in each modality, we define a separate transformation to map the data from the corresponding feature space to the new optimized subspace by exploiting the available information from the class of interest only. We also propose different regularization strategies for the proposed method and provide both linear and non-linear formulations. The proposed Multimodal Subspace Support Vector Data Description outperforms all the competing methods using data from a single modality or fusing data from all modalities in four out of five datasets.

Recent advances in intelligent surveillance systems have enabled a new era of smart monitoring in a wide range of applications from health monitoring to homeland security. However, this boom in data gathering, analyzing and sharing brings in also significant privacy concerns. We propose a Compressive Sensing (CS) based data encryption that is capable of both obfuscating selected sensitive parts of documents and compressively sampling, hence encrypting both sensitive and non-sensitive parts of the document. The scheme uses a data hiding technique on CS-encrypted signal to preserve the one-time use obfuscation matrix. The proposed privacy-preserving approach offers a low-cost multi-tier encryption system that provides different levels of reconstruction quality for different classes of users, e.g., semi-authorized, full-authorized. As a case study, we develop a secure video surveillance system and analyze its performance.

This paper proposes an incremental solution to Fast Subclass Discriminant Analysis (fastSDA). We present an exact and an approximate linear solution, along with an approximate kernelized variant. Extensive experiments on eight image datasets with different incremental batch sizes show the superiority of the proposed approach in terms of training time and accuracy being equal or close to fastSDA solution and outperforming other methods.

In this paper, we propose a novel unsupervised color constancy method, called Probabilistic Color Constancy (PCC). We define a framework for estimating the illumination of a scene by weighting the contribution of different image regions using a graph-based representation of the image. To estimate the weight of each (super-)pixel, we rely on two assumptions: (Super-)pixels with similar colors contribute similarly and darker (super-)pixels contribute less. The resulting system has one global optimum solution. The proposed method achieves competitive performance, compared to the state-of-the-art, on INTEL-TAU dataset.

For autonomous unmanned surface vehicles (USV) operations, it is important to be able to observe the surroundings using visual information. Water segmentation is a task where the water surface is recognized and separated from everything else. The algorithm performing the segmentation must be robust, because safety is the most important feature of autonomous USVs. This is especially challenging in many USV applications, where the rapidly changing weather and lighting conditions can cause significant distribution shifts. In this study, we analyze the robustness of different color spaces (e.g., RGB and HSV) for water segmentation and consider how to use different color channels in training and testing to maximize the robustness. We evaluate the segmentation performance on a challenging completely unseen test dataset, recorded in vastly different conditions and with different equipment.

Deep learning approaches are highly specialized and require training separate models for different tasks. Multidomain learning looks at ways to learn a multitude of different tasks, each coming from a different domain, at once. The most common approach in multi-domain learning is to form a domain agnostic model, the parameters of which are shared among all domains, and learn a small number of extra domain-specific parameters for each individual new domain. However, different domains come with different levels of difficulty; parameterizing the models of all domains using an augmented version of the domain agnostic model leads to unnecessarily inefficient solutions, especially for easy to solve tasks. We propose an adaptive parameterization approach to deep neural networks for multidomain learning. The proposed approach performs on par with the original approach while reducing by far the number of parameters, leading to efficient multi-domain learning solutions.

Early exits provide an effective way of implementing adaptive computational graphs over deep learning models. In this way it is possible to adapt them on-the-fly to the available computational resources or even to the difficulty of each input sample, reducing the energy and computational power requirements in many embedded and mobile applications. However, performing this kind of adaptive inference also comes with several challenges, since the difficulty of each sample must be estimated and the most appropriate early exit must be selected. It is worth noting that existing approaches often lead to highly unbalanced distributions over the selected early exits, reducing the efficiency of the adaptive inference process. At the same time, only a few resources can be devoted to the aforementioned process, in order to ensure that an adequate speedup will be obtained. The main contribution of this work is to provide an easy to use and tune adaptive inference approach for early exits that can overcome some of these limitations. In this way, the proposed method allows for a) obtaining a more balanced inference distribution among the early exits, b) relying on a single and interpretable hyperparameter for tuning its behavior (ranging from faster inference to higher accuracy), and c) improving the performance of the networks (increasing the accuracy and reducing the time needed for inference). Indeed, the effectiveness of the proposed method over existing approaches is demonstrated using four different image datasets.

In this paper, we propose a novel color constancy approach, called Bag of Color Features (BoCF), building upon Bag-of-Features pooling. The proposed method substantially reduces the number of parameters needed for illumination estimation. At the same time, the proposed method is consistent with the color constancy assumption stating that global spatial information is not relevant for illumination estimation and local information (edges, etc.) is sufficient. Furthermore, BoCF is consistent with color constancy statistical approaches and can be interpreted as a learning-based extension of many statistical approaches. To further improve the illumination estimation accuracy, we propose a novel attention mechanism for the BoCF model with two variants based on self-attention. BoCF approach and its variants achieve competitive, compared to the state of the art, results while requiring much fewer parameters on three benchmark datasets: ColorChecker RECommended, INTEL-TUT version 2, and NUS8.

Using early exits provide a straightforward way to implement models that can adapt on-the-fly to the available computational resources. However, early exits in many cases suffer from significant limitations, which often prohibit their practical application, especially when placed on convolutional layers with narrow receptive fields. In this work, we propose a method capable of overcoming these limitations by a) using a Bag-of-Features (BoF)-based pooling approach, that allows for keeping more information regarding the distribution of the extracted feature vectors, while also maintaining more spatial information and b) employing a simple, yet effective, hierarchical approach for designing the exits, allowing for efficiently re-using the information that was already extracted by the previous layers. It is experimentally demonstrated that the proposed approach leads to significant performance improvements, allowing early exits to be a more practical tool that can be used in many real-world embedded applications.

This paper proposes a novel method for solving one-class classification problems. The proposed approach, namely Subspace Support Vector Data Description, maps the data to a subspace that is optimized for one-class classification. In that feature space, the optimal hypersphere enclosing the target class is then determined. The method iteratively optimizes the data mapping along with data description in order to define a compact class representation in a low-dimensional feature space. We provide both linear and non-linear mappings for the proposed method. Experiments on 14 publicly available datasets indicate that the proposed Subspace Support Vector Data Description provides better performance compared to baselines and other recently proposed one-class classification methods.

In training radial basis function neural networks (RBFNNs), the locations of Gaussian neurons are commonly determined by clustering. Training inputs can be clustered on a fully unsupervised manner (input clustering), or some supervision can be introduced, for example, by concatenating the input vectors with weighted output vectors (input-output clustering). In this paper, we propose to apply clustering separately for each class (class-specific clustering). The idea has been used in some previous works, but without evaluating the benefits of the approach. We compare the class-specific, input, and input-output clustering approaches in terms of classification performance and computational efficiency when training RBFNNs. To accomplish this objective, we apply three different clustering algorithms and conduct experiments on 25 benchmark data sets. We show that the class-specific approach significantly reduces the overall complexity of the clustering, and our experimental results demonstrate that it can also lead to a significant gain in the classification performance, especially for the networks with a relatively few Gaussian neurons. Among other applied clustering algorithms, we combine, for the first time, a dynamic evolutionary optimization method, multidimensional particle swarm optimization, and the class-specific clustering to optimize the number of cluster centroids and their locations.

Low-level features (also called descriptors) play a central role in content-based image retrieval (CBIR) systems. Features are various types of information extracted from the content and represent some of its characteristics or signatures. However, especially the (low-level) features, which can be extracted automatically usually lack the discrimination power needed for accurate description of the image content and may lead to a poor retrieval performance. In order to efficiently address this problem, in this paper we propose a multi- dimensional evolutionary feature synthesis technique, which seeks for the optimal linear and non-linear operators so as to synthesize highly discriminative set of features in an optimal dimension. The optimality therein is sought by the multi-dimensional particle swarm optimization method along with the fractional global-best formation technique. Clustering and CBIR experiments where the proposed feature synthesizer is evolved using only the minority of the image database, demonstrate a significant performance improvement and exhibit a major discrimination between the features of different classes.

In this paper, we focus on advanced classification and data retrieval schemes that are instrumental when processing large taxonomical image datasets. With large number of classes, classification and an efficient retrieval of a particular benthic macroinvertebrate image within a dataset will surely pose a severe problem. To address this, we propose a novel network of evolutionary binary classifiers, which is scalable, dynamically adaptable and highly accurate for the classification and retrieval of large biological species-image datasets. The classification and retrieval results for the macroinvertebrate test data attain taxonomic accuracy that equals and even surpasses that of an average expert. Our findings are encouraging for aquatic biomonitoring where cost intensity of sample analysis currently poses a bottleneck for routine biomonitoring.