Graph convolutional network (GCN)-based methods have shown strong performance in 3D human pose estimation by leveraging the natural graph structure of the human skeleton. However, their local receptive field limits their ability to capture long-range dependencies essential for handling occlusions and depth ambiguities. They also exhibit spectral bias, which prioritizes low-frequency components while struggling to model high-frequency details. In this paper, we introduce PoseKAN, an adaptive graph Kolmogorov-Arnold Network (KAN), framework that extends KANs to graph-based learning for 2D-to-3D pose lifting from a single image. Unlike GCNs that use fixed activation functions, KANs employ learnable functions on graph edges, allowing data-driven, adaptive feature transformations. This enhances the model's adaptability and expressiveness, making it more expressive in learning complex pose variations. Our model employs multi-hop feature aggregation, ensuring the body joints can leverage information from both local and distant neighbors, leading to improved spatial awareness. It also incorporates residual PoseKAN blocks for deeper feature refinement, and a global response normalization for improved feature selectivity and contrast. Extensive experiments on benchmark datasets demonstrate the competitive performance of our model against state-of-the-art methods. Code is available at: https://github.com/shahjahan0275/PoseKAN

Long-term time series forecasting in centralized environments poses unique challenges regarding data privacy, communication overhead, and scalability. To address these challenges, we propose FedTime, a federated large language model (LLM) tailored for long-range time series prediction. Specifically, we introduce a federated pre-trained LLM with fine-tuning and alignment strategies. Prior to the learning process, we employ K-means clustering to partition edge devices or clients into distinct clusters, thereby facilitating more focused model training. We also incorporate channel independence and patching to better preserve local semantic information, ensuring that important contextual details are retained while minimizing the risk of information loss. We demonstrate the effectiveness of our FedTime model through extensive experiments on various real-world forecasting benchmarks, showcasing substantial improvements over recent approaches. In addition, we demonstrate the efficiency of FedTime in streamlining resource usage, resulting in reduced communication overhead.

Road scene understanding is crucial in autonomous driving, enabling machines to perceive the visual environment. However, recent object detectors tailored for learning on datasets collected from certain geographical locations struggle to generalize across different locations. In this paper, we present RSUD20K, a new dataset for road scene understanding, comprised of over 20K high-resolution images from the driving perspective on Bangladesh roads, and includes 130K bounding box annotations for 13 objects. This challenging dataset encompasses diverse road scenes, narrow streets and highways, featuring objects from different viewpoints and scenes from crowded environments with densely cluttered objects and various weather conditions. Our work significantly improves upon previous efforts, providing detailed annotations and increased object complexity. We thoroughly examine the dataset, benchmarking various state-of-the-art object detectors and exploring large vision models as image annotators1.1Dataset and Code: https://github.com/hasibzunair/RSUD20K

Recognizing multiple objects in an image is challenging due to occlusions, and becomes even more so when the objects are small. While promising, existing multi-label image recognition models do not explicitly learn context-based representations, and hence struggle to correctly recognize small and occluded objects. Intuitively, recognizing occluded objects requires knowledge of partial input, and hence context. Motivated by this intuition, we propose Masked Supervised Learning (MSL), a single-stage, model-agnostic learning paradigm for multi-label image recognition. The key idea is to learn context-based representations using a masked branch and to model label co-occurrence using label consistency. Experimental results demonstrate the simplicity, applicability and more importantly the competitive performance of MSL against previous state-of-the-art methods on standard multi-label image recognition benchmarks. In addition, we show that MSL is robust to random masking and demonstrate its effectiveness in recognizing non-masked objects. Code and pretrained models are available on GitHub.

In human pose estimation methods based on graph convolutional architectures, the human skeleton is usually modeled as an undirected graph whose nodes are body joints and edges are connections between neighboring joints. However, most of these methods tend to focus on learning relationships between body joints of the skeleton using first-order neighbors, ignoring higher-order neighbors and hence limiting their ability to exploit relationships between distant joints. In this paper, we introduce a higher-order regular splitting graph network (RS-Net) for 2D-to-3D human pose estimation using matrix splitting in conjunction with weight and adjacency modulation. The core idea is to capture long-range dependencies between body joints using multi-hop neighborhoods and also to learn different modulation vectors for different body joints as well as a modulation matrix added to the adjacency matrix associated to the skeleton. This learnable modulation matrix helps adjust the graph structure by adding extra graph edges in an effort to learn additional connections between body joints. Instead of using a shared weight matrix for all neighboring body joints, the proposed RS-Net model applies weight unsharing before aggregating the feature vectors associated to the joints in order to capture the different relations between them. Experiments and ablations studies performed on two benchmark datasets demonstrate the effectiveness of our model, achieving superior performance over recent state-of-the-art methods for 3D human pose estimation.

Internet of Things (IoT) sensors in smart buildings are becoming increasingly ubiquitous, making buildings more livable, energy efficient, and sustainable. These devices sense the environment and generate multivariate temporal data of paramount importance for detecting anomalies and improving the prediction of energy usage in smart buildings. However, detecting these anomalies in centralized systems is often plagued by a huge delay in response time. To overcome this issue, we formulate the anomaly detection problem in a federated learning setting by leveraging the multi-task learning paradigm, which aims at solving multiple tasks simultaneously while taking advantage of the similarities and differences across tasks. We propose a novel privacy-by-design federated learning model using a stacked long short-time memory (LSTM) model, and we demonstrate that it is more than twice as fast during training convergence compared to the centralized LSTM. The effectiveness of our federated learning approach is demonstrated on three real-world datasets generated by the IoT production system at General Electric Current smart building, achieving state-of-the-art performance compared to baseline methods in both classification and regression tasks. Our experimental results demonstrate the effectiveness of the proposed framework in reducing the overall training cost without compromising the prediction performance.

Detecting various types of cells in and around the tumor matrix holds a special significance in characterizing the tumor micro-environment for cancer prognostication and research. Automating the tasks of detecting, segmenting, and classifying nuclei can free up the pathologists' time for higher value tasks and reduce errors due to fatigue and subjectivity. To encourage the computer vision research community to develop and test algorithms for these tasks, we prepared a large and diverse dataset of nucleus boundary annotations and class labels. The dataset has over 46,000 nuclei from 37 hospitals, 71 patients, four organs, and four nucleus types. We also organized a challenge around this dataset as a satellite event at the International Symposium on Biomedical Imaging (ISBI) in April 2020. The challenge saw a wide participation from across the world, and the top methods were able to match inter-human concordance for the challenge metric. In this paper, we summarize the dataset and the key findings of the challenge, including the commonalities and differences between the methods developed by various participants. We have released the MoNuSAC2020 dataset to the public.

Graph convolutional networks learn effective node embeddings that have proven to be useful in achieving high-accuracy prediction results in semi-supervised learning tasks, such as node classification. However, these networks suffer from the issue of over-smoothing and shrinking effect of the graph due in large part to the fact that they diffuse features across the edges of the graph using a linear Laplacian flow. This limitation is especially problematic for the task of node classification, where the goal is to predict the label associated with a graph node. To address this issue, we propose an anisotropic graph convolutional network for semi-supervised node classification by introducing a nonlinear function that captures informative features from nodes, while preventing oversmoothing. The proposed framework is largely motivated by the good performance of anisotropic diffusion in image and geometry processing, and learns nonlinear representations based on local graph structure and node features. The effectiveness of our approach is demonstrated on three citation networks and two image datasets, achieving better or comparable classification accuracy results compared to the standard baseline methods.

3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models. This benchmark provided a far stricter challenge than previous shape benchmarks. We have added 145 new models for use as a separate training set, in order to standardise the training data used and provide a fairer comparison. We have also included experiments with the FAUST dataset of human scans. All participants of the previous benchmark study have taken part in the new tests reported here, many providing updated results using the new data. In addition, further participants have also taken part, and we provide extra analysis of the retrieval results. A total of 25 different shape retrieval methods are compared.

We present a two stage framework for automatic video text removal to detect and remove embedded video texts and fill-in their remaining regions by appropriate data. In the video text detection stage, text locations in each frame are found via an unsupervised clustering performed on the connected components produced by the stroke width transform (SWT). Since SWT needs an accurate edge map, we develop a novel edge detector which benefits from the geometric features revealed by the bandlet transform. Next, the motion patterns of the text objects of each frame are analyzed to localize video texts. The detected video text regions are removed, then the video is restored by an inpainting scheme. The proposed video inpainting approach applies spatio-temporal geometric flows extracted by bandlets to reconstruct the missing data. A 3D volume regularization algorithm, which takes advantage of bandlet bases in exploiting the anisotropic regularities, is introduced to carry out the inpainting task. The method does not need extra processes to satisfy visual consistency. The experimental results demonstrate the effectiveness of both our proposed video text detection approach and the video completion technique, and consequently the entire automatic video text removal and restoration process.

In this paper, we propose a text detection method based on a feature vector generated from connected components produced via the stroke width transform. Several properties, such as variant directionality of gradient of text edges, high contrast with background, and geometric properties of text components jointly with the properties found by the stroke width transform are considered in the formation of feature vectors. Then, k-means clustering is performed by employing the feature vectors in a bid to distinguish text and non-text components. Finally, the obtained text components are grouped and the remaining components are discarded. Since the stroke width transform relies on a precise edge detection scheme, we introduce a novel bandlet-based edge detector which is quite effective at obtaining text edges in images while dismissing noisy and foliage edges. Our experimental results indicate a high performance for the proposed method and the effectiveness of our proposed edge detector for text localization purposes.

Model checking, a formal and automatic verification method, has been widely used to check specifications expressed not only as qualitative properties (e.g safety and liveliness), but also as quantitative properties (e.g. degree of reliability and reachability). In this paper, we present a method for probabilistic model checking of multi-agent systems specified by a probabilistic-epistemic logic PCTLK. We define transformations from probabilistic interpreted systems into Discrete-time Markov chains (DTMC) and from PCTLK formulae to PCTL formulae so that we are able to convert the problem of model checking PCTLK to the one of PCTL. The algorithm is implemented in the probabilistic model checker PRISM. Some properties, including agents' probabilistic knowledge, are verified and simulations are shown.

In this paper, we address the video completion problem for two general cases: 1) filling-in the missing regions of videos captured by a non-stationary camera, and 2) filling-in the missing part of video sequences recorded by a stationary camera. For each case, a novel video completion technique based on the bandlet transform is presented. In the first case, a priority-based exemplar algorithm, which applies the bandlet transform and its generated coefficients along with motion information, is used to fill-in the occluded moving object or the removed region. In the second case, our proposed method is followed by a foreground/background segmentation preprocessing step to generate moving objects and background frames in order to facilitate the video completion task. The technique fills-in the background frames after removing objects by means of a precise optimization in the bandlet transform domain. Then, the occluded part of a moving object is completed by a priority-based algorithm which applies frames' geometry properties using the bandlet transform. Our experimental results indicate that the proposed video completion technique maintains both the spatial and temporal consistency and also demonstrate the effectiveness of the bandlet transform in video completion.

We present a bandlet transform-based technique to complete missing parts of a video sequence captured with a static camera. The method is followed by a preprocessing step to separate the foreground which consists of moving objects and background frames in order to facilitate the video completion task. The technique considers two cases: 1) filling-in the background frames after removing objects, and 2) fillingin the occluded parts of a moving object. In the first case, a precise optimization in the bandlet domain is performed to complete the background video. In the second case, a priority based exemplar algorithm, which applies bandlet geometry properties, is used to fill-in the occluded moving object. Our experimental results indicate the effectiveness of the proposed video completion technique.

In this paper, we propose a nonrigid image registration technique by optimizing a generalized information-theoretic similarity measure using the quasi-Newton method as an optimization scheme and cubic B-splines for modeling the nonrigid deformation field between the fixed and moving 3-D image pairs. To achieve a compromise between the nonrigid registration accuracy and the associated computational cost, we implement a three-level hierarchical multiresolution approach such that the image resolution is increased in a coarse to fine fashion. Experimental results are provided to demonstrate the registration accuracy of our approach. The feasibility of the proposed method is demonstrated on a 3-D magnetic resonance data volume and also on clinically acquired 4-D CT image datasets.

We present a 3D mesh denoising method based on kernel density estimation. The proposed approach is able to reduce the over-smoothing effect and effectively remove undesirable noise while preserving prominent geometric features of a 3D mesh such as curved surface regions, sharp edges, and fine details. The experimental results demonstrate the effectiveness of the proposed approach in comparison to existing mesh denoising techniques.

In this paper, we present a hashing technique for 3D models using spectral graph theory and entropic spanning trees. The main idea is to partition a 3D triangle mesh into an ensemble of sub- meshes, then apply eigen-decomposition to the Laplace-Beltrami matrix of each sub-mesh, followed by computing the hash value of each sub-mesh. This hash value is defined in terms of spectral coefficients and Tsallis entropy estimate. The experimental results on a variety of 3D models demonstrate the effectiveness of the proposed technique in terms of robustness against the most common attacks including Gaussian noise, mesh smoothing, mesh compression, scaling, rotation as well as combinations of these attacks.

In this paper, we introduce an image alignment method by maximizing a Tsallis entopy-based divergence using a modified simultaneous perturbation stochastic approximation algorithm. Due to its convexity property, this divergence measure attains its maximum value when the conditional intensity probabilities between the reference image and the transformed target image are degenerate distributions. Experimental results are provided to show the registration accuracy of the proposed approach in comparison with existing entropic image alignment techniques.

We introduce a new weighted Laplace test statistic for software reliability growth modelling. The proposed model not only takes into account the activity in the system but also the proportion of reliability growth within the model. This generalized approach is defined as a weighted combination of a growth reliability model and a non-growth reliability model. Experimental results illustrate the effectiveness and the much improved performance of the proposed method in software reliability modelling.

We propose a robust and imperceptible spectral watermarking method for high rate embedding of a watermark into 3D polygonal meshes. Our approach consists of four main steps: (1) the mesh is partitioned into smaller sub-meshes, and then the watermark embedding and extraction algorithms are applied to each sub-mesh, (2) the mesh Laplacian spectral compression is applied to the sub-meshes, (3) the watermark data is distributed over the spectral coefficients of the compressed sub-meshes, (4) the modified spectral coefficients with some other basis functions are used to obtain uncompressed watermarked 3D mesh. The main attractive features of this approach are simplicity, flexibility in data embedding capacity, and fast implementation. Extensive experimental results show the improved performance of the proposed method, and also its robustness against the most common attacks including the geometric transformations, adaptive random noise, mesh smoothing, mesh cropping, and combinations of these attacks.

We introduce a new method to detect multiple outliers in high-dimensional datasets using the concepts of hierarchical clustering and principal component analysis. The proposed algorithm is computationally fast and robust to outliers detection. A comparative study with existing techniques is performed on both low and high dimensional datasets. Our experimental results demonstrate an improved performance of our algorithm in comparison with existing multivariate outlier detection techniques.

We present a vertex-based diffusion for 3-D mesh denoising by solving a nonlinear discrete partial differential equation. The core idea behind our proposed technique is to use geometric insight in helping construct an efficient and fast 3-D mesh smoothing strategy to fully preserve the geometric structure of the data. Illustrating experimental results demonstrate a much improved performance of the proposed approach in comparison with existing methods currently used in 3-D mesh smoothing.

We present a new scheme for digital watermarking and secure copyright protection of digital images using non-negative matrix factorization and singular value decomposition approaches. The proposed method improves the performance of the data embedding system effectively, and it is resistant to a variety of intentional attacks and normal visual processes. The experimental results clearly illustrate the much improved performance of the proposed watermarking methodology in comparison with existing techniques

Recognition of images and shapes has long been the central theme of computer vision. Its importance is increasing rapidly in the field of computer graphics and multimedia communication because it is difficult to process information efficiently without its recognition. In this paper, we propose a new approach for object matching based on a global geodesic measure. The key idea behind our methodology is to represent an object by a probabilistic shape descriptor that measures the global geodesic distance between two arbitrary points on the surface of an object. In contrast to the Euclidean distance which is more suitable for linear spaces, the geodesic distance has the advantage to be able to capture the intrinsic geometric structure of the data. The matching task therefore becomes a one-dimensional comparison problem between probability distributions which is clearly much simpler than comparing three-dimensional structures. Object matching can then be carried out by an information-theoretic dissimilarity measure calculations between geodesic shape distributions, and is additionally computationally efficient and inexpensive.

The importance of shape recognition is increasing rapidly in the field of computer graphics and multimedia communication because it is difficult to process information efficiently without its recognition. In this paper, we present a 3D object recognition approach based on a global geodesic measure. The key idea behind our methodology is to represent an object by a probabilistic shape descriptor that measures the global geodesic distance between two arbitrary points on the surface of an object. The geodesic distance has the advantage to be able to capture the intrinsic geometric structure of the data. Object matching can then be carried out by an information-theoretic dissimilarity measure calculations between geodesic shape distributions.

We present a novel nearest neighbor rule-based implementation of the structural risk minimization principle to address a generic classification problem. We propose a fast reference set thinning algorithm on the training data set similar to a support vector machine approach. We then show that the nearest neighbor rule based on the reduced set implements the structural risk minimization principle, in a manner which does not involve selection of a convenient feature space. Simulation results on real data indicate that this method significantly reduces the computational cost of the conventional support vector machines, and achieves a nearly comparable test error performance.

We present a feature-based object representation for topological modeling of three-dimensional illuminated surfaces. The proposed approach encodes an object into the Reeb graph concept from computational topology. This skeletal structure is based on the generalized height function in the light direction defined on the illuminated surface. In this paper, the topological properties of the proposed representation are analyzed in the Morse theoretic framework, and its close relationship to the shading problem is also highlighted. Some numerical simulations with synthetic and real 3D data are provided to demonstrate the potential of object singularities in topological modeling.

Based on nonparametric statistics, we propose robust variational filters for image denoising. The approach is a result of optimizing smooth statistical influence functionals subject to some noise constraints. Substantiating numerical examples are provided to demonstrate the potential and the good performance of the proposed algorithms in environmental image filtering.

We present a novel nearest neighbor rule-based implementation of the structural risk minimization principle to address a generic classification problem. We propose a fast reference set thinning algorithm on the training data set similar to a support vector machine approach. We then show that the nearest neighbor rule based on the reduced set implements the structural risk minimization principle, in a manner, which does not involve selection of a convenient feature space. Simulation results on real data indicate that this method significantly reduces the computational cost of the conventional support vector machines, and achieves a nearly comparable test error performance.

Image segmentation is a crucial step in computer vision, medical imaging and image processing. There has been recently an interest in a nonlinear partial differential equation based approach, motivated by a more systematic approach for image segmentation. In this paper, a novel active contour model expressed in terms of an energy functional is formulated in a calculus of variations framework. The key idea behind the proposed technique is to segment objects from the background of images that may have non-uniform brightness because of illumination. Simulation results showing a much improved performance of the proposed method in image segmentation are analyzed and illustrated.

Image singularities are prominent landmarks and their detection, recognition, and classification is a crucial step in image processing and computer vision. Such singularities carry important information for further operations, such as image registration, shape analysis, motion estimation, and object recognition. We propose a topological gradient descent flow for image singularities. The approach is expressed in the higher order variational framework as a minimizer of a variational integral involving the gradient and the Hessian matrix of the height function defined on a manifold. We demonstrate through numerical simulations the power of the proposed technique in preserving image singularities.

The high sensitivity of many specific filters to an accurate modeling of the noise that is to be removed led us to investigate the existence of a new class of filters using the theory of robust estimation. The latter class includes a large number of filters whose optimality when given a specific noise distribution is attained by merely adjusting weights. We also show that a convex combination of the mean and relaxed median filters exhibits many good properties. Some deterministic and asymptotic properties are studied, and comparisons with other filtering schemes are performed. Experimental results showing a much improved performance of the proposed filters in the presence of mixed Gaussian and heavy-tailed noise are analyzed and illustrated.

A connection between the maximum a posteriori (MAP) estimation and the variational formulation based on the minimization of a given variational integral subject to some noise constraints is established in this paper. A MAP estimator which uses a Markov or a maximum entropy random field model for the prior distribution can be viewed as a minimizer of a variational problem. Inspired by the maximum entropy principle, a nonlinear variational filter called improved entropic gradient descent flow is proposed. It minimizes a hybrid functional between the neg-entropy variational integral and the total variation subject to some noise constraints. Simulation results showing a much improved performance of the proposed filter in the presence of Gaussian and Laplacian noise are analyzed and illustrated.