Search Results (29)

Video Anomaly Detection (VAD) is commonly formulated as a one-class classification task. Global motion, with temporal variations across most pixels within an object-centric region, e.g., walking, is typically regular, whereas localized motion, e.g., waving, can be ambiguous. Decoupled spatial and temporal jigsaw puzzles (DSTJiP) is a self-supervised method that learns discriminative representations by predicting the original order of spatially and temporally shuffled patches. However, DSTJiP’s uniform sampling and equal weighting do not assign stronger supervision to global-motion examples within the temporal objective. Consequently, the temporal supervision allocated to global-motion examples may become insufficient across training-data regimes with varying proportions of these examples, deteriorating VAD performance. Nevertheless, excessively strengthening such supervision also degrades performance. To address these issues, we propose spatial and extra temporal jigsaw puzzles (SETJiP) with two RGB-only training schemes that provide stronger and more conservative temporal supervision for global-motion examples, respectively. One scheme strengthens temporal supervision on these examples via additional temporal jigsaw puzzles. The other does so more conservatively by upweighting their temporal jigsaw puzzles. Experiments on four VAD benchmarks show that both schemes improve on DSTJiP and remain highly competitive with state-of-the-art methods. Full article

Grayscale-based Encryption-then-Compression (EtC) systems transform RGB images into the YCbCr color space, concatenate the components into a single grayscale image, and apply block permutation, block rotation/flipping, and block-wise negative–positive inversion. Because this pipeline separates color components and disrupts inter-channel statistics, existing extended jigsaw puzzle solvers (JPSs) have been regarded as ineffective, and grayscale-based EtC systems have been considered resistant to ciphertext-only visual reconstruction. In this paper, we present a practical ciphertext-only attack against grayscale-based EtC. The proposed attack introduces three key components: (i) Texture-Based Component Classification (TBCC) to distinguish luminance (Y) and chrominance (Cb/Cr) blocks and focus reconstruction on structure-rich regions; (ii) Regularized Single-Channel Edge Compatibility (R-SCEC), which applies Tikhonov regularization to a single-channel variant of the Mahalanobis Gradient Compatibility (MGC) measure to alleviate covariance rank-deficiency while maintaining robustness under inversion and geometric transforms; and (iii) Adaptive Pruning based on the TBCC-reduced search space that skips redundant boundary matching computations to further improve reconstruction efficiency. Experiments show that, in settings where existing extended JPS solvers fail, our method can still recover visually recognizable semantic content, revealing a potential vulnerability in grayscale-based EtC and calling for a re-evaluation of its security. Full article

Contemporary medical education is shifting from traditional, teacher-centred anatomy instruction toward interactive, student-centred, and clinically integrated approaches. The Jigsaw Method aligns with this shift by fostering collective competence, which is vital for effective clinical practice. This study aimed to introduce the jigsaw model to medical students and explore its perceived effectiveness in teaching anatomy. A phenomenological qualitative design was employed to explore the experiences of second-year medical students (n = 120) at the Faculty of Health-Care Sciences, Eastern University, Sri Lanka. Open-ended questions were used to elicit students’ reflections on the effectiveness of jigsaw learning. Thematic analysis was conducted using NVivo software (ver.14). Students reported generally favourable perceptions of the jigsaw method. Four major themes emerged: two described the positive impact of the approach—enhanced understanding through peer learning and improved interpersonal and communication skills; the remaining themes addressed challenges in implementation and suggestions for refinement. Participants appreciated the structured collaboration and positive interdependence fostered by the method. Moreover, students viewed the jigsaw technique as well-aligned with student-centred learning principles. The jigsaw method was perceived as an effective cooperative learning strategy that enhanced engagement, promoted active participation, and fostered teamwork in anatomy education. These findings support the integration of structured peer-based approaches into medical curricula to enrich students’ learning experiences. Full article

Precise and real-time estimation of the robotic arm’s position on the patient’s side is essential for the success of remote robotic surgery in Tactile Internet (TI) environments. This paper presents a prediction model based on the Transformer-based Informer framework for accurate and efficient position estimation, combined with a Four-State Hidden Markov Model (4-State HMM) to simulate realistic packet loss scenarios. The proposed approach addresses challenges such as network delays, jitter, and packet loss to ensure reliable and precise operation in remote surgical applications. The method integrates the optimization problem into the Informer model by embedding constraints such as energy efficiency, smoothness, and robustness into its training process using a differentiable optimization layer. The Informer framework uses features such as ProbSparse attention, attention distilling, and a generative-style decoder to focus on position-critical features while maintaining a low computational complexity of $\mathcal{O}(LlogL)$. The method is evaluated using the JIGSAWS dataset, achieving a prediction accuracy of over 90% under various network scenarios. A comparison with models such as TCN, RNN, and LSTM demonstrates the Informer framework’s superior performance in handling position prediction and meeting real-time requirements, making it suitable for Tactile Internet-enabled robotic surgery. Full article

Action Quality Assessment (AQA)—the task of evaluating how well human actions are performed—is essential in domains such as sports and medicine. Existing AQA methods typically rely on score regression following feature extraction but often neglect the ambiguity inherent in extracted features. In this work, we introduce a novel AQA framework that incorporates a modified attention module to better capture relevant information. Our approach segments video data into clips, extracts features using the I3D network, and applies attention mechanisms to highlight salient features while suppressing irrelevant ones. To assess feature quality, we employ score distribution regression and propose an uncertainty-aware score distribution learning strategy that models features as Gaussian distributions. We further leverage Variational Autoencoders (VAEs) to capture complex latent representations and quantify uncertainty. Extensive experiments on the MTL-AQA and JIGSAWS datasets demonstrate the effectiveness and robustness of our proposed method. Full article

Sentiment analysis is a vital component of natural language processing (NLP), enabling the classification of text into positive, negative, or neutral sentiments. It is widely used in customer feedback analysis and social media monitoring but faces a significant challenge: bias. Biases, often introduced through imbalanced training datasets, can distort model predictions and result in unfair outcomes. To address this, we propose a bias-aware sentiment analysis framework leveraging Bias-BERT (Bidirectional Encoder Representations from Transformers), a customized classifier designed to balance accuracy and fairness. Our approach begins with adapting the Jigsaw Unintended Bias in Toxicity Classification dataset by converting toxicity scores into sentiment labels, making it suitable for sentiment analysis. This process includes data preparation steps like cleaning, tokenization, and feature extraction, all aimed at reducing bias. At the heart of our method is a novel loss function incorporating a bias-aware term based on the Kullback–Leibler (KL) divergence. This term guides the model toward fair predictions by penalizing biased outputs while maintaining robust classification performance. Ethical considerations are integral to our framework, ensuring the responsible deployment of AI models. This methodology highlights a pathway to equitable sentiment analysis by actively mitigating dataset biases and promoting fairness in NLP applications. Full article

We propose an enhanced privacy-preserving method for image classification using ConvMixer, which is an extremely simple model that is similar in spirit to the Vision Transformer (ViT). Most privacy-preserving methods using encrypted images cause the performance of models to degrade due to the influence of encryption, but a state-of-the-art method was demonstrated to have the same classification accuracy as that of models without any encryption under the use of ViT. However, the method, in which a common secret key is assigned to each patch, is not robust enough against ciphertext-only attacks (COAs) including jigsaw puzzle solver attacks if compressible encrypted images are used. In addition, ConvMixer is less robust than ViT because there is no position embedding. To overcome this issue, we propose a novel block-wise encryption method that allows us to assign an independent key to each patch to enhance robustness against attacks. In experiments, the effectiveness of the method is verified in terms of image classification accuracy and robustness, and it is compared with conventional privacy-preserving methods using image encryption. Full article

Surgical gesture recognition is an important research direction in the field of computer-assisted intervention. Currently, research on surgical gesture recognition primarily focuses on robotic surgery, with a lack of studies in traditional surgery, particularly open surgery. Therefore, this study established a dataset simulating open surgery for research on surgical gesture recognition in the field of open surgery. With the assistance of professional surgeons, we defined a vocabulary of 10 surgical gestures based on suturing tasks in open procedures. In addition, this paper proposes a surgical gesture recognition method that integrates the R3D network with a multi-head attention mechanism (R3D-MHA). This method uses the R3D network to extract spatiotemporal features and combines it with the multi-head attention mechanism for relational learning of these features. The effectiveness of the R3D-MHA method in the field of open surgery gesture recognition was validated through two experiments: offline recognition and online recognition. The accuracy at the gesture instance level for offline recognition was 92.3%, and the frame accuracy for online recognition was 73.4%. Finally, its performance was further validated on the publicly available JIGSAWS dataset. Compared to other online recognition methods, the accuracy improved without using additional data. This work lays the foundation for research on surgical gesture recognition in open surgery and has significant applications in process monitoring, surgeon skill assessment and educational training for open surgeries. Full article

Virtual reality (VR) enables the development of virtual training frameworks suitable for various domains, especially when real-world conditions may be hazardous or impossible to replicate because of unique additional resources (e.g., equipment, infrastructure, people, locations). Although VR technology has significantly advanced in recent years, methods for evaluating immersion (i.e., the extent to which the user is engaged with the sensory information from the virtual environment or is invested in the intended task) continue to rely on self-reported questionnaires, which are often administered after using the virtual scenario. Having an objective method to measure immersion is particularly important when using VR for training, education, and applications that promote the development, fine-tuning, or maintenance of skills. The level of immersion may impact performance and the translation of knowledge and skills to the real-world. This is particularly important in tasks where motor skills are combined with complex decision making, such as surgical procedures. Efforts to better measure immersion have included the use of physiological measurements including heart rate and skin response, but so far they do not offer robust metrics that provide the sensitivity to discriminate different states (idle, easy, and hard), which is critical when using VR for training to determine how successful the training is in engaging the user’s senses and challenging their cognitive capabilities. In this study, electroencephalography (EEG) data were collected from 14 participants who completed VR jigsaw puzzles with two different levels of task difficulty. Machine learning was able to accurately classify the EEG data collected during three different states, obtaining accuracy rates of 86% and 97% for differentiating easy versus hard difficulty states and baseline vs. VR states. Building on these results may enable the identification of robust biomarkers of immersion in VR, enabling real-time recognition of the level of immersion that can be used to design more effective and translative VR-based training. This method has the potential to adjust aspects of VR related to task difficulty to ensure that participants are immersed in VR. Full article

Effective features play an important role in synthetic aperture radar (SAR) image interpretation. However, since SAR images contain a variety of terrain types, it is not easy to extract effective features of different terrains from SAR images. Deep learning methods require a large amount of labeled data, but the difficulty of SAR image annotation limits the performance of deep learning models. SAR images have inevitable geometric distortion and coherence speckle noise, which makes it difficult to extract effective features from SAR images. If effective semantic context features cannot be learned for SAR images, the extracted features struggle to distinguish different terrain categories. Some existing terrain classification methods are very limited and can only be applied to some specified SAR images. To solve these problems, a jigsaw puzzle self-supervised learning (JPSSL) framework is proposed. The framework comprises a jigsaw puzzle pretext task and a terrain classification downstream task. In the pretext task, the information in the SAR image is learned by completing the SAR image jigsaw puzzle to extract effective features. The terrain classification downstream task is trained using only a small number of labeled data. Finally, fully connected conditional random field processing is performed to eliminate noise points and obtain a high-quality terrain classification result. Experimental results on three large-scene high-resolution SAR images confirm the effectiveness and generalization of our method. Compared with the supervised methods, the features learned in JPSSL are highly discriminative, and the JPSSL achieves good classification accuracy when using only a small amount of labeled data. Full article

Medical education acknowledges our need to teach our physicians about “social determinants of health” and “health care disparities”. However, educators often lack actionable training to address this need. We describe a faculty development activity, a health disparities journal club, using the jigsaw strategy with the intent of increasing awareness, encouraging self-directed learning, and inspiring future teaching of the subject to health professional learners. We completed six workshops at six individual hospitals, with 95 total attendees in medicine and numerous other health professions. Our evaluation asked trainees to: report the number of journal articles about health disparities they had read, excluding the assigned journal club articles, in the past 12 months, and to predict future plans for reading about health disparities. In total, 28.9% responded they had “never read” a prior article on health or healthcare disparities, while 54.2% responded “1–5 articles”. Many (60%) reported they would continue to investigate this topic. Our experience has demonstrated the utility and positive impact of a “flipped classroom” jigsaw method, showing it can be used successfully in Inter-Professional (IPE) Faculty Development to increase active exposure and discussion of the content. Additionally, this method promotes individual reflection and enhances continued collective engagement. Full article

Nowadays, medical imaging has become an indispensable tool for the diagnosis of some pathologies and as a health prevention instrument. In addition, medical images are transmitted over all types of computer networks, many of them insecure or susceptible to intervention, making sensitive patient information vulnerable. Thus, image watermarking is a popular approach to embed copyright protection, Electronic Patient Information (EPR), institution information, or other digital image into medical images. However, in the medical field, the watermark must preserve the quality of the image for diagnosis purposes. In addition, the inserted watermark must be robust both to intentional and unintentional attacks, which try to delete or weaken it. This work presents a bio-inspired watermarking algorithm applied to retinal fundus images used in computer-aided retinopathy diagnosis. The proposed system uses the Steered Hermite Transform (SHT), an image model inspired by the Human Vision System (HVS), as a spread spectrum watermarking technique, by leveraging its bio-inspired nature to give imperceptibility to the watermark. In addition, the Singular Value Decomposition (SVD) is used to incorporate the robustness of the watermark against attacks. Moreover, the watermark is embedded into the RGB fundus images through the blood vessel patterns extracted by the SHT and using the luma band of Y’CbCr color model. Also, the watermark was encrypted using the Jigsaw Transform (JST) to incorporate an extra level of security. The proposed approach was tested using the image public dataset MESSIDOR-2, which contains 1748 8-bit color images of different sizes and presenting different Diabetic Retinopathy (DR). Thus, on the one hand, in the experiments we evaluate the proposed bio-inspired watermarking method over the entire MESSIDOR-2 dataset, showing that the embedding process does not affect the quality of the fundus images and the extracted watermark, by obtaining average Peak Signal-to-Noise Ratio (PSNR) values higher to 53 dB for the watermarked images and average PSNR values higher to 32 dB to the extracted watermark for the entire dataset. Also, we tested the method against image processing and geometric attacks successfully extracting the watermarking. A comparison of the proposed method against state-of-the-art was performed, obtaining competitive results. On the other hand, we classified the DR grade of the fundus image dataset using four trained deep learning models (VGG16, ResNet50, InceptionV3, and YOLOv8) to evaluate the inference results using the originals and marked images. Thus, the results show that DR grading remains both in the non-marked and marked images. Full article

Is it possible to experience healing and growth when you grieve? How and where do you find meaning again? During the COVID-19 pandemic, many people were looking for answers to these questions. This autoethnography explores how I experienced personal transformation through the method of Music and Imagery (MI) therapy in the midst of the pandemic and huge personal loss. This transformation also impacted my faith in Christ. Through documenting my journey using music listening, artwork, journaling, memories, and peers’ feedback, I realized just how possible it was to grow and find healing in trying times. I pieced all the information together like a jigsaw puzzle until I could see the complete picture. Full article

Composite patches are widely accepted as a useful practice for the repair of cracked aircraft components and the repair method is of vital importance to the final performance of the repaired structures. The present research experimentally studied the repair efficiency and processing stability of pre-cured, prepreg (including unidirectional and plain weave prepregs) and wet-layup methods for use on cracked Ti-alloy panels through the configuration of a butt joint bonded with a one-sided composite patch. The efficiency and stability of these repair methods were elaborately evaluated and compared via the load bearing behavior, the microstructure of the bonding interface, and the structural failure morphology through two batches of testing specimens. Typical patterns were found in load-displacement curves where the initial damage and ultimate bearing load points divided them into elastic-linear, damage propagation and complete fracture phases. Although the co-cure process of both unidirectional prepreg and wet-layup methods can form a jigsaw-like demarcation interface between the adhesive layer and the composite patch to achieve a good bonding force and a high recovery of loading performance, the latter presents porous patches with a high coefficient of variation in load-carrying capacity. Conversely, the pre-cured laminate and the plain weave prepreg patches failed to restore the mechanical properties owing to the weak bonding interface and the low axial patch strength, respectively. The unidirectional prepreg patch was proven to be the optimal repair method for the cracked metallic structures when balancing repair efficiency and processing stability. Full article

This study proposed two algorithms for reconstructing jigsaw puzzles by using a color compatibility feature. Two realistic application cases were examined: one involved using the original image, while the other did not. We also calculated the transformation matrix to obtain the real positions of each puzzle piece and transmitted the positional information to the robotic arm, which then put each puzzle piece in its correct position. The algorithms were tested on 35-piece and 70-piece puzzles, achieving an average success rate of 87.1%. Compared with the human visual system, the proposed methods demonstrated enhanced accuracy when handling more complex textural images. Full article