A. Kotegar Karunakar

Goal: This study aims to explore the temporal dynamics of functional connectivity in drug-resistant focal epilepsy, focusing on Temporal Lobe Epilepsy (TLE) and Extra-Temporal Lobe Epilepsy (ETLE), using magnetoencephalography (MEG). Methods: Temporal metrics such as Change Between States, Entropy of Transition Patterns, Entropy of Transition Probabilities, Dwell Time, Stability, and Max L1 Distance derived from dynamic functional connectivity matrices were analyzed across eight frequency bands (delta, theta, alpha, beta, low gamma, mid gamma, high gamma and broadband) in TLE and ETLE patients. Results: Significant differences were observed between TLE and ETLE. ETLE exhibited more widespread and unpredictable connectivity transitions, while TLE demonstrated localized and structured patterns. Entropy metrics indicated higher randomness in ETLE, and dwell time analysis revealed shorter state persistence in ETLE compared to TLE. Conclusions: The findings highlight the potential of MEG-based temporal connectivity metrics in characterizing network disruptions in focal epilepsy.

Temporal Lobe Epilepsy (TLE), a common form of focal epilepsy, is associated with recurrent seizures originating in the temporal lobe, often leading to cognitive and psychological impairments. This study explores dynamic functional connectivity (dFC) patterns in TLE patients compared to Healthy Controls (HC) using resting-state Magnetoencephalography (MEG) data. dFC, which captures the temporal variability of brain networks, was analyzed across eight frequency bands (delta, theta, alpha, beta, low gamma, mid gamma, high gamma, and broadband) in 21 TLE patients and 21 HC. Nine dFC metrics, including state transitions, connectivity strength, network stability, and overall network movement, were derived using amplitude envelope correlations between 68 brain regions mapped to resting-state networks. Results reveal heightened variability in beta band transitions and increased entropy in delta band transitions, indicating unstable and diverse network configurations. TLE patients showed reduced dwell time in visual networks and increased dwell time in the dorsal attention network, suggesting compensatory mechanisms. Reduced connectivity in alpha and beta bands, coupled with increased variability in theta and low gamma bands, highlights widespread network instability. These findings emphasize dFC metrics as potential biomarkers for TLE, offering insights for targeted therapeutic interventions to stabilize brain dynamics.

Multi-object tracking (MOT) aims to establish connections between target objects throughout consecutive video frames to capture the complete trajectories of these moving objects. Due to the progress made in deep neural networks (DNN) and the growing need for intelligent video analysis, MOT has garnered considerable attention in “computer vision”. MOT exhibits scholarly and economic promise in various domains, including urban public security, military applications, self-driving technology, etc. Despite the diverse range of approaches researchers propose to address this challenge, it doesn’t remain easy due to changing objects’ appearances, significant occlusion, and non-linear motion patterns. Our review process provides fundamental insights into multi-object tracking. It covers essential aspects such as the basic workflow, different approaches to conducting the MOT task, challenges encountered, dataset requirements, evaluation metrics, and procedure for result submission to MOT and CodaLab servers. This study analyses the benefits and constraints of current strategies, techniques, and methods through a systematic review of the latest advancements in object detection and online private detection-based MOT algorithms published. Additionally, we present a quantitative comparison and analysis of experimental evidence of the top-performing MOT algorithms across various metrics. Finally, we propose future research directions by analyzing the commonalities among several methods demonstrating excellent performance.

Detecting AI-synthesized images remains a challenge due to their increasing realism. Traditional methods often fall short in addressing this evolving landscape where testing images can be produced by more powerful generative models or combined with various post-processing operations. To address this, we propose a robust method capitalizing on the distinctive global fingerprints present in real images from physical cameras and fixed patterns in synthesized images generated by generative models. Our approach builds on adapting camera fingerprinting initially designed for source camera identification, leveraging global fingerprints from the mid-frequency band. We rigorously evaluated our methodology through cross-model testing, demonstrating its exceptional generalization capability across different generative models and datasets. Our results, validated on the $DF^{3}$ and CNN-aug datasets with a broader range of generative models, highlight the method’s effectiveness in detecting AI-synthesized images and distinguishing between generative models. Comparisons with state-of-the-art methods show that our approach achieves superior performance, particularly in scenarios involving post-processing operations. This camera fingerprinting approach stands out for its resilience and accuracy, offering a promising solution for image forensics in addressing the challenges posed by sophisticated AI-generated content.