Short-form video content has gained importance as a popular form of digital media due to the rising popularity of social media platforms and the decreasing attention spans of consumers. However, a major obstacle to popularity detection in short-form content is the heterogeneous nature of the data, encompassing textual, visual, and metadata components. To tackle this challenge, we propose FUSEPOP, a robust multi-modal architecture. The proposed framework utilizes ResNet-50 for visual feature extraction and XLM-RoBERTa for encoding multilingual textual information. FUSEPOP employs a mutual information-based modality weighting mechanism with logarithmic smoothing and a 0.7 weight ceiling to balance contributions from each input stream. Furthermore, FUSEPOP implements a robust stacked generalization strategy trained via stratified 5-fold cross-validation. This approach utilizes a logistic regression meta-learner to dynamically synthesize predictions from random forest, XGBoost, and a neural network-based classifier. Experimental results show that this architecture significantly outperforms benchmark models, achieving an accuracy of 0.980 and an average F1-score of 0.964 on the feature configuration selected for this study, and remains competitive on a literature-aligned alternative configuration. These findings confirm that the proposed model successfully detects popularity on short-form social media content.

Medical image analysis plays a vital role in the early diagnosis of diseases. However, current deep learning approaches in this field have certain structural limitations. Although Convolutional Neural Networks (CNNs) demonstrate superior performance in extracting local features thanks to inductive bias, they fall short in capturing the global context. On the other hand, Vision Transformer (ViT) architectures are powerful in modeling global relationships; however, they have disadvantages such as loss of local detail, excessive data requirements, and high computational costs. CNN-ViT hybrid models typically use multi-branch structures that combine the outputs of independent and large backbones. This significantly increases the model's computational load and number of parameters, reducing efficiency and making it difficult to use in clinical applications. To overcome these limitations, this study proposes the original and efficient CoDeSwiT architecture. CoDeSwiT integrates local and global features into a low-cost architecture through its parallel arms designed on a single data stream and weighted fusion capability, unlike computationally intensive hybrid structures. The proposed architecture effectively reduces dimensions using the modern ConvNeXt stem for rich feature representation, while integrating the Swin Transformer encoder to model the global context hierarchically and computationally efficiently. The Depthwise Separable Convolution (DWS) and Squeeze-and-Excitation (SE) local attention branch, designed in parallel with the Transformer stream in the architecture, ensures the capture of fine texture details and local features. The outputs of these heterogeneous branches are fused through a learnable gating mechanism, unlike standard static fusion operations in the literature. The gating mechanism dynamically determines and weights the diagnostic importance of local or global information for each image sample, enabling the model to adaptively focus on critical findings. The effectiveness of the proposed architecture was evaluated on three comprehensive datasets with different modalities: the Alzheimer MRI dataset, the Chest X-Ray dataset, and the Tuberculosis dataset. Experimental results show that CoDeSwiT outperforms state-of-the-art (SOTA) transfer learning models based on CNN and ViT, achieving accuracy rates of 96.46% on the Alzheimer MRI dataset, 96.84% on the Chest X-Ray dataset, and 99.67% on the Tuberculosis dataset. CoDeSwiT, which contains approximately 28 million parameters, exhibits a computationally efficient structure compared to large-scale architectures in the literature. The model, which achieves a processing time of 2.21 ms per image, has been observed to have the potential to offer an effective solution for supporting fast and accurate diagnosis processes in clinical environments with limited hardware resources.

Background/Objectives: Dental caries is one of the most common oral diseases worldwide, and early diagnosis is essential for effective treatment. However, detecting carious lesions in panoramic radiographs is challenging because of low image contrast, anatomical complexity, and overlapping structures. This study aimed to develop an improved object detection framework for dental caries localization in panoramic radiographs. Methods: A modified YOLOv8 architecture was developed by integrating ConvNeXtV2 blocks into the Cross-Stage Partial (C2f) modules to enhance feature extraction and gradient propagation. To improve detection performance and reduce overfitting, key training hyperparameters were optimized using a genetic algorithm. The proposed model was evaluated on a dataset of 474 panoramic dental radiographs annotated by experts using bounding boxes. Results: The optimized model achieved a box precision of 78.4%, a recall of 53.6%, and a mean average precision at 50% intersection-over-union threshold (AP50) of 62.6%. Compared with the baseline YOLOv8 model, the proposed approach improved precision and AP50. Visual and quantitative analyses demonstrated that the ConvNeXtV2-enhanced architecture enabled more accurate localization of carious regions. Conclusions: The results indicate that combining ConvNeXtV2-based architectural enhancement with genetic algorithm-based hyperparameter optimization is an effective strategy for dental caries localization in panoramic radiographs. Although recall remains a limitation, the proposed framework shows potential as a computer-aided diagnostic tool for supporting clinical caries assessment.