In recent e-commerce, deals in agricultural products have also increased. The service of direct farm delivery displays each farmer’s photo to present the farm producer’s information. Their photos are composed of different elements of each subject. We focus on the effects of these various elements, such as farmers’ gender, age, facial expressions, and agricultural products. This study reports the effects of different photos composed of each element.
Video captioning stands at the intersection of computer vision and natural language processing, presenting unique challenges in interpreting dynamic visual content and generating coherent textual descriptions. Traditional approaches often struggle with capturing the temporal intricacies and complex interactions inherent in video data. This paper introduces the (STG-VC), a novel framework designed to enhance the accuracy and contextuality of video captions. By representing videos as spatio-temporal graphs, the STG-VC model captures detailed interactions and temporal dynamics that conventional sequence-based methods often overlook. The core of the model consists of a graph transformer encoder that processes these graphs to produce rich contextual embeddings. A sophisticated caption generation decoder then translates these embeddings into descriptive, accurate captions. We evaluate the STG-VC model across several challenging datasets, including YouCook2, Flickr30k, and Activity Net, where it demonstrates superior performance in generating contextually relevant and temporally coherent captions compared to existing state-of-the-art methods. This work not only advances the technology of video captioning but also opens new avenues for future research in multimedia content analysis.
We have developed our previous work by focusing on the types of fetal malformation cases collected from the Children’s Hospital of the Ministry of Health in the Syrian Arab Republic during the period 2020–2023. These cases were classified into four categories: the first is moderate to severe malformations, which represent about 4
Forest fires pose significant risks to ecosystems, biodiversity, and human life, exacerbated by climate change and extreme weather events. Traditional detection methods often face limitations in efficiency, cost, and adaptability to complex environments. This study introduces SE-VGG16, a modified VGG16-based convolutional neural network (CNN) enhanced with Squeeze-and-Excitation Blocks (SEBlocks). The proposed model aims to improve feature representation, enabling accurate detection of small-scale flames and smoke under dense vegetation and varying environmental conditions. We evaluated the model performance using a diverse Kaggle dataset, demonstrating superior accuracy (98
Energy consumption has become crucial in every aspect of our lives. Researchers proposed how to cut down energy usage in various fields, specifically in computer science. New solutions for green data centers as well as placing energy-aware software within each architectural layer from the cloud through the edge to the device may result in visible energy reduction and more energy-efficient processing. In this article, we present results of performance and energy investigation of web/server request processing scenarios implemented in Spring framework using imperative and reactive paradigms respectively. Both approaches were tested using various application models – request processing with database operations as well as request processing that involves compute-intensive operations. Tests were performed for both static and dynamically changing client load. We investigated how different paradigms affect performance and energy usage and determined that while in all considered cases the reactive processing framework consumes more energy per request it provides almost faultless processing and continuous stability under a growing load.
