With the growing number of sophisticated deep learning algorithms and fake video generation applications, it is now possible to create highly realistic deepfake videos. Faceswap is the most commonly employed deepfakes...
详细信息
The presence of water in human life is crucial, and God has blessed humans much with its availability. This paper tries to reduce the amount of water that people use for washing in all aspects of daily life and instea...
详细信息
In this paper, we study the impact of various eaves-dropping attacks on the secrecy performance in wireless power transfer (WPT)-based secure multi-hop transmission. Since each node has a limited power supply, each no...
详细信息
Heritage sites are central to the cultural identity and historical narrative of a community. The Al Qattara Oasis, located in the United Arab Emirates (UAE), illustrates this function well. This study addresses the pr...
详细信息
This paper presents a new IPT compensation topology that can be operated at two different frequencies to form either primary series and secondary parallel (S-P) or primary parallel and secondary parallel (P-P) compens...
详细信息
This paper reports on the design and development of a customized Automated Optical Inspection (AOI) solution aimed at detecting defects in a production line related to the correct mounting of integrated circuits. Cont...
详细信息
Human action recognition in videos is an important task of computer vision that aims to automatically recognize and classify human actions in video sequences. However, accurately recognizing human actions can be chall...
Human action recognition in videos is an important task of computer vision that aims to automatically recognize and classify human actions in video sequences. However, accurately recognizing human actions can be challenging due to the complexity and variability of human motion and appearance. In this paper, we propose ActiViT, a novel approach for human action recognition in videos based on a Transformer architecture. Unlike existing methods that rely on convolutional or recurrent layers, our model is entirely based on the Transformer encoder, enabling us to leverage valuable information in action image patches features. We demonstrate that by dynamically selecting key patches guided by specific human poses, our model learns informative features useful for distinguishing between different actions. Our experimental results on real-world datasets convincingly demonstrate the effectiveness of our model and the importance of selecting discriminative key poses for action recognition.
The volume of network traffic data has become so big and complicated as a result of the development in Internet-based services that it is extremely difficult to process using typical data processing techniques. Due to...
详细信息
Handwriting verification, a subset of signature verification, involves using handwritten text to verify or authorize someone's identification. Although simple handwriting can serve as a signature, it is often modi...
详细信息
Identifying functional and non-functional requirements at an early phase is essential for project success. However, the requirements engineering community still lacks a comprehensive understanding of these requirement...
详细信息
ISBN:
(数字)9798331515331
ISBN:
(纸本)9798331515348
Identifying functional and non-functional requirements at an early phase is essential for project success. However, the requirements engineering community still lacks a comprehensive understanding of these requirements, which are often intertwined and expressed in natural language. Requirements classification is crucial for correctly extracting and organizing functional and non-functional requirements into specified categories. Automated classification reduces development costs, uncertainty, and misunderstanding. Machine learning (ML) and deep learning approaches have been applied for automatic classification in recent studies. This study conducts a comparative analysis by combining two publicly available PROMISE_exp and DOSSPRE datasets, which was classified as functional and non-functional classes of software requirements. First of all, we applied natural language processing (NLP) techniques to the requirements text to extract feature embeddings, followed by training four popular machine learning (ML) algorithms on these requirements. Inspired by the success of large language models (LLMs) in various tasks, we also fine-tuned four text-based pretrained (LLMs) and compared their performance with traditional ML models. Our empirical analysis shows that these models outperform traditional ML models on the combined dataset, offering developers an efficient method to detect and classify software requirements early.
暂无评论