教学课程资源库 更多>>

关键词： Layout   Accuracy   Deep learning   Classification algorithms   Cameras   Text analysis   Image analysis   Detectors   Computer science   Complexity theory   DIA   deep learning models   Pashto   SSD  

摘要： The paper explores the layout analysis and classification task of Pashto document images, a field with limited research due to the language's low-resource status. It uses Document Image Analysis (DIA) to detect one-column and two-column text blocks from Pashto documents captured using handheld cameras. A novel dataset containing real-world documents is annotated using bounding boxes to distinguish between one-column and two-column layouts. Layout analysis plays a vital role in Document Image Analysis (DIA) and answers questions about the nature of Document Images integral parts (components). These components are mainly text, graphics, and tabular data. The detection/identification of such elements is initially dependent on the general layout of a document. Textual columns are one of the basic layout structures present in document images. Such textual columns need identification as one-column or two-column before feeding the textual blocks into an Optical Character Recognition (OCR) system. Also, it becomes more crucial if the document images belong to a low-resource language like Pashto. Thus, this work contributes mainly in two aspects. First, it contributes to creating a dataset containing camera-captured document images with one-column and two-column patterns. Second, it proposes a deep learning model to identify/detect one-column and two-column textual blocks in the Pashto text images. The proposed model utilizes a reputed variant of a Faster Region-based Convolutional Neural Network (R-CNN) called single shot detector (SSD). The evaluation was done by examining the test set and a mean average precision (mAP) of 89% is achieved as a baseline.

关键词： Authentication   Public key   Privacy   Security   Protocols   Training   Performance evaluation   Data privacy   Computer science   Artificial intelligence   VANETs   anonymous credentials   decentralization   authentication   privacy preservation  

摘要： In Vehicular Ad-hoc Networks (VANETs), vehicles must authenticate their identities before accessing services. However, existing authentication schemes based on anonymous credentials still face single-point failure in multi-authority scenarios. In addition, in traditional anonymous credential schemes, the public key of credential authority is used directly to verify the credential, which may increase the risk of vehicle privacy being misused. To address these issues, we propose a decentralized threshold credential management system with fine-grained authentication for VANETs. The decentralized credential management architecture is proposed for VANETs with multiple credential authorities, each credential authority consists of multiple credential managers who issue credentials using the threshold mechanism, effectively solving the single-point failure. Based on this architecture, we design a fine-grained, privacy-preserving authentication scheme that allows vehicles to autonomously perform selective attribute disclosure, credential aggregation, and randomization before requesting verification from the Cloud Service Provider, thereby achieving a balance between privacy preservation and authentication efficiency. The security proofs and analysis show that our scheme satisfies the target security properties. Performance evaluations indicate that our scheme enables efficient, flexible credential management and authentication in VANETs while ensuring privacy preservation.

关键词： Semantics   Computational efficiency   Feature extraction   Training   Computational modeling   Biological system modeling   Visualization   Computer science   Web sites   Video on demand   Text-video retrieval   vision-and-language pre-training   CLIP model   consistent learning  

摘要： Adapting large-scale image-text pre-training models, e.g., CLIP, to the video domain represents the current state-of-the-art for text-video retrieval. The primary approaches involve transferring text-video pairs to a common embedding space and leveraging cross-modal interactions on specific entities for semantic alignment. Though effective, these paradigms entail prohibitive computational costs, leading to inefficient retrieval. To address this, we propose a simple yet effective method, Global-Local Semantic Consistent Learning (GLSCL), which capitalizes on latent shared semantics across modalities for text-video retrieval. Specifically, we introduce a parameter-free global interaction module to explore coarse-grained alignment. Then, we devise a shared local interaction module that employs several learnable queries to capture latent semantic concepts for learning fine-grained alignment. Furthermore, an Inter-Consistency Loss (ICL) is devised to accomplish the concept alignment between the visual query and corresponding textual query, and an Intra-Diversity Loss (IDL) is developed to repulse the distribution within visual (textual) queries to generate more discriminative concepts. Extensive experiments on five widely used benchmarks (i.e., MSR-VTT, MSVD, DiDeMo, LSMDC, and ActivityNet) substantiate the superior effectiveness and efficiency of the proposed method. Remarkably, our method achieves comparable performance with SOTA as well as being nearly 220 times faster in terms of computational cost. Code is available at: https://***/zchoi/GLSCL

关键词： Tuning   Transformers   Vectors   Adaptation models   Transfer learning   Speech processing   Natural language processing   Computer science   Computational modeling   Benchmark testing   Pre-trained language model   parameter-efficient tuning   memory mechanism  

摘要： Conventional fine-tuning encounters increasing difficulties given the size of current Pre-trained Language Models, which makes parameter-efficient tuning become the focal point of frontier research. Recent advances in this field is the unified tuning methods that aim to tune the representations of both multi-head attention (MHA) and fully connected feed-forward network (FFN) simultaneously, but they rely on existing tuning methods and do not explicitly model domain knowledge for downstream tasks. In this work, we propose memory-tuning, a novel unified parameter-efficient tuning method with task-specific knowledge learning, for both MHA and FFN components in Transformer blocks. We also prove that the well-known prefix tuning is also a kind of memory tuning, which further ensures memory tuning is a genuine unified tuning method. Experiments on eight benchmark data sets including both sentence- and token-level tasks demonstrate that our method outperforms the state-of-the-art baselines even full-tuning in most cases.

关键词： Emotion recognition   Oral communication   Commonsense reasoning   History   Information processing   Generators   Computers   Computer science   Visualization   Semantics   Emotion support conversation   strategy prompt reasoning  

摘要： An emotional support conversation (ESC) system aims to reduce users' emotional distress by engaging in conversation using various reply strategies as guidance. To develop instructive reply strategies for an ESC system, it is essential to consider the dynamic transitions of users' emotional states through the conversational turns. However, existing methods for strategy-guided ESC systems struggle to capture these transitions as they overlook the inference of fine-grained user intentions. This oversight poses a significant obstacle, impeding the model's ability to derive pertinent strategy information and, consequently, hindering its capacity to generate emotionally supportive responses. To tackle this limitation, we propose a novel dynamic strategy prompt reasoning model (DSR), which leverages sparse context relation deduction to acquire adaptive representation of reply strategies as prompts for guiding the response generation process. Specifically, we first perform turn-level commonsense reasoning with different approaches to extract auxiliary knowledge, which enhances the comprehension of user intention. Then we design a context relation deduction module to dynamically integrate interdependent dialogue information, capturing granular user intentions and generating effective strategy prompts. Finally, we utilize the strategy prompts to guide the generation of more relevant and supportive responses. DSR model is validated through extensive experiments conducted on a benchmark dataset, demonstrating its superior performance compared to the latest competitive methods in the field.

关键词： Security   Smart homes   Privacy   Protection   Internet of Things   Authorization   Thermostats   Computer science   Training   Sun   Smart home   self-sovereign delegation   forward-secure   integrity  

摘要： Aiming to provide people with great convenience and comfort, smart home systems have been deployed in thousands of homes. In this paper, we focus on handling the security and privacy issues in such a promising system by customizing a new cryptographic primitive to provide the following security guarantees: 1) fine-grained, privacy-preserving authorization for smart home users and integrity protection of communication contents;2) flexible self-sovereign permission delegation;3) forward security of previous messages. To our knowledge, no previous system has been designed to consider these three security and privacy requirements simultaneously. To tackle these challenges, we put forward the first-ever efficient cryptographic primitive called the Forward-secure Hierarchical Delegable Signature (FS-HDS) scheme for smart homes. Specifically, we first propose a new primitive, efficient Hierarchical Delegable Signature (HDS) scheme, which is capable of supporting partial delegation capability while realizing privacy-preserving authorization and integrity guarantee. Then, we present an FS-HDS for smart homes with the efficient HDS as the underlying building block, which not only inherits all the desirable features of HDS but also ensures that the past content integrity is not affected even if the current secret key is compromised. We provide comprehensively strict security proofs to prove the security of our proposed solutions. Its performance is also validated via experimental simulations to showcase its practicability and effectiveness.

关键词： Robots   Three-dimensional displays   Programming   Visualization   Programming profession   Mobile applications   Education   Usability   Python   Operating systems   Computational thinking   educational robotics (ER)   pre-university education   programming  

摘要： RoblockLLy is an educational robotics simulator designed for primary and secondary school students, whose goal is to increase their interest in science, technology, engineering, and mathematics. In the particular case of computer science, it allows developing computational thinking skills. It has been designed with ease of use in mind. This free tool is available through a web browser and does not need a complex installation or specific hardware requirements, allowing educational robotics to be introduced to a wide range of users by working on practical projects that will help them understand key concepts of robotics and programming. The effectiveness of RoblockLLy has been validated based on motivation, usability, and user experience criteria. The tool was validated with 212 secondary school students (12-16 years old). Specifically, motivation was measured with the Intrinsic Motivation Inventory, usability with the System Usability Scale, and user experience with the User Experience Questionnaire. Generally speaking, the results demonstrate that students perceived RoblockLLy as a novel and interesting tool. The ratings for usability were predominantly positive, although a few students indicated a preference for expert assistance. The overall rating of the user experience was positive as well, yet notable differences in attitudes toward motivation and usability were observed between genders.

关键词： Deepfakes   Feature extraction   Streaming media   Accuracy   Computer science   Visualization   Petroleum   Systematic literature review   Robustness   Real-time systems   Deepfake   multimedia   audio-video analysis   temporal analysis   media authenticity  

摘要： The rise of deepfake technology poses significant threats to the authenticity of content on social media. This research introduces Sach-AI, a pioneering framework for detecting various deepfakes in video, audio, and image data. Leveraging the power of deep neural networks, Sach-AI utilizes Eulerian Video Magnification combined with the ResNext architecture for enhanced detection. For video deepfakes, Long Short-Term Memory (LSTM) networks are integrated to improve classification tasks. This combination allows Sach-AI to effectively address the evolving, multimodal nature of deepfakes. The framework has been rigorously evaluated using diverse datasets, such as Celeb-DF and FaceForensics++, demonstrating its robustness and accuracy. Sach-AI achieved 97.76% accuracy in video deepfake detection, surpassing Intel's FakeCatcher, 99.13% accuracy in audio deepfake detection, and 93.64% accuracy in image deepfake detection. These results underscore Sach-AI's reliability in safeguarding digital media integrity against deceptive synthetic content in an era increasingly dominated by artificial technologies.

关键词： online STEM education   student engagement   qualitative research   thematic analysis   learning strategies   course design   peer interaction   digital learning environments   educational resources  

摘要： Student engagement is widely recognized as a critical factor influencing the success of engineering students in both traditional and online learning environments. Research indicates that engaged students develop a deeper understanding of course content, acquire practical skills, and maintain motivation in their field. Despite the theoretical importance of engagement, applying these concepts to specific online STEM courses presents challenges, particularly in mitigating student disengagement. This study addresses the need to better understand the characteristics of online STEM courses and student experiences that influence engagement. The study aims to identify the key factors influencing student engagement in online STEM education. By examining students' experiences and perceptions, the research seeks to provide insights into the strategies and activities that promote active learning and foster a sense of community in online courses. In-depth interviews were conducted with 33 undergraduate students enrolled in online computer science courses at Oregon State University. The interviews were transcribed and analyzed using thematic analysis to identify emerging themes and patterns related to student engagement. The findings reveal two main themes influencing student engagement in STEM courses: course characteristics & structure, and human interactions in learning. Course characteristics & structure, including resources, content delivery format, and course difficulty, impacted student engagement. Human interactions, both student-student and student-instructor/TA, played a crucial role in fostering engagement and a sense of community. The insights gained contribute to the understanding of effective teaching practices in online computer science education and provide valuable recommendations for designing engaging and inclusive online learning experiences that promote student success. The study highlights the importance of well-structured courses, diverse learning resources

关键词： Computer Science   Programming Languages,F.3.2  

摘要： We propose a new step-wise approach to proving observational equivalence, and in particular reasoning about fragility of observational equivalence. Our approach is based on what we call local reasoning. The local reasoning exploits the graphical concept of neighbourhood, and it extracts a new, formal, concept of robustness as a key sufficient condition of observational equivalence. Moreover, our proof methodology is capable of proving a generalised notion of observational equivalence. The generalised notion can be quantified over syntactically restricted contexts instead of all contexts, and also quantitatively constrained in terms of the number of reduction steps. The operational machinery we use is given by a hypergraph-rewriting abstract machine inspired by Girard's Geometry of Interaction. The behaviour of language features, including function abstraction and application, is provided by hypergraph-rewriting rules. We demonstrate our proof methodology using the call-by-value lambda-calculus equipped with (higher-order) state.