Search Results

Vision-language models, such as the Contrastive Language-Image Pre-Training (CLIP) model, have achieved significant success in image classification tasks. CLIP demonstrates high expressive power in few-shot learning scenarios due to its pairing of text ...

Recommender systems have become important tools in the daily life of human beings since they are powerful to address information overload, and discover relevant and useful items for users. The success of recommender systems largely relies on the ...

Broken object-level authorization (BOLA) vulnerabilities are among the most critical security risks facing database-backed applications. However, there is still a significant gap in our systematic understanding of these vulnerabilities. To bridge this ...

Artificial Intelligence (AI) has emerged as a key driver of precision agriculture, facilitating enhanced crop productivity, optimized resource management, and sustainable farming practices. Also, the expansion of genome sequencing technology has ...

In the field of Vision-Language Models (VLM), the Contrastive Language-Image Pretraining (CLIP) model has yielded outstanding performance on many downstream tasks through prompt tuning. By integrating image and text representations, CLIP exhibits zero-...

The IFDS algorithm is pivotal in solving field-sensitive data-flow problems. However, its conventional use of access paths for field sensitivity leads to the generation of a large number of data-flow facts. This causes scalability challenges in larger ...

Within-subject multimodal groupwise registration aims to align a group of multimodal images into a common structural space. Existing groupwise registration methods often rely on intensity-based similarity measures, but can be computationally ...

Unsupervised domain adaptation leverages knowledge from source domain(s)/task(s) to facilitate learning in target task, particularly in unsatisfied and complex scenarios with data scarcity and distribution shifts. This approach helps reduce the high costs ...

Context-free language reachability (CFL-reachability) is a fundamental formulation for program analysis with many applications. CFL-reachability analysis is computationally expensive, with a slightly subcubic time complexity concerning the number of ...

Credit risk classification is a crucial area in machine learning-enhanced financial decision support systems, and numerous studies have achieved significant progress. However, data in the modern financial landscape is inherently complex, ...

• An SHDA method is proposed for the few-sample CRC with few labels and class imbalance.
• The SHDA method can solve the three primary problems in CRC using only one model.
• An imbalanced data augmentation method is suggested to enhance ...

Context-free language (CFL) reachability is a fundamental framework for formulating program analyses. CFL-reachability analysis works on top of an edge-labeled graph by deriving reachability relations and adding them as labeled edges to the graph. ...

Deep reinforcement learning is used in various domains, but usually under the assumption that the environment has stationary conditions like transitions and state distributions. When this assumption is not met, performance suffers. For this reason, ...

Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying relation graph. Existing methods for learning this graph primarily focus on agent-pair relations, neglecting higher-...

Recommender systems are one of the most successful applications of using AI for providing personalized e-services to customers. However, data sparsity is presenting enormous challenges that are hindering the further development of advanced recommender ...

Knowledge distillation (KD) provides an efficient framework for transferring knowledge from a teacher model to a student model by aligning their predictive distributions. The existing KD methods adopt the same strategy as the teacher to formulate the ...

Variational policy optimization has become increasingly attractive to the reinforcement learning community because of its strong capability in uncertainty modeling and environment generalization. However, almost all existing studies in this area rely on ...

Bayesian deep learning (BDL) is an emerging field that combines the strong function approximation power of deep learning with the uncertainty modeling capabilities of Bayesian methods. In addition to those virtues, however, there are accompanying issues ...

Trust region policy optimization (TRPO) is one of the landmark policy optimization algorithms in deep reinforcement learning. Its purpose is to maximize a surrogate objective based on an advantage function, subject to the limited Kullback–Leibler ...

Multistream classification aims to predict the target stream by transferring knowledge from labeled source streams amid nonstationary processes with concept drifts. While existing methods address label scarcity, covariate shift, and asynchronous concept ...

In order to solve the defects of existing restoration algorithms due to the lack of sufficient contextual information, poor results in repairing large broken areas and uncontrollable restoration results, a dual-modal text-guided image restoration model ...