Temporal Mask-Embedding Learning and Query-Refined Head Network for Visual Tracking [0.03%]
用于视觉跟踪的时序掩码嵌入学习和查询细化头部网络
Jiabing Xiong,Yuejie Lu,Qiang Ling
Jiabing Xiong
Recent trackers aim to improve tracking performance by propagating temporal information across consecutive frames. However, they usually rely on a single compressed temporal token, which restricts information capacity and may lead to inform...
TMMSAM2: Tracker-Aided Multitemporal Memory SAM2 for Hyperspectral Object Tracking [0.03%]
基于跟踪器的多时相记忆SAM2高光谱目标跟踪方法
Xiyou Fu,Ting Zhang,Xiaoyu Zhang et al.
Xiyou Fu et al.
Segment Anything Model 2 (SAM2) demonstrates outstanding performance in prompt-based visual segmentation. However, directly applying it to hyperspectral object-tracking tasks still faces numerous challenges. This article proposes TMMSAM2, a...
Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph [0.03%]
基于标签增强和特征图的颗粒球模糊多邻域噪声抵抗特征选择方法
Lin Sun,Wenjuan Du,Weiping Ding et al.
Lin Sun et al.
Due to the increasing volume of multilabel data, interactions and complementarity among features are not fully explored in feature selection; the descriptive differences of labels to samples are frequently overlooked, and the abundant featu...
Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework [0.03%]
利用ARTMAP模型对抗进化垃圾信息：一种健壮的在线检测框架
Michael Shi,Jiao Yin,Chee Peng Lim et al.
Michael Shi et al.
Email spam detection is a core cybersecurity challenge in which data samples (emails) normally arrive as a continuous, nonstationary stream. The corresponding data samples are often noisy or deliberately obfuscated. To effectively classify ...
HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems [0.03%]
基于超图神经网络的带权最大可满足性问题求解方法
Qiyue Chen,Shaolin Tan,Suixiang Gao et al.
Qiyue Chen et al.
Graph neural networks (GNNs) have shown promising performance in solving both Boolean satisfiability (SAT) and maximum satisfiability (MaxSAT) problems due to their ability to efficiently model and capture the structural dependencies betwee...
Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification [0.03%]
基于D-S证据理论的多源信息融合中基本概率分配的否定及在模式分类中的应用研究
Xingyu Liu,Linlin Fan,Xuekai Wei et al.
Xingyu Liu et al.
In the construction of complex decision-making systems, which often involve uncertainties from multiple sources of information, effectively expressing the uncertainty of information remains an unresolved issue. Therefore, on the basis of De...
Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning [0.03%]
基于驾驶员风险承受能力的人机协作安全轨迹规划方法
Mengqi Zhang,Wanzhong Zhao,Chunyan Wang et al.
Mengqi Zhang et al.
The primary goal of human-machine collaborative driving is to improve driving safety, and the inconsistent tracking goals between humans and machines are one of the main factors causing safety accidents. Therefore, this article proposes a h...
A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction [0.03%]
基于预训练模型和模糊图网络的药物相互作用预测统一微调框架
Zhuo Chen,Xiaofeng Man,Chao Sun et al.
Zhuo Chen et al.
Combination therapy has become increasingly prevalent in modern clinical practice, yet the concomitant issue of drug-drug interactions (DDIs) poses significant challenges to medication safety. Accurate DDI prediction is therefore crucial fo...
Self-Supervised Continuous Dynamic Graph Representation Learning via Hawkes Processes [0.03%]
基于霍克斯过程的自监督连续动态图表示学习方法
Ruyue Liu,Rong Yin,Xingrui Zhou et al.
Ruyue Liu et al.
Dynamic graph representation learning (DGRL) has garnered significant attention due to its prevalence in real-world applications. However, existing methods often rely on labeled data for training, which can be costly. Furthermore, these met...
Yao Zhang,Ke Wang,Jun Tang et al.
Yao Zhang et al.
As one of the classical strategies for positive-unlabeled (PU) learning, the cost-sensitive methods achieve binary classification by minimizing the overall risk. To achieve this goal, the class prior is usually exploited to guide model lear...