Explainable Molecular Property Prediction: Aligning Chemical Concepts with Predictions via Language Models [0.03%]
可解释的分子性质预测：通过语言模型对齐化学概念与预测结果
Zhenzhong Wang,Zehui Lin,Wanyu Lin et al.
Zhenzhong Wang et al.
Providing explainable molecular property predictions is critical for many scientific domains, such as drug discovery and material science. Though transformer-based language models have shown great potential in accurate molecular property pr...
Generalized Distribution Aggregation Protocol for Federated Statistical Heterogeneity [0.03%]
用于联合统计异质性的广义分布聚合协议
Mingwei Xu,Xiaofeng Cao,Ivor W Tsang et al.
Mingwei Xu et al.
Federated heterogeneity refers to the disparities in data distributions, model architectures, and communication capabilities across various devices or institutional entities. In real-world scenarios, statistical heterogeneity can often lead...
Exploring and Tailoring the Test-Time Augmentation for Sequential Recommendation [0.03%]
探索和定制序列推荐的测试时间数据增强方法
Yizhou Dang,Enneng Yang,Yuting Liu et al.
Yizhou Dang et al.
Data augmentation is an effective technique for tackling data sparsity in sequential recommendation (SR). Existing methods generate new data during the model training to improve the performance. However, deploying them on a backbone model r...
OmniHD-Scenes: A Next-Generation Multimodal Dataset for Autonomous Driving [0.03%]
OmniHD-Scene：用于自动驾驶的下一代多模态数据集
Lianqing Zheng,Long Yang,Qunshu Lin et al.
Lianqing Zheng et al.
The rapid advancement of deep learning has intensified the need for comprehensive data for use by autonomous driving algorithms. High-quality datasets are crucial for the development of effective data-driven autonomous driving solutions. Ne...
Thermal3D-GS: Physics-induced 3D Gaussians for Thermal Infrared Novel-view Synthesis with a Large-Scale Dataset [0.03%]
基于物理的热红外图像大规模数据集和新型视角合成三维高斯模型(Thermal3D-GS)
Qian Chen,Shihao Shu,Heng Sun et al.
Qian Chen et al.
Thermal infrared imaging has attracted widespread attention in many fields due to the advantages of all-weather imaging and strong penetration. However, existing methods for thermal infrared novel-view synthesis often produce results with c...
Bo Peng,Zichuan Wang,Sheng Yu et al.
Bo Peng et al.
Deep learning based face-swap videos, widely known as deepfakes, have drawn wide attention due to their threat to information credibility. Recent works mainly focus on the problem of deepfake detection that aims to reliably tell deepfakes a...
Lei-Lei Li,Jianwu Fang,Junbin Xiao et al.
Lei-Lei Li et al.
Understanding traffic accident scenes is a long-standing research for vision-based safe driving. It seeks to answer why accidents occur, how near-crash scenes develop, and what the key elements of an accident are. This research is challengi...
A Personalized and Privacy-Preserving Federated Transformer Framework for Multilingual Sentiment Analysis [0.03%]
一种用于多语言情感分析的个性化和保护隐私的联邦Transformer框架
Jothi Prakash V,Arul Antran Vijay S,Gopikrishnan Sundaram
Jothi Prakash V
Personalized federated learning for multilingual sentiment analysis poses significant challenges arising from linguistic heterogeneity, non-IID data distributions, and strict privacy requirements. This paper proposes FedPerX, a federated tr...
Boosting Learning Efficiency in Few-Shot Tasks With Layer-Adaptive PID Control [0.03%]
基于层自适应PID控制的Few-shot任务学习效率提升方法
Pengfei Zhang,Xinde Li,Le Yu et al.
Pengfei Zhang et al.
Few-shot learning seeks to recognize novel classes from limited examples. Model-agnostic meta-learning (MAML), known for its simplicity and flexibility, learns an effective initialization for fast adaptation in data-scarce settings. However...
Shaobo Hu,Hui Huang,Nan Zhang et al.
Shaobo Hu et al.
Although multiview learning methods have been widely studied, they mostly focus on improving accuracy while ignoring decision uncertainty. In the real world, multiview data often encounters misalignment issues, resulting in conflictive inst...