研究方向
时间序列与时空数据挖掘
基于注意力机制的时间序列预测、交通流量预测与网络异常检测。
该方向面向序列数据与时空数据构建深度模型。相关工作包括:面向时间序列预测的可调序列注意力机制(Expert Systems with Applications)、基于注意力的时空融合交通流量预测网络(WISA),以及基于注意力机制与 LSTM 的网络流量异常检测。
主要主题
相关成果 (6)
- 01
SHARP: Structure-aware Heterogeneous Attention with Rotational Processing for Conversational Sentiment Quadruple Analysis
期刊论文CCF-C中科院一区 - 02
An Adjustable Series-wise Attention Mechanism for Time Series Forecasting
期刊论文CCF-C中科院一区 - 03
CSAI: Cross- and Self-Attention Interaction for Compositional Text-to-Image Generation
会议论文CCF-CEI新新 - 04
Improve Visual Grounding with Dynamic Gating and Dual Stream Attention
会议论文CCF-CEI - 05
Multi-relational Context Learning with Cross-Attention Augmentation for Human Object Interaction Detection
会议论文CCF-CEI优秀论文奖 - 06
Attention-Based Spatial-Temporal Fusion Networks for Traffic Flow Prediction
会议论文CCF-CEI
