整理研究方向（1）【未完成】_icfinder: a ubiquitous approach todetecting illega-CSDN博客

这篇博客梳理了多个知名研究团队的工作，包括郑宇、林友芳、姚骅修、王韫博等团队。内容涵盖时空预测、元学习、时空数据挖掘、时间序列分析、计算机视觉等多个领域。各团队的研究涵盖了从论文发表到研究方向的转变，以及对未来的思考和心得。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

系列文章目录

Discovering Actual Delivery Locations from Mis-Annotated Couriers‘ Trajectories（ICDE2022) paper
TraSS: Efficient Trajectory Similarity Search Based on Key-Value DataStores (ICDE2022) paper 别人的论文笔记
Detecting Loaded Trajectories for Hazardous Chemicals Transportation (ICDE2022) paper
DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning (AAAI2022) paper
Shortening passengers’ travel time: A dynamic metro train scheduling approach using deep reinforcement learning (TKDE) paper 别人的论文笔记
Crowd-sensing Enhanced Parking Patrol using Sharing Bikes’ Trajectories (TKDE) paper 别人的论文笔记

Distributed Spatio-Temporal k Nearest Neighbors Join (SIGSPATIAL) (System) paper
JUST-Traj: A Distributed and Holistic Trajectory Data Management System (Demo Paper) (SIGSPATIAL) (System) paper
SALON: A Universal Stay Point-Based Location Analysis Platform (Demo paper) (SIGSPATIAL) (System) paper
ICFinder: A Ubiquitous Approach to Detecting Illegal Hazardous Chemical Facilities with Truck Trajectories (Short Paper) (SIGSPATIAL) paper
POI Alias Discovery in E-commerce Delivery Address Data using User Check-ins (Short Paper) (SIGSPATIAL) paper
Filling Delivery Time Automatically Based on Couriers’ Trajectories (TKDE) paper
Network-Wide Traffic States Imputation Using Self-interested Coalitional Learning (KDD) paper
MTrajRec: Map-Constrained Trajectory Recovery via Seq2Seq Multi-task Learning (KDD) paper
TrajMesa: A Distributed NoSQL-Based Trajectory Data Management System (TKDE) paper
Visual Cascade Analytics of Large-scale Spatiotemporal Data (IEEE TVCG) paper
AutoSTG: Neural Architecture Search for Predictions of Spatio-Temporal Graphs (WWW) paper
Fine-Grained Urban Flow Prediction (WWW) paper
Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network (AAAI) paper
Robust Spatio-Temporal Purchase Prediction via Deep Meta Learning (AAAI) paper

包括万怀宇，郭晟楠等人，为ASTGCN、STSGCN等作者团队

Traffic Inflow and Outflow Forecasting by Modeling Intra- and Inter-Relationship between Flows (TIST 2022)
DeepRoute+: Modeling Couriers’ Spatial-Temporal Behaviors and Decision Preferences for Package Pick-up Route Prediction (TIST) paper
Graph2Route: A Dynamic Spatial-Temporal Graph Neural Network for Pick-up and Delivery Route Prediction (KDD 2022)
GSNet: Learning Spatial-Temporal Correlations from Geographical and Semantic Aspects for Traffic Accident Risk Forecasting （AAAI 2021) paper
Pre-training Time-Aware Location Embeddings from Spatial-Temporal Trajectories (TKDE 2021) paper
Learning Dynamics and Heterogeneity of Spatial-Temporal Graph Data for Traffic Forecasting (TKDE 2021) paper
Package Pick-up Route Prediction via Modeling Couriers’ Spatial-Temporal Behaviors (ICDE 2021) paper

Multi-View Spatial-Temporal Graph Convolutional Networks with Domain Generalization for Sleep Stage Classification （2021 IEEE TNSRE) paper
HetEmotionNet: Two-Stream Heterogeneous Graph Recurrent Neural Network for Multi-modal Emotion Recognition （2021 ACM MM) paper
SalientSleepNet: Multimodal Salient Wave Detection Network for Sleep Staging (2021 IJCAI) paper

Flexible Hybrid Lenses Light Field Super-Resolution using Layered Refinement （2022 ACM MM)
Occlusion-aware Bi-directional Guided Network for Light Field Salient Object Detection (2021 ACM MM) paper
Removing Foreground Occlusions in Light Field using Micro-lens Dynamic Filter (2021 IJCAI) paper
Attention-based Multi-Level Fusion Network for Light Field Depth Estimation (2021 AAAI) paper
End-to-End Light Field Spatial Super-Resolution Network using Multiple Epipolar Geometry (2021 TIP) paper

DMVST和STDN的作者团队

Diversify and Disambiguate: Learning From Underspecified Data (短文在ICML 2022） paper
Transferable Neural Processes for Hyperparameter Optimization （短文在 NIPS 2019） paper
Few-Shot Learning With Weak Supervision （ICLR 2021 Workshop) paper

Improving Out-of-Distribution Robustness via Selective Augmentation (ICML) paper
Meta-Learning with Fewer Tasks through Task Interpolation (ICLR) paper
Improving Meta-learning for Low-resource Text Classiﬁcation and Generation via Memory Imitation (ACL) paper
Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer (KDD) paper
Artificial Intelligence for Retrosynthesis Prediction, Engineering (Engineering) paper

Meta-learning with an Adaptive Task Scheduler (NIPS) paper
Functionally Regionalized Knowledge Transfer for Low-resource Drug Discovery (NIPS) paper
Knowledge-Aware Meta-learning for Low-Resource Text Classification (EMNLP) paper
Improving Generalization in Meta-learning via Task Augmentation (ICML) paper
Relation-aware Meta-learning for E-commerce Market Segment Demand Prediction with Limited Records (WSDM) paper
Neural Utility Functions (AAAI) paper
Inductive Contextual Relation Learning for Personalization (TOIS) paper