3 papers
cs.CV2026
Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection
Peisheng Qian, Jie Xu, Xulei Yang +1
Incremental 3D object detection requires a detector to learn novel object classes while remembering previously learned ones over sequentially arriving data. Previous methods, prima…
cs.CV2025
Late-decoupled 3D Hierarchical Semantic Segmentation with Semantic Prototype Discrimination based Bi-branch Supervision
Shuyu Cao, Chongshou Li, Jie Xu +2
3D hierarchical semantic segmentation (3DHS) is crucial for embodied intelligence applications that demand a multi-grained and multi-hierarchy understanding of 3D scenes. Despite t…
cs.LG2025
CoIFNet: A Unified Framework for Multivariate Time Series Forecasting with Missing Values
Kai Tang, Ji Zhang, Hua Meng +5
Multivariate time series forecasting (MTSF) is a critical task with broad applications in domains such as meteorology, transportation, and economics. Nevertheless, pervasive missin…