3 papers
cs.CV2026
ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow
Jiekai Wu, Rong Fu, Chuangqi Li +9
Remote sensing segmentation in real deployment is inherently continual: new semantic categories emerge, and acquisition conditions shift across seasons, cities, and sensors. Despit…
cs.LG2026
FedDis: A Causal Disentanglement Framework for Federated Traffic Prediction
Chengyang Zhou, Zijian Zhang, Chunxu Zhang +4
Federated learning offers a promising paradigm for privacy-preserving traffic prediction, yet its performance is often challenged by the non-identically and independently distribut…
cs.CV2025
Breaking the Passive Learning Trap: An Active Perception Strategy for Human Motion Prediction
Juncheng Hu, Zijian Zhang, Zeyu Wang +3
Forecasting 3D human motion is an important embodiment of fine-grained understanding and cognition of human behavior by artificial agents. Current approaches excessively rely on im…