DySeT: A Dynamic Masked Self-distillation Approach for Robust Trajectory Prediction
The lack of generalization capability of behavior prediction models for autonomous vehicles
is a crucial concern for safe motion planning. One way to address this is via self-supervised …
is a crucial concern for safe motion planning. One way to address this is via self-supervised …
S-CVAE: Stacked CVAE for Trajectory Prediction With Incremental Greedy Region
Y Zhang, J Su, H Guo, C Li, P Lv… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Predicting accurate future trajectories of agents is essential for autonomous navigation in
complex scenarios. Although numerous work has made great progress on this goal, it is still …
complex scenarios. Although numerous work has made great progress on this goal, it is still …
T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving
Understanding the traffic scenes and then generating high-definition (HD) maps present
significant challenges in autonomous driving. In this paper, we defined a novel Traffic …
significant challenges in autonomous driving. In this paper, we defined a novel Traffic …
Casual inference-enabled graph neural networks for generalized fault diagnosis in industrial IoT system
Z Zhang, Q Li, S Liu, Z Zhang, W Chen, L Tang - Information Sciences, 2025 - Elsevier
Data-driven fault diagnosis plays a crucial role in diagnosing the operational status within
the Industrial Internet of Things (IIoT) systems. Although Graph Neural Networks (GNNs) …
the Industrial Internet of Things (IIoT) systems. Although Graph Neural Networks (GNNs) …
Curb Your Attention: Causal Attention Gating for Robust Trajectory Prediction in Autonomous Driving
Trajectory prediction models in autonomous driving are vulnerable to perturbations from non-
causal agents whose actions should not affect the ego-agent's behavior. Such perturbations …
causal agents whose actions should not affect the ego-agent's behavior. Such perturbations …
Causal Composition Diffusion Model for Closed-loop Traffic Generation
Simulation is critical for safety evaluation in autonomous driving, particularly in capturing
complex interactive behaviors. However, generating realistic and controllable traffic …
complex interactive behaviors. However, generating realistic and controllable traffic …
Diverse human motion prediction based on orthogonal basis vectors
H Tong, W Ding, Q Li, X Wang - … International Conference on …, 2025 - spiedigitallibrary.org
The diversity human motion prediction task predicts multiple future motion sequences from
historical data. Existing research uses likelihood-based sampling, but human motion's …
historical data. Existing research uses likelihood-based sampling, but human motion's …
Fine-Grained Distribution Guidance and Collaborative Adversarial Generation for Deep Learning Robustness to Adversarial Attacks
Abstract Model robustness is crucial for defending adversarial attacks. Recent defense
methods have employed teacher-student architecture to enhance the robustness of the …
methods have employed teacher-student architecture to enhance the robustness of the …