The ADE/FDE metrics for various approaches compared to OV-SKTGCNN are displayed. The remaining models utilized the best 20 samples for evaluation. Every model predicts the following 12 frames based on 8 input frames. OV-SKTGCNN has the best average error on both ADE and FDE criteria. The lower, the better.
收藏NIAID Data Ecosystem2026-05-02 收录
数据链接：
官方服务：
资源简介：
The ADE/FDE metrics for various approaches compared to OV-SKTGCNN are displayed. The remaining models utilized the best 20 samples for evaluation. Every model predicts the following 12 frames based on 8 input frames. OV-SKTGCNN has the best average error on both ADE and FDE criteria. The lower, the better.
创建时间：
2025-06-09
