2023/05/15 · In this paper, we propose Di-Long, a new method that employs the distillation of a short-term trajectory model forecaster that guides a student network for ...

2024/03/15 · In this paper, we propose a novel method for multi-modal long-term trajectory prediction using knowledge distillation. III. OUR METHOD. A.

Abstract—Long-term trajectory forecasting is an important and challenging problem in the fields of computer vision, machine learning, and robotics.

Di-Long proposes a knowledge distillation framework for long-term trajectory prediction, achieving state-of-the-art performance.

2023/05/15 · Our approach involves training a student network to solve the long-term trajectory forecasting problem, whereas the teacher network from which ...

Distilling Knowledge for Short-to-Long Term Trajectory Prediction. S Das, G Camporese, S Cheng, L Ballan. IROS (oral), 2024. 3, 2024. Where Are My Neighbors ...

Distilling Knowledge for Short-to-Long Term Trajectory Prediction. S Das, G Camporese, L Ballan. arXiv 2023. [arXiv] [bib] [paper]. Empowering Convolutional ...

In this paper, we propose a new method dubbed Di-Long ("Distillation for Long-Term trajectory") for long-term trajectory forecasting, which is based on ...

Distilling Knowledge for Short-to-Long Term Trajectory Prediction ... Long-term trajectory forecasting is an important and challenging problem in the fields of ...

This is done in the specific context of trajectory forecasting, and we demonstrate that knowledge distillation can lead to effective predictions even when the ...