Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis

Abstract

Multimodal prediction results are essential for trajectory prediction task as there is no single correct answer for the future. Previous frameworks can be divided into three categories: regression, generation and classification frameworks. However, these frameworks have weaknesses in different aspects so that they cannot model the multimodal prediction task comprehensively. In this paper, we present a novel insight along with a brand-new prediction framework by formulating multimodal prediction into three steps: modality clustering, classification and synthesis, and address the shortcomings of earlier frameworks. Exhaustive experiments on popular benchmarks have demonstrated that our proposed method surpasses state-of-the-art works even without introducing social and map information. Specifically, we achieve 19.2% and 20.8% improvement on ADE and FDE respectively on ETH/UCY dataset.

Cite

Text

Sun et al. "Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis." International Conference on Computer Vision, 2021. doi:10.1109/ICCV48922.2021.01300

Markdown

[Sun et al. "Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis." International Conference on Computer Vision, 2021.](https://mlanthology.org/iccv/2021/sun2021iccv-three/) doi:10.1109/ICCV48922.2021.01300

BibTeX

@inproceedings{sun2021iccv-three,
  title     = {{Three Steps to Multimodal Trajectory Prediction: Modality Clustering, Classification and Synthesis}},
  author    = {Sun, Jianhua and Li, Yuxuan and Fang, Hao-Shu and Lu, Cewu},
  booktitle = {International Conference on Computer Vision},
  year      = {2021},
  pages     = {13250-13259},
  doi       = {10.1109/ICCV48922.2021.01300},
  url       = {https://mlanthology.org/iccv/2021/sun2021iccv-three/}
}