Interpretable Social Anchors for Human Trajectory Forecasting in Crowds
Abstract
Human trajectory forecasting in crowds, at its core, is a sequence prediction problem with specific challenges of capturing inter-sequence dependencies (social interactions) and consequently predicting socially-compliant multimodal distributions. In recent years, neural network-based methods have been shown to outperform hand-crafted methods on distance-based metrics. However, these data-driven methods still suffer from one crucial limitation: lack of interpretability. To overcome this limitation, we leverage the power of discrete choice models to learn interpretable rule-based intents, and subsequently utilise the expressibility of neural networks to model scene-specific residual. Extensive experimentation on the interaction-centric benchmark TrajNet++ demonstrates the effectiveness of our proposed architecture to explain its predictions without compromising the accuracy.
Cite
Text
Kothari et al. "Interpretable Social Anchors for Human Trajectory Forecasting in Crowds." Conference on Computer Vision and Pattern Recognition, 2021. doi:10.1109/CVPR46437.2021.01530Markdown
[Kothari et al. "Interpretable Social Anchors for Human Trajectory Forecasting in Crowds." Conference on Computer Vision and Pattern Recognition, 2021.](https://mlanthology.org/cvpr/2021/kothari2021cvpr-interpretable/) doi:10.1109/CVPR46437.2021.01530BibTeX
@inproceedings{kothari2021cvpr-interpretable,
title = {{Interpretable Social Anchors for Human Trajectory Forecasting in Crowds}},
author = {Kothari, Parth and Sifringer, Brian and Alahi, Alexandre},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2021},
pages = {15556-15566},
doi = {10.1109/CVPR46437.2021.01530},
url = {https://mlanthology.org/cvpr/2021/kothari2021cvpr-interpretable/}
}