基于视觉模型的行人动作预期分析
Analysis over vision-based models for pedestrian action anticipation
AI总结：
本文围绕基于视觉的行人动作预期，提出多种CNN与Transformer时空架构，重点分析模型预测的可解释性，指出即使量化结果正确也可能缺乏类人解释，强调需加强可解释性研究。
摘要：
在自动驾驶车辆前方预期人类动作是一项具有挑战性的任务。近期有多篇论文提出了模型架构，通过结合多种输入特征来预测行人过街动作以解决该问题。本文特别聚焦于使用行人场景图像作为输入特征。我们提出了几种时空模型架构，利用标准CNN和Transformer模块作为行人动作预期的骨干网络。然而，本文的目标并非超越最先进的基准，而是分析这些模型的正确预测与错误预测。因此，我们针对基于视觉的Transformer模型在行人动作预测场景中的可解释性提供了见解。我们将重点展示模型能够取得正确量化结果但在定性上无法提供类人解释的案例，强调在行人动作预期问题中投入可解释性研究的重要性。
英文摘要：
Anticipating human actions in front of autonomous vehicles is a challenging task. Several papers have recently proposed model architectures to address this problem by combining multiple input features to predict pedestrian crossing actions. This paper focuses specifically on using images of the pedestrian's context as an input feature. We present several spatio-temporal model architectures that utilize standard CNN and Transformer modules to serve as a backbone for pedestrian anticipation. However, the objective of this paper is not to surpass state-of-the-art benchmarks but rather to analyze the positive and negative predictions of these models. Therefore, we provide insights on the explainability of vision-based Transformer models in the context of pedestrian action prediction. We will highlight cases where the model can achieve correct quantitative results but falls short in providing human-like explanations qualitatively, emphasizing the importance of investing in explainability for pedestrian action anticipation problems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
