Kothari, Parth AshitSifringer, BrianAlahi, Alexandre2021-05-112021-05-112021-05-11202110.1109/CVPR46437.2021.01530https://infoscience.epfl.ch/handle/20.500.14299/178002Human 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.trajectory forecastingsocial interactionsdiscrete choice modelsinterpretabilitycrowdshuman motiontext::conference output::conference proceedings::conference paper