Skip to yearly menu bar Skip to main content


Don't Pour Cereal into Coffee: Differentiable Temporal Logic for Temporal Action Segmentation

Ziwei Xu · Yogesh Rawat · Yongkang Wong · Mohan Kankanhalli · Mubarak Shah

Hall J (level 1) #800

Keywords: [ neurosymbolic methods ] [ Temporal action segmentation ] [ linear temporal logic ]


We propose Differentiable Temporal Logic (DTL), a model-agnostic framework that introduces temporal constraints to deep networks. DTL treats the outputs of a network as a truth assignment of a temporal logic formula, and computes a temporal logic loss reflecting the consistency between the output and the constraints. We propose a comprehensive set of constraints, which are implicit in data annotations, and incorporate them with deep networks via DTL. We evaluate the effectiveness of DTL on the temporal action segmentation task and observe improved performance and reduced logical errors in the output of different task models. Furthermore, we provide an extensive analysis to visualize the desirable effects of DTL.

Chat is not available.