ViPro: Enabling and Controlling Video Prediction for Complex Dynamical Scenarios using Procedural Knowledge

Autor:	Takenaka, Patrick, Maucher, Johannes, Huber, Marco F.
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	We propose a novel architecture design for video prediction in order to utilize procedural domain knowledge directly as part of the computational graph of data-driven models. On the basis of new challenging scenarios we show that state-of-the-art video predictors struggle in complex dynamical settings, and highlight that the introduction of prior process knowledge makes their learning problem feasible. Our approach results in the learning of a symbolically addressable interface between data-driven aspects in the model and our dedicated procedural knowledge module, which we utilize in downstream control tasks. Comment: accepted at NeSy2024, to be published in LNCS/LNAI
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2407.09537 Zobrazit plný text záznamu View this record from Arxiv