Scene Graph Forecasting Using Neural Network-Based Methods
Doklady Mathematics · 2025-08 · 112 (1) · 239-245
DOI: 10.1134/s1064562425700334 ↗Kurz gefasst
Fachartikel in der Zeitschrift Doklady Mathematics, online erschienen am 02.03.2026. Verfasst von A. M. Trunova und 1 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Forecasting the future state of a scene is a key computer vision task needed to build systems capable of proactive perception and decision-making in changing environments. This work addresses the problem of forecasting future scene graphs, where, given a video and a sequence of past graphs, one must predict objects and their relations in subsequent frames. Unlike existing approaches limited to static perception, the proposed method, GraphCast, takes into account semantic vision-language features of objects and their temporal dynamics. We introduce a model architecture based on object-centric encoding with a foundation transformer model, interaction modeling via a biaffine relation classification head, and a specialized object presence classifier. In addition, a temporal convolution module is used to extract features and improve robustness to noise. Experiments on the STAR and Action Genome datasets demonstrate that the proposed architecture outperforms existing baselines.
Zitieren
APA
Trunova, A. M., & Yudin, D. A. (2025). Scene Graph Forecasting Using Neural Network-Based Methods. Doklady Mathematics, 112(1), 239-245. https://doi.org/10.1134/s1064562425700334
Vancouver
Trunova AM, Yudin DA. Scene Graph Forecasting Using Neural Network-Based Methods. Doklady Mathematics. 2025;112(1):239-245. doi:10.1134/s1064562425700334
BibTeX
@article{Trunova2025,
author = {Trunova, A. M. and Yudin, D. A.},
title = {Scene Graph Forecasting Using Neural Network-Based Methods},
journal = {Doklady Mathematics},
year = {2025},
volume = {112},
number = {1},
pages = {239--245},
doi = {10.1134/s1064562425700334}
}
EUVIMED