Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Linok, Sergey, Semenov, Vadim, Trunova, Anastasia, Bulichev, Oleg, Yudin, Dmitry
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.03581
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909602677784576
author Linok, Sergey
Semenov, Vadim
Trunova, Anastasia
Bulichev, Oleg
Yudin, Dmitry
author_facet Linok, Sergey
Semenov, Vadim
Trunova, Anastasia
Bulichev, Oleg
Yudin, Dmitry
contents The analysis of events in dynamic environments poses a fundamental challenge in the development of intelligent agents and robots capable of interacting with humans. Current approaches predominantly utilize visual models. However, these methods often capture information implicitly from images, lacking interpretable spatial-temporal object representations. To address this issue we introduce DyGEnc - a novel method for Encoding a Dynamic Graph. This method integrates compressed spatial-temporal structural observation representation with the cognitive capabilities of large language models. The purpose of this integration is to enable advanced question answering based on a sequence of textual scene graphs. Extended evaluations on the STAR and AGQA datasets indicate that DyGEnc outperforms existing visual methods by a large margin of 15-25% in addressing queries regarding the history of human-to-object interactions. Furthermore, the proposed method can be seamlessly extended to process raw input images utilizing foundational models for extracting explicit textual scene graphs, as substantiated by the results of a robotic experiment conducted with a wheeled manipulator platform. We hope that these findings will contribute to the implementation of robust and compressed graph-based robotic memory for long-horizon reasoning. Code is available at github.com/linukc/DyGEnc.
format Preprint
id arxiv_https___arxiv_org_abs_2505_03581
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DyGEnc: Encoding a Sequence of Textual Scene Graphs to Reason and Answer Questions in Dynamic Scenes
Linok, Sergey
Semenov, Vadim
Trunova, Anastasia
Bulichev, Oleg
Yudin, Dmitry
Computer Vision and Pattern Recognition
The analysis of events in dynamic environments poses a fundamental challenge in the development of intelligent agents and robots capable of interacting with humans. Current approaches predominantly utilize visual models. However, these methods often capture information implicitly from images, lacking interpretable spatial-temporal object representations. To address this issue we introduce DyGEnc - a novel method for Encoding a Dynamic Graph. This method integrates compressed spatial-temporal structural observation representation with the cognitive capabilities of large language models. The purpose of this integration is to enable advanced question answering based on a sequence of textual scene graphs. Extended evaluations on the STAR and AGQA datasets indicate that DyGEnc outperforms existing visual methods by a large margin of 15-25% in addressing queries regarding the history of human-to-object interactions. Furthermore, the proposed method can be seamlessly extended to process raw input images utilizing foundational models for extracting explicit textual scene graphs, as substantiated by the results of a robotic experiment conducted with a wheeled manipulator platform. We hope that these findings will contribute to the implementation of robust and compressed graph-based robotic memory for long-horizon reasoning. Code is available at github.com/linukc/DyGEnc.
title DyGEnc: Encoding a Sequence of Textual Scene Graphs to Reason and Answer Questions in Dynamic Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.03581