Spatial-temporal transformer for dynamic scene graph generation

Yuren Cong, Wentong Liao, Hanno Ackermann, Bodo Rosenhahn, Michael Ying Yang

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

63 Citations (Scopus)
105 Downloads (Pure)

Abstract

Dynamic scene graph generation aims at generating a scene graph of the given video. Compared to the task of scene graph generation from images, it is more challenging because of the dynamic relationships between objects and the temporal dependencies between frames allowing for a richer semantic interpretation. In this paper, we propose Spatial-temporal Transformer (STTran), a neural network that consists of two core modules: (1) a spatial encoder that takes an input frame to extract spatial context and reason about the visual relationships within a frame, and (2) a temporal decoder which takes the output of the spatial encoder as input in order to capture the temporal dependencies between frames and infer the dynamic relationships. Furthermore, STTran is flexible to take varying lengths of videos as input without clipping, which is especially important for long videos. Our method is validated on the benchmark dataset Action Genome (AG). The experimental results demonstrate the superior performance of our method in terms of dynamic scene graphs. Moreover, a set of ablative studies is conducted and the effect of each proposed module is justified. Code available at: https://github.com/yrcong/STTran.

Original languageEnglish
Title of host publication2021 IEEE/CVF International Conference on Computer Vision (ICCV)
PublisherIEEE
Pages16352-16362
Number of pages11
ISBN (Electronic)978-1-6654-2812-5
DOIs
Publication statusPublished - 28 Feb 2022
Event18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021 - Virtual, Online, Canada
Duration: 11 Oct 202117 Oct 2021
Conference number: 18

Conference

Conference18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021
Abbreviated titleICCVW 2021
Country/TerritoryCanada
CityVirtual, Online
Period11/10/2117/10/21

Keywords

  • 22/1 OA procedure

Fingerprint

Dive into the research topics of 'Spatial-temporal transformer for dynamic scene graph generation'. Together they form a unique fingerprint.

Cite this