English

Scenes and Surroundings: Scene Graph Generation using Relation Transformer

Computer Vision and Pattern Recognition 2021-07-13 v1

Abstract

Identifying objects in an image and their mutual relationships as a scene graph leads to a deep understanding of image content. Despite the recent advancement in deep learning, the detection and labeling of visual object relationships remain a challenging task. This work proposes a novel local-context aware architecture named relation transformer, which exploits complex global objects to object and object to edge (relation) interactions. Our hierarchical multi-head attention-based approach efficiently captures contextual dependencies between objects and predicts their relationships. In comparison to state-of-the-art approaches, we have achieved an overall mean \textbf{4.85\%} improvement and a new benchmark across all the scene graph generation tasks on the Visual Genome dataset.

Keywords

Cite

@article{arxiv.2107.05448,
  title  = {Scenes and Surroundings: Scene Graph Generation using Relation Transformer},
  author = {Rajat Koner and Poulami Sinhamahapatra and Volker Tresp},
  journal= {arXiv preprint arXiv:2107.05448},
  year   = {2021}
}

Comments

arXiv admin note: text overlap with arXiv:2004.06193

R2 v1 2026-06-24T04:06:25.874Z