Back close

Scene Graph Generation Using Depth, Spatial, and Visual Cues in 2D Images

Publication Type : Journal Article

Publisher : IEEE Access

Source : IEEE Access, vol. 10, pp. 1968–1978, 2022, doi: 10.1109/access.2021.3139000.

Url : https://ieeexplore.ieee.org/document/9663384

Campus : Amritapuri

School : School of Computing

Center : Computer Vision and Robotics

Year : 2022

Abstract : To understand an image or a scene properly, it is necessary to identify objects participating in the scene, their relationships, and various attributes that describe their properties. A scene graph is a high-level representation that confines all these features in a structured manner. Scene graph generation includes multiple challenges like the semantics of relationships considered and the availability of a well-balanced dataset with sufficient training examples. We tried to mitigate these problems by extracting two subsets, VG-R10 and VG-A16, from the popular Visual Genome dataset. Also, a framework (S2G) is proposed for generating scene graphs directly from images using depth and spatial information of object pairs. Evaluations on the scene graph generation model reveal that the proposed framework achieves better results on our data than the state-of-the-art.

Cite this Research Publication : A. S. Kumar and J. J. Nair, "Scene Graph Generation Using Depth, Spatial, and Visual Cues in 2D Images," IEEE Access, vol. 10, pp. 1968–1978, 2022, doi: 10.1109/access.2021.3139000.

Admissions Apply Now