RelTR: Relation Transformer for Scene Graph Generation

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 45; no. 9; pp. 11169 - 11183
• Main Authors: Cong, Yuren, Yang, Michael Ying, Rosenhahn, Bodo
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Coders; Decoding; Encoders-Decoders; Object detection; Object recognition; One-stage; Predictions; Predictive models; Proposals; scene graph generation; scene understanding; Task analysis; Transformers; visual relationship detection; Visualization

Different objects in the same scene are more or less related to each other, but only a limited number of these relationships are noteworthy. Inspired by Detection Transformer, which excels in object detection, we view scene graph generation as a set prediction problem. In this article, we propose an...