Sherif Abdelkarim — accepted AI-conference papers

2022

RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition

Jun Chen, Aniket Agarwal, Sherif Abdelkarim, Deyao Zhu, Mohamed Elhoseiny

CVPR 2022poster

The visual relationship recognition (VRR) task aims at understanding the pairwise visual relationships between interacting objects in an image. These relationships typically have a long-tail distribution due to their compositional nature. This problem gets more severe when the vocabulary becomes lar…

Cited by 21 PDF ↗code ↗Scholar ↗

2021

Exploring Long Tail Visual Relationship Recognition With Large Vocabulary

Sherif Abdelkarim, Aniket Agarwal, Panos Achlioptas, Jun Chen, Jiaji Huang, Boyang Li +2

ICCV 2021poster

Several approaches have been proposed in recent literature to alleviate the long-tail problem, mainly in object classification tasks. In this paper, we make the first large-scale study concerning the task of Long-Tail Visual Relationship Recognition (LTVRR). LTVRR aims at improving the learning of s…

Cited by 22 PDF ↗code ↗Scholar ↗