no code implementations • 6 Sep 2023 • Hengyue Liu, Bir Bhanu
As each representation's cardinality has different trade-offs between performance and computation overhead, extracting highly representative features efficiently and dynamically is both challenging and crucial for SGG.
1 code implementation • CVPR 2021 • Hengyue Liu, Ning Yan, Masood S. Mortazavi, Bir Bhanu
This paper presents a fully convolutional scene graph generation (FCSGG) model that detects objects and relations simultaneously.
no code implementations • 1 Nov 2020 • Hengyue Liu, Samyak Parajuli, Jesse Hostetler, Sek Chai, Bir Bhanu
Conditional computation for Deep Neural Networks (DNNs) reduce overall computational load and improve model accuracy by running a subset of the network.