no code implementations • 17 Apr 2024 • Jean-Paul Ainam, Erim Yanik, Rahul Rahul, Taylor Kunkes, Lora Cavuoto, Brian Clemency, Kaori Tanaka, Matthew Hackett, Jack Norfleet, Suvranu De
In the first phase, ETI is performed by two subject cohorts: Experts and Novices.
no code implementations • 20 Jul 2022 • Ji Zhang, Jean-Paul Ainam, Li-hui Zhao, Wenai Song, Xin Wang
Based on the complementarity of attribute and category labels, we propose a Multi-task Attribute-Scene Recognition (MASR) network which learns a category embedding and at the same time predicts scene attributes.
1 code implementation • 23 Sep 2018 • Jean-Paul Ainam, Ke Qin, Guisong Liu
We apply a max filter operation to non-overlapping sub-regions on the high feature representation before element-wise multiplied with the output of the second branch.
1 code implementation • 13 Sep 2018 • Jean-Paul Ainam, Ke Qin, Guisong Liu, Guangchun Luo
Finally, we assign a non-uniform label distribution to the generated samples and define a regularized loss function for training.