no code implementations • 30 May 2023 • Hyun Seung Lee, Seungtaek Choi, Yunsung Lee, Hyeongdon Moon, Shinhyeok Oh, Myeongho Jeong, Hyojun Go, Christian Wallraven
To mitigate these issues, here we propose a novel retrieval approach CEAA that provides effective learning in educational text classification.
1 code implementation • 9 Oct 2021 • Daehyun Cho, Christian Wallraven
The deep learning field is growing rapidly as witnessed by the exponential growth of papers submitted to journals, conferences, and pre-print servers.
no code implementations • 9 Oct 2021 • Hoe Sung Ryu, Uijong Ju, Christian Wallraven
Deep neural networks (DNNs) have become remarkably successful in data prediction, and have even been used to predict future actions based on limited input.
no code implementations • 9 Oct 2021 • Hyun Seung Lee, Christian Wallraven
Recent research has found that knowledge distillation can be effective in reducing the size of a network and in increasing generalization.
no code implementations • 9 Oct 2021 • Serin Park, Christian Wallraven
In this work, we compared the recognition performance and attention patterns of humans and machines during a two-alternative forced-choice FER task.
Facial Expression Recognition Facial Expression Recognition (FER)
1 code implementation • 9 Oct 2021 • Doo Yon Kim, Christian Wallraven
AffectNet is one of the most popular resources for facial expression recognition (FER) on relatively unconstrained in-the-wild images.
Facial Expression Recognition Facial Expression Recognition (FER)
1 code implementation • 25 Nov 2020 • Björn Browatzki, Jörn-Philipp Lies, Christian Wallraven
We propose an encoder-decoder framework for the segmentation of blood vessels in retinal images that relies on the extraction of large-scale patches at multiple image-scales during training.
1 code implementation • 24 Nov 2019 • Bjoern Browatzki, Christian Wallraven
Current supervised methods for facial landmark detection require a large amount of training data and may suffer from overfitting to specific datasets due to the massive number of parameters.
Ranked #4 on Face Alignment on AFLW-19 (NME_box (%, Full) metric, using extra training data)