FragNet, a contrastive learning-based transformer model for clustering, interpreting, visualizing, and navigating chemical space
AD Shrivastava, DB Kell - Molecules, 2021 - mdpi.com
The question of molecular similarity is core in cheminformatics and is usually assessed via a
pairwise comparison based on vectors of properties or molecular fingerprints. We recently …
pairwise comparison based on vectors of properties or molecular fingerprints. We recently …
Multi-pose facial expression recognition based on generative adversarial network
D Li, Z Li, R Luo, J Deng, S Sun - IEEE Access, 2019 - ieeexplore.ieee.org
The recognition of human emotions from facial expression images is one of the most
important topics in the machine vision and image processing fields. However, recognition …
important topics in the machine vision and image processing fields. However, recognition …
Anti-transfer learning for task invariance in convolutional neural networks for speech processing
We introduce the novel concept of anti-transfer learning for speech processing with
convolutional neural networks. While transfer learning assumes that the learning process for …
convolutional neural networks. While transfer learning assumes that the learning process for …
Shunting at Arbitrary Feature Levels via Spatial Disentanglement: Toward Selective Image Translation
The past few years have witnessed considerable efforts devoted to translating images from
one domain to another, mainly aiming at editing global style. Here, we focus on a more …
one domain to another, mainly aiming at editing global style. Here, we focus on a more …
Signer-independent sign language recognition with feature disentanglement
İM BAYTAŞ, İ ERDOĞAN - Turkish Journal of Electrical …, 2024 - journals.tubitak.gov.tr
Learning a robust and invariant representation of various unwanted factors in sign language
recognition (SLR) applications is essential. One of the factors that might degrade the sign …
recognition (SLR) applications is essential. One of the factors that might degrade the sign …
Signer-independent sign language recognition with feature disentanglement.
İ ERDOĞAN, İM BAYTAŞ - Turkish Journal of Electrical …, 2024 - search.ebscohost.com
Learning a robust and invariant representation of various unwanted factors in sign language
recognition (SLR) applications is essential. One of the factors that might degrade the sign …
recognition (SLR) applications is essential. One of the factors that might degrade the sign …
Enhancing the Generalization of Convolutional Neural Networks for Speech Emotion Recognition
E Guizzo - 2023 - openaccess.city.ac.uk
Human-machine interaction is rapidly gaining significance in our daily lives. While speech
recognition has achieved near-human performance in recent years, the intricate details …
recognition has achieved near-human performance in recent years, the intricate details …