A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets

K Bayoudh, R Knani, F Hamdaoui, A Mtibaa - The Visual Computer, 2022 - Springer
The research progress in multimodal learning has grown rapidly over the last decade in
several areas, especially in computer vision. The growing potential of multimodal data …

Hardening RGB-D object recognition systems against adversarial patch attacks

Y Zheng, L Demetrio, AE Cinà, X Feng, Z Xia… - Information …, 2023 - Elsevier
RGB-D object recognition systems improve their predictive performances by fusing color and
depth information, outperforming neural network architectures that rely solely on colors …

Deep Domain Adaptation through Inter-modal Self-supervision

L Robbiano - 2020 - webthesis.biblio.polito.it
Computer vision in robotics makes heavy usage of RGB-D data. However, collecting large
manually annotated datasets is extremely time-consuming and therefore costly. A potential …

[PDF][PDF] Robust Speaker Adaptation Framework for Personalized Emotion Recognition in Emotionally-Imbalanced Small-Sample Environments

J Bang - 2019 - uclab.khu.ac.kr
The proposed Robust Speaker Adaptation Framework provides a personalized training
model for the target user utilizing 3 core solutions by selecting the actual case data useful for …