Open-Set Video-based Facial Expression Recognition with Human Expression-sensitive Prompting
In Video-based Facial Expression Recognition (V-FER), models are typically trained on
closed-set datasets with a fixed number of known classes. However, these models struggle …
closed-set datasets with a fixed number of known classes. However, these models struggle …
Slight Corruption in Pre-training Data Makes Better Diffusion Models
Diffusion models (DMs) have shown remarkable capabilities in generating realistic high-
quality images, audios, and videos. They benefit significantly from extensive pre-training on …
quality images, audios, and videos. They benefit significantly from extensive pre-training on …
Contrastive-Based Deep Embeddings for Label Noise-Resilient Histopathology Image Classification
L Dedieu, N Nerrienet, A Nivaggioli, C Simmat… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent advancements in deep learning have proven highly effective in medical image
classification, notably within histopathology. However, noisy labels represent a critical …
classification, notably within histopathology. However, noisy labels represent a critical …
Data-Efficient and Generalizable Machine Learning in Complex Environments
X Xia - 2024 - ses.library.usyd.edu.au
In an age marked by an unprecedented influx of data across diverse domains, the quest for
effective machine learning (ML) solutions has increased significantly. However, data …
effective machine learning (ML) solutions has increased significantly. However, data …