5 papers
TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs
Muhammad Haseeb Aslam, Alessandro Koerich, Marco Pedersoli +2
Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild. ER is inherently multimodal, requiri…
Personalized Feature Translation for Expression Recognition: An Efficient Source-Free Domain Adaptation Method
Masoumeh Sharafi, Soufiane Belharbi, Muhammad Osama Zeeshan +6
Facial expression recognition (FER) models are widely used in video-based affective computing applications, such as human-computer interaction and healthcare monitoring. However, d…
Learning from Stochastic Teacher Representations Using Student-Guided Knowledge Distillation
Muhammad Haseeb Aslam, Clara Martinez, Marco Pedersoli +3
Advances in self-distillation have shown that when knowledge is distilled from a teacher to a student using the same deep learning (DL) architecture, the student performance can su…
Scaling laws in wearable human activity recognition
Tom Hoddes, Alex Bijamov, Saket Joshi +4
Many deep architectures and self-supervised pre-training techniques have been proposed for human activity recognition (HAR) from wearable multimodal sensors. Scaling laws have the…
SASSL: Enhancing Self-Supervised Learning via Neural Style Transfer
Renan A. Rojas-Gomez, Karan Singhal, Ali Etemad +3
Existing data augmentation in self-supervised learning, while diverse, fails to preserve the inherent structure of natural images. This results in distorted augmented samples with…