activity
20242026
collaborators

5 papers

cs.CV2026

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…

cs.CV2026

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…

cs.LG2025

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…

cs.LG2025

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…

cs.CV2024

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…