activity
20242026
collaborators

6 papers

cs.CV2026

Not Every Subject Should Stay: Machine Unlearning for Noisy Engagement Recognition

Alexander Vedernikov

Engagement recognition datasets are typically subject-indexed and often contain noisy, subjective supervision, making post-hoc dataset revision a practical problem. Existing noisy-…

cs.CV2026

PriorNet: Prior-Guided Engagement Estimation from Face Video

Alexander Vedernikov

Engagement estimation from face video remains challenging because facial evidence is often incomplete, labeled data are limited, and engagement annotations are subjective. We prese…

cs.CV2025

Vision Large Language Models Are Good Noise Handlers in Engagement Analysis

Alexander Vedernikov, Puneet Kumar, Haoyu Chen +2

Engagement recognition in video datasets, unlike traditional image classification tasks, is particularly challenged by subjective labels and noise limiting model performance. To ov…

cs.HC2025

Computational Analysis of Stress, Depression and Engagement in Mental Health: A Survey

Puneet Kumar, Alexander Vedernikov, Yuwei Chen +2

Analysis of stress, depression and engagement is less common and more complex than that of frequently discussed emotions such as happiness, sadness, fear and anger. The importance…

cs.CV2024

TCCT-Net: Two-Stream Network Architecture for Fast and Efficient Engagement Estimation via Behavioral Feature Signals

Alexander Vedernikov, Puneet Kumar, Haoyu Chen +2

Engagement analysis finds various applications in healthcare, education, advertisement, services. Deep Neural Networks, used for analysis, possess complex architecture and need lar…

cs.CV2024

Analyzing Participants' Engagement during Online Meetings Using Unsupervised Remote Photoplethysmography with Behavioral Features

Alexander Vedernikov, Zhaodong Sun, Virpi-Liisa Kykyri +3

Engagement measurement finds application in healthcare, education, services. The use of physiological and behavioral features is viable, but the impracticality of traditional physi…