Iterative distillation for better uncertainty estimates in multitask emotion recognition

D Deng, L Wu, BE Shi - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
When recognizing emotions, subtle nuances in displays of emotion generate ambiguity or
uncertainty in emotion perception. Emotion uncertainty has been previously interpreted as …

Collision-probability-aware human-machine cooperative planning for safe automated driving

C Huang, P Hang, Z Hu, C Lv - IEEE Transactions on Vehicular …, 2021 - ieeexplore.ieee.org
In this paper, we investigate a novel collision probability-aware human-machine cooperative
planning and tracking method for enhancing safety of automated vehicles. Firstly, a long …

Dynamic difficulty awareness training for continuous emotion prediction

Z Zhang, J Han, E Coutinho… - IEEE Transactions on …, 2018 - ieeexplore.ieee.org
Time-continuous emotion prediction has become an increasingly compelling task in
machine learning. Considerable efforts have been made to advance the performance of …

The ambiguous world of emotion representation

V Sethu, EM Provost, J Epps, C Busso… - arXiv preprint arXiv …, 2019 - arxiv.org
Artificial intelligence and machine learning systems have demonstrated huge improvements
and human-level parity in a range of activities, including speech recognition, face …

Investigating word affect features and fusion of probabilistic predictions incorporating uncertainty in AVEC 2017

T Dang, B Stasak, Z Huang, S Jayawardena… - Proceedings of the 7th …, 2017 - dl.acm.org
Predicting emotion intensity and severity of depression are both challenging and important
problems within the broader field of affective computing. As part of the AVEC 2017, we …

Estimating the uncertainty in emotion attributes using deep evidential regression

W Wu, C Zhang, PC Woodland - arXiv preprint arXiv:2306.06760, 2023 - arxiv.org
In automatic emotion recognition (AER), labels assigned by different human annotators to
the same utterance are often inconsistent due to the inherent complexity of emotion and the …

Estimating the uncertainty in emotion class labels with utterance-specific Dirichlet priors

W Wu, C Zhang, X Wu… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Emotion recognition is a key attribute for artificial intelligence systems that need to naturally
interact with humans. However, the task definition is still an open problem due to the …

Modelling variability in human annotator simulation

W Wu, W Chen, C Zhang… - Findings of the Association …, 2024 - aclanthology.org
Human annotator simulation (HAS) serves as a cost-effective substitute for human
evaluation tasks such as data annotation and system assessment. It is important to …

It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density Estimation

W Wu, W Chen, C Zhang, PC Woodland - arXiv preprint arXiv:2310.00486, 2023 - arxiv.org
Human annotator simulation (HAS) serves as a cost-effective substitute for human
evaluation such as data annotation and system assessment. Human perception and …

[HTML][HTML] Exploring perception uncertainty for emotion recognition in dyadic conversation and music listening

J Han, Z Zhang, Z Ren, B Schuller - Cognitive Computation, 2021 - Springer
Predicting emotions automatically is an active field of research in affective computing.
Considering the property of the individual's subjectivity, the label of an emotional instance is …