title

Mohammad H. Mahoor, Ph.D.

Professor of Electrical & Computer Engineering at University of Denver

As the Director of Artificial Intelligence and Social Robotics Lab, Dr. Mohammad Mahoor directs pioneering research at the intersection of AI, computer vision, and socially assistive robotics. Under his leadership, the Artificial Intelligence and Social Robotics Lab strives to integrate emotional intelligence into technology, creating solutions that advance human-robot interaction and enhance the quality of life. Our mission is to develop innovative, human-centered tools that foster empathy, empowerment, and meaningful engagement between people and machines.

portfolio

Databases

AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild

AffectNet is a large-scale facial expression database designed to advance affective computing research, particularly in both the categorical and continuous dimensional emotion models (valence and arousal). It contains over 1 million facial images collected from the internet using 1250 emotion-related keywords in six languages. Approximately 440K of these images are manually annotated with seven discrete facial expressions and the intensity of valence and arousal.

As the largest database of its kind, AffectNet supports research in automated facial expression recognition and outperforms conventional machine learning methods and commercial systems in benchmark evaluations.

A. Mollahosseini, B. Hasani, and M. H. Mahoor, “AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild,” IEEE Transactions on Affective Computing, vol. 10, no. 1, pp. 18–31, 2017. DOI: 10.1109/TAFFC.2017.2740923

Databases

AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild

AffectNet is a large-scale facial expression database designed to advance affective computing research, particularly in both the categorical and continuous dimensional emotion models (valence and arousal). It contains over 1 million facial images collected from the internet using 1250 emotion-related keywords in six languages. Approximately 440K of these images are manually annotated with seven discrete facial expressions and the intensity of valence and arousal.

As the largest database of its kind, AffectNet supports research in automated facial expression recognition and outperforms conventional machine learning methods and commercial systems in benchmark evaluations.

A. Mollahosseini, B. Hasani, and M. H. Mahoor, “AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild,” IEEE Transactions on Affective Computing, vol. 10, no. 1, pp. 18–31, 2017. DOI: 10.1109/TAFFC.2017.2740923

DISFA & DISFA+: Dynamic Intensity of Facial Action Units

DISFA and DISFA+ are benchmark databases used to detect the intensity of facial Action Units (AUs) from spontaneous facial expressions. DISFA+ includes additional annotations for valence and arousal, which are useful for modeling continuous dimensional affect.

These databases have supported numerous research studies on automatic Action Unit detection and the interpretation of facial expressions in the context of emotional responses.

RyanSpeech: Speech Emotion Dataset

RyanSpeech is a high-quality male speech corpus designed for text-to-speech (TTS) research. Unlike many publicly available TTS corpora, it features over 10 hours of a professional male voice actor's speech recorded at 44.1 kHz, derived from real-world conversational settings. Optimized for developing TTS systems in real-world applications, RyanSpeech has been used to train state-of-the-art speech models, achieving a 3.36 mean opinion score (MOS) in its best model.

OutFin: A Financial Data Analysis Dataset

Fingerprint-based positioning is emerging as a reliable alternative to GPS and cellular localization in urban areas. However, the lack of public datasets limits research in this field. To address this, we introduce OutFin—a comprehensive outdoor fingerprint dataset collected using two smartphones. It includes WiFi, Bluetooth, and cellular signals, along with sensor data from the magnetometer, accelerometer, gyroscope, barometer, and ambient light sensor. Data was gathered from 122 reference points across four distinct sites, each with unique GNSS visibility and layout. Prior to release, OutFin underwent rigorous testing to ensure data quality, making it a valuable resource for advancing fingerprint-based positioning research.

Research Areas

Computer Vision and Pattern Recognition
Mild Cognitive Impairment Detection using AI
Brain and Human-Computer Interfacing
Socially Assistive Robotics
Machine Learning and Deep Learning
Large Language Models and NLP
Affective Computing

Learn More About My Research

Explore

Select Publications

See All Publications On Google Scholar

  • 3.

    A. Mollahosseini, B. Hasani, and M. H. Mahoor, "AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild", IEEE Transactions on Affective Computing, vol. 10, no. 1, pp. 18–31, 2017. DOI: 10.1109/TAFFC.2017.2740923

  • 2.

    S. M. Mavadati, M. H. Mahoor, K. Bartlett, P. Trinh, and J. F. Cohn, "DISFA: A Spontaneous Facial Action Intensity Database", IEEE Transactions on Affective Computing, vol. 4, no. 2, pp. 151–160, 2013. DOI: 10.1109/T-AFFC.2013.4

  • 1.

    R. Zandie, M. H. Mahoor, J. Madsen, and E. S. Emamian, "RyanSpeech: A Corpus for Conversational Text-to-Speech Synthesis", arXiv preprint arXiv:2106.08468, 2021. DOI: https://arxiv.org/abs/2106.08468