February to March 2025- Research Scientist | Computer Age Management Services (CAMS)
2020 to 2024- Teaching Assistant | Birla Institute of Technology & Science
Research Interest
Dr Rizvi’s research is centred around building intelligent, equitable, and practical AI systems with a focus on affective computing, image enhancement, and algorithmic fairness. His work integrates foundational methods in computer vision and deep learning with applications that are societally relevant and technologically impactful.
In affective computing, he develops models that can accurately perceive and interpret human emotional expressions, especially under real-world constraints such as low-resolution or noisy visual input. His contributions include large-scale dataset development (e.g., InFER, InFER++) and robust FER pipelines. In the domain of image enhancement, Dr Rizvi focuses on emotion-aware super-resolution and refinement techniques that improve visual quality while preserving semantic and affective cues—ensuring downstream tasks like emotion recognition remain reliable in practical deployments.
His work on fairness in AI systems is directed toward mitigating demographic and representational biases in facial analysis. Through techniques like latent alignment and fairness-aware learning, he aims to ensure that AI models perform equitably across diverse populations and do not propagate societal inequalities.
Awards
No data available
Memberships
No data available
Publications
Patents
Projects
Scholars
Interests
Affective Computing
Fairness in AI Systems
Image Refinement)
Thought Leaderships
There are no Thought Leaderships associated with this faculty.
Top Achievements
Education
2019
B.Tech. CSE
Jamia Hamdard
India
2025
PhD
Birla Institute of Technology & Science
India
Experience
February to March 2025- Research Scientist | Computer Age Management Services (CAMS)
2020 to 2024- Teaching Assistant | Birla Institute of Technology & Science
Research Interests
Dr Rizvi’s research is centred around building intelligent, equitable, and practical AI systems with a focus on affective computing, image enhancement, and algorithmic fairness. His work integrates foundational methods in computer vision and deep learning with applications that are societally relevant and technologically impactful.
In affective computing, he develops models that can accurately perceive and interpret human emotional expressions, especially under real-world constraints such as low-resolution or noisy visual input. His contributions include large-scale dataset development (e.g., InFER, InFER++) and robust FER pipelines. In the domain of image enhancement, Dr Rizvi focuses on emotion-aware super-resolution and refinement techniques that improve visual quality while preserving semantic and affective cues—ensuring downstream tasks like emotion recognition remain reliable in practical deployments.
His work on fairness in AI systems is directed toward mitigating demographic and representational biases in facial analysis. Through techniques like latent alignment and fairness-aware learning, he aims to ensure that AI models perform equitably across diverse populations and do not propagate societal inequalities.
February to March 2025- Research Scientist | Computer Age Management Services (CAMS)
2020 to 2024- Teaching Assistant | Birla Institute of Technology & Science
Research Interests
Dr Rizvi’s research is centred around building intelligent, equitable, and practical AI systems with a focus on affective computing, image enhancement, and algorithmic fairness. His work integrates foundational methods in computer vision and deep learning with applications that are societally relevant and technologically impactful.
In affective computing, he develops models that can accurately perceive and interpret human emotional expressions, especially under real-world constraints such as low-resolution or noisy visual input. His contributions include large-scale dataset development (e.g., InFER, InFER++) and robust FER pipelines. In the domain of image enhancement, Dr Rizvi focuses on emotion-aware super-resolution and refinement techniques that improve visual quality while preserving semantic and affective cues—ensuring downstream tasks like emotion recognition remain reliable in practical deployments.
His work on fairness in AI systems is directed toward mitigating demographic and representational biases in facial analysis. Through techniques like latent alignment and fairness-aware learning, he aims to ensure that AI models perform equitably across diverse populations and do not propagate societal inequalities.
