Mani Tellamekala, PhD

Hi there!👋 I am an AI Research Scientist with over 10 years of Machine Learning (ML) experience across industry and academia. My work focuses on building multimodal intelligent systems for human expressive behaviour analysis from face and voice, extracting actionable sentiment insights to create next-generation, empathetic user experiences.

Currently, I am a Computer Vision Scientist at Huawei's Amsterdam Research Center, and previously served as the Head of Research and Development at BlueSkeye AI - a leading provider of state-of-the-art facial behaviour analysis SDKs for in-cabin automotive software, mental health apps & social robots.

My research is published in top-tier AI venues (including CVPR, IEEE TPAMI, and an Interspeech Best Paper Nomination). Additionally, I hold an awarded foundational US patent in sentiment-aware Human-LLM interaction, alongside several key US patent filings in applied ML and Computer Vision.

I received my PhD in Computer Science from the University of Nottingham, advised by Prof. Michel Valstar. My doctoral thesis studies Uncertainty-Aware and Label-Efficient Deep Learning for Emotion Recognition. My recent research focuses on self-supervised multimodal (face and voice) emotion recognition.

During my PhD, I was a Visiting Researcher at the University of Augsburg, Germany, where I worked with Prof. Dr. Björn W. Schuller and Prof. Dr. Elisabeth André.

News

Feb 01, 2026 Started in my new role as Computer Vision Scientist at Huawei Amsterdam Research Center!
Oct 11, 2025 xTrace benchmarking results on SEWA test set are published on Arxiv!
May 09, 2025 xTrace paper pre-print is out on Arxiv!
March 07, 2025 Delivered a guest lecture at the University of Nottingham: "Beyond the Model: Turning ML Models into Products – Challenges and Some Best Practices"
Nov 11, 2024 Awarded a US patent on Multimodal LLM Interaction!!.
Oct 13, 2023 COLD Fusion paper accepted to IEEE TPAMI! 🎉
May 15, 2023 3D Facial Expression Analysis paper accepted to IEEE TAC
April 02, 2023 Started my new role as Head of R&D at BlueSkeye AI!!.
Dec 10, 2022 Graduated with my PhD in Computer Science from the University of Nottingham 🎉

Publications

  1. IEEE TPAMI
    COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognition
    Mani Kumar Tellamekala, Shahin Amiriparian, Björn W. Schuller, Elisabeth André, Timo Giesbrecht, Michel Valstar
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2023
    PDF
  2. CVPR
    Affective Processes: Stochastic Modelling of Temporal Context for Emotion and Facial Expression Recognition
    Enrique Sanchez, Mani Kumar Tellamekala, Michel Valstar, Georgios Tzimiropoulos
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021
    PDF
  3. PhD Thesis
    Towards Uncertainty-Aware and Label-Efficient Machine Learning of Human Expressive Behaviour
    Mani Kumar Tellamekala
    University of Nottingham 2022
    PDF
  4. IEEE TAC
    Are 3D Face Shapes Expressive Enough for Recognising Continuous Emotions and Action Unit Intensities?
    Mani Kumar Tellamekala, Ömer Sümer, Björn W Schuller, Elisabeth André, Timo Giesbrecht, Michel Valstar
    IEEE Transactions on Affective Computing (TAC) 2022
    PDF
  5. IEEE TAC
    Modelling Stochastic Context of Audio-Visual Expressive Behaviour with Affective Processes
    Mani Kumar Tellamekala, Timo Giesbrecht, Michel Valstar
    IEEE Transactions on Affective Computing (TAC) 2022
    PDF
  6. IEEE TAC
    Dimensional Affect Uncertainty Modelling for Apparent Personality Recognition
    Mani Kumar Tellamekala, Timo Giesbrecht, Michel Valstar
    IEEE Transactions on Affective Computing (TAC) 2022
    PDF
  7. Interspeech
    Stochastic Process Regression for Cross-Cultural Speech Emotion Recognition
    Mani Kumar Tellamekala, Enrique Sanchez, Georgios Tzimiropoulos, Timo Giesbrecht, Michel Valstar
    Interspeech 2021 - Best Student Paper Award candidate 🎉
    PDF
  8. ICPR
    Audio-Visual Predictive Coding for Self-Supervised Visual Representation Learning
    Mani Kumar Tellamekala, Michel Valstar, Michael Pound, Timo Giesbrecht
    International Conference on Pattern Recognition (ICPR) 2021
    PDF
  9. IEEE FG
    Apparent Personality Recognition from Uncertainty-Aware Facial Emotion Predictions using Conditional Latent Variable Models
    Mani Kumar Tellamekala, Timo Giesbrecht, Michel Valstar
    IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2021
    PDF
  10. CVPRW
    Time-Continuous Audiovisual Fusion With Recurrence vs Attention for In-the-Wild Affect Recognition
    Vincent Karas, Mani Kumar Tellamekala, Adria Mallol-Ragolta, Michel Valstar, Björn W Schuller
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) workshop 2022
    PDF
  11. ICCVW
    Dynamic Facial Models for Video-Based Dimensional Affect Estimation
    Siyang Song, Enrique Sánchez-Lozano, Mani Kumar Tellamekala, Linlin Shen, Alan Johnston, Michel Valstar
    IEEE/CVF International Conference on Computer Vision (ICCV) workshop 2019
    PDF
  12. ACII
    Temporally Coherent Visual Representations for Dimensional Affect Recognition
    Mani Kumar Tellamekala, Michel Valstar
    Affective Computing and Intelligent Interaction (ACII) 2019
    PDF
  13. ICVGIP
    Tracking Rapid Body Deformation using Sparse Representation of Deep Features
    Debaditya Roy, GSS Bharath, Mani Kumar Tellamekala, C Krishna Mohan
    ACM Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP) 2018
    PDF

Talks

University of Nottingham, School of Computer Science Guest Lecture: Beyond the Model: Turning ML Models into Products – Challenges and Some Best Practices
University of Augsburg Oberseminar 2021: Nondeterministic Temporal Regression for Apparent Affect Recognition
Facebook London PhD Tech Talk 2019: Temporally Coherent Visual Representations for Dimensional Affect Recognition

Open Source Projects

PyAAM A Python tool for Audiovisual Affect Markup developed for Adaptive Interactive Movies (AIM) project

Teaching

Machine Learning Graduate Teaching Assistant for Machine Learning (G53MLE) at the University of Nottingham (Sep 2019 to Dec 2019 & Sep 2020 to Dec 2020)

Academic Activities

Reviewer AISTATS 2024, NeurIPS 2024, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), IEEE Transactions on Affective Computing (TAC), IEEE Transactions on Multimedia (TMM), ACM Multimedia (MM) MuSE
Technical Program Committee ACM Multimedia (MM) MuSE Challenge 2022