GitHub

Welcome!

I'm a research fellow in the Cognitive Vision Group at CVSSP - University of Surrey.

News

  • 🎉 Geo-Sign is accepted to NeurIPS 2025!
  • 🎉 PLOT-TAL: Optimal Transport for Few Shot Temporal Action Localization is accepted to ICCV Workshop CLVL. Paper
  • 🎉 VALLR - Visual ASR Language Model for Lip Reading is accepted to ICCV 2025!
  • 📰 Code and Paper for Geo-Sign now available here
  • I got my PhD! (Oct 24)
  • I've joined CVSSP as a Research Fellow in Computer Vision.
  • I've joined King's College London as a research associate in Responsible AI.
  • 👨🏻‍🔧 Code for our Interspeech paper on zero-shot personalized ASR quantization is released at Samsung Labs: myQASR Code
  • 📚 My work is featured in the Samsung AI Research blog here
  • 🎉 "Multi-resolution audio-visual feature fusion for temporal action localization" is accepted at NeurIPS 23 ML for Audio Workshop (Oct 23).
  • 📚 I secured EU Horizon funding to extend my research in efficient multi-modal video understanding until Feb 24
  • 🎉 "A model for every user and budget - data-free mixed-precision ASR quantization" is accepted for INTERSPEECH 23 (Aug 23)
  • 📚 I am back at The University of Surrey completing my PhD
  • 👨🏻‍🔧 I'm currently working as a research intern at Samsung Research UK (Completed Feb 22 - Feb 23)
  • 🎉 "Two-stream transformer architecture for long form video understanding" is accepted for BMVC 2022 (Mar 22)
  • 🎉 "Re-thinking genre classification with fine-grained semantic experts" is accepted for ICIP 2021 (Nov 21)

Pinned Loading

  1. [NeurIPS 25] Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation

    Python 30 1

  2. [Interspeech 23] "A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization", Interspeech 2023. The paper has been accepted for publication at the INTERSPEECH 2023…

    Jupyter Notebook

  3. SLRTP Sign Production Challenge - CVPR 2025 - Evaluation Code

    Python 5

Read the original on github.com ↗