I am currently a Senior Researcher in the Computing Research Group at Fujitsu Research of Europe. I am interested in multimodal representation learning and explainability with applications in healthcare domain.

In 2019, I received a PhD from the University of Surrey supervised by Prof. John Collomosse. My PhD introduced novel techniques to learn a joint embedding of images and sketches to allow efficient image search using free-hand sketches as the queries. During this time, I undertook an internship at the University of Sao Paulo, Institute of Mathematics and Computer Sciences, supervised under Prof. Moacir Ponti. My PhD viva was examined under Prof. Arnold Smeulders and Dr. Simon Hadfield.

In 2014, I obtained a BEng (Hons) degree in Electronic Engineering (first class) at the University of Surrey during which I spent a professional training year at Sony Digital Cinema.

7/2023 -- Our paper, VADER: Video Alignment Differencing and Retrieval has been accepted at ICCV 2023.

6/2023 -- Our paper, RoSteALS: Robust Steganography using Autoencoder Latent Space has been published at CVPR WMF 2023. Play with our demo here.

8/2022 -- two papers, RepMix: Representation Mixing for Robust Attribution of Synthesized Images and CoGS: Controllable Generation and Search from Sketch and Style, has been accepted at ECCV 2022.

6/2022 -- our paper titled ARIA: Adversarially Robust Image Attribution for Content Provenance has been accepted at CVPR 2022 Workshop on Media Forensics.

11/2021 -- [DECaDE] our paper titled VPN: Video Provenance Network for Robust Content Attribution has been accepted and achieves the best paper award at CVMP 2021.

09/2021 -- Our paper titled Compositional Sketch Search has been accepted at ICIP 2021.

07/2021 -- Our paper titled Scene Designer: a Unified Model for Scene Search and Synthesis from Sketch has been accepted at ICCV 2021 Workshop on Sketching and Human Expressivity.

03/2021 -- [DECaDE] our paper titled OSCAR-Net: Object-centric Scene Graph Attention for Image Attribution has been accepted at ICCV 2021.

03/2021 -- [DECaDE] our paper titled Deep Image Comparator: Learning to Visualize Editorial Change has been accepted at CVPR 2021 Workshop on Media Forensics.