3 citations · 3 across the 5 of their papers we have counts for
5 papers
Improving Personalized Image Generation through Social Context Feedback
Parul Gupta, Abhinav Dhall, Thanh-Toan Do
Personalized image generation, where reference images of one or more subjects are used to generate their image according to a scene description, has gathered significant interest i…
Multiverse Through Deepfakes: The MultiFakeVerse Dataset of Person-Centric Visual and Conceptual Manipulations
Parul Gupta, Shreya Ghosh, Tom Gedeon +2
The rapid advancement of GenAI technology over the past few years has significantly contributed towards highly realistic deepfake content generation. Despite ongoing efforts, the r…
Sing-On-Your-Beat: Simple Text-Controllable Accompaniment Generations
Quoc-Huy Trinh, Minh-Van Nguyen, Trong-Hieu Nguyen Mau +2
Singing is one of the most cherished forms of human entertainment. However, creating a beautiful song requires an accompaniment that complements the vocals and aligns well with the…
Self-supervised Learning for Acoustic Few-Shot Classification
Jingyong Liang, Bernd Meyer, Isaac Ning Lee +1
Labelled data are limited and self-supervised learning is one of the most important approaches for reducing labelling requirements. While it has been extensively explored in the im…
Conditional Distribution Modelling for Few-Shot Image Synthesis with Diffusion Models
Parul Gupta, Munawar Hayat, Abhinav Dhall +1
Few-shot image synthesis entails generating diverse and realistic images of novel categories using only a few example images. While multiple recent efforts in this direction have a…