3 citations · 5 across the 9 of their papers we have counts for
13 papers
Functional compatibility as a determinant of persistent neural learning
Hossein Javidnia
Neural networks can acquire new capabilities while damaging existing ones, but what determines whether new learning persists remains unclear. We identify functional compatibility,…
Semantic Sections: An Atlas-Native Feature Ontology for Obstructed Representation Spaces
Hossein Javidnia
Recent interpretability work often treats a feature as a single global direction, dictionary atom, or latent coordinate shared across contexts. We argue that this ontology can fail…
A Gauge Theory of Superposition: Toward a Sheaf-Theoretic Atlas of Neural Representations
Hossein Javidnia
We develop a discrete gauge-theoretic framework for superposition in large language models (LLMs) that replaces the single-global-dictionary premise with a sheaf-theoretic atlas of…
Multi-scale Attention-Guided Intrinsic Decomposition and Rendering Pass Prediction for Facial Images
Hossein Javidnia
Accurate intrinsic decomposition of face images under unconstrained lighting is a prerequisite for photorealistic relighting, high-fidelity digital doubles, and augmented-reality e…
Benchmarking Microsaccade Recognition with Event Cameras: A Novel Dataset and Evaluation
Waseem Shariff, Timothy Hanley, Maciej Stec +2
Microsaccades are small, involuntary eye movements vital for visual perception and neural processing. Traditional microsaccade studies typically use eye trackers or frame-based ana…
Leveraging AV1 motion vectors for Fast and Dense Feature Matching
Julien Zouein, Hossein Javidnia, François Pitié +1
We repurpose AV1 motion vectors to produce dense sub-pixel correspondences and short tracks filtered by cosine consistency. On short videos, this compressed-domain front end runs c…
High Fidelity Synthetic Face Generation for Rosacea Skin Condition from Limited Data
Anwesha Mohanty, Alistair Sutherland, Marija Bezbradica +1
Similar to the majority of deep learning applications, diagnosing skin diseases using computer vision and deep learning often requires a large volume of data. However, obtaining su…
An Advert Creation System for 3D Product Placements
Ivan Bacher, Hossein Javidnia, Soumyabrata Dev +8
Over the past decade, the evolution of video-sharing platforms has attracted a significant amount of investments on contextual advertising. The common contextual advertising platfo…
Methodology for Building Synthetic Datasets with Virtual Humans
Shubhajit Basak, Hossein Javidnia, Faisal Khan +2
Recent advances in deep learning methods have increased the performance of face detection and recognition systems. The accuracy of these models relies on the range of variation pro…
High-Accuracy Facial Depth Models derived from 3D Synthetic Data
Faisal Khan, Shubhajit Basak, Hossein Javidnia +2
In this paper, we explore how synthetically generated 3D face models can be used to construct a high accuracy ground truth for depth. This allows us to train the Convolutional Neur…
Background Matting
Hossein Javidnia, François Pitié
The current state of the art alpha matting methods mainly rely on the trimap as the secondary and only guidance to estimate alpha. This paper investigates the effects of utilising…
Identifying Candidate Spaces for Advert Implantation
Soumyabrata Dev, Hossein Javidnia, Murhaf Hossari +7
Virtual advertising is an important and promising feature in the area of online advertising. It involves integrating adverts onto live or recorded videos for product placements and…
Versatile Auxiliary Classifier with Generative Adversarial Network (VAC+GAN)
Shabab Bazrafkan, Hossein Javidnia, Peter Corcoran
One of the most interesting challenges in Artificial Intelligence is to train conditional generators which are able to provide labeled adversarial samples drawn from a specific dis…