Hila Manor

AudioEditingCode. Python

GaussianDenoisingPosterior. We derive a fundamental property of the posterior distribution in Gaussian denoising, and use it to propose a new way for uncertainty visualization, which requires no training or fine-tuning.

ee046746-computer-vision. Jupyter Notecbook tutorials for the Technion's EE Computer Vision course

CycleTransformer. Final assignment in the NLP course at the Technion (IEM097215). In this assignment we propose a novel architecture to handle both Text-to-Image translation and Image-to-Text translation tasks on paired data, using a unified architecture of transformers and CNNs and enforcing cycle consistency.

Generative-deep-features. Students Project at the Technion for generating natural looking images from a single image, using deep features of VGG19 and a hierarchical architecture based on SinGAN

Scene-Understanding-Based-on-Text-Extraction. An algorithm (and a wrapping system) for finding the geographic location of a set of given photos based on extracting and analyzing text in the images.