3 papers
cs.CV2022
Detection Masking for Improved OCR on Noisy Documents
Daniel Rotman, Ophir Azulai, Inbar Shapira +2
Optical Character Recognition (OCR), the task of extracting textual information from scanned documents is a vital and broadly used technology for digitizing and indexing physical d…
cs.CV2020
Noise Estimation Using Density Estimation for Self-Supervised Multimodal Learning
Elad Amrani, Rami Ben-Ari, Daniel Rotman +1
One of the key factors of enabling machine learning models to comprehend and solve real-world tasks is to leverage multimodal data. Unfortunately, annotation of multimodal data is…
cs.CV2019
ILS-SUMM: Iterated Local Search for Unsupervised Video Summarization
Yair Shemer, Daniel Rotman, Nahum Shimkin
In recent years, there has been an increasing interest in building video summarization tools, where the goal is to automatically create a short summary of an input video that prope…