Hanoch kremerMaMMUT — A Simple Architecture for Joint Learning for Multi-Modal Tasks (Google)•Common approaches for Multi-Modal (MM) tasksSep 24, 2023Sep 24, 2023
Hanoch kremerVideo Retrieval and Indexing — relax over data requirements by using collaborative expertsBased on one of the works done by Zisseman lab in Oxford trying to improve video retrieval challenge with the following scheme:Sep 10, 2021Sep 10, 2021
Hanoch kremerEfficient Convolutional Network Learning — ScatterNetWhen I led a DNN project based on few data ~20K examples for biometric ID, based on poor quality modality, I was trying to find out ways…Apr 6, 2020Apr 6, 2020