Unsupervsied Deep Multimodal Learning for Object Detection

Summer 2016

Jacob Huh : Electrical Engineering and Computer Science

Mentor: Alexei A. Efros

Recent advances in the artificial neural networks have shown immense success in the computer vision field. While supervised learning tasks in object detection has shown to be a feasible task,  the necessity of the supervision in the task is not observed in humans. Despite the fact that object Information is a unison of all senses,  currently, object detection tasks are restricted to visual data. I will be researching on using multi modal data to tackle object detection in a supervised and unsupervised setting.

I would like to thank the Rose Hills Foundation for funding my research stipend. The donation allows me to focus on my work and alleviate financial problems over the summer. As a senior, the stipend allows me to conclude my undergraduate career with a project that encompasses all my knowledge that I have gained throughout the years.