CloudCV: Large-Scale Distributed Computer Vision as a Cloud Service

We are witnessing a proliferation of massive visual data. Unfortunately scaling existing computer vision algorithms to large datasets leaves researchers repeatedly solving the same algorithmic, logistical, and infrastructural problems. Our goal is to democratize computer vision; one should not have to be a computer vision, big data and distributed computing expert to have access to state-of-the-art distributed computer vision algorithms. We present CloudCV, a comprehensive system to provide access to state-of-the-art distributed computer vision algorithms as a cloud service through a Web Interface and APIs. Harsh Agrawal Virginia Tech, e-mail: [email protected] Clint Solomon Mathialagan Virginia Tech e-mail: [email protected] Yash Goyal Virginia Tech e-mail: [email protected] Neelima Chavali Virginia Tech e-mail: [email protected] Prakriti Banik Virginia Tech e-mail: [email protected] Akrit Mohapatra Virginia Tech e-mail: [email protected] Ahmed Osman Imperial College London e-mail: [email protected] Dhruv Batra Virginia Tech e-mail: [email protected] 1 ar X iv :1 50 6. 04 13 0v 3 [ cs .C V ] 1 3 Fe b 20 17 2 Agrawal, Mathialagan, Goyal, Chavali, Banik, Mohapatra, Osman, Batra