CloudCV: Large Scale Distributed Computer Vision as a Cloud Service Harsh Agrawal, Clint Solomon Mathialagan, Yash Goyal, Neelima Chavali, Prakriti Banik, Akrit Mohapatra, Ahmed Osman, Dhruv Batra Abstract We are witnessing a proliferation of massive visual data. Unfortunately scaling existing computer vision algorithms to large datasets leaves researchers re- peatedly solving the same algorithmic, logistical, and infrastructural problems. Our goal is to democratize computer vision; one should not have to be a computer vi- sion, big data and distributed computing expert to have access to state-of-the-art distributed computer vision algorithms. We present CloudCV, a comprehensive sys- tem 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 arXiv:1506.04130v3 [cs.CV] 13 Feb 2017 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 2 Agrawal, Mathialagan, Goyal, Chavali, Banik, Mohapatra, Osman, Batra 1 Introduction A recent World Economic Form report [18] and a New York Times article [38] de- clared data to be a new class of economic asset, like currency or gold. Visual content is arguably the fastest growing data on the web. Photo-sharing websites like Flickr and Facebook now host more than 6 and 90 Billion photos (respectively).