.. _150218_1130_hardcore_data_science_04:

==================================
Visual Understanding Beyond Naming
==================================

http://strataconf.com/big-data-conference-ca-2015/public/schedule/detail/40181

-------
Summary
-------

If you torture data long enough, it will confess.


"90% of the traffic will be visual data" -- Cisco
This is "Big Data", which is too big for humans.

Visual data is "digital dark matter" because it's noisy, unsegmented, high-entropy, two or three dimentional, so it is difficult to handle.


-------------------------------
Visual similarity via semantics
-------------------------------

Using words to understand/index pictures.
Object naming -> Object categorization
Image labeling (e.g., with CNNs + ImageNet)


------------
Two problems
------------

#. Long tails! We have huge amount of data.
#. There are many more things in our visual world.


------------
Visual world
------------

* Not one-to-one (Visual world -> City)
* The language bottleneck