Just Because Your Data Is Unstructured Doesn’t Mean it Should be Onerous

Visual data (images/videos) is rich in valuable insights. Data science and ML techniques can help understand visual content and enable better customer experience across application domains, in turn driving its exponential growth. A key factor for success in visual ML is to get the foundational data infrastructure right, which can be extremely challenging and time consuming due to a lack of data management solutions designed with visual data or data science in mind.

In this talk, I will start by briefly highlighting why visual data today needs special treatment and how this can be achieved. I will also dive deeper into certain architecture and design decisions that have worked well so far as we build such a database ourselves, and give you a quick preview of our product, ApertureDB, and where we are going next.