Pose Extraction in Retail Industry

In the age when vision technology thrive remarkably, Computer Vision and its application become more and more rife, particularly in retail industry where a host of issues remains unsolved. In AWL Vietnam, we are concentrating on developing a system detecting wrongdoings and analyzing customers’s behaviours. One of the concrete pillar... [Read More]

Triplet loss and its sampling strategies

In my post a year ago, I did discuss about a deep learning technique called DeepRanking. Its core is the triplet loss, which helps to minimize the distance between images in the same group and maximize the ones from different categories . At the moment, I’m working in a project... [Read More]

Mixture Models in Clustering

In the most recent post, I talked about some famous clustering algorithms and they work well in reality. However, we the data scientists don’t really like these methods because of one thing: they are deterministic and nothing in data science have that deterministic, especially in unsupervised learning: we don’t have... [Read More]

PhD and me

The title of this blog is inspired by my favorite film Marley and me. Back to the blog, obviously it is not about sharing knowledge. But don’t be angry at me, it is still about the way I will become a data scientist. I will tell to all of you... [Read More]

Clustering and Retrieval (Part 2)

In this blog, I will dive deeper into the techniques of clustering. Clustering or segmentation has wide applications, particularly in RecSys, when you can have the insight about users’s preferences given their activities. For examples, assuming that we have a list of articles that user A reads everyday, we can... [Read More]