Thoughts and Theory, Computer Vision Tutorials

T-3 sample results (Rank 10). For each query (row) one or more faces of the probe returned the corresponding samples of the gallery as top 10. Here, x (red) depicts false predictions, while true predictions display the relationship type (in green): P for a parent; C for a child; S for a sibling. The author created this image [3].

Table of Contents

· Table of Contents
· Introduction
· Background Information
Problem Statement
The Data
Source Code
· Results and Analysis
Quantitative Results
2020 Results (last RFIW)
Top-ranked families:
Lowest-ranked family:
· Other Use-Cases for Recognizing FIW
· In Summary
· Related Blogs
2021 RFIW Data Challenge
Families In…

In today’s vast information superhighway has leaked into our day-to-day lives in the form of excessive printing of various content readily available at the click of a mouse. Furthermore, traditional views stuck on the misperceived notion that ebooks, digital PDFs, and electronic note-taking does not suffice due to the preference of the ‘look’ and ‘feel’ of textbooks, actual pencil & paper, along with the ability to put heads down (i.e., lean over the material), that has driven many away from digital solutions. In other words, I recall thinking myself that ebooks just were not the same as having a physical copy of a textbook to tab, markup, and later recall: all the while being posed over the textbook such that my head being down was a sort of means to get in the zone of studying the text. Although, it is true that when ebooks were first introduced the available hardware was not yet available for optimal usage (e.g., the need to read a textbook from a laptop felt unnatural to me, for the tools like highlighting, marking up, and tabbing was not a fluid process). Nowadays, this is not the case: many available technologies can truly optimize various aspects of your life, and especially those involved in fields that involve pens, paper, books, files, etc., which is a majority, nowadays. Less is more; minimalism is not a trend, but an adaptation to the new world we live in, as complexities are inherent so it is best to simplify all possible aspects. Hence, let the problems be complex, and the space for which the problems are solved be simple. Now, how to best optimize our space? Source: Pixabay

Table of Contents

· Overview
· Tips to Improve your Space
TIP 1: The days of Printing are Over
TIP 2: No More Notebooks, Paper, or Pens
TIP 3: Update Space to Adapt to TIPs 1 and 2
· In Summary


Over time, ideally…

Snapshot from the keynote: video embedded below! (Screenshot by author)

Table of Contents

  1. Overview
  2. Title
  3. Abstract
  4. Biography


Learn more about AMFG via the workshop website or previous medium post!


Representations for Content Creation, Manipulation, and Animation


“What I cannot create, I do not understand,” said the famous writing on Dr. Feynman’s blackboard. The ability to create or to change objects requires us…

Vast applications based on depth-sensing technology. Image by Author.

There are many real-world uses for depth estimation, with practical significance in robotics, computer vision, and immersive displays (see figure above). We will be looking at depth estimation as a multi-image problem. Multi-view (or image) problems span different problem domains. For instance,

  1. Stereo vision
  2. Structure from motion
  3. Optical flow


Image via Pixabay

For those who have yet to explore Chrome Extensions (per Chrome Web Store), nowadays, there is an abundance of extensions to add on — each designed to enhance the interface, the potential for progress (i.e., productivity), and the features available with an assortment of intentions. Recently, I am setting up…

Face verification data with priority to balance in gender, ethnicity, and identity.

Our paper — FR: Too bias, or Not Too Bias? — published as part of The Workshop of Fair, Data-Efficient, and Trusted Computer Vision held in conjunction with the 2020 Conference on Computer Vision and Pattern Recognition (CVPR).

The purpose of this brief tutorial is to provide the reader with…

Joseph Robinson, PhD

Full-time at Vicarious Surgical. Phd at NEU ‘20. Focus: applied ML w emphasis on vision, big data, automatic face understanding.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store