Reads

Explanations of a concept, built from several papers rather than one.

31 reads, newest first.

Entries marked “on VisionWizard” are by other writers of the publication I ran; they open on Medium under the author's name. The VisionWizard tab lists all of them.

Series

Text2SQL · 5 parts, in order

1. 1Text2SQL — Part 1: Introduction
2. 2Text2SQL — Part 2: Datasets
3. 3Text2SQL — Part 3: Baseline Models
4. 4Text2SQL — Part 4: State-Of-The-Art Models
5. 5Text2SQL — Part 5: Final Insights

Transformers in Vision · 12 parts, in order

1. 1Attention Before Transformers — Score, Squash, Multiply
2. 2Query, Key, Value — Dot-Product Attention from Scratch
3. 3Attention Is All You Need — The Transformer, Block by Block
4. 4Attention Meets Pixels — Windows, Axes and the First Fully Attentional Networks
5. 5DETR — Detection as Set Prediction, No Anchors and No NMS
6. 6An Image Is Worth 16×16 Words — ViT, Patch by Patch
7. 7DeiT — Training a Vision Transformer on ImageNet Alone
8. 8Swin Transformer — Windows, Shifts and a Pyramid for Dense Prediction
9. 9Convolutions Strike Back — Was It the Attention or the Recipe?
10. 10Masked Autoencoders — Hide 75 %, Encode the Rest
11. 11CLIP — Learning Pictures From the Words Next to Them
12. 12Vision Transformers Today — May 2022 to October 2026, Year by Year

Multiple View Geometry · 11 parts, in order

1. 1The Pinhole Camera — A Pixel Is a Ray
2. 2Where Is the Camera? — R, C and t
3. 3Points at Infinity — Horizons, Vanishing Points and the Floor
4. 4Finding the Camera From Known Points — P by Least Squares
5. 5Lens Distortion — Bending Straight Lines Back
6. 6What calibrateCamera Actually Does
7. 7Epipolar Geometry — A Point Becomes a Line
8. 8Triangulation — Two Rays That Almost Meet
9. 9From Matches to Motion — Four Cameras, One Right Answer
10. 10Stereo Depth — Rectification and Z = fB/d
11. 11From Two Photos to a Point Cloud