Module 5- Part 4- Advance computer vision- Object detection (R-CNN, YOLO)- segmentation-captioning

Relevant playlists:
Machine Learning Concepts, simply explained: Machine Learning Concepts (Simply Exp...
Deep Learning Concepts, simply explained: Deep Learning Concepts (Simply Explai...

Instructor: Pedram Jahangiry

All of the slides and notebooks used in this series are available on my GitHub page, so you can follow along and experiment with the code on your own.
https://github.com/PJalgotrader

Lecture Outline:
0:00 Roadmap and recap.
1:37 Beyond classification (object detection, image segmentation, image captioning)
5:46 Object detection details
13:08 R-CNN region-based CNN
16:12 Fast R-CNN
19:01 Faster R-CNN
21:30 Comparing R-CNN-based models
23:56 YOLO (You only look once)
29:43 YOLO-Anchor boxes
34:02 YONO-Non max suppression (NMS)
36:18 Image segmentation (semantic vs instance) FCN:  Fully Convolutional Network
42:20 Image captioning