I am new to image processing. I am trying to understand CNNs from this blog post. Here's an excerpt from that article that mentions these terms.
A ConvNet is able to successfully capture the Spatial and Temporal dependencies in an image through the application of relevant filters. The architecture performs a better fitting to the image dataset due to the reduction in the number of parameters involved and reusability of weights.
I am not able to understand the terms spatial and temporal, and their respective dependencies in images. I have encountered the spatial and temporal many times. However, still, I am not able to understand how space (spatial) and temporal(time) concepts map to an image.
(By the way, in the quote above, what does the term "reusability of weights" mean?)