Traditionally, computer vision problems have been classified into three levels: low (image to image), middle (image to features), and high (features to analysis) . Some typical low-level vision problems include optical flow , stereo  and intrinsic image decomposition . The solution to these problems would then be combined to solve higher level problems, such as action recognition and visual question answering.
|Name||Lecture Notes in Computer Science|
|Name||Image Processing, Computer Vision, Pattern Recognition, and Graphics|
|Conference||European Conference on Computer Vision 2018|
|Abbreviated title||ECCV 2018|
|Period||8/09/18 → 14/09/18|