# Are All Pixels Equally Important?

- Institution: CERN
- Department: CERN Computing Seminar
- Speaker: Gökhan Dr. Yildirim
- Year: 2015
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3004660)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

When we look at our environment, we primarily pay attention to visually distinctive objects. We refer to these objects as visually important or salient. For efficient visual processing, the human visual system identifies salients objects and dedicates most of its processing resources to them. An analogous resource allocation can be performed by salient-object detection algorithms, which identify objects of interest in an image. Consequently, thanks to salient-object detection, complex visual computing operations can focus on the important parts of the visual data and can save time and resources.

About the speaker

Dr. Gokhan Yildirim is a research assistant in the School of Computer and Communication Sciences (IC) at the École Polytechnique Fédérale de Lausanne (EPFL). His research interests include image understanding, multimedia, pattern recognition, machine learning, salient-object detection on images & videos and its applications on image processing and computer vision. He completed his B.Sc. and M.Sc. degrees in Middle East Technical University (METU) in Turkey and his Ph.D. in EPFL. .

0:00:00 Slide 1

0:02:27 Slide 2

0:02:52 Slide 3

0:02:58 Slide 4

0:03:13 Slide 5

0:03:20 Slide 6

0:03:41 Slide 7

0:03:48 Slide 8

0:03:56 Slide 9

0:04:42 Slide 10

0:04:48 Slide 11

0:04:56 Slide 12

0:05:11 Slide 13

0:05:18 Slide 14

0:05:28 Slide 15

0:06:09 Slide 16

0:06:13 Slide 17

0:06:22 Slide 18

0:06:48 Slide 19

0:06:53 Slide 20

0:07:30 Slide 21

0:07:45 Slide 22

0:07:51 Slide 23

0:07:57 Slide 24

0:08:05 Slide 25

0:08:11 Slide 26

0:08:21 Slide 27

0:08:44 Slide 28

0:09:12 Slide 29

0:09:31 Slide 30

0:09:45 Slide 31

0:09:51 Slide 32

0:09:58 Slide 33

0:10:50 Slide 34

0:11:09 Slide 35

0:11:15 Slide 36

0:11:20 Slide 37

0:11:29 Slide 38

0:11:49 Slide 39

0:11:55 Slide 40

0:12:05 Slide 41

0:12:12 Slide 42

0:12:17 Slide 43

0:12:29 Slide 44

0:13:07 Slide 45

0:13:14 Slide 46

0:13:22 Slide 47

0:14:38 Slide 48

0:14:48 Slide 49

0:15:02 Slide…

## Lectures

1. [Are All Pixels Equally Important?](https://invisiblenetwork.ai/learn/cern/3004660/2527e053313d), 1 h 2 min (CERN's player)