On Overparametrization in Variational Methods
49 mins 33 secs,
90.63 MB,
MP3
44100 Hz,
249.73 kbits/sec
Share this media item:
Embed this media item:
Embed this media item:
About this item
| Description: |
Bruckstein, A
Monday 4th September 2017 - 12:00 to 12:50 |
|---|
| Created: | 2017-09-06 13:28 |
|---|---|
| Collection: | Variational methods and effective algorithms for imaging and vision |
| Publisher: | Isaac Newton Institute |
| Copyright: | Bruckstein, A |
| Language: | eng (English) |
| Distribution: |
World
(downloadable)
|
| Explicit content: | No |
| Aspect Ratio: | 16:9 |
| Screencast: | No |
| Bumper: | UCS Default |
| Trailer: | UCS Default |
| Abstract: | The talk will survey the idea of using over-parametrization in variational methods, in cases when some parameterized models for the signals of interest are available. Recently such methods were observed to yield state-of-the art results in recovering optic flow fields and in some signal segmentation problems. |
|---|---|
Available Formats
| Format | Quality | Bitrate | Size | |||
|---|---|---|---|---|---|---|
| MPEG-4 Video | 640x360 | 1.94 Mbits/sec | 720.28 MB | View | Download | |
| WebM | 640x360 | 551.31 kbits/sec | 199.88 MB | View | Download | |
| iPod Video | 480x270 | 522.18 kbits/sec | 189.32 MB | View | Download | |
| MP3 * | 44100 Hz | 249.73 kbits/sec | 90.63 MB | Listen | Download | |
| Auto | (Allows browser to choose a format it supports) | |||||