Semantic video segmentation: Exploring inference efficiency
Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
We explore the efficiency of the CRF inference beyond image level semantic segmentation and perform joint inference in video frames. The key idea is to combine best of two worlds: semantic co-labeling and more expressive models. Our formulation enables us to perform inference over ten thousand images within seconds and makes the system amenable to perform video semantic segmentation most effectively. On CamVid dataset, with TextonBoost unaries, our proposed method achieves up to 8% improvement in accuracy over individual semantic image segmentation without additional time overhead. The source code is available at https: //github. com/subtri/video inference.
Originalsprog | Engelsk |
---|---|
Tidsskrift | ISOCC 2015 - International SoC Design Conference: SoC for Internet of Everything (IoE) |
Sider (fra-til) | 157-158 |
Antal sider | 2 |
DOI | |
Status | Udgivet - 8 feb. 2016 |
Eksternt udgivet | Ja |
Begivenhed | 12th International SoC Design Conference, ISOCC 2015 - Gyeongju, Sydkorea Varighed: 2 nov. 2015 → 5 nov. 2015 |
Konference
Konference | 12th International SoC Design Conference, ISOCC 2015 |
---|---|
Land | Sydkorea |
By | Gyeongju |
Periode | 02/11/2015 → 05/11/2015 |
Bibliografisk note
Publisher Copyright:
© 2015 IEEE.
ID: 301828670