Semantic video segmentation: Exploring inference efficiency
Research output: Contribution to journal › Conference article › Research › peer-review
Standard
Semantic video segmentation : Exploring inference efficiency. / Tripathi, Subarna; Belongie, Serge; Hwang, Youngbae; Nguyen, Truong.
In: ISOCC 2015 - International SoC Design Conference: SoC for Internet of Everything (IoE), 08.02.2016, p. 157-158.Research output: Contribution to journal › Conference article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Semantic video segmentation
T2 - 12th International SoC Design Conference, ISOCC 2015
AU - Tripathi, Subarna
AU - Belongie, Serge
AU - Hwang, Youngbae
AU - Nguyen, Truong
N1 - Publisher Copyright: © 2015 IEEE.
PY - 2016/2/8
Y1 - 2016/2/8
N2 - 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.
AB - 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.
KW - approximate inference
KW - co-labelling
KW - higher-order-clique
KW - semantic segmentation
UR - http://www.scopus.com/inward/record.url?scp=84963812701&partnerID=8YFLogxK
U2 - 10.1109/ISOCC.2015.7401766
DO - 10.1109/ISOCC.2015.7401766
M3 - Conference article
AN - SCOPUS:84963812701
SP - 157
EP - 158
JO - ISOCC 2015 - International SoC Design Conference: SoC for Internet of Everything (IoE)
JF - ISOCC 2015 - International SoC Design Conference: SoC for Internet of Everything (IoE)
Y2 - 2 November 2015 through 5 November 2015
ER -
ID: 301828670