Semantic video segmentation

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

Tripathi, S, Belongie, S, Hwang, Y & Nguyen, T 2016, 'Semantic video segmentation: Exploring inference efficiency', ISOCC 2015 - International SoC Design Conference: SoC for Internet of Everything (IoE), pp. 157-158. https://doi.org/10.1109/ISOCC.2015.7401766

APA

Tripathi, S., Belongie, S., Hwang, Y., & Nguyen, T. (2016). Semantic video segmentation: Exploring inference efficiency. ISOCC 2015 - International SoC Design Conference: SoC for Internet of Everything (IoE), 157-158. https://doi.org/10.1109/ISOCC.2015.7401766

Vancouver

Tripathi S, Belongie S, Hwang Y, Nguyen T. Semantic video segmentation: Exploring inference efficiency. ISOCC 2015 - International SoC Design Conference: SoC for Internet of Everything (IoE). 2016 Feb 8;157-158. https://doi.org/10.1109/ISOCC.2015.7401766

Author

Tripathi, Subarna ; Belongie, Serge ; Hwang, Youngbae ; Nguyen, Truong. / Semantic video segmentation : Exploring inference efficiency. In: ISOCC 2015 - International SoC Design Conference: SoC for Internet of Everything (IoE). 2016 ; pp. 157-158.

Bibtex

@inproceedings{980481283cfc49248c4df69ba80caf92,

title = "Semantic video segmentation: Exploring inference efficiency",

abstract = "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.",

keywords = "approximate inference, co-labelling, higher-order-clique, semantic segmentation",

author = "Subarna Tripathi and Serge Belongie and Youngbae Hwang and Truong Nguyen",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 12th International SoC Design Conference, ISOCC 2015 ; Conference date: 02-11-2015 Through 05-11-2015",

year = "2016",

month = feb,

day = "8",

doi = "10.1109/ISOCC.2015.7401766",

language = "English",

pages = "157--158",

journal = "ISOCC 2015 - International SoC Design Conference: SoC for Internet of Everything (IoE)",

}

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

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

Forskning