Deriving high-level scene descriptions from deep scene CNN features

Akram Bayat; Marc Pomplun

doi:10.1109/IPTA.2017.8310111

Deriving high-level scene descriptions from deep scene CNN features

Akram Bayat
, Marc Pomplun

Computer Science

University of Massachusetts Boston

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Original language	English
Title of host publication	Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781538618417
DOIs	https://doi.org/10.1109/IPTA.2017.8310111
State	Published - Jul 2 2017
Event	7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017 - Montreal, Canada Duration: Nov 28 2017 → Dec 1 2017

Publication series

Name	Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017
Volume	2018-January

Conference

Conference	7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017
Country/Territory	Canada
City	Montreal
Period	11/28/17 → 12/1/17

ASJC Scopus Subject Areas

Signal Processing
Radiology Nuclear Medicine and imaging

Keywords

Convolutional neural network
Deep learning
Global properties
Scene recognition
Shape of a scene
Spatial layout

Access to Document

10.1109/IPTA.2017.8310111

Cite this

Bayat, A., & Pomplun, M. (2017). Deriving high-level scene descriptions from deep scene CNN features. In Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017 (pp. 1-6). (Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017; Vol. 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IPTA.2017.8310111

Deriving high-level scene descriptions from deep scene CNN features. / Bayat, Akram; Pomplun, Marc.
Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1-6 (Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017; Vol. 2018-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Bayat, A & Pomplun, M 2017, Deriving high-level scene descriptions from deep scene CNN features. in Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017. Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017, vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017, Montreal, Canada, 11/28/17. https://doi.org/10.1109/IPTA.2017.8310111

Bayat A, Pomplun M. Deriving high-level scene descriptions from deep scene CNN features. In Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1-6. (Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017). doi: 10.1109/IPTA.2017.8310111

Bayat, Akram ; Pomplun, Marc. / Deriving high-level scene descriptions from deep scene CNN features. Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1-6 (Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017).

@inproceedings{4a516151e1c740ad85156b1020f915d1,

title = "Deriving high-level scene descriptions from deep scene CNN features",

keywords = "Convolutional neural network, Deep learning, Global properties, Scene recognition, Shape of a scene, Spatial layout",

author = "Akram Bayat and Marc Pomplun",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017 ; Conference date: 28-11-2017 Through 01-12-2017",

year = "2017",

month = jul,

day = "2",

doi = "10.1109/IPTA.2017.8310111",

language = "English",

series = "Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--6",

booktitle = "Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017",

}

TY - GEN

T1 - Deriving high-level scene descriptions from deep scene CNN features

AU - Bayat, Akram

AU - Pomplun, Marc

PY - 2017/7/2

Y1 - 2017/7/2

KW - Convolutional neural network

KW - Deep learning

KW - Global properties

KW - Scene recognition

KW - Shape of a scene

KW - Spatial layout

UR - https://www.scopus.com/pages/publications/85050589699

UR - https://www.scopus.com/pages/publications/85050589699#tab=citedBy

U2 - 10.1109/IPTA.2017.8310111

DO - 10.1109/IPTA.2017.8310111

M3 - Conference contribution

AN - SCOPUS:85050589699

T3 - Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017

SP - 1

EP - 6

BT - Proceedings of the 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th International Conference on Image Processing Theory, Tools and Applications, IPTA 2017

Y2 - 28 November 2017 through 1 December 2017

ER -

Deriving high-level scene descriptions from deep scene CNN features

Publication series

Conference

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this