Efficient deep CNNs for cross-modal automated computer vision under time and space constraints

Amirian, Mohammadreza; Rombach, Katharina; Tuggener, Lukas; Schilling, Frank-Peter; Stadelmann, Thilo

doi:10.21256/zhaw-18357

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-18357

Publication type:	Conference paper
Type of review:	No review
Title:	Efficient deep CNNs for cross-modal automated computer vision under time and space constraints
Authors:	Amirian, Mohammadreza Rombach, Katharina Tuggener, Lukas Schilling, Frank-Peter Stadelmann, Thilo
et. al:	No
DOI:	10.21256/zhaw-18357
Conference details:	ECML-PKDD 2019, Würzburg, Germany, 16-19 September 2019
Issue Date:	2019
Publisher / Ed. Institution:	ZHAW Zürcher Hochschule für Angewandte Wissenschaften
Language:	English
Subjects:	AutoDL; Automated deep learning; Convolutional neural networks; MobileNetV2; EfficientNet
Subject (DDC):	006: Special computer methods
Abstract:	We present an automated computer vision architecture to handle video and image data using the same backbone networks. We show empirical results that lead us to adopt MOBILENETV2 as this backbone architecture. The paper demonstrates that neural architectures are transferable from images to videos through suitable preprocessing and temporal information fusion.
URI:	https://digitalcollection.zhaw.ch/handle/11475/18357
Fulltext version:	Accepted version
License (according to publishing contract):	Licence according to publishing contract
Departement:	School of Engineering
Organisational Unit:	Institute of Computer Science (InIT)
Published as part of the ZHAW project:	Ada – Advanced Algorithms for an Artificial Data Analyst
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
2019_Stadelmann_Efficient Deep CNNS_ECML_PKDD_2019.pdf		168.59 kB	Adobe PDF	View/Open

Show full item record

Amirian, M., Rombach, K., Tuggener, L., Schilling, F.-P., & Stadelmann, T. (2019). Efficient deep CNNs for cross-modal automated computer vision under time and space constraints. ECML-PKDD 2019, Würzburg, Germany, 16-19 September 2019. https://doi.org/10.21256/zhaw-18357

Amirian, M. et al. (2019) ‘Efficient deep CNNs for cross-modal automated computer vision under time and space constraints’, in ECML-PKDD 2019, Würzburg, Germany, 16-19 September 2019. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. Available at: https://doi.org/10.21256/zhaw-18357.

M. Amirian, K. Rombach, L. Tuggener, F.-P. Schilling, and T. Stadelmann, “Efficient deep CNNs for cross-modal automated computer vision under time and space constraints,” in ECML-PKDD 2019, Würzburg, Germany, 16-19 September 2019, 2019. doi: 10.21256/zhaw-18357.

AMIRIAN, Mohammadreza, Katharina ROMBACH, Lukas TUGGENER, Frank-Peter SCHILLING und Thilo STADELMANN, 2019. Efficient deep CNNs for cross-modal automated computer vision under time and space constraints. In: ECML-PKDD 2019, Würzburg, Germany, 16-19 September 2019. Conference paper. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. 2019

Amirian, Mohammadreza, Katharina Rombach, Lukas Tuggener, Frank-Peter Schilling, and Thilo Stadelmann. 2019. “Efficient Deep CNNs for Cross-Modal Automated Computer Vision under Time and Space Constraints.” Conference paper. In ECML-PKDD 2019, Würzburg, Germany, 16-19 September 2019. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. https://doi.org/10.21256/zhaw-18357.

Amirian, Mohammadreza, et al. “Efficient Deep CNNs for Cross-Modal Automated Computer Vision under Time and Space Constraints.” ECML-PKDD 2019, Würzburg, Germany, 16-19 September 2019, ZHAW Zürcher Hochschule für Angewandte Wissenschaften, 2019, https://doi.org/10.21256/zhaw-18357.