An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network

Autor: Matei Mancas, Bernard Gosselin, Titus Zaharia, Marc Decombas, Marius Preda, Nathan Hubens, Thierry Dutoit

Publikováno v: APPIS
APPIS 2020: Proceedings of the 3rd International Conference on Applications of Intelligent Systems
APPIS 2020: 3rd International Conference on Applications of Intelligent Systems
APPIS 2020: 3rd International Conference on Applications of Intelligent Systems, Jan 2020, Las Palmas de Gran Canaria, Spain. pp.1-6, ⟨10.1145/3378184.3378224⟩

In recent years, deep neural networks have known a wide success in various application domains. However, they require important computational and memory resources, which severely hinders their deployment, notably on mobile devices or for real-time ap

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7ef46939518799294494edf00624eb42

Video summarization of surveillance cameras

Autor: P. Lai, Kelvin Moutet, Marc Decombas, Robert Laganiere

Publikováno v: AVSS

The number of video surveillance cameras has increased by a large amount in recent years. There is therefore a need to process the captured videos such that human operators can quickly review the activities recorded by a camera over a long period of

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::ce26fce06f42e23897855a558bc78982
https://doi.org/10.1109/avss.2016.7738018

An evaluation criterion of saliency models for video seam carving

Autor: Ioannis Cassagne, Robert Laganiere, Thierry Dutoit, Marc Decombas, Bernard Gosselin, Nicolas Riche, Pierre Marighetto, Matei Mancas

Publikováno v: MMSP

Modeling human attention has been arousing a lot of interest due to its numerous applications. The process that allows us to focus on some more important stimuli is defined as the “attention”. Seam carving is an approach to resize images or video

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::aec0aeb0d8604388dcba2e74f0d04c8a
https://doi.org/10.1109/mmsp.2015.7340841

Seam carving modeling for semantic video coding in security applications

Autor: Younous Fellah, Beatrice Pesquet-Popescu, Frederic Dufaux, Erwann Renan, Francois Capman, Marc Decombas

Publikováno v: APSIPA Transactions on Signal and Information Processing
APSIPA Transactions on Signal and Information Processing, Cambridge University Press, 2015, 4, pp.1

International audience; In some security applications, it is important to transmit just enough information to take the right decisions. Traditional video codecs try to maximize the global quality, irrespectively of the video content pertinence for ce

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bd7729794f48f48e6028bbbea320ab45
https://doi.org/10.1017/atsip.2015.4

Improved seam carving for semantic video cod

Autor: Erwann Renan, B. Pequet-Popesu, Frederic Dufaux, Marc Decombas, Francois Capman

Publikováno v: MMSP

Traditional video codecs like H.264/AVC encode video sequences to minimize the Mean Squared Error (MSE)at a given bitrate. Seam carving is a content-aware resizing method. In this paper, we propose a semantic video compression scheme based on seam ca

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5d6f4ec9a34b8f27247002680ce68dca
https://doi.org/10.1109/mmsp.2012.6343415