no code implementations • 19 Jan 2024 • Nam Le, Honglei Zhang, Francesco Cricri, Ramin G. Youvalari, Hamed Rezazadegan Tavakoli, Emre Aksu, Miska M. Hannuksela, Esa Rahtu
Image coding for machines (ICM) aims at reducing the bitrate required to represent an image while minimizing the drop in machine vision analysis accuracy.
no code implementations • 8 Oct 2022 • Honglei Zhang, Francesco Cricri, Hamed Rezazadegan Tavakoli, Emre Aksu, Miska M. Hannuksela
Nevertheless, the proposed LIC systems are still inferior to the state-of-the-art traditional techniques, for example, the Versatile Video Coding (VVC/H. 266) standard, due to either their compression performance or decoding complexity.
no code implementations • 16 Dec 2021 • Nannan Zou, Honglei Zhang, Francesco Cricri, Ramin G. Youvalari, Hamed R. Tavakoli, Jani Lainema, Emre Aksu, Miska Hannuksela, Esa Rahtu
In this work, we propose an end-to-end learned video codec that introduces several architectural novelties as well as training novelties, revolving around the concepts of adaptation and attention.
no code implementations • 24 Aug 2021 • Honglei Zhang, Francesco Cricri, Hamed R. Tavakoli, Nannan Zou, Emre Aksu, Miska M. Hannuksela
Recently, multi-scale autoregressive models have been proposed to address this limitation.
no code implementations • 31 Jul 2020 • Nannan Zou, Honglei Zhang, Francesco Cricri, Hamed R. -Tavakoli, Jani Lainema, Miska Hannuksela, Emre Aksu, Esa Rahtu
In a second phase, the Model-Agnostic Meta-learning approach is adapted to the specific case of image compression, where the inner-loop performs latent tensor overfitting, and the outer loop updates both encoder and decoder neural networks based on the overfitting performance.
no code implementations • 20 Apr 2020 • Nannan Zou, Honglei Zhang, Francesco Cricri, Hamed R. -Tavakoli, Jani Lainema, Emre Aksu, Miska Hannuksela, Esa Rahtu
One of the core components of conventional (i. e., non-learned) video codecs consists of predicting a frame from a previously-decoded frame, by leveraging temporal correlations.
no code implementations • 3 Jul 2019 • Peter Fasogbon, Emre Aksu
This is not necessarily true for special imaging device such as fisheye lenses.
no code implementations • 24 May 2019 • Caglar Aytekin, Francesco Cricri, Antti Hallapuro, Jani Lainema, Emre Aksu, Miska Hannuksela
In this manuscript we propose two objective terms for neural image compression: a compression objective and a cycle loss.
no code implementations • 10 May 2019 • Yat Hong Lam, Alireza Zare, Caglar Aytekin, Francesco Cricri, Jani Lainema, Emre Aksu, Miska Hannuksela
In this paper, we present a novel approach for fine-tuning a decoder-side neural network in the context of image compression, such that the weight-updates are better compressible.
no code implementations • 3 May 2019 • Caglar Aytekin, Francesco Cricri, Emre Aksu
In this paper we apply a compressibility loss that enables learning highly compressible neural network weights.
no code implementations • 28 May 2018 • Caglar Aytekin, Xingyang Ni, Francesco Cricri, Jani Lainema, Emre Aksu, Miska Hannuksela
In this work, we propose an end-to-end block-based auto-encoder system for image compression.
no code implementations • 8 Feb 2018 • Caglar Aytekin, Francesco Cricri, Emre Aksu
In this work, we propose an improvement over DCF based trackers by combining saliency based and other features based filter responses.
no code implementations • 1 Feb 2018 • Caglar Aytekin, Xingyang Ni, Francesco Cricri, Emre Aksu
We show the effect of l2 normalization on anomaly detection accuracy.
no code implementations • 24 Jan 2018 • Caglar Aytekin, Francesco Cricri, Lixin Fan, Emre Aksu
In order to have an in-depth theoretical understanding, in this manuscript, we investigate the graph degree in spectral graph clustering based and kernel based point of views and draw connections to a recent kernel method for the two sample problem.
no code implementations • 27 Dec 2017 • Caglar Aytekin, Xingyang Ni, Francesco Cricri, Lixin Fan, Emre Aksu
By using these encoded images, we train a memory-efficient network using only 0. 048\% of the number of parameters that other deep salient object detection networks have.
1 code implementation • 6 Dec 2016 • Francesco Cricri, Xingyang Ni, Mikko Honkala, Emre Aksu, Moncef Gabbouj
Thanks to the recurrent connections, the decoder can exploit temporal summaries generated from all layers of the encoder.