1 code implementation • 14 Jan 2025 • Hanene F. Z. Brachemi Meftah, Wassim Hamidouche, Sid Ahmed Fezza, Olivier Déforges, Kassem Kallas
This demonstrates the vulnerability of DNNs to energy backdoor attacks.
no code implementations • 11 Nov 2024 • Ahmed Telili, Wassim Hamidouche, Ibrahim Farhat, Hadi Amirpour, Christian Timmerer, Ibrahim Khadraoui, Jiajie Lu, The Van Le, Jeonneung Baek, Jin Young Lee, Yiying Wei, Xiaopeng Sun, Yu Gao, JianCheng Huangl, Yujie Zhong
In this paper, we outline the challenge framework, detailing the two competition tracks and highlighting the SR solutions proposed by the top-performing models.
1 code implementation • 22 Aug 2024 • Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene, Abdelmalik Taleb-Ahmed, Abdenour Hadid
Leveraging the benefits of zero-shot learning, FIDAVL exploits the complementarity between vision and language along with soft prompt-tuning strategy to detect fake images and accurately attribute them to their originating source models.
1 code implementation • 3 Apr 2024 • Mamadou Keita, Wassim Hamidouche, Hassen Bougueffa, Abdenour Hadid, Abdelmalik Taleb-Ahmed
This study contributes to the advancement of synthetic image detection by exploiting the capabilities of visual language models such as BLIP-2 and ViTGPT2.
1 code implementation • 2 Apr 2024 • Mamadou Keita, Wassim Hamidouche, Hessen Bougueffa Eutamene, Abdenour Hadid, Abdelmalik Taleb-Ahmed
Advancements in deep image synthesis techniques, such as generative adversarial networks (GANs) and diffusion models (DMs), have ushered in an era of generating highly realistic images.
no code implementations • 2 Apr 2024 • Nassim Sehad, Lina Bariah, Wassim Hamidouche, Hamed Hellaoui, Riku Jäntti, Mérouane Debbah
Over the past two decades, the Internet-of-Things (IoT) has become a transformative concept, and as we approach 2030, a new paradigm known as the Internet of Senses (IoS) is emerging.
1 code implementation • 1 Mar 2024 • Ahmed Telili, Ibrahim Farhat, Wassim Hamidouche, Hadi Amirpour
Omnidirectional or 360-degree video is being increasingly deployed, largely due to the latest advancements in immersive virtual reality (VR) and extended reality (XR) technology.
no code implementations • 28 Feb 2024 • Ahmed Ghorbel, Wassim Hamidouche, Luce Morin
Neural fields, also known as implicit neural representations (INRs), have shown a remarkable capability of representing, generating, and manipulating various data types, allowing for continuous data reconstruction at a low memory footprint.
no code implementations • 31 Oct 2023 • Mohit K. Sharma, Chen-Feng Liu, Ibrahim Farhat, Nassim Sehad, Wassim Hamidouche, Merouane Debbah
However, achieving this immersive experience necessitates encoding omnidirectional videos in high resolution, leading to increased bitrates.
no code implementations • 23 Oct 2023 • Ahmed Telili, Wassim Hamidouche, Hadi Amirpour, Sid Ahmed Fezza, Luce Morin, Christian Timmerer
A key component of HAS is the bitrate ladder, which provides the encoding parameters (e. g., bitrate-resolution pairs) to encode the source video.
no code implementations • 19 Oct 2023 • Thomas Amestoy, Naty Sidaty, Wassim Hamidouche, Pierrick Philippe, Daniel Menard
The results consistently demonstrate that VVC outperforms HEVC, achieving bit-rate savings of up to 40% on the subjective quality scale, particularly at realistic bit-rates and quality levels.
no code implementations • 9 Oct 2023 • Kevin Reuzé, Wassim Hamidouche, Pierrick Philippe, Olivier Déforges
The high efficiency video coding (HEVC) standard and the joint exploration model (JEM) codec incorporate 35 and 67 intra prediction modes (IPMs) respectively, which are essential for efficient compression of Intra coded blocks.
no code implementations • 19 Jul 2023 • Xiaohong Liu, Xiongkuo Min, Wei Sun, Yulun Zhang, Kai Zhang, Radu Timofte, Guangtao Zhai, Yixuan Gao, Yuqin Cao, Tengchuan Kou, Yunlong Dong, Ziheng Jia, Yilin Li, Wei Wu, Shuming Hu, Sibin Deng, Pengxiang Xiao, Ying Chen, Kai Li, Kai Zhao, Kun Yuan, Ming Sun, Heng Cong, Hao Wang, Lingzhi Fu, Yusheng Zhang, Rongyu Zhang, Hang Shi, Qihang Xu, Longan Xiao, Zhiliang Ma, Mirko Agarla, Luigi Celona, Claudio Rota, Raimondo Schettini, Zhiwei Huang, Yanan Li, Xiaotao Wang, Lei Lei, Hongye Liu, Wei Hong, Ironhead Chuang, Allen Lin, Drake Guan, Iris Chen, Kae Lou, Willy Huang, Yachun Tasi, Yvonne Kao, Haotian Fan, Fangyuan Kong, Shiqi Zhou, Hao liu, Yu Lai, Shanshan Chen, Wenqi Wang, HaoNing Wu, Chaofeng Chen, Chunzheng Zhu, Zekun Guo, Shiling Zhao, Haibing Yin, Hongkui Wang, Hanene Brachemi Meftah, Sid Ahmed Fezza, Wassim Hamidouche, Olivier Déforges, Tengfei Shi, Azadeh Mansouri, Hossein Motamednia, Amir Hossein Bakhtiari, Ahmad Mahmoudi Aznaveh
61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions.
no code implementations • 12 Jul 2023 • Ahmed Ghorbel, Wassim Hamidouche, Luce Morin
Over the last few years, neural image compression has gained wide attention from research and industry, yielding promising end-to-end deep neural codecs outperforming their conventional counterparts in rate-distortion performance.
no code implementations • 12 Jul 2023 • Ahmed Ghorbel, Wassim Hamidouche, Luce Morin
Motivated by the efficiency investigation of the Tranformer-based transform coding framework, namely SwinT-ChARM, we propose to enhance the latter, as first, with a more straightforward yet effective Tranformer-based channel-wise auto-regressive prior model, resulting in an absolute image compression transformer (ICT).
no code implementations • 5 Jul 2023 • Ahmed Ghorbel, Wassim Hamidouche, Luce Morin
Recently, the performance of neural image compression (NIC) has steadily improved thanks to the last line of study, reaching or outperforming state-of-the-art conventional codecs.
no code implementations • 1 Oct 2022 • Sid Ahmed Fezza, Mohammed Yasser Ouis, Bachir Kaddar, Wassim Hamidouche, Abdenour Hadid
Thanks to the remarkable advances in generative adversarial networks (GANs), it is becoming increasingly easy to generate/manipulate images.
1 code implementation • 31 Aug 2022 • Ahmed Telili, Sid Ahmed Fezza, Wassim Hamidouche, Hanene F. Z. Brachemi Meftah
Recently, with the growing popularity of mobile devices as well as video sharing platforms (e. g., YouTube, Facebook, TikTok, and Twitch), User-Generated Content (UGC) videos have become increasingly common and now account for a large portion of multimedia traffic on the internet.
Ranked #10 on
Video Quality Assessment
on LIVE-VQC
(using extra training data)
no code implementations • 21 Jul 2022 • Fatemeh Nasiri, Wassim Hamidouche, Luce Morin, Nicolas Dholland, Jean-Yves Aubié
When compared to static bitrate ladder, the proposed method can offer about 13% bitrate reduction in terms of BD-BR with a negligible additional computational overhead.
1 code implementation • 5 Jul 2022 • Ahmed Ghorbel, Ahmed Aldahdooh, Shadi Albarqouni, Wassim Hamidouche
The quality of patient care associated with diagnostic radiology is proportionate to a physician workload.
no code implementations • 30 Jun 2022 • Anup Saha, Wassim Hamidouche, Miguel Chavarrías, Guillaume Gautier, Fernando Pescador, Ibrahim Farhat
Hence, in July 2020 the Versatile Video Coding (VVC) standard was released providing up to 50% bit-rate saving for the same video quality compared to its predecessor High Efficiency Video Coding (HEVC).
1 code implementation • 15 Jun 2022 • Zoubida Ameur, Wassim Hamidouche, Edouard François, Miloš Radosavljević, Daniel Menard, Claire-Hélène Demarty
In the context of video coding, the random nature of film grain makes it both difficult to preserve and very expensive to compress.
no code implementations • 5 Jun 2022 • Ahmed Aldahdooh, Wassim Hamidouche, Olivier Déforges
Adversarial training (AT) is found to be the most promising approach against evasion attacks and it is widely studied for convolutional neural network (CNN).
1 code implementation • 24 May 2022 • Thomas Amestoy, Pierre-loup Cabarat, Guillaume Gautier, Wassim Hamidouche, Daniel Menard
The new generation video coding standard, called Versatile Video Coding (VVC), has been developed by the Joint Video Experts Team, and offers coding capability beyond the previous generation High Efficiency Video Coding (HEVC) standard.
no code implementations • 1 Feb 2022 • Charles Bonnineau, Wassim Hamidouche, Jean-François Travers, Naty Sidaty, Jean-Yves Aubié, Olivier Deforges
Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), and a deep conditional autoencoder with hyperprior (AE-HP) as an enhancement-layer (EL) model.
no code implementations • 8 Dec 2021 • Fatemeh Nasiri, Wassim Hamidouche, Luce Morin, Nicolas Dhollande, Gildas Cocherel
The upcoming video coding standard, Versatile Video Coding (VVC), has shown great improvement compared to its predecessor, High Efficiency Video Coding (HEVC), in terms of bitrate saving.
no code implementations • 14 Sep 2021 • Charles Bonnineau, Wassim Hamidouche, Jerome Fournier, Naty Sidaty, Jean-Francois Travers, Olivier Deforges
With the growing data consumption of emerging video applications and users requirement for higher resolutions, up to 8K, a huge effort has been made in video compression technologies.
no code implementations • 24 Jul 2021 • Ibrahim Farhat, Wassim Hamidouche, Adrien Grill, Daniel Ménard, Olivier Déforges
The proposed module has been integrated in an ASIC UHD decoder targeting energy-aware decoding of VVC videos on consumer devices.
1 code implementation • 12 Jul 2021 • Anouar Kherchouche, Sid Ahmed Fezza, Wassim Hamidouche
Despite the enormous performance of deepneural networks (DNNs), recent studies have shown theirvulnerability to adversarial examples (AEs), i. e., care-fully perturbed inputs designed to fool the targetedDNN.
no code implementations • 7 Jul 2021 • Mouath Aouayeb, Wassim Hamidouche, Catherine Soladie, Kidiyo Kpalma, Renaud Seguier
The multiple sources of the available databases raised several challenges for facial recognition task.
Ranked #1 on
Facial Expression Recognition (FER)
on RaFD
no code implementations • 27 Jun 2021 • Wassim Hamidouche, Thibaud Biatek, Mohsen Abdoli, Edouard François, Fernando Pescador, Miloš Radosavljević, Daniel Menard, Mickael Raulet
The amount of video content and the number of applications based on multimedia information increase each day.
no code implementations • 7 Jun 2021 • Ahmed Aldahdooh, Wassim Hamidouche, Olivier Deforges
For instance, we found that 1) Vanilla ViTs or hybrid-ViTs are more robust than CNNs under Lp-based attacks and under adaptive attacks.
1 code implementation • 24 May 2021 • Yi Zhang, Lu Zhang, Kang Wang, Wassim Hamidouche, Olivier Deforges
Salient human detection (SHD) in dynamic 360{\deg} immersive videos is of great importance for various applications such as robotics, inter-human and human-object interaction in augmented reality.
no code implementations • 12 May 2021 • Fatemeh Nasiri, Wassim Hamidouche, Luce Morin, Nicolas Dhollande, Gildas Cocherel
This paper presents a framework for Convolutional Neural Network (CNN)-based quality enhancement task, by taking advantage of coding information in the compressed video signal.
no code implementations • 7 May 2021 • Fatemeh Nasiri, Wassim Hamidouche, Luce Morin, Nicolas Dhollande, Gildas Cocherel
Moreover, an optional Model Selection (MS) strategy is adopted to pick the best trained model among available ones at the encoder side and signal it to the decoder side.
no code implementations • 7 May 2021 • Jinjin Gu, Haoming Cai, Chao Dong, Jimmy S. Ren, Yu Qiao, Shuhang Gu, Radu Timofte, Manri Cheon, SungJun Yoon, Byungyeon Kang, Junwoo Lee, Qing Zhang, Haiyang Guo, Yi Bin, Yuqing Hou, Hengliang Luo, Jingyu Guo, ZiRui Wang, Hai Wang, Wenming Yang, Qingyan Bai, Shuwei Shi, Weihao Xia, Mingdeng Cao, Jiahao Wang, Yifan Chen, Yujiu Yang, Yang Li, Tao Zhang, Longtao Feng, Yiting Liao, Junlin Li, William Thong, Jose Costa Pereira, Ales Leonardis, Steven McDonagh, Kele Xu, Lehan Yang, Hengxing Cai, Pengfei Sun, Seyed Mehdi Ayyoubzadeh, Ali Royat, Sid Ahmed Fezza, Dounia Hammou, Wassim Hamidouche, Sewoong Ahn, Gwangjin Yoon, Koki Tsubota, Hiroaki Akutsu, Kiyoharu Aizawa
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021.
1 code implementation • 3 May 2021 • Yi Zhang, Lu Zhang, Wassim Hamidouche, Olivier Deforges
In the past few years, numerous deep learning methods have been proposed to address the task of segmenting salient objects from RGB images.
1 code implementation • 1 May 2021 • Ahmed Aldahdooh, Wassim Hamidouche, Sid Ahmed Fezza, Olivier Deforges
In this paper, we focus on image classification task and attempt to provide a survey for detection methods of test-time evasion attacks on neural network classifiers.
1 code implementation • 28 Apr 2021 • Yi Zhang, Geng Chen, Qian Chen, Yujia Sun, Yong Xia, Olivier Deforges, Wassim Hamidouche, Lu Zhang
We propose a novel Synergistic Attention Network (SA-Net) to address the light field salient object detection by establishing a synergistic effect between multi-modal features with advanced attention mechanisms.
1 code implementation • 19 Apr 2021 • Théo Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, Olivier Déforges
This paper introduces a practical learned video codec.
no code implementations • ICLR Workshop Neural_Compression 2021 • Théo Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, Olivier Déforges
This paper introduces a novel framework for end-to-end learned video coding.
no code implementations • 16 Apr 2021 • Charles Bonnineau, Wassim Hamidouche, Jean-Francois Travers, Naty Sidaty, Olivier Deforges
The proposed solution enables a good performance in both mitigating coding artifacts and super-resolution with fewer network parameters compared to traditional specialized architectures.
1 code implementation • 9 Mar 2021 • Alexandre Tissier, Wassim Hamidouche, Souhaiel Belhadj Dit Mdalsi, Jarno Vanne, Franck Galpin, Daniel Menard
This new approach leads to five possible splits at each block depth and thereby improves the coding efficiency of VVC over that of the preceding High Efficiency Video Coding (HEVC) standard, which only supports Quad-Tree (QT) partitioning with a single split per block depth.
1 code implementation • 9 Mar 2021 • Ahmed Aldahdooh, Wassim Hamidouche, Olivier Déforges
Moreover, the state-of-the-art detection techniques have been designed for specific attacks or broken by others, need knowledge about the attacks, are not consistent, increase model parameters overhead, are time-consuming, or have latency in inference time.
no code implementations • 29 Dec 2020 • Glenn Herrou, Charles Bonnineau, Wassim Hamidouche, Patrick Dumenil, Jerome Fournier, Luce Morin
In this paper, we propose a Variable Frame Rate (VFR) solution to determine the minimum (critical) frame-rate that preserves the perceived video quality of HFR video.
no code implementations • 6 Aug 2020 • Théo Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, Olivier Déforges
MOFNet aims at computing and conveying the Optical Flow and a pixel-wise coding Mode selection.
no code implementations • 6 Jul 2020 • Théo Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, Olivier Déforges
In this paper, a mode selection network (ModeNet) is proposed to enhance deep learning-based video compression.
no code implementations • 21 Feb 2020 • Théo Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, Olivier Deforges
In this paper, we propose to enhance learned image compression systems with a richer probability model for the latent variables.
2 code implementations • 22 Jan 2020 • Yi Zhang, Lu Zhang, Wassim Hamidouche, Olivier Deforges
Experimental results show a limitation of the current methods when used for SOD in panoramic images, which indicates the proposed dataset is challenging.
1 code implementation • 1 Jun 2019 • Sid Ahmed Fezza, Yassine Bakhti, Wassim Hamidouche, Olivier Déforges
However, all the works proposed in the literature for generating adversarial examples have used the $L_{p}$ norms ($L_{0}$, $L_{2}$ and $L_{\infty}$) as distance metrics to quantify the similarity between the original image and the adversarial example.