Home › Researcher directory › Sid Ahmed Fezza
Sid Ahmed Fezza
Affiliation : Ecole Nationale Supérieur des Télécommunications et des Technologies de l’Information et de la Communication, Abdelhafid Boussouf
- 52Publications (affiliation in Algeria)
- 61Total publications
- 879Citations
- 15h-index
Is this you? Get your research seen
Create your free DzCademia profile and add your articles: they will show up more easily on Google and in AI assistants like ChatGPT, so more people can read and cite your work.
Create my free profile Add my publicationsResearch areas
- Image and Video Quality Assessment
- Video Coding and Compression Technologies
- Digital Media Forensic Detection
- Adversarial Robustness in Machine Learning
- Advanced Data Compression Techniques
Publications (52)
- Does data augmentation help or hinder the generalization of deepfake video detection?
- Complexity prediction of hardware and software video transcoding in the cloud
- Convex Hull Prediction Methods for Bitrate Ladder Construction: Design, Evaluation, and Comparison
- Energy Backdoor Attack to Deep Neural Networks
- PCG Classification for Diseases Detection: Windowing vs. Heart Cycle Segmentation
- Deepfake Detection Using Spatiotemporal Transformer
- Energy Consumption and Carbon Emissions of Modern Software Video Encoders
- On the effectiveness of handcrafted features for deepfake video detection
- Energy Consumption and Carbon Footprint of Modern Video Decoding Software
- Efficient Per-Shot Transformer-Based Bitrate Ladder Prediction for Adaptive Video Streaming
- Evaluating the Vulnerability of Deep Learning-based Image Quality Assessment Methods to Adversarial Attacks
- Adversarial example detection for DNN models: a review and experimental comparison
- Evaluation of Pre-Trained CNN Models for Geographic Fake Image Detection
- Benchmarking Learning-based Bitrate Ladder Prediction Methods for Adaptive Video Streaming
- Hardware-Friendly Multiple Transform Selection Module for the VVC Standard
- Visual Security Evaluation of Perceptually Encrypted Images based on Multi-Task Learning
- NTIRE 2021 Challenge on Perceptual Image Quality Assessment
- HCiT: Deepfake Video Detection Using a Hybrid Model of CNN features and Vision Transformer
- Light Field Image Coding Using VVC Standard and View Synthesis Based on Dual Discriminator GAN
- Detect and defense against adversarial examples in deep learning using natural scene statistics and adaptive denoising
- EGB: Image Quality Assessment based on Ensemble of Gradient Boosting
- Deep multi-task learning for image/video distortions identification
- Visual Quality and Security Assessment of Perceptually Encrypted Images Based on Multi-Output Deep Neural Network
- Detection of Adversarial Examples in Deep Neural Networks with Natural Scene Statistics
- Light Field Image Coding Using Dual Discriminator Generative Adversarial Network And VVC Temporal Scalability
- Natural Scene Statistics for Detecting Adversarial Examples in Deep Neural Networks
- Effect of Video Transcoding Parameters on Visual Object Tracking for Surveillance Systems
- Light Field Image Coding Using Dual Discriminator Generative Adversarial Network and VVC Temporal Scalability
- DDSA: A Defense Against Adversarial Attacks Using Deep Denoising Sparse Autoencoder
- Perceptual Evaluation of Adversarial Attacks for CNN-based Image Classification
- Subjective Evaluation of Light Field Image Compression Methods based on View Synthesis
- RDO-Based Light Field Image Coding Using Convolutional Neural Networks and Linear Approximation
- Visual Security Assessment of Selective Video Encryption
- Using distortion and asymmetry determination for blind stereoscopic image quality assessment strategy
- Towards light-compensated saliency prediction for omnidirectional images
- Perceptually Driven Nonuniform Asymmetric Coding of Stereoscopic 3D Video
- Universal blind image quality assessment for stereoscopic images
- Adaptive colorization-based compression for stereoscopic images
- Color calibration of multi-view video plus depth for advanced 3D video
- Color Correction for Stereo and Multi-view Coding
- Feature-Based Color Correction of Multiview Video for Coding and Rendering Enhancement
- Stereoscopic image quality metric based on local entropy and binocular just noticeable difference
- Stereoscopic 3D image quality assessment based on cyclopean view and depth map
- Asymmetric coding using Binocular Just Noticeable Difference and depth information for stereoscopic 3D
- Asymmetric coding of stereoscopic 3D based on perceptual significance
- No-reference perceptual blur metric for stereoscopic images
- Stereo image coding: State of the art
- Coding and rendering enhancement of multi-view video by color correction
- Fast stereo matching via graph cuts
- A comparison of prediction structures for multi-view video coding based on the H.264/AVC standard
- New Prediction Structure for Stereoscopic Video Coding Based on the H.264/AVC Standard
- Stereoscopic video coding based on the H.264/AVC standard
Co-authors
- Kamel Mohamed Faraoun
- Bachir Kaddar
- Ghalem Belalem
- Samira Ouddane
- Taieb Chachou
- Dounia Hammou
- Mamadou Keïta
- Elhocine Boutellaa
- Yassine Bakhti
- anouar kherchouche
- Aymen Abderraouf Rahmani
- Reda Abdellah Kamraoui
Bibliographic data from OpenAlex (open database).
Why choose Dzcademia?
Profiles, articles and conference contributions: give your research a structured public presence. Integrated metadata help search engines and AI assistants identify your work and understand its references.
Comment with Google
Sign in with Google to comment directly on this page.