RRReza Razavi

Reza Razavi

*This is an algorithmically generated author record based on publicly available information.

Reza Razavi has a total of 10 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    FedVSR: Towards Model-Agnostic Federated Learning in Video Super-Resolution

    by Ali Mollaahmadi Dehaghi, Hossein KhademSohi, Reza Razavi, Steve Drew, Mohammad Moshirpour

    Video super-resolution (VSR) aims to enhance low-resolution videos by leveraging both spatial and temporal information. While deep learning has led to impressive progress, it typically requires centralized data, which raises privacy concerns. Federated learning (FL) offers a privacy-friendly solution, but general FL frameworks often struggle with low-level vision tasks, resulting in blurry, low-quality outputs. To address this, we introduce FedVSR, the first FL framework specifically designed for VSR. It is architecture-agnostic and stateless, and introduces a lightweight loss function based on the Discrete Wavelet Transform (DWT) to better preserve high-frequency details during local training. Additionally, a loss-aware aggregation strategy combines both DWT-based and task-specific losses to guide global updates effectively. Extensive experiments across multiple VSR models and datasets show that FedVSR not only improves perceptual video quality (up to +0.89 dB PSNR, +0.0370 SSIM, -0.0347 LPIPS and 4.98 VMAF) but also achieves these gains with close to zero computation and communication overhead compared to its rivals. These results demonstrate Fed-VSR's potential to bridge the gap between privacy, efficiency, and perceptual quality, setting a new benchmark for federated learning in low-level vision tasks. Please refer to this link for the code. https://github.com/alimd94/FedVSR


  • Open Access

    VIDEA-Dublin Dataset: 8K 60FPS Video Sequences for Analysis and Development

    by Tariq Al Shoura, Ali Mollaahmadi Dehaghi, Reza Razavi, Mohammad Moshirpour

    Ultra-high-definition (UHD) video datasets have played a critical role in advancing video quality assessment (VQA), compression, and general computer vision (CV) research. Despite recent progress in the availability of 8K datasets, existing resources remain limited in their coverage of real-world urban environments, where complex motion, uncontrolled lighting, crowds, traffic, and nighttime conditions pose challenges that are not adequately represented in cu-rated or semi-controlled recordings. To address this gap, we present VIDEA-Dublin, an additive urban extension to the VIDEA-8K-60FPS dataset, captured entirely in real-world public environments across Dublin, Ireland. VIDEA-Dublin consists of 135 native 8K (8192×4320) video sequences recorded at 60 FPS, and taking 9.78 TB. The dataset comprises of 80 clips of 10s, 40 clips of 30s, and 15 clips of 60s, captured using the same camera hardware, acquisition settings, and processing pipeline as the original VIDEA dataset to ensure full compatibility and consistency. The collection spans a diverse set of urban scenarios, including pedestrian areas, architecture, traffic scenes, parks, waterfronts, and nighttime environments, exhibiting substantial variability in motion dynamics, illumination, contrast, and color composition. GitHub: https://github.com/talshoura/VIDEA-8K-60FPS-Dublin

  • Open Access

    VIDEA-8K-60FPS Dataset: 8K 60FPS Video Sequences for Analysis and Development

    by Tariq Al Shoura, Ali Mollaahmadi Dehaghi, Reza Razavi, Mohammad Moshirpour


  • Open Access

    Closed-Loop Clustering-Based Global Bandwidth Prediction in Real-Time Video Streaming

    by Sepideh Afshar, Reza Razavi, Mohammad Moshirpour

    Accurate throughput forecasting is essential for ensuring the seamless operation of Real-Time Communication (RTC) applications. These demands for accurate throughput forecasting become particularly challenging when dealing with wireless access links, as they inherently exhibit fluctuating bandwidth. Ensuring an exceptional user Quality of Experience (QoE) in this scenario depends on accurately predicting available bandwidth in the short term since it plays a pivotal role in guiding video rate adaptation. Yet, current methodologies for short-term bandwidth prediction (SBP) struggle to perform adequately in dynamically changing real-world network environments and lack generalizability to adapt across varied network conditions. Also, acquiring long and representative traces that capture real-world network complexity is challenging. To overcome these challenges, we propose closed-loop clustering-based Global Forecasting Models (GFMs) for SBP. Unlike local models, GFMs apply the same function to all traces enabling cross-learning, and leveraging relationships among traces to address the performance issues seen in current SBP algorithms. To address potential heterogeneity within the data and improve prediction quality, a clustered-wise GFM is utilized to group similar traces based on prediction accuracy. Finally, the proposed method is validated using real-world datasets of HSDPA 3G, NYC LTE, and Irish 5G data demonstrating significant improvements in accuracy and generalizability.


  • Open Access

    SEPE Dataset: 8K Video Sequences and Images for Analysis and Development

    by Tariq Al Shoura, Ali Mollaahmadi Dehaghi, Reza Razavi, Behrouz Far, Mohammad Moshirpour

    This paper provides an overview of our open (Software Engineering Practice and Education) SEPE 8K dataset which is made of 40 different 8K (8192 x 4320) video sequences and 40 variant 8K (8192 x 5464) images. The video sequences were captured at a framerate of 29.97 frames per second (FPS) and had been encoded into videos using AVC/H.264, HEVC/H.265, and AV1 codecs at resolutions from 8K to 480p. The images, video sequences, encoded videos, and various other statistics related to the media that make the dataset are stored online, published, and maintained on the repo on GitHub for non-commercial use. In this paper, the dataset components are described and analyzed using various methods. The proposed dataset is - as far as we know - the first to publish true 8K natural sequences; thus, it is important for the next level of applications dealing with multimedia such as video quality assessment, super-resolution, video coding, video compression, and many more. GitHub: https://github.com/talshoura/SEPE-8K-Dataset