Chen Feng

冯     晨

PhD Student
Visual Information Laboratory
Electrical, Electronic and Mechanical Engineering
University of Bristol

1.23, 1 Cathedral Square
Bristol BS1 5DD, United Kingdom
chen.feng@bristol.ac.uk





About

I am a final year PhD student in Visual Information Laboratory at University of Bristol under the supervision of Prof. David Bull and Dr Aaron Zhang, funded by the Amazon Research Awards 2022. My main research interests are low-level computer vision including deep video quality assessment, deep video compression and restoration, and subjective video quality assessment.

I obtained an MSc (Distinction) in image and video communication and signal processing from the University of Bristol, where I researched on Video Compression with CNN-based Post Processing in the Visual Information Laboratory under the supervision of Prof. David Bull. I completed a BEng in Measuring and Control Technology at the School of Automation and Electrical Engineering at the University of Science and Technology Beijing under the supervision of Prof. Qing Li.

Currently, I am working as an Applied Scientist Intern at Video Coding Standards Research Team of Amazon Prime Video in Seattle, US.

News & Activities

[Older news and activities]


Signature Research Projects


arXiv 2024

MVAD: A Multiple Visual Artifact Detector for Video Streaming
"The first multi-artifact detection framework without replying on VQA!"
Chen Feng, Duolikun Danier, Fan Zhang and David Bull
arXiv, 2024
[arXiv]

WACV 2024

RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training
"The first deep VQA model optimised through ranking-based training!"
Chen Feng, Duolikun Danier, Fan Zhang, David Bull
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
[arXiv] [project] [code]

ECCV 2024

MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution
"A student model can outperform its teaching models through MTKD!"
Yuxuan Jiang, Chen Feng, Fan Zhang and David Bull
ECCV, 2024
[arXiv] [code]

ECCV AIM Workshop 2024

RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content
"The first deep VQA model based on RMT!"
Tianhao Peng*,Chen Feng*, Duolikun Danier, Fan Zhang, Benoit Vallade, Alex Mackin and David Bull
ECCV AIM Workshop, 2024
[arXiv] [Code]

PCS 2024

BVI-Artefact: An artefact detection benchmark dataset for streamed videos
"The first public database for detecting artefacts in streamed PGC videos!"
Chen Feng*, Duolikun Danier*, Fan Zhang, Alex Mackin, Andy Collins and David Bull
PCS, 2024
[Paper] [Database]

PCS 2024

RankDVQA-mini: Knowledge distillation-driven deep video quality assessment
"The first lightweight deep VQA achieving competitive performance!"
Chen Feng, Duolikun Danier, Haoran Wang, Fan Zhang, Benoit Vallade, Alex Mackin and David Bull
PCS, 2024
[Paper] [Project]


arXiv 2024

BVI-UGC: A Video Quality Database for User-Generated Content Transcoding
"The first video quality database focusing on UGC transcoding!"
Zihao Qi, Chen Feng, Fan Zhang, Xiaozhong Xu, Shan Liu, David Bull
arXiv, 2024
[arXiv] [Database]

Experience

Applied Scientist Intern

Amazon Prime Video Seattle, US    Jul. 2024 - Present

  • Video Coding Standards Research Team - Research on Deep Video Compression.
Teaching Assistant

University of Bristol Bristol, UK    Feb. 2021 - Present

  • Image Processing and Computer Vision: supported lectures and independently delivered tutorial sessions
  • Immersive Interaction and Audio Design (VR Development): designed and supported lab sessions (Unity)
  • Augmenting the Real World (AR Development): designed and supported lab sessions (C#, Unity)

Research Supervision

University of Bristol Bristol, UK    Jun. 2022 - Present

  • Mentored twelve postgraduate students and six undergraduate students through their final-year thesis and internship projects, providing guidance on research methodologies and experimental design.
  • Topics included video quality assessment, video compression, and image processing.

Awards and Honours

  • 1st Place in Video Perception at the 6th Challenge on Learned Image Compression in DCC 2024
  • (award letter)
  • 1st Winner in the 3rd Practical End-to-End Image/Video Compression Challenge in IEEE MMSP 2024
  • 3rd Place in the 5th AIM Challenge on Efficient Video Super-Resolution in ECCV 2024
  • The FIRST Prize in IEEE/CVF WACV 2023 HDR VQM Grand Challenge hosted by Amazon Prime Video (award letter)
  • UKRI MyWorld Strength Research Students Awards Scheme Scholarship.
  • PhD is funded by the Amazon Research Awards 2022
  • Top Six in the 5th Challenge on Learned Image Compression in IEEE/CVF CVPR 2022
  • Second Prize in the Grand Challenge on NN-based Video Coding in IEEE ISCAS 2022
  • University of Bristol - Bristol PLUS Award


Professional Activities

  • Reviewer for the Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS) 2024
  • Reviewer for the International Conference on Learning Representations (ICLR) 2025
  • Reviewer for the European Conference on Computer Vision (ECCV) 2024
  • Reviewer for the Picture Coding Symposium (PCS) 2024
  • Reviewer of IEEE Transactions on Image Processing (TIP)
  • Reviewer of IEEE Transactions on Circuits and Systems for Video Technology (T-CSVT)
  • Reviewer of IEEE Transactions on Broadcasting
  • Reviewer of Pattern Recognition Letters
  • Reviewer of IEEE Transactions on Artificial Intelligence (T-AI)
  • Reviewer of IEEE Signal Processing Letters


Publications (Google Scholar)


arXiv Papers
  1. MVAD: A Multiple Visual Artifact Detector for Video Streaming
    C. Feng, D. Danier, F. Zhang, and D. R. Bull
    Submitted to NeurIPS 2024
    [project]

  2. BVI-UGC: A Video Quality Database for User-Generated Content Transcoding
    Z. Qi, C. Feng, F. Zhang, X. Xu, S. Liu, and D. R. Bull
    arXiv:2408.07171, 2024
    [project]

  3. Enhancing HDR Video Compression through CNN-based Effective Bit Depth Adaptation
    C. Feng, Z. Qi, D. Danier, F. Zhang, X. Xu, S. Liu, and D. R. Bull
    arXiv:2207.08634, 2022
    [project]

Journal Papers
  1. Video Compression with CNN-based Postprocessing
    F. Zhang, D. Ma, C. Feng, and D. R. Bull
    IEEE MultiMedia, 2021
    [paper] | [project]

Conference Papers
  1. RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training
    C. Feng, D. Danier, F. Zhang, and D. R. Bull
    IEEE/CVF WACV, 2024
    [project]

  2. MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution
    Y. Jiang, C. Feng, F. Zhang, and D. Bull
    IEEE/CVF ECCV, 2024
    [paper]

  3. RMT-BVQA: Recurrent Memory Transformer-based Blind VQA for Enhanced Video Content
    Tianhao Peng*, C. Feng*, D. Danier, F. Zhang, and D. Bull
    ECCV Workshop in AIM, 2024
    [paper]

  4. BVI-Artefact: An Artefact Detection Benchmark Dataset for Streamed Videos
    C. Feng, D. Danier, F. Zhang, and D. Bull
    Picture Coding Symposium (PCS), 2024 (Oral Session)
    [paper] | [project]

  5. RankDVQA-mini: Knowledge Distillation-Driven Deep Video Quality Assessment
    C. Feng, D. Danier, H. Wang, F. Zhang, and D. R. Bull
    Picture Coding Symposium (PCS), 2024 (Oral Session)
    [paper] | [project]

  6. Full-reference Video Quality Assessment for User Generated Content Transcoding
    Z. Qi, C. Feng, D. Danier, F. Zhang, X. Xu, S. Liu, and D. R. Bull
    Picture Coding Symposium (PCS), 2024 (Oral Session)
    [paper] | [project]

  7. ViSTRA3: Video Coding with Deep Parameter Adaptation and Post Processing
    C. Feng, D. Danier, C. Tan, F. Zhang, and D. Bull
    IEEE ISCAS, 2022
    [paper] | [project]

  8. Enhancing VVC with Deep Learning based Multi-Frame Post-Processing
    D. Danier, C. Feng, F. Zhang, and D. Bull
    CVPR 5th Challenge on Learned Image Compression, 2022
    [paper] | [project]

  9. Enhancing VVC through CNN-based Post-Processing
    F. Zhang, C. Feng, and D. Bull
    IEEE ICME, 2020
    [paper] | [project]


Technical Skills

  • Programming: Python, Matlab, C++, C\#, Java, Assembly, Statistical Analysis.
  • PyTorch, Tensorflow, Generative Models, CNNs, GAN, Transformer, Autoencoders.
  • Tools: Unity(VR\&AR Development), Git, Docker, IDEs, LaTeX, Raspberry Pi, LabVIEW