IVP Seminars
a seminar series in image and video processing
about
Regular hybrid seminars are organised by VI-Lab academics Dr Aaron Zhang and Dr Pui Anantrasirichai, featuring both internal and external speakers. The seminars are held every Wednesday at 2pm (UK time).
Teams: Link
list of seminars
| No. | Date | Speaker | Title | Links |
|---|---|---|---|---|
| 61 | 11/02/2026 | Edward Huang | Bayesian Neural Networks for One-to-Many Mapping in Image Enhancement | paper |
| 60 | 11/02/2026 | Adrian Azzarelli | Splatography: Sparse multi-view dynamic Gaussian Splatting for filmmaking challenges | paper |
| 59 | 28/01/2026 | *Zirui Wang (Oxford) | Evaluation and Active Vision for 3D Tasks | paper1 paper2 paper3 |
| 58 | 03/12/2025 | Peiran Wu | ST-Think: Reasoning About 4D Worlds from Ego-Centric Videos | paper |
| 57 | 19/11/2025 | Wenqi Zhou | X-LeBench: Extremely Long Egocentric Video Benchmark | paper |
| 56 | 05/11/2025 | Xinyi Zheng | CULTURE3D: Cultural Landmarks and Terrain Dataset | paper |
| 55 | 25/06/2025 | Jasmine Peng | Instance Data Condensation for Image Super-Resolution | paper |
| 54 | 11/06/2025 | Xin Tian | TaGAT: Topology-Aware Graph Attention Network | paper |
| 53 | 30/04/2025 | *Yixuan Li (CityUHK) | Multimodal Foundation Models for Quality Assessment and Forensics | paper |
| 52 | 02/04/2025 | Yini Li | Zero-TIG: Temporal Consistency-Aware Zero-Shot Low-light Video Enhancement | paper |
| 51 | 19/03/2025 | *Yangming Li (Cambridge) | Risk-sensitive diffusion | paper |
| 50 | 19/02/2025 | Ge Gao | PNVC: Towards Practical INR-based Video Compression | paper |
| 49 | 05/02/2025 | *Hengyi Wang (UCL) | Building 3D Foundation Models | paper |
| 48 | 22/01/2025 | *Duolikun Danier (Edinburgh) | DepthCues: Evaluating Monocular Depth Perception in Large Vision Models | paper |
| 47 | 27/11/2024 | Ho Man Kwan | NVRC: Neural Video Representation Compression | paper |
| 46 | 30/10/2024 | Zihao Qi | BVI-UGC: A Video Quality Database for User-Generated Content Transcoding | paper |
| 45 | 16/10/2024 | Kelvis Leung | Vector Space Representation Learning for Downhole Microseismic Phase Picking | paper |
| 44 | 02/10/2024 | Perla Jazmin Mayo Diaz de Leon | StoDIP: Efficient 3D MRF image reconstruction | paper |
| 43 | 18/09/2024 | Robert Popescu | Anomaly detection for volcanic unrest in satellite imagery | paper |
| 42 | 04/09/2024 | Jasmine Peng | RMT-BVQA: Recurrent Memory Transformer-based BVQA | paper |
| 41 | 07/08/2024 | *Fu-Zhao Ou (CityUHK) | Face Image Quality Assessment in the Deep Learning Era | paper |
| 40 | 24/07/2024 | Yuxuan Jiang | MTKD: Multi-Teacher Knowledge Distillation for Image Super-Resolution | paper |
| 39 | 10/07/2024 | Crispian Morris | DaBiT: Depth and Blur Informed Transformer | paper |
| 38 | 26/06/2024 | *Sadaf Salehkalaibar (Toronto) | Perceptual loss functions for learned video coding | paper |
| 37 | 15/05/2024 | Zihao Qi | Full-reference Video Quality Assessment for UGC Transcoding | paper |
| 36 | 01/05/2024 | *Issa Khalifeh (QMUL) | Efficient Kernel-Based Video Frame Interpolation | paper |
| 35 | 17/04/2024 | Joanne Lin Rachel Lin | Feature Denoising for Low-Light Instance Segmentation; Low-light Video Enhancement | paper1 paper2 |
| 34 | 20/03/2024 | Simon Zeng | Training dynamics in Physics-Informed Neural Networks | paper |
| 33 | 21/02/2024 | Xin Tian Tianqi Yang | OCT2Confocal; DUBLINE | paper1 paper2 |
| 32 | 07/02/2024 | Yuxuan Jiang Haoran Wang | Compressing Deep Image Super-Resolution Models; RankDVQA-mini | paper1 paper2 |
| 31 | 24/01/2024 | Adrian Azzarelli | WavePlanes: A Compact Wavelet Representation for Dynamic NeRFs | paper |
| 30 | 29/11/2023 | Xinyi Wang | UGC quality assessment with saliency | paper |
| 29 | 15/11/2023 | *Xin Zhao (Cardiff) | CUDAS: Distortion-Aware Saliency Benchmark | paper |
| 28 | 01/11/2023 | Chen Feng | RankDVQA: Deep VQA based on Ranking-inspired Hybrid Training | paper |
| 27 | 18/10/2023 | Jasmine Peng | Complexity reduction for end-to-end optimised deep video compression | |
| 26 | 20/09/2023 | Simon Zeng | Video-SwinUNet: Spatio-temporal Framework for VFSS Segmentation | paper |
| 25 | 06/09/2023 | Duolikun Danier | LDMVFI: Video Frame Interpolation with Latent Diffusion Models | paper |
| 24 | 28/06/2023 | Ho Man Kwan | HiNeRV: Video Compression with Hierarchical Encoding | paper |
| 23 | 14/06/2023 | *Bo Zhao (Edinburgh) | Data-efficient Learning with Dataset Condensation | paper |
| 22 | 31/05/2023 | Adrian Azzarelli | Towards a Robust Framework for NeRF Evaluation | paper |
| 21 | 03/05/2023 | Pengcheng Hao | A hybrid particle-stochastic map filter | paper |
| 20 | 19/04/2023 | *Darren Ramsook (Trinity) | Compressed video enhancement using learnt deep prior features | paper |
| 19 | 22/03/2023 | Jakub Nawala | Modelling the Response Generation Process in Multimedia QoE Assessment | paper |
| 18 | 08/03/2023 | Crispian Morris | Knowledge Distillation-Driven Frame Interpolation | paper |
| 17 | 08/02/2023 | *Heming Sun (Waseda) | Q-LIC: Quantizing Learned Image Compression with Channel Splitting | paper |
| 16 | 25/01/2023 | Yuxuan Jiang | Image Super Resolution | paper |
| 15 | 11/01/2023 | Duolikun Danier | Diffusion models | paper |
| 14 | 30/11/2022 | Adrian Azzarelli | Introduction to Neural Radiance Fields | paper |
| 13 | 16/11/2022 | Tianqi Yang Xudong Ma | Vision Transformer | paper1 paper2 |
| 12 | 02/11/2022 | Xin Tian | Optimal Transport-Based Graph Matching for 3D Retinal OCT Image Registration | paper |
| 11 | 05/10/2022 | Xudong Ma | Unsupervised image fusion using deep image prior | paper |
| 10 | 21/09/2022 | Ge Gao | Neural Image Compression | paper |
| 9 | 08/09/2022 | *Zoe Liu (Visionular) | Advancing Video Compression Through Intelligent Optimization | |
| 8 | 26/08/2022 | Duolikun Danier | Subjective Quality Study for Video Frame Interpolation | paper |
| 7 | 12/08/2022 | Alexandra Malyugina | A Topological Loss Function for Low-Light Image Denoising | paper |
| 6 | 29/07/2022 | Tianqi Yang | Contrastive Learning | paper |
| 5 | 15/07/2022 | Zihao Qi | Deep video compression | |
| 4 | 01/07/2022 | Ruixiong Wang Crispian Morris | Fluorescent image translation using attention-based conditional GAN; Knowledge distillation for complexity reduction | paper paper |
| 3 | 17/06/2022 | Xin Tian Xudong Ma | Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks; Unsupervised Deformable Registration for Multi-Modal Images via Disentangled Representations | paper |
| 2 | 20/05/2022 | Chen Feng | Deep video quality assessment | paper |
| 1 | 06/05/2022 | Duolikun Danier | Video frame interpolation | paper |
* external speakers
contact
Dr Aaron Zhang: fan.zhang@bristol.ac.uk