Skip to main content

Visual computing research seminars

The VLunch meeting is a regular event to discuss research of interest to the Visual Computing Group.

Seminars will be held at 12:10.

All are welcome to attend. More seminars will be added to the list throughout the year so please check back regularly.

Seminars are now in person, and are located in Abacws, room 3.38.

DateSpeakerTitle
30 October 2024

Rayan BinlajdamYaser

Abu Awwad

Integrating Multi-Source Data with Remote Sensing for Forest Health Assessment
Illuminating the Dark: Datasets and Challenges in Low-Light Video Enhancement
09 October 2024Paul RosinRemote Sensing Research - Pre-2020
02 October 2024Oktay KarakusReSIDA and Its Vision for Advancing Remote Sensing Research
20 September 2024Liang Zheng (Australian National University)The many meanings with image pairs
18 September 2024Shishikui Yoshiaki (Meiji University, Japan)Quality of 8K Ultra-High-Definition Television Viewing Experience
22 May 2024

Xinbo Wu

Rayan Binlajdam

Style-Edited Image Quality Assessment

Assessing Forest Health Through Remote Sensing Technologies
15 May 2024Leandro Beltrachini (CUBRIC)The Forward and Inverse Problems in electro/magnetoencephalography: perspectives and challenges
08 May 2024Kirill SidorovChallenges in Computational Music
01 May 2024Robin Moore (Director, Shwsh)Generative AI and media production
24 April 2024

Xinbo Wu

Zhengyan Dong

Perceptual Modelling of Quality Induced Saliency Shifts in Video

Emotion-aware IQA
17 April 2024Teodor Nikolov (School of Psychology)Evaluating face detection algorithms on a head-mounted camera dataset of young children with and without Down Syndrome
20 March 2024

Jingwen Sun

Huasheng Wang

Hybrid Mapping for Indoor Robot Semantic Navigation

KSIQA: A Knowledge Sharing Model for No-reference Image Quality Assessment
06 March 2024Professor Azeddine Beghdadi (Institut Galilee, University Sorbonne Paris Nord)Image Quality Assessment and Enhancement in the Context of Medical Imaging and Diagnosis
28 February 2024Victor Romero CanoEnvironmental perception for social robot navigation
21 February 2024

Wanli Ma

Benjamin Wiriyapong

Semi supervised learning for remote sensing imagery

Multimodal posterior problem in Variational Bayes
14 February 2024

Shuang Song

Stephen Miles

Feature Proliferation - the "Cancer" in StyleGAN and its Treatments

Towards real world super resolution trained on synthetic images generated by Stable Diffusion
7 February 2024Ze Ji (School of Engineering)Active Robot Learning for Autonomous Manipulation and Navigation
31 January 2024Padraig CorcoranHow to write a systematic literature review
DateSpeakerTitle
*6 December 2023Kirill SidorovChess as a platform for interpretable AI research
*29 November 2023Darren Cosker (Microsoft Research Ltd)AI for Human Understanding in Mixed Reality
*22 November 2023Jing WuVisual Analytics in Deep Learning for Computer Vision
*8 November 2023Xianfang SunMedical Image Segmentation
*1 November 2023Wei ZhouImmersive Visual Processing: From Human Perception to Machine Intelligence
*25 October 2023Yipeng QinSome Thoughts on the Spaces and Distributions of Deep Generative Models
*18 October 2023Hantao LiuVisual Saliency Prediction Using Deep Learning
*11 October 2023Maëliss Jallais (CUBRIC)Fast and robust likelihood-free Bayesian inference with machine learning
*4 October 2023Paddy SlaterUnsupervised and self-supervised machine learning for quantitative medical image analysis
14 June 2023Bin Zhu (Bristol University)Food Computing from a Multimedia Perspective
10 May 2023Samuel Evans (Dentistry)The forensic photography and analysis of bruises in child protection
7 May 2023

Xin Zhao

CUDAS: Distortion-Aware Saliency Benchmark
3 May 2023Huasheng WangDeep Ordinal Regression Framework for No-Reference Image Quality Assessment
3 May 2023Ogechukwu UkwanduDeveloping A Robust Artificial Intelligence System for Precision Diagnosis of Prostate Cancer Using Magnetic Resonance Imaging
26 April 2023Yukun LaiLearning based Visual Content Generation and Editing
19 April 2023Naheed Akhtar (COMSATS, Pakistan)Video Temporal Tampering Detection
19 April 2023

Yun Zhang (Communication University of Zhejiang, China)

Content Manipulation of 360-degree Panoramas on the Sphere
8 March 2023Wassim Jabi (School of Architecture)Integrating Geometry, Topology, and Information in Architecture
1 March 2023

Abacws, Room 0.04   
Agnethe Olsen (School of Biosciences)Computer vision in disease ecology
1 March 2023

Abacws, Room 0.04
Yun Zhang (Communication University of Zhejiang, China)Content Manipulation of 360-degree Panoramas on the Sphere
8 February 2023Zhengyan DongIdentifying Pitfalls in the Evaluation of Saliency Models for Videos
8 February 2023Iris Xin ZhaoHuman VS Computer: A new experiment (VISES) to evaluate saliency prediction performance
DateSpeakerTitle
30 November 2022Fahd Alhamazani3D shapes: Depth Completion and evaluation metric
30 November 2022Njuod AlsudaysAFPSNet: Multi-Class Part Parsing based on Scaled Attention and Feature Fusion
23 November 2022Oliver van Kaick (Carleton University, Canada)Guided Creation of Computer Graphics Content with Neural Networks
16 November 2022Yuanbang LiangExploring and Exploiting Hubness Priors for High-Quality GAN Latent Sampling
16 November 2022Xinbo WuAnalysis of Video Quality Induced Spatio-Temporal Saliency Shift
9 November 2022Abdulkerim Duman (School of Engineering)Clinical Applications of Brain Tumour Segmentation
2 November 2022Oktay KarakuAn informal talk on earth observation for environmental challenges
2 November 2022Paul RosinAn informal talk on my struggles with skulls and affine invariant 3D curve moments
25 May 2022Amir Vaxman (Utrecht University)High-order and Degree Directional Fields
18 May 2022Aaron Zhang (University of Bristol)Perceptually Inspired Deep Video Compression
11 May 2022Zien MaMetabolite Quantification with Magnetic Resonance Spectroscopy and Spectrum Signal Processing using an Autoencoder Architecture
4 May 2022Wanli MaMulti-modal Remote Sensing Image Fusion for Land Cover Mapping
23 March 2022Peng Song (Singapore University of Technology and Design)Computational Assemblies for Digital Fabrication
16 March 2022Hateef AlshewaierEnsemble Method for Medical Image Segmentation
9 March 2022Marco PalomboPerspectives on AI-powered brain microstructure imaging
2 March 2022Ben Daubney (MBDA)Image Processing in Industry: Complex Weapons
23 February 2022Nobuyuki Umetani (University of Tokyo)Interactive Design Optimization in Computational Fabrication
16 February 2022Sophie Shermer (Swansea University)Quantitative MRI and Spectroscopy: from quantification of chemicals in the brain to diagnostic tools for prostate cancer
9 February 2022Yueran MaTraditional vs. Deep Learning Methods for Medical Image Quality Assessment
2 February 2022Igor Rizaev (University of Bristol)SAR simulation: features in imaging of sea waves and ship wakes
DateSpeakerTitle
8 December 2021Tiantian Liu (Taichi Graphics)A hands-on tutorial of the Taichi Programming Language
1 December 2021Irtaza Khalid and Frank LangbeinReinforcement Learning and Robust Quantum Control for Spin Transfer and Magnetic Resonance Spectroscopy
24 November 2021Jianxun Lou / Xin ZhaoStudy of saccadic eye movements in diagnostic imaging / A metric for quantifying image quality induced saliency variation
17 November 2021Paul Rosin (Cardiff University)Simple Computer Vision Algorithms
26 May 2021Oktay Karakus (University of Bristol)Can We Sense the Call of the Ocean? Marine Monitoring via Remote Sensing Computational Imaging
19 May 2021Jungong Han (Aberystwyth University)Image Saliency Detection: From Convolutional Neural Network to Capsule Network
12 May 2021Shih-Yuan Wang (National Yang Ming Chiao Tung University, Taiwan)Architectural Robotics
21 April 2021Robert Roithmayr (Donau-Universität Krems, Austria)Computational Modelling and Engineering of Tensile Membrane Structures
24 March 2021Hein Min Htike (Cardiff University)AR glasses as mobility aid for people with low vision
10 March 2021Xiangxu Yu (University of Texas at Austin)Predicting the quality of compressed videos with pre-existing distortions
10 February 2021Ralph MartinMy new 3D printer
27 January 2021Damian Farnell (School of Dentistry, Cardiff University), Tom HartleyOrthodontics and 3D Imaging and Multivariate Statistical Models of Shape/Explaining Failure: Investigation of Surprise and Expectation in CNNs
13 January 2021Xin ZhaoDeep Learning VS. Traditional Algorithms for Saliency Prediction of Distorted Images
DateSpeakerTitle
16 December 2020Stefano ZappalaCan Registration Methods for Neuroimaging Follow a Biomechanical Deformation? Optimisation on Two Biofidelic Fields
2 December 2020Ian Grimstead (Office for National Statistics)Estimating vehicle and pedestrian activity from town and city traffic cameras
18 November 2020Ethan Dickson (Cardiff University and Orbital Media), Joseph Redfern, Frank LangbeinMixed session on hot topics and useful tools
4 November 2020Ethan Dickson (Cardiff University and Orbital Media)Speech-Driven Avatar Synthesis
29 April 2020Hongjin LyuWatercolour style transfer
22 April 2020Meijing Gao (Yanshan University, China)Optical micro-scanning thermal microscope imaging system
18 March 2020Sen-Zhe Xu (Tsinghua University, China)Simultaneous multi-attribute image-to-image translation
11 March 2020Zhongyu Jiang (Tianjin University, China)Reference Guided Face Super-Resolution via 3D Morphable Modeling
4 March 2020Qian Xie (Nanjing University of Aeronautics and Astronautics, China)A brief introduction of deep learning on 3D point cloud
26 February 2020Han LiuGranular Computing Based Machine Learning for Deep Processing of Unstructured Data
19 February 2020Salma Al-QazzazDeep Learning-based Brain Tumour Image Segmentation with Extension to Stroke lesion Segmentation
12 February 2020Fahd Alhamazani3DSA-GAN: 3D Self-Attention GAN for Shape Completion from Single-View Depth Images
5 February 2020Brendan McCane
University of Otago, New Zealand
3D reconstruction of vertebrae from bi-planar x-rays
29 January 2020Paul RosinNeural Style Transfer with Additional Information
22 January 2020Mark Hall
The Open University
This is not funny
15 January 2020Emin Zerman
Trinity College Dublin
Perception and quality assessment for immersive imaging technologies
5 January 2020Feng Zhou
Beihang University, China
A small talk on semantic segmentation from RGB to RGBD
DateSpeakerTitle
4 December 2019Dalia AlfarasaniMeasuring 3D mesh saliency using eye tracker
27 November 2019Roberto DykeShape correspondence and registration with non-isometric deformations
20 November 2019Yukun LaiGenerative models for images and 3D shapes
13 November 2019Richard BoothA brief introduction to belief revision and some potential connections with computer vision
6 November 2019Yue Peng
University of Science and Technology of China
Accelerating ADMM for efficient simulation and optimization
30 October 2019Daniel FinneganHis recently CHI paper submission
23 October 2019Yipeng QinTowards understanding how GANs really work
16 October 2019Bailin DengTowards scalable geometry processing (without solving linear systems)
17 July 2019Changhao Chen (National University of Defense Technology, China)

Learning methods for robust localization

17 July 2019Xiaofeng He (National University of Defense Technology, China)Bio-inspired navigation technology
12 June 2019Matthias TrederPredictive modelling of MR images using convolutional neural networks
5 June 2019Ran Song and Karina Rodriguez Echavarria
University of Brighton 
Analysis and applications of 3D objects to support audiences to engage with 3D content, including cultural heritage objects
29 May 2019Ethan Dickson
Cardiff University and Orbital Media 
Talking heads: Speech driven facial modelling and video synthesis
22 May 2019Bo Li
Nanchang Hangkong University
Image colourisation
15 May 2019David HumphreysEnhancing shortest grammar algorithms for analysis of musical scores
10 April 2019David Pickup
FiveAI
Building an autonomous vehicle
3 April 2019Heejune Ahn
SeoulTech
Computer vision and  deep learning algorithms for 2-D image based virtual cloth try-on
27 March 2019Tim Ellis
Kingston University
Looking at people - measuring falls and interactions
20 March 2019Mark Hall
Martin-Luther-Universität Halle-Wittenberg
Visual interfaces for exploring digital cultural heritage
13 March 2019Joseph RedfernAssociation of violence with urban points of interest
6 March 2019Julien SchroeterWeakly-supervised temporal localisation via occurrence count learning
27 February 2019Darren Cosker
University of Bath
Motion capture, analysis and animation research at CAMERA
20 February 2019Hantao LiuMaking use of eye-tracking data
13 February 2019Paul RosinReverse correlation for image downsampling
6 February 2019Xianfang SunImage super-resolution
30 January 2019Hantao LiuDemonstration and examples of eye tracking
23 January 2019Stefano ZappalaIs your brain deforming? An in-vivo investigation of positional brain shift
16 January 2019David George
Swansea University
Feature driven learning techniques for 3D shape segmentation
9 January 2019Abraham Nieva De La HidalgaApplication of semantic segmentation for processing of large image datasets from natural history collections
DateSpeakerTitle
5 December 2018Jing WuSeeing the unseen: Locating objects from visual reflections
28 November 2018Aled OwenWhere is the ball? Self-supervised representations for team sports
21 November 2018Bailin DengAnderson acceleration for geometry optimization and physics simulation
14 November 2018Thomas HartleyPruning convolutional neural networks
7 November 2018Nicholas Wardhana
Welsh School of Architecture
Topologic: A toolkit for spatial and topological architectural modelling and exploration
31 October 2018Yuhua LiNovelty detection: Know unknowns from knowns
24 October 2018Zeliang WangPolynomial matrix eigenvalue decomposition techniques for multichannel signal processing
17 October 2018Dietmar Saupe
University of Konstanz, Germany
KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment
10 October 2018Hui Huang Zhao
HengYang Normal University, China
Image style transfer using deep CNNs
3 October 2018Juncheng Liu
Peking University, China
Image driven co-segmentation of 3D models

Enquiries

Please direct all questions about this research seminar programme to:

Professor Paul Rosin

Professor Paul Rosin

Professor of Computer Vision

Email
rosinpl@cardiff.ac.uk
Telephone
+44 (0)29 2087 5585