Huge congratulations to the incredible researchers of PAI and CVSSP!

Their work is the pillar behind our no. 1 in computer vision ranking since records began – CS Rankings, retrieved 12 July 2024: tinyurl.com/5n8zs5yh

We are immensely proud of their record of publishing impactful papers and presenting at prestigious conferences. Their hard work, dedication, and ground-breaking ideas are inspiring.

Here are just some of their recent achievements:

?

ECCV2024

Josef Kittler had two papers accepted:

·??????? Title: Efficient Few-Shot Action Recognition via Multi-Level Post-Reasoning. Authors: Josef Kittler and (from Jiangnan University): Cong Wu, Xiao-Jun Wu, Lin-Ze Li, Tianyang Xu, Zhenhua Feng

·??????? R. Li, Z. Feng, T. Xu, L. Li, X-J. Wu, M. Awais, S. Atito, J. Kittler, "C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition."

?

Adrian Hilton had two papers accepted:

·??????? "CoLeaF: A Contrastive-Collaborative Learning Framework for Weakly Supervised Audio-Visual Video Parsing" – Adrian Hilton, Faegheh (Fay) Sardari, Armin Mustafa and Philip Jackson (https://arxiv.org/pdf/2405.10690).

·??????? COSMU: Complete 3D human shape from monocular unconstrained images"? Adrian Hilton and Marco Pesavento

?

Yi-Zhe Song had three papers accepted:

·??????? Gemma Canet Tarrés, Zhe Lin, Zhifei Zhang, Jianming Zhang, Yi-Zhe Song, Dan Ruta, Andrew Gilbert, John Collomosse , Soo Ye Kim: "Thinking Outside the BBox: Unconstrained Generative Object Compositing."

·??????? Kam Woh Ng, Xiatian Zhu, Yi-Zhe Song, Tao Xiang: “PartCraft: Crafting Creative Objects by Parts.” Code released at https://github.com/kamwoh/partcraft/.

·??????? Aneeshan Sain, Pinaki Nath Chowdhury, Subhadeep Koley, Ayan Kumar Bhunia, Yi-Zhe Song: “Freeview Sketching: View-Aware Fine-Grained. Sketch-Based Image Retrieval.” arXiv link: https://arxiv.org/abs/2407.01810, PDF: https://arxiv.org/pdf/2407.01810.

?

Gustavo Carneiro had seven papers accepted and was co- organiser of the Workshop More Exploration, Less Exploitation (MELEX), held in conjunction with ECCV 2024.

·??????? Yuyuan Liu, Yuanhong Chen, Hu Wang, Vasileios Belagiannis, Ian Reid, Gustavo Carneiro. ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation.

·??????? Arpit Garg, Cuon Nguyen, Rafael Felix, Thanh-Toan Do, Gustavo Carneiro. Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation.

·??????? Yuanhong Chen, Chong Wang, Yuyuan Liu, Hu Wang, Gustavo Carneiro. CPM: Class-conditional Prompting Machine for Audio-visual Segmentation.

·??????? Cuong Pham, Hoang Dung, Cuong Nguyen, Trung Le, Dinh Phung, Gustavo Carneiro, Thanh-Toan Do. MetaAug: Meta-Data Augmentation for Post-Training Quantization.

·??????? Zheng Zhang, Wenjie Ai, Kevin Wells, David Rosewarne, Thanh-Toan Do, Gustavo Carneiro. Learning to Complement and to Defer to Multiple Users.

·??????? Zhi Qin Tan, Olga Isupova, Gustavo Carneiro, Xiatian Zhu, Yunpeng Li. Bayesian Detector Combination for Object Detection with Crowdsourced Annotations.

·??????? Bayesian Detector Combination for Object Detection with Crowdsourced Annotations Tan, Zhi Qin, Isupova, Olga, Carneiro, Gustavo,? Zhu, Xiatian, and Li, Yunpeng

?

“GroundUp: Rapid Sketch-Based 3D City Massing.”

Gizem Unlu, Mohamed Sayed, Yulia Gryaditskaya, Gabriel Brostow. Collaboration between UCL, London and CVSSP, PAI, University of Surrey.

?

Xiatian Zhu had two papers accepted:

·??????? PartCraft: Crafting Creative Objects by Parts Ng, Kam Woh,? Zhu, Xiatian, Song, Yi-Zhe, and Xiang, Tao

·??????? Bayesian Detector Combination for Object Detection with Crowdsourced Annotations Tan, Zhi Qin, Isupova, Olga, Carneiro, Gustavo,? Zhu, Xiatian, and Li, Yunpeng

?

Many congratulations to CVSSP student Oliver Cory, whose paper, "Modelling the Distribution of Human Motion for Sign Language Assessment" was accepted for oral presentation

-at the Assistive Computer Vision and Robotics ACVR2024 workshop at the European Conference on Computer Vision ECCV2024. Other CVSSP participants in the paper are Dr ?zge Mercano?lu, Dr Matthew Vowels, and Principal Investigator Professor Richard Bowden. This is work done with partners in Switzerland as part of ongoing collaborations in the hashtag#SMILEII and IICT Flagship projects.

?

CVPR2024

Many congratulations to Gemma Canet Tarrés, PhD student at CVSSP and Research Scientist Intern at Adobe presenting her research PARASOL at CVPR2024 June 2024.This is a great honour for a PHD researcher: Gemma Canet Tarrés, Dan Ruta, Tu Bui, John Collomosse: "PARASOL: Parametric Style Control for Diffusion Image Synthesis" presented as an oral at WiCV (Women in Computer Vision) workshop at CVPR 2024.

?

ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D image: Professor Adrian Hilton

Source-Free Domain Adaptation with Frozen Multimodal Foundation Model: Dr Xiatian Zhu: tinyurl.com/2b5cpvhm Open Vocabulary Scene Sketch Semantic Understanding: Ahmed Bourouis, Judith Ellen Fan, Yulia Gryaditskaya: tinyurl.com/3wddmaup

A Closer Look at Audio-Visual Segmentation: Professor Gustavo Carneiro: tinyurl.com/4su72d47

ProMark: Proactive Diffusion Watermarking for Causal Attribution: Professor John Collomosse: arxiv.org/abs/2403.09914

Professor Yi-Zhe Song had 10 papers accepted:

·??????? Wired Perspectives: Multi-View Wire Art Embraces Generative AI: t.ly/EtM0p

·??????? DemoFusion: Democratising High-Resolution Image Generation With No $$$ tinyurl.com/32frn968

·??????? You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval

·??????? Doodle Your 3D: From Abstract Freehand Sketches to Precise 3D Shapes tinyurl.com/yck4hb6f

·??????? Text-to-Image Diffusion Models are Great Sketch-Photo Matchmakers

·??????? How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?

·??????? SketchINR: A First Look into Sketches as Implicit Neural Representations

·??????? It's All About Your Sketch: Democratising Sketch Control in Diffusion Models

·??????? A Little Trust Goes a Long Way: What Sketch Explainability Really Means for Downstream Tasks

·??????? DemoCaricature: Democratising Caricature Generation with a Rough Sketch tinyurl.com/r5a94svs

?

IROS2024 - IEEE / RSJ International Conference on Intelligent Robots and Systems

Tav Shore: “BEV-CV: Birds-Eye-View Transform for Cross-View Geo-Localisation.” -?? Location: Abu Dhabi, October 2024

?

Automatic Face and Gesture Recognition FG2024

Congratulations to Anton Pelykh, PhD researcher at CVSSP, who has had a busy and productive summer! In May, he and other members of the Cognitive Vision Group at CVSSP; Harry Walsh, ?zge Mercano?lu, Professor Richard Bowden and Maksym Ivashechkin; attended the18th International Conference on Automatic Face and Gesture Recognition FG2024. Anton was invited to present his paper there: "Giving a Hand to Diffusion Models: a Two-Stage Approach to Improving Conditional Human Image Generation."

EEML2024

In July, Anton Pelykh participated in the Eastern European Machine Learning Summer School EEML2024 in Novi Sad, Serbia and was awarded Best Poster Award.

?

NeTTT2024

Archchana Sindhujan, a PhD student, presented a paper remotely in the conference NeTTT (New Trends in Translation and Technology), Varna, Bulgaria. Paper Topic: Optimizing Quality Estimation for Low-Resource Language Translations: Exploring the Role of Language Relatedness. https://nettt-conference.com/accepted-papers/.

?

IEEE NSS MIC RTSD 2024

Robert John and Kevin Wells had two papers accepted:

·??????? Can PET FDG Deep Texture Representations Be Made Robust? Authors - Robert John, Ian Ackerley, Rhodri Smith, Andrew Robinson, Vineet Prakash, Manu Shastry, Peter Strouhal, Kevin Wells

·??????? Deep Texture Analysis for Automated TNM Staging Authors - Robert John, Ian Ackerley, Rhodri Smith, Andrew Robinson, Vineet Prakash, Manu Shastry, Peter Strouhal, Kevin Wells

Gustavo Carneiro had three papers accepted

·??????? Chong Wang, Yuanhong Chen, Fengbei Liu, Michael Elliott, Chun Fung Kwok, Carlos Pe?a-Solorzano, Helen Frazer, Davis James McCarthy, and Gustavo Carneiro (2024). An Interpretable and Accurate Deep-learning Diagnosis Framework Modelled with Fully and Semi-supervised Reciprocal Learning.?IEEE Transactions on Medical Imaging 43(1): 392-404. 2024.

·??????? Coen de Vente, Koenraad A. Vermeer, Nicolas Jaccard, He Wang, Hongyi Sun, Firas Khader, Daniel Truhn, Temirgali Aimyshev, Yerkebulan Zhanibekuly, Tien-Dung Le, Adrian Galdran, Miguel ángel González Ballester, Gustavo Carneiro, Devika R G, Hrishikesh P S, Densen Puthussery, Hong Liu, Zekang Yang, Satoshi Kondo, Satoshi Kasai, Edward Wang, Ashritha Durvasula, Jónathan Heras, Miguel ángel Zapata, Teresa Araújo, Guilherme Aresta, Hrvoje Bogunovi?, Mustafa Arikan, Yeong Chan Lee, Hyun Bin Cho, Yoon Ho Choi, Abdul Qayyum, Imran Razzak, Bram van Ginneken, Hans G. Lemij, Clara I. Sánchez (2024). AIROGS: Artificial Intelligence for RObust Glaucoma Screening Challenge. IEEE Transactions on Medical Imaging 43(1): 542-557. 2024.

·??????? Yap, M.H., Cassidy, B., Byra, M., Liao, T.Y., Yi, H., Galdran, A., Chen, Y.H., Brüngel, R., Koitka, S., Friedrich, C.M., Lo, Y.W., Yang, C., Li, K., Lao, Q., Ballester, M.A.G., Carneiro, G., Ju, Y., Huang, J., Pappachan J.M., Reeves, N.D., Chandrabalan, V., Dancey, D., Kendrick, C. (2024). Diabetic foot ulcers segmentation challenge report: Benchmark and analysis. Medical Image Analysis, 94, p.103153. 2024.

?

MIUA2024

Robert John had two papers accepted, presented in Manchester on July 26th.

·??????? Deep Texture Analysis in Whole-Body PET Using Graph Neural Network Analysis of the Sub-Logit Layer.

·??????? Title - Deep Texture Analysis for Automated TNM Staging Authors - Robert John, Ian Ackerley, Rhodri Smith, Andrew Robinson, Vineet Prakash, Manu Shastry, Peter Strouhal, Kevin Wells

?

ACM Multimedia 2024

As well as his ECCV 2024 success (see above), Xiatian Zhu and colleagues have had other recent paper successes:

·??????? Adversarial Experts Model for Black-box Domain Adaptation Siying Xiao, Mao Ye, Qichen He, Shuaifeng Li, Song Tang, Xiatian Zhu

·??????? International Journal of Computer Vision 2024

·??????? Knowledge Distillation Meets Open-Set Semi-Supervised Learning Yang, Jing,? Zhu, Xiatian, Bulat, Adrian, Martinez, Brais, and Tzimiropoulos, Georgios

·??????? Vision Transformers: From Semantic Segmentation to Dense Prediction Zhang, Li, Lu, Jiachen, Zheng, Sixiao, Zhao, Xinxuan,? Zhu, Xiatian, Fu, Yanwei, Xiang, Tao, and Feng, Jianfeng

·??????? Softmax-free linear transformers Lu, Jiachen, Zhang, Li, Zhang, Junge,? Zhu, Xiatian, Feng, Jianfeng, and Xiang, Tao.

?

FGVC11

Professor Yi-Zhe Song? was awarded, with colleagues KamWoh Ng (first author), Dr Xiatian Zhu, Professor Tao Xiang, Best Paper Award at FGVC11 (The Eleventh Workshop on Fine-Grained Visual Categorization) workshop at CVPR24 in Seattle for: "Interpretable Fine-Grained Hashing with Concept Discovery."

?

Gustavo Carneiro has been invited to speak at the following conferences:

AI-DLDA: International Summer School on Artificial Intelligence at the Universita Degli Studi Di Udine: Talk title: Learning to Complement and to Defer to Multiple Users using Personalized Human-AI Collaborative Classifiers.

Technical University of Munich, 2024: Talk title: People-centred Medical Image Analysis.

The 5th International Conference on Medical Imaging and Computer-Aided Diagnosis: Keynote speaker