Program-html.html

Monday, July 15, 2024

9 : 3 0

– 1 0 : 0 0

Registration at 115 New Cavendish Campus

– University of Westminster

1 0 : 0 0

– 1 2 : 0 0

Workshop 1 - Generative AI: generating images using AI
Instructor: Assist. Prof. Ester Bonmati and Assoc. Prof. Barbara Villarini
Room: Cavendish CG.24/25 Innovation Space

1 2 : 3 0

– 1 3 : 3 0

Lunch Break

Room: Pavilion C1.18

1 4 : 0 0

– 16:00

Workshop 2

– Reinforcement Learning for image analysis

Instructor: Iani Gayo, Assist. Prof. Ester Bonmati and Assoc. Prof.
Barbara Villarini
Room: Cavendish CG.24/25 Innovation Space

Tuesday, July 16, 2024

8 : 3 0

– 9 : 0 0

Registration at 115 New Cavendish Campus

– University of Westminster

Coffee Break

Room: Pavilion C1.18

9 : 0 0

– 9 : 1 0

Opening Conference

Welcome by IEEE ICPRS24 General Chairs and Local Chairs

Welcome from Prof. Peter Bonfield, Vice-Chancellor and President

University of Westminster

Room: Large Lecture Theatre (C2.12)

9 : 1 0 - 1 0 : 0 0

Invited Talk: Towards Resilient AI in healthcare, Prof. Paolo Soda
Chair: Prof. Rodrigo Salas
Room: Large Lecture Theatre (C2.12)

IEEE 14

International Conference on Pattern

Recognition Systems (ICPRS) 2024

Conference Programme

Session 1

Machine Learning in Medical
Applications (I)

Session 2

Machine Learning in Medical
Applications (II)

Session 3

Biometrics and Case Studies

Session 4

Pattern Recognition and Image
Analysis (I)

Session 5

Computer Vision and Real-Time
Systems

Session 6

Artificial Intelligence Techniques
in Pattern Recognition

Session 7

Natural Language Processing and
Recognition

Session 8

Pattern Recognition Principles

Session 9

Pattern Recognition and Image
Analysis (II)

Session 10

Data mining and Big Data

Session 11

Pattern Recognition in Agriculture

Session 1 Machine Learning in Medical Applications (I)
Chair: Assoc. Prof. Anastasia Angelopoulou
Room: Large Lecture Theatre (C2.12)

1 0 : 0 0

– 1 0 : 2 0

Transformer-Based Skin Carcinoma Classification using
Histopathology Images via Incremental Learning
Muhammad Imran, Muhammad Usman Akram, Anum Abdul Salam

1 0 : 2 0

– 10:40

Efficient colorectal polyps segmentation using a deep learning
ensemble framework from colonoscopy images
Deepak Bajhaiya, Sujatha Narayanan Unni

1 0 : 4 0

– 1 1 : 0 0

In Domain Transfer Learning for Prostate MRI Segmentation
Larbi Touijer, Matteo Santacesaria, Francesca Odone, Vito Paolo Pastore

1 1 : 0 0

– 1 1 : 2 0

Explainable Machine-Learning for identifying the genetic biomarker
MGMT in brain tumors using magnetic resonance imaging radiomics
Sebastian Ponce, Steren Chabert, Leondry Mayeta, Pamela Franco,
Francisco Plaza-Vega, Marvin Querales, Rodrigo Salas

1 1 : 2 0

– 1 1 : 4 0

Coffee Break

Room: Pavilion C1.18

Session 2 Machine Learning in Medical Applications (II)
Chair: Assist. Prof. Ester Bonmati Coll
Room: Large Lecture Theatre (C2.12)

1 1 : 4 0

– 1 2 : 0 0

PRS24

onf

ere

Progr

Leveraging large language models for medical text classification: a
hospital readmission prediction case
Nodira Nazyrova, Salma Chahed, Thierry Chaussalet, Miriam Dwek

1 2 : 0 0

– 1 2 : 2 0

Autism Spectrum Disorder Prediction Using Machine Learning
Classifiers
Faisal Aburub, Wael Hadi, Abedal-Kareem Al-Banna, Mohammad Arafah

1 2 : 2 0

– 1 2 : 4 0

Focal Atrophy Structure-focused Neurodegeneration Convolutional
Neural Network for Modelling and Classification of Alzheimer’s
Disease
Simisola Odimayo, Chollette C. Olisah, Khadijah Mohammed

1 2 : 4 0

– 1 3 : 0 0

SEDNet: Shallow Encoder Decoder Network for Brain Tumor
Segmentation
Chollette C. Olisah, Sofie Van Cauter

1 3 : 0 0

– 1 4 : 0 0

Lunch Break

Room: Pavilion C1.18

1 4 : 0 0 - 1 4 : 5 0

Invited Talk: Opportunities in Egocentric Video Understanding, Prof. Dima
Damen
Chair: Assoc. Prof. Barbara Villarini
Room: Large Lecture Theatre (C2.12)

Session 3 Biometrics and Case Studies
Chair: Assoc. Prof. Barbara Villarini
Room: Large Lecture Theatre (C2.12)

1 4 : 5 0

– 1 5 : 1 0

MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic
Emotion Recognition
Peihao Xiang, Chaohao Lin, Kaida Wu, Ou Bai

1 5 : 1 0

– 1 5 : 3 0

Shrinking embeddings, not accuracy: Performance-Preserving
Reduction of Facial Embeddings for Complex Face Verification
Computations
Philipp Hofer, Philipp Schwarz, Michael Roland, Rene Mayrhofer

1 5 : 3 0

– 1 5 : 5 0

Analysing Emotional and Topical Patterns in Conspiracy Theory
Narratives: A Discourse Comparative Study on the 2023 Hawaii
Wildfires
Nikolai Dubinko, Marjory Da Costa Abreu, Petra Saskia Bayerl, Helen
Gibson

1 5 : 5 0

– 1 6 : 1 0

Coffee Break

Room: Pavilion C1.18

Session 4 Pattern Recognition and Image Analysis (I)
Chair: Prof. Rodrigo Salas
Room: Large Lecture Theatre (C2.12)

1 6 : 1 0

– 1 6 : 3 0

PRS24

onf

ere

Progr

Enhancing Authenticity Verification with Transfer Learning and
Ensemble Techniques in Facial Feature-Based Deepfake Detection
Nadeem Qazi, Iftikhar Ahmed

1 6 : 3 0

– 1 6 : 5 0

VLS-FWA: Real-time end-to-end neural network pipeline of vision-
based landing system for fixed-wing aircraft
Dheeraj Bharti, Chiranjeev Prachand, K S Venkatesh

1 6 : 5 0

– 1 7 : 1 0

SAI-ChileanDiet: A multi-label food dataset with self-acquired images
of the Chilean diet
Roberto Morales, Bastian Munoz, Angela Martinez, Eduardo Aguilar

1 7 : 1 0

– 1 7 : 3 0

Exploring neighborhood variancy for rule search optimization in Life-
like Network Automata
Kallil M. C. Zielinski, Leonardo Scabini, Lucas C. Ribas, Odemir M. Bruno

Wednesday, July 17, 2024

8 : 3 0

– 9 : 0 0

Registration at 115 New Cavendish Campus

– University of Westminster

Coffee Break

Room: Pavilion C1.18

9 : 0 0 - 9 : 5 0

Invited Talk: Multimodal Self-Supervised Learning, Prof. Sean Gong
Chair: Prof. Sergio Velastin
Room: Large Lecture Theatre (C2.12)

Session 5 Computer Vision and Real-Time Systems
Chair: Prof. Sergio Velastin
Room: Large Lecture Theatre (C2.12)

9 : 5 0

– 1 0 : 1 0

SiVIC-Adverse: A Framework for Generating Synthetic Datasets for
Visual Perception in Adverse Scenarios and Automated Driving
Wei Xu, Dominique Gruyer, Alexandra Duminil, Sio-Song Ieng

1 0 : 1 0

– 10:30

Enhancing Vehicle Aerodynamics with Deep Reinforcement Learning
in Voxelised Models
Jignesh Patel, Yannis Spyridis, Vasileios Argyriou

1 0 : 3 0

– 1 0 : 5 0

Semantic Video Moment Retrieval by Temporal Feature Perturbation
and Refinement
Weitong Cai, Jiabo Huang, Jian Hu, Shaogang Gong, Hailin Jin, Yang Liu

1 0 : 5 0

– 1 1 : 1 0

Computer Vision-Driven Recommendation System for London
Explorers
Khadidja Mekiri, Kashif Talpur, Shakeel Ahmad

1 1 : 1 0

– 1 1 : 3 0

A Cross-Domain Threat Screening and Localization Framework Using
Vision Transformers and Self-supervised Learning
Ammara Nasim, Muhammad Usman Akram, Muhammad Belal Afsar
Khan, Asad Mansoor Khan, Taimur Hassan

1 1 : 3 0

– 1 1 : 5 0

Coffee Break

Room: Pavilion C1.18

Session 6 Artificial Intelligence Techniques in Pattern Recognition
Chair: Assist. Prof. Marie Beurton-Aimar
Room: Large Lecture Theatre (C2.12)

1 1 : 5 0

– 1 2 : 1 0

PRS24

onf

ere

Progr

LLM-aided Knowledge Graph construction for Zero-Shot Visual
Object State Classification
Filippos Gouidis, Katerina Papantoniou, Konstantinos Papoutsakis,
Theodore Patkos, Antonis Argyros, Dimitris Plexousakis

1 2 : 1 0

– 1 2 : 3 0

Evaluation of road users trajectories from aerial-view data for risk
analysis
Josue Manuel Rivera Velazquez, Pascal Houssam Salmane, Guillaume
Saint Pierre, Louahdi Khoudour, Trung-Thai Do, Martin Emery

1 2 : 3 0

– 1 2 : 5 0

Deep Learning-Based Instance Segmentation to Characterize the
Morphology of Compact Aggregates through Image Analysis
Leo Theodon, Carole Coufort-Saudejaud, Johan Debayle

1 2 : 5 0

– 1 3 : 1 0

Optimizing Multi-Target Sessioning Through Airborne Passive
Sensor Management
Hao Ren,Xiaojun Ban,Shengkun Xie

1 3 : 1 0

– 1 4 : 1 0

Lunch Break

Room: Pavilion C1.18

Session 7 Natural Language Processing and Recognition
Chair: Assoc. Prof. Romina Torres
Room: Large Lecture Theatre (C2.12)

1 4 : 1 0

– 1 4 : 3 0

Multi-Task Learning Transformers: Comparative Analysis of Emotion
Classification and Intensity Prediction in Social Media
Qasid Labeed, Xing Liang

1 4 : 3 0

– 1 4 : 5 0

A Deep Learning model for Question Analysis in Low-resource
Languages: A Dataset and Case Study for Persian
Fatemeh Ebrahimi Khaksefidi, Afsaneh Fatemi, Mohammad Ali
Nematbakhsh, Mahsa Abazari Kia

1 4 : 5 0

– 1 5 : 1 0

Automatic detection of contextual laterality in Mammography
Reports using Large Language Models
Eduardo Godoy, Joaquin De Ferrari, Diego Mellado, Steren Chabert,
Rodrigo Salas

1 5 : 1 0

– 1 5 : 3 0

Arabic Tweet Act: A Graph Convolution Network-based Classifier for
Classifying Arabic Speech Acts in Twitter
Khadejaa Alshehri, Areej Alhothali,Nahed Alowidi

1 5 : 3 0

– 1 5 : 5 0

An Attention-based Ensemble Model for Emotion Recognition in
Conversation
Misbah Farooq, Varuna De Silva, Xiyu Shi

1 5 : 5 0

– 1 6 : 1 0

Coffee Break

Room: Pavilion C1.18

Session 8 Pattern Recognition Principles
Chair: Assoc. Prof. Anastasia Angelopoulou
Room: Large Lecture Theatre (C2.12)

1 6 : 1 0

– 1 6 : 3 0

Confe

ren

Progr

Adversarial Contrastive Representation Learning for Passive WiFi
Fingerprinting of Individuals
Varuna De Silva, Corentin Artaud

1 6 : 3 0

– 1 6 : 5 0

Missing Data Imputation With Contextual Granules and AI-driven
Bankruptcy Prediction
Debarati Chakraborty, Ravi Ranjan

1 6 : 5 0

– 1 7 : 1 0

Exploratory Analysis of Machine Learning Methods for Total Organic
Carbon Prediction Using Well-Log Data of Kolmani Field
Fodio Longman, Rasheed O. Ojulari, Husaini Balarabe, Olaniyi J.
Olatomiwa, Ifeanyichukwu Edeh, Olabisi Joshua, Habeeb Balogun

1 7 : 1 0

– 1 7 : 3 0

Comparative Analysis of Micro/Minichannel Flow Boiling Pattern
Recognition and Classification using Clustering Algorithms
Mohammad Harris, Anastasia Angelopoulou, Hongwei Wu, Wenbin Zhang

Thursday, July 18, 2024

8 : 3 0

– 9 : 0 0

Registration at 115 New Cavendish Campus

– University of Westminster

Coffee Break

Room: Pavilion C1.18

ICPRS24 Dinner

Best Conference Paper Prizes Ceremony

Room: Pavilion C1.18

Time: 18:30

– 21:00

9 : 0 0 - 9 : 5 0

Invited Talk: Inductive Biases for Robot Reinforcement Learning, Prof.
Jan Peters
Chair: Prof. Boris X. Vintimilla B.
Room: Large Lecture Theatre (C2.12)

Session 9 Pattern Recognition and Image Analysis (II)
Chair: Prof. Boris X. Vintimilla B.
Room: Large Lecture Theatre (C2.12)

9 : 5 0

– 1 0 : 1 0

Depth-Conditioned Thermal-like Image Generation
Patricia Suarez, Angel Sappa

1 0 : 1 0

– 10:30

Preliminary results on food weight estimation with RGB-D images
Bryan Gonzalez, Osmar Gecele, Jaime Ramirez, Gonzalo Garcia, Sergio
Velastin, Gonzalo Farias

1 0 : 3 0

– 1 0 : 5 0

Self-Occluded Human Pose Recovery in Monocular Video Motion
Capture
Leila Malekian, Rudy Lapeer

1 0 : 5 0

– 1 1 : 3 0

Coffee Break

Room: Pavilion C1.18

Session 10 Data mining and Big Data
Chair: Prof. Thierry Chaussalet
Room: Large Lecture Theatre (C2.12)

1 1 : 3 0

– 1 1 : 5 0

A Laplacian Evolution Approach to Identify the Source-Sink Pattern
of Human Mobility in Urban
Peng Zhang, Wanyu Cong, Yi Shi, Junyan Yang, Qiao Wang

1 1 : 5 0

– 1 2 : 1 0

An Evaluation of Standard Statistical Models and LLMs on Time
Series Forecasting
Rui Cao, Qiao Wang

1 2 : 1 0

– 1 2 : 3 0

A Concept Drift Based Approach To Evaluating Model Performance
And Theoretical Lifespan
Mustafa Hajmohammed, Panagiotis Chountas, Thierry Chaussalet

1 2 : 3 0

– 1 3 : 3 0

Lunch Break

Room: Pavilion C1.18

Session 11 Pattern Recognition in Agriculture
Chair: Assoc. Prof. Saumya Reni
Room: Large Lecture Theatre (C2.12)

1 3 : 3 0

– 1 3 : 5 0

Carabids hierarchical classification with ensemble model
architecture
Gabin Moulie, Marie Beurton-Aimar, Matthieu Vale

1 3 : 5 0

– 1 4 : 1 0

Enhancing Apple

’s Defect Classification: Insights from Visible

Spectrum and Narrow Spectral Band Imaging
Omar Coello, Moises Coronel, Dario Carpio, Boris Vintimilla, Luis
Chuquimarca

1 4 : 1 0

– 1 4 : 3 0

Deep learning for Root System Extraction from Barley Plants
Maichol Dadi, Alessandra Lumini, Annalisa Franco, Giuseppe Sangiorgi

1 4 : 3 0

– 1 4 : 5 0

Non-Invasive Estimation of Moisture Content in Mushrooms Using
Hyperspectral Imaging and Machine Learning-Based Stacking
Regressor Model
Jyotisana Meena, Sujatha Narayanan Unni

1 4 : 5 0

– 1 5 : 1 0

Classifying Healthy and Defective Fruits with a Siamese Architecture
and CNN Models
Luis Chuquimarca, Boris Vintimilla, Sergio Velastin