Alan F. Smeaton

Lorin Sweeney, Mihai Gabriel Constantin, Claire-Hélène Demarty et al. · harvard, mit

This paper describes the 5th edition of the Predicting Video Memorability Task as part of MediaEval2022. This year we have reorganised and simplified the task in order to lubricate a greater depth of inquiry. Similar to last year, two datasets are provided in order to facilitate generalisation, however, this year we have replaced the TRECVid2019 Video-to-Text dataset with the VideoMem dataset in order to remedy underlying data quality issues, and to prioritise short-term memorability prediction by elevating the Memento10k dataset as the primary dataset. Additionally, a fully fledged electroencephalography (EEG)-based prediction sub-task is introduced. In this paper, we outline the core facets of the task and its constituent sub-tasks; describing the datasets, evaluation metrics, and requirements for participant submissions.

Alba García Deco de Herrera, Mihai Gabriel Constantin, Chaire-Hélène Demarty et al. · harvard, mit

The Predicting Media Memorability task in the MediaEval evaluation campaign has been running annually since 2018 and several different tasks and data sets have been used in this time. This has allowed us to compare the performance of many memorability prediction techniques on the same data and in a reproducible way and to refine and improve on those techniques. The resources created to compute media memorability are now being used by researchers well beyond the actual evaluation campaign. In this paper we present a summary of the task, including the collective lessons we have learned for the research community.

Iya Chivileva, Philip Lynch, Tomas E. Ward et al.

Evaluating the quality of videos generated from text-to-video (T2V) models is important if they are to produce plausible outputs that convince a viewer of their authenticity. We examine some of the metrics used in this area and highlight their limitations. The paper presents a dataset of more than 1,000 generated videos from 5 very recent T2V models on which some of those commonly used quality metrics are applied. We also include extensive human quality evaluations on those videos, allowing the relative strengths and weaknesses of metrics, including human assessment, to be compared. The contribution is an assessment of commonly used quality metrics, and a comparison of their performances and the performance of human evaluations on an open dataset of T2V videos. Our conclusion is that naturalness and semantic matching with the text prompt used to generate the T2V output are important but there is no single measure to capture these subtleties in assessing T2V model output.

Ayush K. Rai, Tarun Krishna, Feiyan Hu et al.

Video Anomaly Detection (VAD) is an open-set recognition task, which is usually formulated as a one-class classification (OCC) problem, where training data is comprised of videos with normal instances while test data contains both normal and anomalous instances. Recent works have investigated the creation of pseudo-anomalies (PAs) using only the normal data and making strong assumptions about real-world anomalies with regards to abnormality of objects and speed of motion to inject prior information about anomalies in an autoencoder (AE) based reconstruction model during training. This work proposes a novel method for generating generic spatio-temporal PAs by inpainting a masked out region of an image using a pre-trained Latent Diffusion Model and further perturbing the optical flow using mixup to emulate spatio-temporal distortions in the data. In addition, we present a simple unified framework to detect real-world anomalies under the OCC setting by learning three types of anomaly indicators, namely reconstruction quality, temporal irregularity and semantic inconsistency. Extensive experiments on four VAD benchmark datasets namely Ped2, Avenue, ShanghaiTech and UBnormal demonstrate that our method performs on par with other existing state-of-the-art PAs generation and reconstruction based methods under the OCC setting. Our analysis also examines the transferability and generalisation of PAs across these datasets, offering valuable insights by identifying real-world anomalies through PAs.

Hamza Riaz, Alan F. Smeaton

There are many computer vision applications including object segmentation, classification, object detection, and reconstruction for which machine learning (ML) shows state-of-the-art performance. Nowadays, we can build ML tools for such applications with real-world accuracy. However, each tool works well within the domain in which it has been trained and developed. Often, when we train a model on a dataset in one specific domain and test on another unseen domain known as an out of distribution (OOD) dataset, models or ML tools show a decrease in performance. For instance, when we train a simple classifier on real-world images and apply that model on the same classes but with a different domain like cartoons, paintings or sketches then the performance of ML tools disappoints. This presents serious challenges of domain generalisation (DG), domain adaptation (DA), and domain shifting. To enhance the power of ML tools, we can rebuild and retrain models from scratch or we can perform transfer learning. In this paper, we present a comparison study between vision-based technologies for domain-specific and domain-generalised methods. In this research we highlight that simple convolutional neural network (CNN) based deep learning methods perform poorly when they have to tackle domain shifting. Experiments are conducted on two popular vision-based benchmarks, PACS and Office-Home. We introduce an implementation pipeline for domain generalisation methods and conventional deep learning models. The outcome confirms that CNN-based deep learning models show poor generalisation compare to other extensive methods.

Lorin Sweeney, Graham Healy, Alan F. Smeaton

As part of the MediaEval 2022 Predicting Video Memorability task we explore the relationship between visual memorability, the visual representation that characterises it, and the underlying concept portrayed by that visual representation. We achieve state-of-the-art memorability prediction performance with a model trained and tested exclusively on surrogate dream images, elevating concepts to the status of a cornerstone memorability feature, and finding strong evidence to suggest that the intrinsic memorability of visual content can be distilled to its underlying concept or meaning irrespective of its specific visual representational.

Siddhant Jaydeep Mahajani, Shashank Srivastava, Alan F. Smeaton

Lexicon-based approaches to sentiment analysis of text are based on each word or lexical entry having a pre-defined weight indicating its sentiment polarity. These are usually manually assigned but the accuracy of these when compared against machine leaning based approaches to computing sentiment, are not known. It may be that there are lexical entries whose sentiment values cause a lexicon-based approach to give results which are very different to a machine learning approach. In this paper we compute sentiment for more than 150,000 English language texts drawn from 4 domains using the Hedonometer, a lexicon-based technique and Azure, a contemporary machine-learning based approach which is part of the Azure Cognitive Services family of APIs which is easy to use. We model differences in sentiment scores between approaches for documents in each domain using a regression and analyse the independent variables (Hedonometer lexical entries) as indicators of each word's importance and contribution to the score differences. Our findings are that the importance of a word depends on the domain and there are no standout lexical entries which systematically cause differences in sentiment scores.

Colin Hehir, Alan F. Smeaton

The matrix profile (MP) is a data structure computed from a time series which encodes the data required to locate motifs and discords, corresponding to recurring patterns and outliers respectively. When the time series contains noisy data then the conventional approach is to pre-filter it in order to remove noise but this cannot apply in unsupervised settings where patterns and outliers are not annotated. The resilience of the algorithm used to generate the MP when faced with noisy data remains unknown. We measure the similarities between the MP from original time series data with MPs generated from the same data with noisy data added under a range of parameter settings including adding duplicates and adding irrelevant data. We use three real world data sets drawn from diverse domains for these experiments Based on dissimilarities between the MPs, our results suggest that MP generation is resilient to a small amount of noise being introduced into the data but as the amount of noise increases this resilience disappears

Xiao Liu, Alan F. Smeaton, Alessandra Mileo

Recent developments in in-situ monitoring and process control in Additive Manufacturing (AM), also known as 3D-printing, allows the collection of large amounts of emission data during the build process of the parts being manufactured. This data can be used as input into 3D and 2D representations of the 3D-printed parts. However the analysis and use, as well as the characterization of this data still remains a manual process. The aim of this paper is to propose an adaptive human-in-the-loop approach using Machine Learning techniques that automatically inspect and annotate the emissions data generated during the AM process. More specifically, this paper will look at two scenarios: firstly, using convolutional neural networks (CNNs) to automatically inspect and classify emission data collected by in-situ monitoring and secondly, applying Active Learning techniques to the developed classification model to construct a human-in-the-loop mechanism in order to accelerate the labeling process of the emission data. The CNN-based approach relies on transfer learning and fine-tuning, which makes the approach applicable to other industrial image patterns. The adaptive nature of the approach is enabled by uncertainty sampling strategy to automatic selection of samples to be presented to human experts for annotation.

Ayush K. Rai, Tarun Krishna, Julia Dietlmeier et al.

The task of Generic Event Boundary Detection (GEBD) aims to detect moments in videos that are naturally perceived by humans as generic and taxonomy-free event boundaries. Modeling the dynamically evolving temporal and spatial changes in a video makes GEBD a difficult problem to solve. Existing approaches involve very complex and sophisticated pipelines in terms of architectural design choices, hence creating a need for more straightforward and simplified approaches. In this work, we address this issue by revisiting a simple and effective self-supervised method and augment it with a differentiable motion feature learning module to tackle the spatial and temporal diversities in the GEBD task. We perform extensive experiments on the challenging Kinetics-GEBD and TAPOS datasets to demonstrate the efficacy of the proposed approach compared to the other self-supervised state-of-the-art methods. We also show that this simple self-supervised approach learns motion features without any explicit motion-specific pretext task.

Alan F. Smeaton

This position paper explores the rapid development of Foundation Models (FMs) in AI and their implications for intelligence and reasoning. It examines the characteristics of FMs, including their training on vast datasets and use of embedding spaces to capture semantic relationships. The paper discusses recent advancements in FMs' reasoning abilities which we argue cannot be attributed to increased model size but to novel training techniques which yield learning phenomena like grokking. It also addresses the challenges in benchmarking FMs and compares their structure to the human brain. We argue that while FMs show promising developments in reasoning and knowledge representation, understanding their inner workings remains a significant challenge, similar to ongoing efforts in neuroscience to comprehend human brain function. Despite having some similarities, fundamental differences between FMs and the structure of human brain warn us against making direct comparisons or expecting neuroscience to provide immediate insights into FM function.

Aniket Jagtap, RamaKrishna Venkatesh Saripalli, Joe Lemley et al.

Event cameras, also known as neuromorphic cameras, are an emerging technology that offer advantages over traditional shutter and frame-based cameras, including high temporal resolution, low power consumption, and selective data acquisition. In this study, we propose to harnesses the capabilities of event-based cameras to capture subtle changes in the surface of the skin caused by the pulsatile flow of blood in the wrist region. We investigate whether an event camera could be used for continuous noninvasive monitoring of heart rate (HR). Event camera video data from 25 participants, comprising varying age groups and skin colours, was collected and analysed. Ground-truth HR measurements obtained using conventional methods were used to evaluate of the accuracy of automatic detection of HR from event camera data. Our experimental results and comparison to the performance of other non-contact HR measurement methods demonstrate the feasibility of using event cameras for pulse detection. We also acknowledge the challenges and limitations of our method, such as light-induced flickering and the sub-conscious but naturally-occurring tremors of an individual during data capture.

Lorin Sweeney, Graham Healy, Alan F. Smeaton

In a world of ephemeral moments, our brain diligently sieves through a cascade of experiences, like a skilled gold prospector searching for precious nuggets amidst the river's relentless flow. This study delves into the elusive "moment of memorability" -- a fleeting, yet vital instant where experiences are prioritised for consolidation in our memory. By transforming subjects' encoding phase electroencephalography (EEG) signals into the visual domain using scaleograms and leveraging deep learning techniques, we investigate the neural signatures that underpin this moment, with the aim of predicting subject-specific recognition of video. Our findings not only support the involvement of theta band (4-8Hz) oscillations over the right temporal lobe in the encoding of declarative memory, but also support the existence of a distinct moment of memorability, akin to the gold nuggets that define our personal river of experiences.

Hamza Riaz, Alan F. Smeaton

Domain generalisation involves pooling knowledge from source domain(s) into a single model that can generalise to unseen target domain(s). Recent research in domain generalisation has faced challenges when using deep learning models as they interact with data distributions which differ from those they are trained on. Here we perform domain generalisation on out-of-distribution (OOD) vision benchmarks using vision transformers. Initially we examine four vision transformer architectures namely ViT, LeViT, DeiT, and BEIT on out-of-distribution data. As the bidirectional encoder representation from image transformers (BEIT) architecture performs best, we use it in further experiments on three benchmarks PACS, Home-Office and DomainNet. Our results show significant improvements in validation and test accuracy and our implementation significantly overcomes gaps between within-distribution and OOD data.

Tarun Krishna, Ayush K. Rai, Yasser A. D. Djilali et al.

Whilst computer vision models built using self-supervised approaches are now commonplace, some important questions remain. Do self-supervised models learn highly redundant channel features? What if a self-supervised network could dynamically select the important channels and get rid of the unnecessary ones? Currently, convnets pre-trained with self-supervision have obtained comparable performance on downstream tasks in comparison to their supervised counterparts in computer vision. However, there are drawbacks to self-supervised models including their large numbers of parameters, computationally expensive training strategies and a clear need for faster inference on downstream tasks. In this work, our goal is to address the latter by studying how a standard channel selection method developed for supervised learning can be applied to networks trained with self-supervision. We validate our findings on a range of target budgets $t_{d}$ for channel computation on image classification task across different datasets, specifically CIFAR-10, CIFAR-100, and ImageNet-100, obtaining comparable performance to that of the original network when selecting all channels but at a significant reduction in computation reported in terms of FLOPs.

Vaibhav Mudgal, Qingyang Wang, Lorin Sweeney et al.

Video memorability is a measure of how likely a particular video is to be remembered by a viewer when that viewer has no emotional connection with the video content. It is an important characteristic as videos that are more memorable are more likely to be shared, viewed, and discussed. This paper presents results of a series of experiments where we improved the memorability of a video by selectively cropping frames based on image saliency. We present results of a basic fixed cropping as well as the results from dynamic cropping where both the size of the crop and the position of the crop within the frame, move as the video is played and saliency is tracked. Our results indicate that especially for videos of low initial memorability, the memorability score can be improved.

Xiao Liu, Alessandra Mileo, Alan F. Smeaton

The development of computer vision and in-situ monitoring using visual sensors allows the collection of large datasets from the additive manufacturing (AM) process. Such datasets could be used with machine learning techniques to improve the quality of AM. This paper examines two scenarios: first, using convolutional neural networks (CNNs) to accurately classify defects in an image dataset from AM and second, applying active learning techniques to the developed classification model. This allows the construction of a human-in-the-loop mechanism to reduce the size of the data required to train and generate training data.

Sean Cummins, Lorin Sweeney, Alan F. Smeaton

We investigate the memorability of a 5-season span of a popular crime-drama TV series, CSI, through the application of a vision transformer fine-tuned on the task of predicting video memorability. By investigating the popular genre of crime-drama TV through the use of a detailed annotated corpus combined with video memorability scores, we show how to extrapolate meaning from the memorability scores generated on video shots. We perform a quantitative analysis to relate video shot memorability to a variety of aspects of the show. The insights we present in this paper illustrate the importance of video memorability in applications which use multimedia in areas like education, marketing, indexing, as well as in the case here namely TV and film production.

Alan F. Smeaton, Aparajita Dey-Plissonneau, Hyowon Lee et al.

Second language learning can be enabled by tandem collaboration where students are grouped into video conference calls while learning the native language of other student(s) on the calls. This places students in an online environment where the more outgoing can actively contribute and engage in dialogue while those more shy and unsure of their second language skills can sit back and coast through the calls. We have built and deployed the L2L system which records timings of conversational utterances from all participants in a call. We generate visualisations including participation rates and timelines for each student in each call and present these on a dashboard. We have recently developed a measure called personal conversational volatility for how dynamic has been each student's contribution to the dialogue in each call. We present an analysis of conversational volatility measures for a sample of 19 individual English-speaking students from our University who are learning Frenchm, in each of 86 tandem telecollaboration calls over one teaching semester. Our analysis shows there is a need to look into the nature of the interactions and see if the choices of discussion topics assigned to them were too difficult for some students and that may have influenced their engagement in some way.

Lifeng Han, Gareth J. F. Jones, Alan F. Smeaton

Word meaning, representation, and interpretation play fundamental roles in natural language understanding (NLU), natural language processing (NLP), and natural language generation (NLG) tasks. Many of the inherent difficulties in these tasks stem from Multi-word Expressions (MWEs), which complicate the tasks by introducing ambiguity, idiomatic expressions, infrequent usage, and a wide range of variations. Significant effort and substantial progress have been made in addressing the challenging nature of MWEs in Western languages, particularly English. This progress is attributed in part to the well-established research communities and the abundant availability of computational resources. However, the same level of progress is not true for language families such as Chinese and closely related Asian languages, which continue to lag behind in this regard. While sub-word modelling has been successfully applied to many Western languages to address rare words improving phrase comprehension, and enhancing machine translation (MT) through techniques like byte-pair encoding (BPE), it cannot be applied directly to ideograph language scripts like Chinese. In this work, we conduct a systematic study of the Chinese character decomposition technology in the context of MWE-aware neural machine translation (NMT). Furthermore, we report experiments to examine how Chinese character decomposition technology contributes to the representation of the original meanings of Chinese words and characters, and how it can effectively address the challenges of translating MWEs.

Dinh Viet Cuong, Phuc H. Le-Khac, Adam Stapleton et al.

Calculating an Air Quality Index (AQI) typically uses data streams from air quality sensors deployed at fixed locations and the calculation is a real time process. If one or a number of sensors are broken or offline, then the real time AQI value cannot be computed. Estimating AQI values for some point in the future is a predictive process and uses historical AQI values to train and build models. In this work we focus on gap filling in air quality data where the task is to predict the AQI at 1, 5 and 7 days into the future. The scenario is where one or a number of air, weather and traffic sensors are offline and explores prediction accuracy under such situations. The work is part of the MediaEval'2022 Urban Air: Urban Life and Air Pollution task submitted by the DCU-Insight-AQ team and uses multimodal and crossmodal data consisting of AQI, weather and CCTV traffic images for air pollution prediction.

Kilian Carolan, Laura Fennelly, Alan F. Smeaton

Large Language Models (LLMs) have recently emerged as a focal point of research and application, driven by their unprecedented ability to understand and generate text with human-like quality. Even more recently, LLMs have been extended into multi-modal large language models (MM-LLMs) which extends their capabilities to deal with image, video and audio information, in addition to text. This opens up applications like text-to-video generation, image captioning, text-to-speech, and more and is achieved either by retro-fitting an LLM with multi-modal capabilities, or building a MM-LLM from scratch. This paper provides an extensive review of the current state of those LLMs with multi-modal capabilities as well as the very recent MM-LLMs. It covers the historical development of LLMs especially the advances enabled by transformer-based architectures like OpenAI's GPT series and Google's BERT, as well as the role of attention mechanisms in enhancing model performance. The paper includes coverage of the major and most important of the LLMs and MM-LLMs and also covers the techniques of model tuning, including fine-tuning and prompt engineering, which tailor pre-trained models to specific tasks or domains. Ethical considerations and challenges, such as data bias and model misuse, are also analysed to underscore the importance of responsible AI development and deployment. Finally, we discuss the implications of open-source versus proprietary models in AI research. Through this review, we provide insights into the transformative potential of MM-LLMs in various applications.

Zhengwei Wang, Qi She, Alan F. Smeaton et al.

Generative adversarial networks (GANs) are increasingly attracting attention in the computer vision, natural language processing, speech synthesis and similar domains. However, evaluating the performance of GANs is still an open and challenging problem. Existing evaluation metrics primarily measure the dissimilarity between real and generated images using automated statistical methods. They often require large sample sizes for evaluation and do not directly reflect human perception of image quality. In this work, we introduce an evaluation metric called Neuroscore, for evaluating the performance of GANs, that more directly reflects psychoperceptual image quality through the utilization of brain signals. Our results show that Neuroscore has superior performance to the current evaluation metrics in that: (1) It is more consistent with human judgment; (2) The evaluation process needs much smaller numbers of samples; and (3) It is able to rank the quality of images on a per GAN basis. A convolutional neural network (CNN) based neuro-AI interface is proposed to predict Neuroscore from GAN-generated images directly without the need for neural responses. Importantly, we show that including neural responses during the training phase of the network can significantly improve the prediction capability of the proposed model. Codes and data can be referred at this link: https://github.com/villawang/Neuro-AI-Interface.

Zhengwei Wang, Qi She, Alan F. Smeaton et al.

Generative adversarial networks (GANs) are increasingly attracting attention in the computer vision, natural language processing, speech synthesis and similar domains. Arguably the most striking results have been in the area of image synthesis. However, evaluating the performance of GANs is still an open and challenging problem. Existing evaluation metrics primarily measure the dissimilarity between real and generated images using automated statistical methods. They often require large sample sizes for evaluation and do not directly reflect human perception of image quality. In this work, we describe an evaluation metric we call Neuroscore, for evaluating the performance of GANs, that more directly reflects psychoperceptual image quality through the utilization of brain signals. Our results show that Neuroscore has superior performance to the current evaluation metrics in that: (1) It is more consistent with human judgment; (2) The evaluation process needs much smaller numbers of samples; and (3) It is able to rank the quality of images on a per GAN basis. A convolutional neural network (CNN) based neuro-AI interface is proposed to predict Neuroscore from GAN-generated images directly without the need for neural responses. Importantly, we show that including neural responses during the training phase of the network can significantly improve the prediction capability of the proposed model. Materials related to this work are provided at https://github.com/villawang/Neuro-AI-Interface.

Hitesh Raju, Ankit Sharma, Aoife Smeaton et al.

Epilepsy or the occurrence of epileptic seizures, is one of the world's most well-known neurological disorders affecting millions of people. Seizures mostly occur due to non-coordinated electrical discharges in the human brain and may cause damage, including collapse and loss of consciousness. If the onset of a seizure can be forecast then the subject can be placed into a safe environment or position so that self-injury as a result of a collapse can be minimised. However there are no definitive methods to predict seizures in an everyday, uncontrolled environment. Previous studies have shown that pet dogs have the ability to detect the onset of an epileptic seizure by scenting the characteristic volatile organic compounds exuded through the skin by a subject prior a seizure occurring and there are cases where assistance dogs, trained to scent the onset of a seizure, can signal this to their owner/trainer. In this work we identify how we can automatically detect the signalling behaviours of trained assistance dogs and use this to alert their owner. Using data from an accelerometer worn on the collar of a dog we describe how we gathered movement data from 11 trained dogs for a total of 107 days as they exhibited signalling behaviour on command. We present the machine learning techniques used to accurately detect signalling from routine dog behaviour. This work is a step towards automatic alerting of the likely onset of an epileptic seizure from the signalling behaviour of a trained assistance dog.

Phúc H. Le Khac, Graham Healy, Alan F. Smeaton

This paper addresses key challenges in object-centric representation learning of video. While existing approaches struggle with complex scenes, we propose a novel weakly-supervised framework that emphasises geometric understanding and leverages pre-trained vision models to enhance object discovery. Our method introduces an efficient slot decoder specifically designed for object-centric learning, enabling effective representation of multi-object scenes without requiring explicit depth information. Results on synthetic video benchmarks with increasing complexity in terms of objects and their movement, object occlusion and camera motion demonstrate that our approach achieves comparable performance to supervised methods while maintaining computational efficiency. This advances the field towards more practical applications in complex real-world scenarios.

Ayush K. Rai, Kyle Min, Tarun Krishna et al.

Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using information from visible tokens. However, a key challenge in such approaches lies in selecting an appropriate masking strategy. Previous studies have explored predefined masking techniques, including random and tube-based masking, as well as approaches that leverage key motion priors, optical flow and semantic cues from externally pre-trained models. In this work, we introduce a novel and generalizable Trajectory-Aware Adaptive Token Sampler (TATS), which models the motion dynamics of tokens and can be seamlessly integrated into the masked autoencoder (MAE) framework to select motion-centric tokens in videos. Additionally, we propose a unified training strategy that enables joint optimization of both MAE and TATS from scratch using Proximal Policy Optimization (PPO). We show that our model allows for aggressive masking without compromising performance on the downstream task of action recognition while also ensuring that the pre-training remains memory efficient. Extensive experiments of the proposed approach across four benchmarks, including Something-Something v2, Kinetics-400, UCF101, and HMDB51, demonstrate the effectiveness, transferability, generalization, and efficiency of our work compared to other state-of-the-art methods.

Hamza Riaz, Alan F. Smeaton

With the growing sizes of AI models like large language models (LLMs) and vision transformers, deploying them on devices with limited computational resources is a significant challenge particularly when addressing domain generalisation (DG) tasks. This paper introduces a novel grouped structural pruning method for pre-trained vision transformers (ViT, BeiT, and DeiT), evaluated on the PACS and Office-Home DG benchmarks. Our method uses dependency graph analysis to identify and remove redundant groups of neurons, weights, filters, or attention heads within transformers, using a range of selection metrics. Grouped structural pruning is applied at pruning ratios of 50\%, 75\% and 95\% and the models are then fine-tuned on selected distributions from DG benchmarks to evaluate their overall performance in DG tasks. Results show significant improvements in inference speed and fine-tuning time with minimal trade-offs in accuracy and DG task performance. For instance, on the PACS benchmark, pruning ViT, BeiT, and DeiT models by 50\% using the Hessian metric resulted in accuracy drops of only -2.94\%, -1.42\%, and -1.72\%, respectively, while achieving speed boosts of 2.5x, 1.81x, and 2.15x. These findings demonstrate the effectiveness of our approach in balancing model efficiency with domain generalisation performance.

Hamza Riaz, Alan F. Smeaton

Modern AI models excel in controlled settings but often fail in real-world scenarios where data distributions shift unpredictably - a challenge known as domain generalisation (DG). This paper tackles this limitation by rigorously evaluating vision tramsformers, specifically the BEIT architecture which is a model pre-trained with masked image modelling (MIM), against synthetic out-of-distribution (OOD) benchmarks designed to mimic real-world noise and occlusions. We introduce a novel framework to generate OOD test cases by strategically masking object regions in images using grid patterns (25\%, 50\%, 75\% occlusion) and leveraging cutting-edge zero-shot segmentation via Segment Anything and Grounding DINO to ensure precise object localisation. Experiments across three benchmarks (PACS, Office-Home, DomainNet) demonstrate BEIT's known robustness while maintaining 94\% accuracy on PACS and 87\% on Office-Home, despite significant occlusions, outperforming CNNs and other vision transformers by margins of up to 37\%. Analysis of self-attention distances reveals that the BEIT dependence on global features correlates with its resilience. Furthermore, our synthetic benchmarks expose critical failure modes: performance degrades sharply when occlusions disrupt object shapes e.g. 68\% drop for external grid masking vs. 22\% for internal masking. This work provides two key advances (1) a scalable method to generate OOD benchmarks using controllable noise, and (2) empirical evidence that MIM and self-attention mechanism in vision transformers enhance DG by learning invariant features. These insights bridge the gap between lab-trained models and real-world deployment that offer a blueprint for building AI systems that generalise reliably under uncertainty.

Sen Yan, David J. O'Connor, Xiaojun Wang et al.

Urban pollution poses serious health risks, particularly in relation to traffic-related air pollution, which remains a major concern in many cities. Vehicle emissions contribute to respiratory and cardiovascular issues, especially for vulnerable and exposed road users like pedestrians and cyclists. Therefore, accurate air quality monitoring with high spatial resolution is vital for good urban environmental management. This study aims to provide insights for processing spatiotemporal datasets with high missing data rates. In this study, the challenge of high missing data rates is a result of the limited data available and the fine granularity required for precise classification of PM2.5 levels. The data used for analysis and imputation were collected from both mobile sensors and fixed stations by Dynamic Parcel Distribution, the Environmental Protection Agency, and Google in Dublin, Ireland, where the missing data rate was approximately 82.42%, making accurate Particulate Matter 2.5 level predictions particularly difficult. Various imputation and prediction approaches were evaluated and compared, including ensemble methods, deep learning models, and diffusion models. External features such as traffic flow, weather conditions, and data from the nearest stations were incorporated to enhance model performance. The results indicate that diffusion methods with external features achieved the highest F1 score, reaching 0.9486 (Accuracy: 94.26%, Precision: 94.42%, Recall: 94.82%), with ensemble models achieving the highest accuracy of 94.82%, illustrating that good performance can be obtained despite a high missing data rate.

Alan Byju, Aman Sudhindra Ladwa, Lorin Sweeney et al.

With the expanding use of the short-form video format in advertising, social media, entertainment, education and more, there is a need for such media to both captivate and be remembered. Video memorability indicates to us how likely a video is to be remembered by a viewer who has no emotional or personal connection with its content. This paper presents the results of using generative outpainting to expand the screen size of a short-form video with a view to improving its memorability. Advances in machine learning and deep learning are compared and leveraged to understand how extending the borders of video screensizes can affect their memorability to viewers. Using quantitative evaluation we determine the best-performing model for outpainting and the impact of outpainting based on image saliency on video memorability scores

Xianjuan Chen, Shuxiang Cai, Alan F. Smeaton

This study uses data from domestic electricity smart meters to estimate annual electricity bills for a whole year. We develop a method for back-filling data smart meter for up to six missing months for users who have less than one year of smart meter data, ensuring reliable estimates of annual consumption. We identify five distinct electricity consumption user profiles for homes based on day, night, and peak usage patterns, highlighting the economic advantages of Time-of-Use (ToU) tariffs over fixed tariffs for most users, especially those with higher nighttime consumption. Ultimately, the results of this study empowers consumers to manage their energy use effectively and to make informed choices regarding electricity tariff plans.

Xiao Liu, Alessandra Mileo, Alan F. Smeaton

In-situ monitoring incorporating data from visual and other sensor technologies, allows the collection of extensive datasets during the Additive Manufacturing (AM) process. These datasets have potential for determining the quality of the manufactured output and the detection of defects through the use of Machine Learning during the manufacturing process. Open and annotated datasets derived from AM processes are necessary for the machine learning community to address this opportunity, which creates difficulties in the application of computer vision-related machine learning in AM. This systematic review investigates the availability of open image-based datasets originating from AM processes that align with a number of pre-defined selection criteria. The review identifies existing gaps among the current image-based datasets in the domain of AM, and points to the need for greater availability of open datasets in order to allow quality assessment and defect detection during additive manufacturing, to develop.

Deniss Strods, Alan F. Smeaton

Gaps, dropouts and short clips of corrupted audio are a common problem and particularly annoying when they occur in speech. This paper uses machine learning to regenerate gaps of up to 320ms in an audio speech signal. Audio regeneration is translated into image regeneration by transforming audio into a Mel-spectrogram and using image in-painting to regenerate the gaps. The full Mel-spectrogram is then transferred back to audio using the Parallel-WaveGAN vocoder and integrated into the audio stream. Using a sample of 1300 spoken audio clips of between 1 and 10 seconds taken from the publicly-available LJSpeech dataset our results show regeneration of audio gaps in close to real time using GANs with a GPU equipped system. As expected, the smaller the gap in the audio, the better the quality of the filled gaps. On a gap of 240ms the average mean opinion score (MOS) for the best performing models was 3.737, on a scale of 1 (worst) to 5 (best) which is sufficient for a human to perceive as close to uninterrupted human speech.

Lorin Sweeney, Graham Healy, Alan F. Smeaton

This paper describes our approach to the Predicting Media Memorability task in MediaEval 2021, which aims to address the question of media memorability by setting the task of automatically predicting video memorability. This year we tackle the task from a comparative standpoint, looking to gain deeper insights into each of three explored modalities, and using our results from last year's submission (2020) as a point of reference. Our best performing short-term memorability model (0.132) tested on the TRECVid2019 dataset -- just like last year -- was a frame based CNN that was not trained on any TRECVid data, and our best short-term memorability model (0.524) tested on the Memento10k dataset, was a Bayesian Ride Regressor fit with DenseNet121 visual features.

Rukiye Savran Kiziltepe, Mihai Gabriel Constantin, Claire-Helene Demarty et al.

This paper describes the MediaEval 2021 Predicting Media Memorability}task, which is in its 4th edition this year, as the prediction of short-term and long-term video memorability remains a challenging task. In 2021, two datasets of videos are used: first, a subset of the TRECVid 2019 Video-to-Text dataset; second, the Memento10K dataset in order to provide opportunities to explore cross-dataset generalisation. In addition, an Electroencephalography (EEG)-based prediction pilot subtask is introduced. In this paper, we outline the main aspects of the task and describe the datasets, evaluation metrics, and requirements for participants' submissions.

Rukiye Savran Kiziltepe, Lorin Sweeney, Mihai Gabriel Constantin et al.

Using a collection of publicly available links to short form video clips of an average of 6 seconds duration each, 1,275 users manually annotated each video multiple times to indicate both long-term and short-term memorability of the videos. The annotations were gathered as part of an online memory game and measured a participant's ability to recall having seen the video previously when shown a collection of videos. The recognition tasks were performed on videos seen within the previous few minutes for short-term memorability and within the previous 24 to 72 hours for long-term memorability. Data includes the reaction times for each recognition of each video. Associated with each video are text descriptions (captions) as well as a collection of image-level features applied to 3 frames extracted from each video (start, middle and end). Video-level features are also provided. The dataset was used in the Video Memorability task as part of the MediaEval benchmark in 2020.

Andrew Merrigan, Alan F. Smeaton

Images posted online present a privacy concern in that they may be used as reference examples for a facial recognition system. Such abuse of images is in violation of privacy rights but is difficult to counter. It is well established that adversarial example images can be created for recognition systems which are based on deep neural networks. These adversarial examples can be used to disrupt the utility of the images as reference examples or training data. In this work we use a Generative Adversarial Network (GAN) to create adversarial examples to deceive facial recognition and we achieve an acceptable success rate in fooling the face recognition. Our results reduce the training time for the GAN by removing the discriminator component. Furthermore, our results show knowledge distillation can be employed to drastically reduce the size of the resulting model without impacting performance indicating that our contribution could run comfortably on a smartphone

Joe Kinahan, Alan F. Smeaton

There is a marked increase in delivery services in urban areas, and with Jeff Bezos claiming that 86% of the orders that Amazon ships weigh less than 5 lbs, the time is ripe for investigation into economical methods of automating the final stage of the delivery process. With the advent of semi-autonomous drone delivery services, such as Irish startup `Manna', and Malta's `Skymax', the final step of the delivery journey remains the most difficult to automate. This paper investigates the use of simple images captured by a single RGB camera on a UAV to distinguish between safe and unsafe landing zones. We investigate semantic image segmentation frameworks as a way to identify safe landing zones and demonstrate the accuracy of lightweight models that minimise the number of sensors needed. By working with images rather than video we reduce the amount of energy needed to identify safe landing zones for a drone, without the need for human intervention.

Srijith Unni, Sushma Suryanarayana Gowda, Alan F. Smeaton

Lifelogging has become a prominent research topic in recent years. Wearable sensors like Fitbits and smart watches are now increasingly popular for recording ones activities. Some researchers are also exploring keystroke dynamics for lifelogging. Keystroke dynamics refers to the process of measuring and assessing a persons typing rhythm on digital devices. A digital footprint is created when a user interacts with devices like keyboards, mobile phones or touch screen panels and the timing of the keystrokes is unique to each individual though likely to be affected by factors such as fatigue, distraction or emotional stress. In this work we explore the relationship between keystroke dynamics as measured by the timing for the top-10 most frequently occurring bi-grams in English, and the emotional state and stress of an individual as measured by heart rate variability (HRV). We collected keystroke data using the Loggerman application while HRV was simultaneously gathered. With this data we performed an analysis to determine the relationship between variations in keystroke dynamics and variations in HRV. Our conclusion is that we need to use a more detailed representation of keystroke timing than the top-10 bigrams, probably personalised to each user.

Aparajita Dey-Plissonneau, Hyowon Lee, Michael Scriney et al.

This pilot study focuses on a tool called L2L that allows second language (L2) learners to visualise and analyse their Zoom interactions with native speakers. L2L uses the Zoom transcript to automatically generate conversation metrics and its playback feature with timestamps allows students to replay any chosen portion of the conversation for post-session reflection and self-review. This exploratory study investigates a seven-week teletandem project, where undergraduate students from an Irish University learning French (B2) interacted with their peers from a French University learning English (B2+) via Zoom. The data collected from a survey (N=43) and semi-structured interviews (N=35) show that the quantitative conversation metrics and qualitative review of the synchronous content helped raise students' confidence levels while engaging with native speakers. Furthermore, it allowed them to set tangible goals to improve their participation, and be more aware of what, why and how they are learning.

Alan F. Smeaton

Computer vision and multimedia information processing have made extreme progress within the last decade and many tasks can be done with a level of accuracy as if done by humans, or better. This is because we leverage the benefits of huge amounts of data available for training, we have enormous computer processing available and we have seen the evolution of machine learning as a suite of techniques to process data and deliver accurate vision-based systems. What kind of applications do we use this processing for ? We use this in autonomous vehicle navigation or in security applications, searching CCTV for example, and in medical image analysis for healthcare diagnostics. One application which is not widespread is image or video search directly by users. In this paper we present the need for such image finding or re-finding by examining human memory and when it fails, thus motivating the need for a different approach to image search which is outlined, along with the requirements of computer vision to support it.

Zaid Amin, Nazlena Mohamad Ali, Alan F. Smeaton

Information sharing on social media must be accompanied by attentive behavior so that in a distorted digital environment, users are not rushed and distracted in deciding to share information. The spread of misinformation, especially those related to the COVID-19, can divide and create negative effects of falsehood in society. Individuals can also cause feelings of fear, health anxiety, and confusion in the treatment COVID-19. Although much research has focused on understanding human judgment from a psychological underline, few have addressed the essential issue in the screening phase of what technology can interfere amidst users' attention in sharing information. This research aims to intervene in the user's attention with a visual selective attention approach. This study uses a quantitative method through studies 1 and 2 with pre-and post-intervention experiments. In study 1, we intervened in user decisions and attention by stimulating ten information and misinformation using the Visual Selective Attention System (VSAS) tool. In Study 2, we identified associations of user tendencies in evaluating information using the Implicit Association Test (IAT). The significant results showed that the user's attention and decision behavior improved after using the VSAS. The IAT results show a change in the association of user exposure, where after the intervention using VSAS, users tend not to share misinformation about COVID-19. The results are expected to be the basis for developing social media applications to combat the negative impact of the infodemic COVID-19 misinformation.

Aparajita Dey-Plissonneau, Hyowon Lee, Vincent Pradier et al.

An important part of second language learning is conversation which is best practised with speakers whose native language is the language being learned. We facilitate this by pairing students from different countries learning each others' native language. Mixed groups of students have Zoom calls, half in one language and half in the other, in order to practice and improve their conversation skills. We use Zoom video recordings with audio transcripts enabled which generates recognised speech from which we extract timestamped utterances and calculate and visualise conversation metrics on a dashboard. A timeline highlights each utterance, colour coded per student, with links to the video in a playback window. L2L was deployed for a semester and recorded almost 250 hours of zoom meetings. The conversation metrics visualised on the dashboard are a beneficial asset for both students and lecturers.

Hyowon Lee, Mingming Liu, Michael Scriney et al.

Much of the delivery of University education is now by synchronous or asynchronous video. For students, one of the challenges is managing the sheer volume of such video material as video presentations of taught material are difficult to abbreviate and summarise because they do not have highlights which stand out. Apart from video bookmarks there are no tools available to determine which parts of video content should be replayed at revision time or just before examinations. We have developed and deployed a digital library for managing video learning material which has many dozens of hours of short-form video content from a range of taught courses for hundreds of students at undergraduate level. Through a web browser we allow students to access and play these videos and we log their anonymised playback usage. From these logs we score to each segment of each video based on the amount of playback it receives from across all students, whether the segment has been re-wound and re-played in the same student session, whether the on-screen window is the window in focus on the student's desktop/laptop, and speed of playback. We also incorporate negative scoring if a video segment is skipped or fast-forward, and overarching all this we include a decay function based on recency of playback, so the most recent days of playback contribute more to the video segment scores. For each video in the library we present a usage-based graph which allows students to see which parts of each video attract the most playback from their peers, which helps them select material at revision time. Usage of the system is fully anonymised and GDPR-compliant.

Luka Murn, Saverio Blasi, Alan F. Smeaton et al.

The versatility of recent machine learning approaches makes them ideal for improvement of next generation video compression solutions. Unfortunately, these approaches typically bring significant increases in computational complexity and are difficult to interpret into explainable models, affecting their potential for implementation within practical video coding applications. This paper introduces a novel explainable neural network-based inter-prediction scheme, to improve the interpolation of reference samples needed for fractional precision motion compensation. The approach requires a single neural network to be trained from which a full quarter-pixel interpolation filter set is derived, as the network is easily interpretable due to its linear structure. A novel training framework enables each network branch to resemble a specific fractional shift. This practical solution makes it very efficient to use alongside conventional video coding schemes. When implemented in the context of the state-of-the-art Versatile Video Coding (VVC) test model, 0.77%, 1.27% and 2.25% BD-rate savings can be achieved on average for lower resolution sequences under the random access, low-delay B and low-delay P configurations, respectively, while the complexity of the learned interpolation schemes is significantly reduced compared to the interpolation with full CNNs.

Lifeng Han, Gareth J. F. Jones, Alan F. Smeaton

To facilitate effective translation modeling and translation studies, one of the crucial questions to address is how to assess translation quality. From the perspectives of accuracy, reliability, repeatability and cost, translation quality assessment (TQA) itself is a rich and challenging task. In this work, we present a high-level and concise survey of TQA methods, including both manual judgement criteria and automated evaluation metrics, which we classify into further detailed sub-categories. We hope that this work will be an asset for both translation model researchers and quality assessment researchers. In addition, we hope that it will enable practitioners to quickly develop a better understanding of the conventional TQA field, and to find corresponding closely relevant evaluation solutions for their own needs. This work may also serve inspire further development of quality assessment and evaluation methodologies for other natural language processing (NLP) tasks in addition to machine translation (MT), such as automatic text summarization (ATS), natural language understanding (NLU) and natural language generation (NLG).

George Awad, Asad A. Butt, Keith Curtis et al.

The TREC Video Retrieval Evaluation (TRECVID) is a TREC-style video analysis and retrieval evaluation with the goal of promoting progress in research and development of content-based exploitation and retrieval of information from digital video via open, metrics-based evaluation. Over the last twenty years this effort has yielded a better understanding of how systems can effectively accomplish such processing and how one can reliably benchmark their performance. TRECVID has been funded by NIST (National Institute of Standards and Technology) and other US government agencies. In addition, many organizations and individuals worldwide contribute significant time and effort. TRECVID 2020 represented a continuation of four tasks and the addition of two new tasks. In total, 29 teams from various research organizations worldwide completed one or more of the following six tasks: 1. Ad-hoc Video Search (AVS), 2. Instance Search (INS), 3. Disaster Scene Description and Indexing (DSDI), 4. Video to Text Description (VTT), 5. Activities in Extended Video (ActEV), 6. Video Summarization (VSUM). This paper is an introduction to the evaluation framework, tasks, data, and measures used in the evaluation campaign.

Lorin Sweeney, Graham Healy, Alan F. Smeaton

Memories are the tethering threads that tie us to the world, and memorability is the measure of their tensile strength. The threads of memory are spun from fibres of many modalities, obscuring the contribution of a single fibre to a thread's overall tensile strength. Unfurling these fibres is the key to understanding the nature of their interaction, and how we can ultimately create more meaningful media content. In this paper, we examine the influence of audio on video recognition memorability, finding evidence to suggest that it can facilitate overall video recognition memorability rich in high-level (gestalt) audio features. We introduce a novel multimodal deep learning-based late-fusion system that uses audio gestalt to estimate the influence of a given video's audio on its overall short-term recognition memorability, and selectively leverages audio features to make a prediction accordingly. We benchmark our audio gestalt based system on the Memento10k short-term video memorability dataset, achieving top-2 state-of-the-art results.

Lifeng Han, Gareth J. F. Jones, Alan F. Smeaton et al.

Chinese character decomposition has been used as a feature to enhance Machine Translation (MT) models, combining radicals into character and word level models. Recent work has investigated ideograph or stroke level embedding. However, questions remain about different decomposition levels of Chinese character representations, radical and strokes, best suited for MT. To investigate the impact of Chinese decomposition embedding in detail, i.e., radical, stroke, and intermediate levels, and how well these decompositions represent the meaning of the original character sequences, we carry out analysis with both automated and human evaluation of MT. Furthermore, we investigate if the combination of decomposed Multiword Expressions (MWEs) can enhance the model learning. MWE integration into MT has seen more than a decade of exploration. However, decomposed MWEs has not previously been explored.