Search Results for author:
Found 71 papers, 12 papers with code
Reinforcement Learning meets Masked Video Modeling : Trajectory-Guided Adaptive Token Selection
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.
Resilience of Vision Transformers for Domain Generalisation in the Presence of Out-of-Distribution Noisy Images
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).
Comparative Analysis of Machine Learning-Based Imputation Techniques for Air Quality Datasets with High Missing Data Rates
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.
Efficient Object-centric Representation Learning with Pre-trained Geometric Prior
This paper addresses key challenges in object-centric representation learning of video.
Generative Outpainting To Enhance the Memorability of Short-Form Videos
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.
Back-filling Missing Data When Predicting Domestic Electricity Consumption From Smart Meter Data
This study uses data from domestic electricity smart meters to estimate annual electricity bills for a whole year.
Capturing Bias Diversity in LLMs
In this paper, through experiments, we demonstrate the capabilities of a GPT model to embed different biases which, when combined, can open the possibilities of more inclusive AI technologies.
Understanding Foundation Models: Are We Back in 1924?
This position paper explores the rapid development of Foundation Models (FMs) in AI and their implications for intelligence and reasoning.
A Review of Multi-Modal Large Language and Vision Models
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.
A Systematic Review of Available Datasets in Additive Manufacturing
In-situ monitoring incorporating data from visual and other sensor technologies, allows the collection of extensive datasets during the Additive Manufacturing (AM) process.
Lifelogging As An Extreme Form of Personal Information Management -- What Lessons To Learn
Personal data includes the digital footprints that we leave behind as part of our everyday activities, both online and offline in the real world.
Video Anomaly Detection via Spatio-Temporal Pseudo-Anomaly Generation : A Unified Approach
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.
A Comparison of Lexicon-Based and ML-Based Sentiment Analysis: Are There Outlier Words?
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.
Using Saliency and Cropping to Improve Video Memorability
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.
Heart Rate Detection Using an Event Camera
Ground-truth HR measurements obtained using conventional methods were used to evaluate of the accuracy of automatic detection of HR from event camera data.
Measuring the Quality of Text-to-Video Model Outputs: Metrics and Dataset
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.
Memories in the Making: Predicting Video Memorability with Encoding Phase EEG
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.
Domain Generalisation with Bidirectional Encoder Representations from Vision Transformers
Domain generalisation involves pooling knowledge from source domain(s) into a single model that can generalise to unseen target domain(s).
Defect Classification in Additive Manufacturing Using CNN-Based Vision Processing
The development of computer vision and in-situ monitoring using visual sensors allows the collection of large datasets from the additive manufacturing (AM) process.
Calculating the matrix profile from noisy data
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.
Enhancing Gappy Speech Audio Signals with Generative Adversarial Networks
Audio regeneration is translated into image regeneration by transforming audio into a Mel-spectrogram and using image in-painting to regenerate the gaps.
Automatic Detection of Signalling Behaviour from Assistance Dogs as they Forecast the Onset of Epileptic Seizures in Humans
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.
Vision Based Machine Learning Algorithms for Out-of-Distribution Generalisation
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.
Diffusing Surrogate Dreams of Video Scenes to Predict Video Memorability
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.
Managing Large Dataset Gaps in Urban Air Quality Prediction: DCU-Insight-AQ at MediaEval 2022
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.
Overview of The MediaEval 2022 Predicting Video Memorability Task
This paper describes the 5th edition of the Predicting Video Memorability Task as part of MediaEval2022.
An adaptive human-in-the-loop approach to emission detection of Additive Manufacturing processes and active learning with computer vision
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.
Experiences from the MediaEval Predicting Media Memorability Task
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.
Motion Aware Self-Supervision for Generic Event Boundary Detection
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.
Periodicity Intensity of the 24 h Circadian Rhythm in Newborn Calves Show Indicators of Herd Welfare
Circadian rhythms are a process of the sleep-wake cycle that regulates the physical, mental and behavioural changes in all living beings with a period of roughly 24 h. Wearable accelerometers are typically used in livestock applications to record animal movement from which we can estimate the activity type.
Analysing the Memorability of a Procedural Crime-Drama TV Series, CSI
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.
Dynamic Channel Selection in Self-Supervised Learning
Currently, convnets pre-trained with self-supervision have obtained comparable performance on downstream tasks in comparison to their supervised counterparts in computer vision.
Analysis of Individual Conversational Volatility in Tandem Telecollaboration for Second Language Learning
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.
Predicting Media Memorability: Comparing Visual, Textual and Auditory Features
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.
Overview of The MediaEval 2021 Predicting Media Memorability Task
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.
An Annotated Video Dataset for Computing Video Memorability
Data includes the reaction times for each recognition of each video.
Using a GAN to Generate Adversarial Examples to Facial Image Recognition
Images posted online present a privacy concern in that they may be used as reference examples for a facial recognition system.
Image Segmentation to Identify Safe Landing Zones for Unmanned Aerial Vehicles
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.
Computer Vision for Supporting Image Search
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.
Facilitating reflection in teletandem through automatically generated conversation metrics and playback video
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.
Improved CNN-based Learning of Interpolation Filters for Low-Complexity Inter Prediction in Video Coding
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.
Translation Quality Assessment: A Brief Survey on Manual and Automatic Methods
To facilitate effective translation modeling and translation studies, one of the crucial questions to address is how to assess translation quality.
TRECVID 2020: A comprehensive campaign for evaluating video retrieval tasks across multiple application domains
In total, 29 teams from various research organizations worldwide completed one or more of the following six tasks: 1.
The Influence of Audio on Video Memorability with an Audio Gestalt Regulated Video Memorability System
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.
Chinese Character Decomposition for Neural MT with Multi-Word Expressions
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.
Attention-Based Neural Networks for Chroma Intra Prediction in Video Coding
Simplifications include a framework for reducing the overhead of the convolutional operations, a simplified cross-component processing model integrated into the original architecture, and a methodology to perform integer-precision approximations with the aim to obtain fast and hardware-aware implementations.
Detecting Deepfake Videos Using Euler Video Magnification
This involves replacing the face of an individual from a source video with the face of a second person, in the destination video.
Attention Based Video Summaries of Live Online Zoom Classes
We can also factor in other criteria into video summary generation such as parts where the student was not paying attention while others in the class were, and parts of the video that other students have replayed extensively which a given student has not.
Leveraging Audio Gestalt to Predict Media Memorability
Memorability determines what evanesces into emptiness, and what worms its way into the deepest furrows of our minds.
Investigating Memorability of Dynamic Media
The Predicting Media Memorability task in MediaEval'20 has some challenging aspects compared to previous years.
Overview of MediaEval 2020 Predicting Media Memorability Task: What Makes a Video Memorable?
This paper describes the MediaEval 2020 \textit{Predicting Media Memorability} task.
Using GANs to Synthesise Minimum Training Data for Deepfake Generation
There are many applications of Generative Adversarial Networks (GANs) in fields like computer vision, natural language processing, speech synthesis, and more.
Contrastive Representation Learning: A Framework and Review
Examples of how contrastive learning has been applied in computer vision, natural language processing, audio processing, and others, as well as in Reinforcement Learning are also presented.
A Comparative Study of Existing and New Deep Learning Methods for Detecting Knee Injuries using the MRNet Dataset
Overall we achieved a performance of 93. 4% AUC on the validation data by using the more recent deep learning architectures and data augmentation strategies.
TRECVID 2019: An Evaluation Campaign to Benchmark Video Activity Detection, Video Captioning and Matching, and Video Search & Retrieval
The TREC Video Retrieval Evaluation (TRECVID) 2019 was a TREC-style video analysis and retrieval evaluation, the goal of which remains to promote progress in research and development of content-based exploitation and retrieval of information from digital video via open, metrics-based evaluation.
Tracking Skin Colour and Wrinkle Changes During Cosmetic Product Trials Using Smartphone Images
Materials and Methods: 12 women aged 30 to 60 years participated in a product trial and had close-up images of the cheek and temple regions of their faces taken with a high-resolution Antera 3D CS camera at the start and end of a 4-week period.
Utilising Visual Attention Cues for Vehicle Detection and Tracking
We investigate: 1) How a visual attention map such as a \emph{subjectness} attention or saliency map and an \emph{objectness} attention map can facilitate region proposal generation in a 2-stage object detector; 2) How a visual attention map can be used for tracking multiple objects.
Chroma Intra Prediction with attention-based CNN architectures
Neural networks can be used in video coding to improve chroma intra-prediction.
Interpreting CNN for Low Complexity Learned Sub-pixel Motion Compensation in Video Coding
Deep learning has shown great potential in image and video compression tasks.
MultiMWE: Building a Multi-lingual Multi-Word Expression (MWE) Parallel Corpora
The only bilingual MWE corpora that we are aware of is from the PARSEME (PARSing and Multi-word Expressions) EU Project.
Optimised Convolutional Neural Networks for Heart Rate Estimation and Human Activity Recognition in Wrist Worn Sensing Applications
These same sampling frequencies also yielded a robust heart rate estimation which was comparative with that achieved at the more energy-intensive rate of 256 Hz.
A Neuro-AI Interface for Evaluating Generative Adversarial Networks
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.
End-to-End Conditional GAN-based Architectures for Image Colourisation
In this work recent advances in conditional adversarial networks are investigated to develop an end-to-end architecture based on Convolutional Neural Networks (CNNs) to directly map realistic colours to an input greyscale image.
A Neuro-AI Interface: Learning DNNs from the Human Brain
Deep neural networks (DNNs) are inspired from the human brain and the interconnection between the two has been widely studied in the literature.
Synthetic-Neuroscore: Using A Neuro-AI Interface for Evaluating Generative Adversarial Networks
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.
Spatial Filtering Pipeline Evaluation of Cortically Coupled Computer Vision System for Rapid Serial Visual Presentation
In this paper we make two primary contributions to that field: 1) We propose a novel spatial filtering method which we call the Multiple Time Window LDA Beamformer (MTWLB) method; 2) we provide a comprehensive comparison of nine spatial filtering pipelines using three spatial filtering schemes namely, MTWLB, xDAWN, Common Spatial Pattern (CSP) and three linear classification methods Linear Discriminant Analysis (LDA), Bayesian Linear Regression (BLR) and Logistic Regression (LR).
An Interpretable Machine Vision Approach to Human Activity Recognition using Photoplethysmograph Sensor Data
We then use the 2048 dimensional features from the penultimate layer as input to a support vector machine.
Use of Neural Signals to Evaluate the Quality of Generative Adversarial Network Performance in Facial Image Generation
We propose a novel approach that combines a brain-computer interface (BCI) with GANs to generate a measure we call Neuroscore, which closely mirrors the behavioral ground truth measured from participants tasked with discerning real from synthetic images.
Exploring EEG for Object Detection and Retrieval
We show that it is indeed possible to detect such objects in complex images and, also, that users with previous knowledge on the dataset or experience with the RSVP outperform others.
Detector adaptation by maximising agreement between independent data sources
Traditional methods for creating classifiers have two main disadvantages.
