Physical Sciences and Mathematics Commons^™

Language-Driven Region Pointer Advancement For Controllable Image Captioning, Annika Lindh, Robert J. Ross, John D. Kelleher

Conference papers

Controllable Image Captioning is a recent sub-field in the multi-modal task of Image Captioning wherein constraints are placed on which regions in an image should be described in the generated natural language caption. This puts a stronger focus on producing more detailed descriptions, and opens the door for more end-user control over results. A vital component of the Controllable Image Captioning architecture is the mechanism that decides the timing of attending to each region through the advancement of a region pointer. In this paper, we propose a novel method for predicting the timing of region pointer advancement by treating the …

Energy-Based Neural Modelling For Large-Scale Multiple Domain Dialogue State Tracking, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

Scaling up dialogue state tracking to multiple domains is challenging due to the growth in the number of variables being tracked. Furthermore, dialog state tracking models do not yet explicitly make use of relationships between dialogue variables, such as slots across domains. We propose using energy-based structure prediction methods for large-scale dialogue state tracking task in two multiple domain dialogue datasets. Our results indicate that: (i) modelling variable dependencies yields better results; and (ii) the structured prediction output aligns with the dialogue slot-value constraint principles. This leads to promising directions to improve state-of-the-art models by incorporating variable dependencies into their …

F-Measure Optimisation And Label Regularisation For Energy-Based Neural Dialogue State Tracking Models, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

In recent years many multi-label classification methods have exploited label dependencies to improve performance of classification tasks in various domains, hence casting the tasks to structured prediction problems. We argue that multi-label predictions do not always satisfy domain constraint restrictions. For example when the dialogue state tracking task in task-oriented dialogue domains is solved with multi-label classification approaches, slot-value constraint rules should be enforced following real conversation scenarios.

To address these issues we propose an energy-based neural model to solve the dialogue state tracking task as a structured prediction problem. Furthermore we propose two improvements over previous methods with respect …

Automatic Flood Detection In Sentinei-2 Images Using Deep Convolutional Neural Networks, Pallavi Jain, Bianca Schoen-Phelan, Robert J. Ross

Conference papers

The early and accurate detection of floods from satellite imagery can aid rescue planning and assessment of geophysical damage. Automatic identification of water from satellite images has historically relied on hand-crafted functions, but these often do not provide the accuracy and robustness needed for accurate and early flood detection. To try to overcome these limitations we investigate a tiered methodology combining water index like features with a deep convolutional neural network based solution to flood identification against the MediaEval 2019 flood dataset. Our method builds on existing deep neural network methods, and in particular the VGG16 network. Specifically, we explored …

Multimodal Fusion Strategies For Outcome Prediction In Stroke, Esra Zihni, John D. Kelleher, Vince I. Madai, Ahmed Khalil, Ivana Galinovic, Jochen Fiebach, Michelle Livne, Dietmar Frey

Conference papers

Data driven methods are increasingly being adopted in the medical domain for clinical predictive modeling. Prediction of stroke outcome using machine learning could provide a decision support system for physicians to assist them in patient-oriented diagnosis and treatment. While patient-specific clinical parameters play an important role in outcome prediction, a multimodal fusion approach that integrates neuroimaging with clinical data has the potential to improve accuracy. This paper addresses two research questions: (a) does multimodal fusion aid in the prediction of stroke outcome, and (b) what fusion strategy is more suitable for the task at hand. The baselines for our experimental …

Language Model Co-Occurrence Linking For Interleaved Activity Discovery, Eoin Rogers, Robert J. Ross, John D. Kelleher

Conference papers

As ubiquitous computer and sensor systems become abundant, the potential for automatic identification and tracking of human behaviours becomes all the more evident. Annotating complex human behaviour datasets to achieve ground truth for supervised training can however be extremely labour-intensive, and error prone. One possible solution to this problem is activity discovery: the identification of activities in an unlabelled dataset by means of an unsupervised algorithm. This paper presents a novel approach to activity discovery that utilises deep learning based language production models to construct a hierarchical, tree-like structure over a sequential vector of sensor events. Our approach differs from …

Modelling Interleaved Activities Using Language Models, Eoin Rogers, Robert J. Ross, John D. Kelleher

Conference papers

We propose a new approach to activity discovery, based on the neural language modelling of streaming sensor events. Our approach proceeds in multiple stages: we build binary links between activities using probability distributions generated by a neural language model trained on the dataset, and combine the binary links to produce complex activities. We then use the activities as sensor events, allowing us to build complex hierarchies of activities. We put an emphasis on dealing with interleaving, which represents a major challenge for many existing activity discovery systems. The system is tested on a realistic dataset, demonstrating it as a promising …

Mutual Information Decay Curves And Hyper-Parameter Grid Search Design For Recurrent Neural Architectures, Abhijit Mahalunkar, John Kelleher

Conference papers

We present an approach to design the grid searches for hyper-parameter optimization for recurrent neural architectures. The basis for this approach is the use of mutual information to analyze long distance dependencies (LDDs) within a dataset. We also report a set of experiments that demonstrate how using this approach, we obtain state-of-the-art results for DilatedRNNs across a range of benchmark datasets.