Benchmarking Data and Computational Efficiency of ActionFormer on Temporal Action Localization Tasks: Analysing the Performance and Generalizability of ActionFormer in Resource-constrained Environments

In temporal action localization, given an input video, the goal is to predict which actions it contains, where they begin and where they end. Training and testing current state-of-the-art, deep learning models is done assuming access to large amounts of data and computational power. Gathering such data is however a challenging task and access to...

Efficient Temporal Action Localization via Vision-Language Modelling: An Empirical Study on the STALE Model's Efficiency and Generalizability in Resource-constrained Environments

Temporal Action Localization (TAL) aims to localize the start and end times of actions in untrimmed videos and classify the corresponding action types. TAL plays an important role in understanding video. Existing TAL approaches heavily rely on deep learning and require large-scale data and expensive training processes. Recent advances in...

TemporalMaxer Performance in the Face of Constraint: A Study in Temporal Action Localization: A Comprehensive Analysis on the Adaptability of TemporalMaxer in Resource-Scarce Environments

This paper presents an analysis of the data and compute efficiency of the TemporalMaxer deep learning model in the context of temporal action localization (TAL), which involves accurately detecting the start and end times of specific video actions. The study explores the performance and scalability of the TemporalMaxer model under limited...

Comparison of an Explicit and Implicit Time Integration Method on GPUs for Shallow Water Flows on Structured Grids

The accuracy, stability and computational efficiency of numerical methods on central processing units (CPUs) for the depth-averaged shallow water equations were well covered in the literature. A large number of these methods were already developed and compared. However, on graphics processing units (GPUs), such comparisons are relatively scarce....

Less Machine (=) More Vision: Approaches towards Practical and Efficient Machine Vision with Applications in Face Analysis

Machines that interact with humans can do so better if they can also visually understand us, but they have limited resources to do so. The main topic of this dissertation is contrasting the use of resources by machine vision systems against the accuracy obtained by them. This thesis focuses on reducing the need for data, memory, and computation...

An Efficient 3D-model for the Micro-Scale Analysis of Geometrically Imperfect Fibre-Reinforced Composites

This work develops a stand-alone Finite Element-based Unit Cell for the modelling of Fibre Reinforced Composites, capable of capturing 3D stress states and geometrical imperfections at the micro-scale. The project considers different beam and 3D elements for this purpose and draws comparisons between them based on computational efficiency,...

Efficient computation of states and sensitivities for compound structural optimisation problems using a Linear Dependency Aware Solver (LDAS)

Real-world structural optimisation problems involve multiple loading conditions and design constraints, with responses typically depending on states of discretised governing equations. Generally, one uses gradient-based nested analysis and design approaches to solve these problems. Herein, solving both physical and adjoint problems dominates...

Cross-Coupled Iterative Learning Control for Complex Systems: A Monotonically Convergent and Computationally Efficient Approach

Cross-coupled iterative learning control (ILC) can achieve high performance for manufacturing applications in which tracking a contour is essential for the quality of a product. The aim of this paper is to develop a framework for norm-optimal cross-coupled ILC that enables the use of exact contour errors that are calculated offline, and...

Efficient multi-partition topology optimization

In topology optimization, the state of structures is typically obtained by numerically evaluating a discretized PDE-based model. The degrees of freedom of such a model can be partitioned in free and prescribed sets to define the boundary conditions. A multi-partition problem involves multiple partitions of the same discretization, typically...

Stereo Visual Inertial Odometry for Robots with Limited Computational Resources*

Current existing stereo visual odometry algorithms are computationally too expensive for robots with restricted resources. Executing these algorithms on such robots leads to a low frame rate and unacceptable decay in accuracy. We modify S-MSCKF, one of the most computationally efficient stereo Visual Inertial Odometry (VIO) algorithm, to improve...

Accelerating system adequacy assessment using the multilevel Monte Carlo approach

Accurately and efficiently estimating system performance under uncertainty is paramount in power system planning and operation. Monte Carlo simulation is often used for this purpose, but convergence may be slow, especially when detailed models are used. Previously published methods to speed up computations may severely constrain model complexity...

Topology optimization using the Finite Cell Method

The ongoing demand for better performing designs, has resulted in an increase in the complexity of topology optimization problems. Traditionally, the majority of the corresponding computational cost comes from solving the analysis equations using linear finite elements (FE). In this thesis a topology optimization method is presented, that is...

Efficient scheme for the shallow water equations on unstructured grids with application to the Continental Shelf

In this paper, a shallow-water flow solver is presented, based on the finite-volume method on unstructured grids The method is suitable for flows that occur in rivers, channels, sewer systems (1D), shallow seas, rivers, overland flow (2D), and estuaries, lakes and shelf breaks (3D). We present an outline of the numerical approach and show three...

An automated approach for solution based mesh adaptation to enhance numerical accuracy for a given number of grid cells

Mesh adaptation is a fairly established tool to obtain numerically accurate solutions for flow problems. Computational efficiency is, however, not always guaranteed for the adaptation strategies found in literature. Typically excessive mesh growth diminishes the potential efficiency gain. This paper, therefore, extends the strategy proposed by ...