Related papers: Responsive DNN Adaptation for Video Analytics agai…

Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of…

Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. However, existing methods for model adaptation usually update all model parameters, i.e., full fine-tuning paradigm, which is…

Although Recurrent Neural Network (RNN) has been a powerful tool for modeling sequential data, its performance is inadequate when processing sequences with multiple patterns. In this paper, we address this challenge by introducing a novel…

Advancements in attention mechanisms have led to significant performance improvements in a variety of areas in machine learning due to its ability to enable the dynamic modeling of temporal sequences. A particular area in computer vision…

Deep learning models are sensitive to domain shift phenomena. A model trained on images from one domain cannot generalise well when tested on images from a different domain, despite capturing similar anatomical structures. It is mainly…

This paper presents Variables Adaptive Mixture of Experts (VAMoE), a novel framework for incremental weather forecasting that dynamically adapts to evolving spatiotemporal patterns in real time data. Traditional weather prediction models…

Mobile Edge Caching (MEC) integrated with Deep Neural Networks (DNNs) is an innovative technology with significant potential for the future generation of wireless networks, resulting in a considerable reduction in users' latency. The MEC…

Foundation models have revolutionized AI, but adapting them efficiently for multimodal tasks, particularly in dual-stream architectures composed of unimodal encoders, such as DINO and BERT, remains a significant challenge.…

An increasing number of software applications incorporate runtime Deep Neural Networks (DNNs) to process sensor data and return inference results to humans. Effective deployment of DNNs in these interactive scenarios requires meeting…

We investigate multitask edge-user communication-computation resource allocation for $360^\circ$ video streaming in an edge-computing enabled millimeter wave (mmWave) multi-user virtual reality system. To balance the…

3D dynamic point cloud (DPC) compression relies on mining its temporal context, which faces significant challenges due to DPC's sparsity and non-uniform structure. Existing methods are limited in capturing sufficient temporal dependencies.…

Recent attempts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for multi-task adaptation of Large Language Models (LLMs) often replace whole attention/FFN layers with switch experts or append parallel expert branches,…

Pre-trained vision language models have shown remarkable performance on visual recognition tasks, but they typically assume the availability of complete multimodal inputs during both training and inference. In real-world scenarios, however,…

Deploying deep convolutional neural networks (CNNs) on resource-constrained devices presents significant challenges due to their high computational demands and rigid, static architectures. To overcome these limitations, this thesis explores…

In mobile edge computing (MEC) networks, mobile users generate diverse machine learning tasks dynamically over time. These tasks are typically offloaded to the nearest available edge server, by considering communication and computational…

Reinforcement Learning (RL) agents often struggle in real-world applications where environmental conditions are non-stationary, particularly when reward functions shift or the available action space expands. This paper introduces MORPHIN, a…

The attention mechanism of the Listen, Attend and Spell (LAS) model requires the whole input sequence to calculate the attention context and thus is not suitable for online speech recognition. To deal with this problem, we propose…

Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams while retaining past competence, yet texture-biased backbones risk error accumulation and catastrophic forgetting. Drawing…

Mixture-of-Experts (MoE) models offer immense capacity via sparsely gated expert subnetworks, yet adapting them to multiple domains without catastrophic forgetting remains an open challenge. Existing approaches either incur prohibitive…

This thesis focuses on video understanding for human action and interaction recognition. We start by identifying the main challenges related to action recognition from videos and review how they have been addressed by current methods. Based…