相关论文: Revisiting the Encoding of Satellite Image Time Se…

Earth Observation (EO) Foundation Modelling (FM) holds great promise for simplifying and improving the use of EO data for diverse real-world tasks. However, most existing models require additional adaptation before they can be used and are…

We study a crucial yet often overlooked issue inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which hurt the performance of ViTs in downstream dense prediction tasks such as semantic…

Unpaired Image-to-Image Translation (I2IT) tasks often suffer from lack of data, a problem which self-supervised learning (SSL) has recently been very popular and successful at tackling. Leveraging auxiliary tasks such as rotation…

Low Dose Computed Tomography suffers from a high amount of noise and/or undersampling artefacts in the reconstructed image. In the current article, a Deep Learning technique is exploited as a regularization term for the iterative…

In recent years, analysis of remote sensing data has benefited immensely from borrowing techniques from the broader field of computer vision, such as the use of shared models pre-trained on large and diverse datasets. However, satellite…

Any explicit functional representation $f$ of a density is hampered by two main obstacles when we wish to use it as a generative model: designing $f$ so that sampling is fast, and estimating $Z = \int f$ so that $Z^{-1}f$ integrates to 1.…

Achieving reliable multidimensional Vehicle-to-Vehicle (V2V) channel state information (CSI) prediction is both challenging and crucial for optimizing downstream tasks that depend on instantaneous CSI. This work extends traditional…

The recently developed and publicly available synthetic image generation methods and services make it possible to create extremely realistic imagery on demand, raising great risks for the integrity and safety of online information.…

Rapid, large-scale 3D reconstruction from multi-date satellite imagery is vital for environmental monitoring, urban planning, and disaster response, yet remains difficult due to illumination changes, sensor heterogeneity, and the cost of…

With the advent of Transformers, time series forecasting has seen significant advances, yet it remains challenging due to the need for effective sequence representation, memory construction, and accurate target projection. Time series…

Procedural video representation learning is an active research area where the objective is to learn an agent which can anticipate and forecast the future given the present video input, typically in conjunction with textual annotations.…

Surgical phase segmentation is central to computer-assisted surgery, yet robust models remain difficult to develop when labeled surgical videos are scarce. We study data-efficient phase segmentation for manual small-incision cataract…

Vision Transformer (ViT)-based models have shown state-of-the-art performance (e.g., accuracy) in vision-based AI tasks. However, realizing their capability in resource-constrained embedded AI systems is challenging due to their inherent…

Satellite image classification is a challenging problem that lies at the crossroads of remote sensing, computer vision, and machine learning. Due to the high variability inherent in satellite data, most of the current object classification…

Video frame interpolation (VFI) aims to improve the temporal resolution of a video sequence. Most of the existing deep learning based VFI methods adopt off-the-shelf optical flow algorithms to estimate the bidirectional flows and…

As a special type of transformer, Vision Transformers (ViTs) are used to various computer vision applications (CV), such as image recognition. There are several potential problems with convolutional neural networks (CNNs) that can be solved…

While vision transformers have achieved impressive results, effectively and efficiently accelerating these models can further boost performances. In this work, we propose a dense/sparse training framework to obtain a unified model, enabling…

Hyperspectral image (HSI) super-resolution without additional auxiliary image remains a constant challenge due to its high-dimensional spectral patterns, where learning an effective spatial and spectral representation is a fundamental…

Time series classification is a fundamental task in healthcare and industry, yet the development of time series foundation models (TSFMs) remains limited by the scarcity of publicly available time series datasets. In this work, we propose…

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…