Related papers: Toward Standardized Classification of Foveated Dis…
The practical impact of deep learning on complex supervised learning problems has been significant, so much so that almost every Artificial Intelligence problem, or at least a portion thereof, has been somehow recast as a deep learning…
We present a novel, automatic eye gaze tracking scheme inspired by smooth pursuit eye motion while playing mobile games or watching virtual reality contents. Our algorithm continuously calibrates an eye tracking system for a head mounted…
Learning visual semantic similarity is a critical challenge in bridging the gap between images and texts. However, there exist inherent variations between vision and language data, such as information density, i.e., images can contain…
Visual Grounding, also known as Referring Expression Comprehension and Phrase Grounding, aims to ground the specific region(s) within the image(s) based on the given expression text. This task simulates the common referential relationships…
Fine-grained object classification is a challenging task due to the subtle inter-class difference and large intra-class variation. Recently, visual attention models have been applied to automatically localize the discriminative regions of…
While eye tracking provides valuable capabilities for virtual reality, such as gaze interaction and dynamic foveated rendering (DFR), eye-tracking data can inadvertently reveal sensitive user information if not properly protected. Current…
Image classification is a fundamental computer vision task and an important baseline for deep metric learning. In decades efforts have been made on enhancing image classification accuracy by using deep learning models while less attention…
Foreground segmentation is an essential task in the field of image understanding. Under unsupervised conditions, different images and instances always have variable expressions, which make it difficult to achieve stable segmentation…
Deep learning architectures are an extremely powerful tool for recognizing and classifying images. However, they require supervised learning and normally work on vectors the size of image pixels and produce the best results when trained on…
Language-aligned vision foundation models perform strongly across diverse downstream tasks. Yet, their learned representations remain opaque, making interpreting their decision-making difficult. Recent work decompose these representations…
We investigate a fundamental aspect of machine vision: the measurement of features, by revisiting clustering, one of the most classic approaches in machine learning and data analysis. Existing visual feature extractors, including ConvNets,…
Large curved displays have emerged as a powerful platform for collaboration, data visualization, and entertainment. These displays provide highly immersive experiences, a wider field of view, and higher satisfaction levels. Yet, large…
Previous work has demonstrated the utility of reductions in the level of detail (LOD) in the periphery of head-tracked, large field of view displays. This paper provides a psychophysically based model, centered around an eye/head movement…
Vision Foundation Models (VFMs) have become the cornerstone of modern computer vision, offering robust representations across a wide array of tasks. While recent advances allow these models to handle varying input sizes during training,…
Few-Shot Object Detection (FSOD) is a rapidly growing field in computer vision. It consists in finding all occurrences of a given set of classes with only a few annotated examples for each class. Numerous methods have been proposed to…
In recent years, model explanation methods have been designed to interpret model decisions faithfully and intuitively so that users can easily understand them. In this paper, we propose a framework, Faithful Attention Explainer (FAE),…
Visual Question and Answering (VQA) problems are attracting increasing interest from multiple research disciplines. Solving VQA problems requires techniques from both computer vision for understanding the visual contents of a presented…
Image-text matching tasks have recently attracted a lot of attention in the computer vision field. The key point of this cross-domain problem is how to accurately measure the similarity between the visual and the textual contents, which…
Traditional learning from demonstration (LfD) generally demands a cumbersome collection of physical demonstrations, which can be time-consuming and challenging to scale. Recent advances show that robots can instead learn from human videos…
This dissertation advances the state of the art for AR/VR tracking systems by increasing the tracking frequency by orders of magnitude and proposes an efficient algorithm for the problem of edge-aware optimization. AR/VR is a natural way of…