Related papers: PREVIS -- A Combined Machine Learning and Visual I…
This is the preprint version of our paper on Advances in Engineering Software. With several characteristics, such as large scale, diverse predictability and timeliness, the city traffic data falls in the range of definition of Big Data. A…
Neural rendering-based urban scene reconstruction methods commonly rely on images collected from driving vehicles with cameras facing and moving forward. Although these methods can successfully synthesize from views similar to training…
Production planning in the manufacturing industry is crucial for fully utilizing factory resources (e.g., machines, raw materials and workers) and reducing costs. With the advent of industry 4.0, plenty of data recording the status of…
The use of machine learning rapidly increases in high-risk scenarios where decisions are required, for example in healthcare or industrial monitoring equipment. In crucial situations, a model that can offer meaningful explanations of its…
Unsupervised representation learning methods like SwAV are proved to be effective in learning visual semantics of a target dataset. The main idea behind these methods is that different views of a same image represent the same semantics. In…
This paper presents a visual tool, AVIATOR, that integrates the progressive visual analytics paradigm in the IR evaluation process. This tool serves to speed-up and facilitate the performance assessment of retrieval models enabling a result…
Interactive model analysis, the process of understanding, diagnosing, and refining a machine learning model with the help of interactive visualization, is very important for users to efficiently solve real-world artificial intelligence and…
Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement. Visual concept-based methods, while increasingly used for this purpose, face challenges: (1) most…
GeneVis is a web-based tool to visualize complementary data sets of different disciplines within the field of genetics. It overlays gene-cluster information, gene-interaction data and gene-disease association data by means of web-based…
Real-time visibility determination in expansive or dynamically changing environments has long posed a significant challenge in computer graphics. Existing techniques are computationally expensive and often applied as a precomputation step…
Machine learning practitioners often need to compare multiple models to select the best one for their application. However, current methods of comparing models fall short because they rely on aggregate metrics that can be difficult to…
Metal manufacturing often results in the production of defective products, leading to operational challenges. Since traditional manual inspection is time-consuming and resource-intensive, automatic solutions are needed. The study utilizes…
We propose the first deep learning solution to video frame inpainting, a challenging instance of the general video inpainting problem with applications in video editing, manipulation, and forensics. Our task is less ambiguous than frame…
Model visualization (ModelVis) has emerged as a major research direction, yet existing taxonomies are largely organized by data or tasks, making it difficult to treat models as first-class analysis objects. We present a model-centric…
We present a novel optimization-based Visual-Inertial SLAM system designed for multiple partially overlapped camera systems, named MAVIS. Our framework fully exploits the benefits of wide field-of-view from multi-camera systems, and the…
Vision-Language Navigation requires the agent to follow natural language instructions to reach a specific target. The large discrepancy between seen and unseen environments makes it challenging for the agent to generalize well. Previous…
Novel view synthesis (NVS) and video prediction (VP) are typically considered disjoint tasks in computer vision. However, they can both be seen as ways to observe the spatial-temporal world: NVS aims to synthesize a scene from a new point…
Contrastive learning, which aims at minimizing the distance between positive pairs while maximizing that of negative ones, has been widely and successfully applied in unsupervised feature learning, where the design of positive and negative…
In this paper, we present an innovative approach to self-supervised learning for Vision Transformers (ViTs), integrating local masked image modeling with progressive layer freezing. This method focuses on enhancing the efficiency and speed…
There is a growing trend of applying machine learning methods to medical datasets in order to predict patients' future status. Although some of these methods achieve high performance, challenges still exist in comparing and evaluating…