Related papers: Task-Aware Scanning Parameter Configuration for Ro…
Fine-tuning from pre-trained ImageNet models has become the de-facto standard for various computer vision tasks. Current practices for fine-tuning typically involve selecting an ad-hoc choice of hyperparameters and keeping them fixed to…
Language-guided active sensing is a robotics subtask where a robot with an onboard sensor interacts efficiently with the environment via object manipulation to maximize perceptual information, following given language instructions. These…
Visual error metrics play a fundamental role in the quantification of perceived image similarity. Most recently, use cases for them in real-time applications have emerged, such as content-adaptive shading and shading reuse to increase…
Medical imaging systems are commonly assessed and optimized by the use of objective measures of image quality (IQ). The performance of the ideal observer (IO) acting on imaging measurements has long been advocated as a figure-of-merit to…
Autonomous robotic inspection, where a robot moves through its environment and inspects points of interest, has applications in industrial settings, structural health monitoring, and medicine. Planning the paths for a robot to safely and…
Many autonomous robotic applications require object-level understanding when deployed. Actively reconstructing objects of interest, i.e. objects with specific semantic meanings, is therefore relevant for a robot to perform downstream tasks…
Successfully addressing a wide variety of tasks is a core ability of autonomous agents, requiring flexibly adapting the underlying decision-making strategies and, as we argue in this work, also adapting the perception modules. An analogical…
An adaptive guidance system that supports equipment operators requires a comprehensive model, which involves a variety of user behaviors that considers different skill and knowledge levels, as well as rapid-changing task situations. In the…
Recent 3D generative models produce high-quality textures for 3D mesh objects. However, they commonly rely on the heavy assumption that input 3D meshes are accompanied by manual mesh parameterization (UV mapping), a manual task that…
Computer vision is experiencing an AI renaissance, in which machine learning models are expediting important breakthroughs in academic research and commercial applications. Effectively training these models, however, is not trivial due in…
Object Referring-guided Scanpath Prediction (ORSP) aims to predict the human attention scanpath when they search for a specific target object in a visual scene according to a linguistic description describing the object. Multimodal…
Intelligent inspection robots are widely used in substation patrol inspection, which can help check potential safety hazards by patrolling the substation and sending back scene images. However, when patrolling some marginal areas with weak…
Instruction tuning has shown promising potential for developing general-purpose AI capabilities by using large-scale pre-trained models and boosts growing research to integrate multimodal information for creative applications. However,…
An examination of object recognition challenge leaderboards (ILSVRC, PASCAL-VOC) reveals that the top-performing classifiers typically exhibit small differences amongst themselves in terms of error rate/mAP. To better differentiate the top…
Many mobile robots rely on 2D laser scanners for localization, mapping, and navigation. However, those sensors are unable to correctly provide distance to obstacles such as glass panels and tables whose actual occupancy is invisible at the…
We propose a multi-stage convolutional neural network (MSCNN) based integrated method for reducing uncertainty of 3D point accuracy of lasar scanner (LS) in rough indoor rooms, providing more accurate spatial measurements for high-precision…
We conducted an extensive computational experiment, lasting multiple CPU-years, to optimally select parameters for two important classes of algorithms for finding sparse solutions of underdetermined systems of linear equations. We make the…
Traversability estimation is critical for enabling robots to navigate across diverse terrains and environments. While recent self-supervised learning methods achieve promising results, they often fail to capture the characteristics of…
Deep-learning and large scale language-image training have produced image object detectors that generalise well to diverse environments and semantic classes. However, single-image object detectors trained on internet data are not optimally…
Property Directed Reachability (PDR) is a powerful algorithm for formal verification of hardware and software systems, but its performance is highly sensitive to parameter configurations. Manual parameter tuning is time-consuming and…