Related papers: BandRe: Rethinking Band-Pass Filters for Scale-Wis…
Recently, sparsity-based algorithms are proposed for super-resolution spectrum estimation. However, to achieve adequately high resolution in real-world signal analysis, the dictionary atoms have to be close to each other in frequency,…
This work presents BundleSeg, a reliable, reproducible, and fast method for extracting white matter pathways. The proposed method combines an iterative registration procedure with a recently developed precise streamline search algorithm…
Detecting tiny objects ( e.g., less than 20 x 20 pixels) in large-scale images is an important yet open problem. Modern CNN-based detectors are challenged by the scale mismatch between the dataset for network pre-training and the target…
Resonant periodic surfaces and films enable new functionalities with wide applicability in practical optical systems. Their material sparsity, ease of fabrication, and minimal interface count provide environmental and thermal stability and…
We propose a method to reduce non-uniform sample variance to a predetermined target level. The proposed space-variant filter can equalize variance of the non-stationary signal, or vary filtering strength based on image features, such as…
When considering perceptions, the observation scale and resolution are closely related properties. There is consensus in considering resolution as the density of elementary pieces of information in a specified information space.…
Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-down…
Deep learning based object detectors are commonly deployed on mobile devices to solve a variety of tasks. For maximum accuracy, each detector is usually trained to solve one single specific task, and comes with a completely independent set…
This paper presents a state-of-the-art approach in object detection for being applied in future SLAM problems. Although, many SLAM methods are proposed to create suitable autonomy for mobile robots namely ground vehicles, they still face…
Parametric filters, such as the Extended Kalman Filter and the Unscented Kalman Filter, typically scale well with the dimensionality of the problem, but they are known to fail if the posterior state distribution cannot be closely…
We have designed, fabricated, and measured a 5-channel prototype spectrometer pixel operating in the WR10 band to demonstrate a novel moderate-resolution (R=f/{\Delta}f~100), multi-pixel, broadband, spectrometer concept for mm and…
The 3D localisation of an object and the estimation of its properties, such as shape and dimensions, are challenging under varying degrees of transparency and lighting conditions. In this paper, we propose a method for jointly localising…
In the last decade, due to high resolution cameras and accurate meta-phase analyzes, the accuracy of chromosome classification has improved substantially. However, current Karyotyping systems demand large number of high quality train data…
We demonstrate a wavefront sensor based on the compressive sensing, single-pixel camera. Using a high-resolution spatial light modulator (SLM) as a variable waveplate, we weakly couple an optical field's transverse-position and polarization…
Scale variation across object instances remains a key challenge in object detection task. Despite the remarkable progress made by modern detection models, this challenge is particularly evident in the semi-supervised case. While existing…
Most of the recent successful methods in accurate object detection build on the convolutional neural networks (CNN). However, due to the lack of scale normalization in CNN-based detection methods, the activated channels in the feature space…
We propose a method for tracking an unknown number of targets based on measurements provided by multiple sensors. Our method achieves low computational complexity and excellent scalability by running belief propagation on a suitably devised…
There is an intense and partly recent literature focussing on the problem of selecting the bandwidth parameter for kernel density estimators. Available methods are largely `very nonparametric', in the sense of not requiring any knowledge…
In the this paper, the authors propose to estimate the density of a targeted population with a weighted kernel density estimator (wKDE) based on a weighted sample. Bandwidth selection for wKDE is discussed. Three mean integrated squared…
Unsupervised evaluation of segmentation quality is a crucial step in image segmentation applications. Previous unsupervised evaluation methods usually lacked the adaptability to multi-scale segmentation. A scale-constrained evaluation…