Related papers: Group frame neural network of moving object ghost …
Classical ghost imaging is a correlation-imaging technique in which the image of the object is found through intensity correlations of light. We analyze three different quality parameters, namely the visibility, the signal-to-noise ratio…
Few-shot image classification has become a popular research topic for its wide application in real-world scenarios, however the problem of supervision collapse induced by single image-level annotation remains a major challenge. Existing…
Multi-robot systems such as swarms of aerial robots are naturally suited to offer additional flexibility, resilience, and robustness in several tasks compared to a single robot by enabling cooperation among the agents. To enhance the…
We present Better Together, a method that simultaneously solves the human pose estimation problem while reconstructing a photorealistic 3D human avatar from multi-view videos. While prior art usually solves these problems separately, we…
Convolutional Neural Networks (CNNs) have achieved superior performance on object image retrieval, while Bag-of-Words (BoW) models with handcrafted local features still dominate the retrieval of overlapping images in 3D reconstruction. In…
Motion reasoning serves as the cornerstone of multi-object tracking (MOT), as it enables consistent association of targets across frames. However, existing motion estimation approaches face two major limitations: (1) instability caused by…
We apply the measurement reduction technique to optimally reconstruct an object image from multiplexed ghost images (GI) while taking into account both GI correlations and object image sparsity. We show that one can reconstruct an image in…
A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information…
Quantum correlations become formidable tools for beating classical capacities of measurement. Preserving these advantages in practical systems, where experimental imperfections are unavoidable, is a challenge of the utmost importance. Here…
Image segmentation is the process of partitioning the image into significant regions easier to analyze. Nowadays, segmentation has become a necessity in many practical medical imaging methods as locating tumors and diseases. Hidden Markov…
In this work, we present an end-to-end framework to settle data association in online Multiple-Object Tracking (MOT). Given detection responses, we formulate the frame-by-frame data association as Maximum Weighted Bipartite Matching…
A new Bayesian state and parameter learning algorithm for multiple target tracking (MTT) models with image observations is proposed. Specifically, a Markov chain Monte Carlo algorithm is designed to sample from the posterior distribution of…
Neural network ensembles, such as Bayesian neural networks (BNNs), have shown success in the areas of uncertainty estimation and robustness. However, a crucial challenge prohibits their use in practice. BNNs require a large number of…
A novel algorithm is proposed for segmenting an image into multiple levels using its mean and variance. Starting from the extreme pixel values at both ends of the histogram plot, the algorithm is applied recursively on sub-ranges computed…
Recent Multiple Object Tracking (MOT) methods have gradually attempted to integrate object detection and instance re-identification (Re-ID) into a united network to form a one-stage solution. Typically, these methods use two separated…
This paper proposes an enhancement of convolutional neural networks for object detection in resource-constrained robotics through a geometric input transformation called Visual Mesh. It uses object geometry to create a graph in vision…
3D Multi-object tracking (MOT) is crucial to autonomous systems. Recent work uses a standard tracking-by-detection pipeline, where feature extraction is first performed independently for each object in order to compute an affinity matrix.…
Ghost imaging radar is a new system of gaze imaging radar with high detection sensitivity, super-resolution and better anti-interference performance, but the relative motion between the radar system and the target will make the target…
Neural networks have shown great abilities in estimating depth from a single image. However, the inferred depth maps are well below one-megapixel resolution and often lack fine-grained details, which limits their practicality. Our method…
In this paper, we first propose a Bayesian neighborhood selection method to estimate Gaussian Graphical Models (GGMs). We show the graph selection consistency of this method in the sense that the posterior probability of the true model…