Related papers: Edge direction matrixes-based local binar patterns…
Texture recognition is one of the most important tasks in computer vision and, despite the recent success of learning-based approaches, there is still need for model-based solutions. This is especially the case when the amount of data…
Multi-Angled Parallelism (MAP) is a method to recognize lines in binary images. It is suitable to be implemented in parallel processing and image processing hardware. The binary image is transformed into directional planes, upon which,…
Feature matching in omnidirectional vision systems is a challenging problem, mainly because complicated optical systems make the theoretical modelling of invariance and construction of invariant feature descriptors hard or even impossible.…
In this paper, we design linear time algorithms to recognize and determine topological invariants such as the genus and homology groups in 3D. These properties can be used to identify patterns in 3D image recognition. This has tremendous…
Graph embedding algorithms are used to efficiently represent (encode) a graph in a low-dimensional continuous vector space that preserves the most important properties of the graph. One aspect that is often overlooked is whether the graph…
Graph representation learning is a fundamental problem for modeling relational data and benefits a number of downstream applications. Traditional Bayesian-based graph models and recent deep learning based GNN either suffer from…
Lightweight vision networks have witnessed remarkable progress in recent years, yet achieving a satisfactory balance among parameter scale, computational overhead, and task performance remains difficult. Although many existing lightweight…
Latent diffusion models (LDMs) power state-of-the-art high-resolution generative image models. LDMs learn the data distribution in the latent space of an autoencoder (AE) and produce images by mapping the generated latents into RGB image…
Binary segmentation is used to distinguish objects of interest from background, and is an active area of convolutional encoder-decoder network research. The current decoders are designed for specific objects based on the common backbones as…
We present Location Field Descriptors, a novel approach for single image 3D model retrieval in the wild. In contrast to previous methods that directly map 3D models and RGB images to an embedding space, we establish a common low-level…
To perform unconstrained face recognition robust to variations in illumination, pose and expression, this paper presents a new scheme to extract "Multi-Directional Multi-Level Dual-Cross Patterns" (MDML-DCPs) from face images. Specifically,…
The performance of sparse matrix computation highly depends on the matching of the matrix format with the underlying structure of the data being computed on. Different sparse matrix formats are suitable for different structures of data.…
Low-precision networks, with weights and activations quantized to low bit-width, are widely used to accelerate inference on edge devices. However, current solutions are uniform, using identical bit-width for all filters. This fails to…
Federated learning enables multiple medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains a major challenge. Many existing works attempt to address this issue…
Geometric deep learning enables the encoding of physical symmetries in modeling 3D objects. Despite rapid progress in encoding 3D symmetries into Graph Neural Networks (GNNs), a comprehensive evaluation of the expressiveness of these…
Being symmetric positive-definite (SPD), covariance matrix has traditionally been used to represent a set of local descriptors in visual recognition. Recent study shows that kernel matrix can give considerably better representation by…
We present Latent Diffeomorphic Dynamic Mode Decomposition (LDDMD), a new data reduction approach for the analysis of non-linear systems that combines the interpretability of Dynamic Mode Decomposition (DMD) with the predictive power of…
Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to…
Matching of images and analysis of shape differences is traditionally pursued by energy minimization of paths of deformations acting to match the shape objects. In the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework,…
Texture is an important cue for different computer vision tasks and applications. Local Binary Pattern (LBP) is considered one of the best yet efficient texture descriptors. However, LBP has some notable limitations, mostly the sensitivity…