Spatial pyramid matching (SPM) has been widely used to compute the similarity of two images in computer vision and image processing. While comparing images, SPM implicitly assumes that: in two images from the same category, similar objects will appear in similar locations. However, this is not always the case. In this paper, we propose hyper-spatial matching (HSM), a more flexible image similarity computing method, to alleviate the mis-matching problem in SPM. Besides the match between corresponding regions, HSM considers the relationship of all spatial pairs in two images, which includes more meaningful match than SPM. We propose two learning strategies to learn SVM models with the proposed HSM kernel in image classification, which are hundreds of times faster than a general purpose SVM solver applied to the HSM kernel (in both training and testing). We compare HSM and SPM on several challenging benchmarks, and show that HSM is better than SPM in describing image similarity.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/TIP.2014.2344296 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
A new species of Bryk, 1949 (Lepidoptera, Erebidae, Herminiinae) from Jiangxi, China.
Biodivers Data J
January 2025
School of Forestry, Northeast Forestry University, Harbin, China School of Forestry, Northeast Forestry University Harbin China.
Background: Bryk, 1949 (Erebidae, Herminiinae) is a medium-sized, frail-bodied genus of moths that externally resembles other genera in the generic complex. All known larvae of this genus feed on fresh leaves of moss. This genus is widely distributed from the Himalayas to Southeast Asia, Japan, Borneo, Sulawesi and New Guinea.
View Article and Find Full Text PDFIntroduction: Diagnostic performance of optical coherence tomography (OCT) to detect Alzheimer's disease (AD) and mild cognitive impairment (MCI) remains limited. We aimed to develop a deep-learning algorithm using OCT to detect AD and MCI.
Methods: We performed a cross-sectional study involving 228 Asian participants (173 cases/55 controls) for model development and testing on 68 Asian (52 cases/16 controls) and 85 White (39 cases/46 controls) participants.
The canonical deep neural network as a model for human symmetry processing.
iScience
January 2025
Division of Optometry, Health Sciences, City University of London, London EC1V 0HB, UK.
A key property of our environment is the mirror symmetry of many objects, although symmetry is an abstract global property with no definable shape template, making symmetry identification a challenge for standard template-matching algorithms. We therefore ask whether Deep Neural Networks (DNNs) trained on typical natural environmental images develop a selectivity for symmetry similar to that of the human brain. We tested a DNN trained on such typical natural images with object-free random-dot images of 1, 2, and 4 symmetry axes.
View Article and Find Full Text PDFRepeat expansions in gene in refractory chronic cough.
ERJ Open Res
January 2025
Centre for Human and Applied Physiological Sciences, School of Basic and Medical Biosciences, Faculty of Life Sciences and Medicine, King's College London, London, UK.
Introduction: Refractory chronic cough (RCC), persisting despite addressing contributory diagnoses, is likely underpinned by neurally mediated cough hypersensitivity. disorders are genetic neurodegenerative conditions caused by biallelic repeat expansion sequences, commonly presenting with cough, followed by neurological features including cerebellar ataxia with neuropathy and vestibular areflexia syndrome (CANVAS). The prevalence and identifying clinical characteristics of repeat-expansion disorders in patients with RCC are unknown.
View Article and Find Full Text PDFProspects of elafibranor in treating alcohol-associated liver diseases.
World J Gastroenterol
January 2025
School of Basic Medicine, Qilu Medical University, Zibo 255300, Shandong Province, China.
Alcohol-related liver disease (ALD), which is induced by excessive alcohol consumption, is a leading cause of liver-related morbidity and mortality. ALD patients exhibit a spectrum of liver injuries, including hepatic steatosis, inflammation, and fibrosis, similar to symptoms of nonalcohol-associated liver diseases such as primary biliary cholangitis, metabolic dysfunction-associated steatotic liver disease, and nonalcoholic steatohepatitis. Elafibranor has been approved for the treatment of primary biliary cholangitis and has been shown to improve symptoms in both animal models and cell models of metabolic dysfunction-associated steatotic liver disease and nonalcoholic steatohepatitis.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!