Real-Time Scale Selection in Hybrid Multi-scale Representations

Mixed Rossby‐gravity (MRG) waves play a significant role in tropical variability. Their kinetic energy spectra exhibit maximal amplitudes at synoptic scales in the upper troposphere and at planetary scales in the upper stratosphere. The mechanism for different scale selection in the two regions has remained elusive. Here, we use a spherical barotropic model with the background zonal wind profiles derived from ERA5 reanalysis to show that the recently introduced MRG wave excitation mechanism wave‐mean flow interactions produces MRG waves with the observed scale properties in the two regions. Simulations with idealized zonal jets show that the jet position determines the MRG scale selection: the closer the jet to the equator, the smaller the scale of the excited MRG waves. Therefore, midlatitude jets, such as found in the upper stratosphere, support the excitation of planetary‐scale MRG waves.

Scale selection for anisotropic diffusion filter by Markov random field model

Recently, the multiscale problem in computer vision has gradually attracted people's attention. This article focuses on multiscale representation for object detection and recognition, comprehensively introduces the development of multiscale deep learning, and constructs an easy-to-understand, but powerful knowledge structure. First, we give the definition of scale, explain the multiscale mechanism of human vision, and then lead to the multiscale problem discussed in computer vision. Second, advanced multiscale representation methods are introduced, including pyramid representation, scale-space representation, and multiscale geometric representation. Third, the theory of multiscale deep learning is presented, which mainly discusses the multiscale modeling in convolutional neural networks (CNNs) and Vision Transformers (ViTs). Fourth, we compare the performance of multiple multiscale methods on different tasks, illustrating the effectiveness of different multiscale structural designs. Finally, based on the in-depth understanding of the existing methods, we point out several open issues and future directions for multiscale deep learning.

In this paper, we propose a novel watermarking method based on a multi-scale JNC (Just Noticeable Contrast) map. The main idea consists in using this JNC map to determine the optimal strength for embedding the watermark providing an invisible and robust watermarking scheme. The image is first decomposed into a multi-scale representation using the scale space decomposition. A multi-scale band limited contrast is then computed. The watermark is inserted into these contrast images. An experimental evaluation is carried out to demonstrate the performance of the proposed technique in terms of transparency and robustness to a wide variety of attacks.

In this paper we present a new approach towards the extraction of affine image regions based on detecting shape-stable boundaries from a multi-scale image representation. We construct an affine morphological scale space (AMSS) representation [1], which performs anisotropic diffusion while preserving boundaries and being invariant to affine transformations. We extract the transition boundaries of the diffusivity velocity map and track their evolution at each level of the scale-space. We then determine the stability of the boundary shape through a minimization process over different scales. Unlike most state of the art detectors which use the Gaussian scale space for multi-scale image representation, our approach is intrinsically affine invariant. We evaluate our detector by measuring repeatability of regions in transformed images of the same scene and comparing it to the state-of-the-art region detectors [2].

Face spoofing detection (i.e. face anti-spoofing) is emerging as a new research area and has already attracted a good number of works during the past five years. This paper addresses for the first time the key problem of the variation in the input image quality and resolution in face anti-spoofing. In contrast to most existing works aiming at extracting multiscale descriptors from the original face images, we derive a new multiscale space to represent the face images before texture feature extraction. The new multiscale space representation is derived through multiscale filtering. Three multiscale filtering methods are considered including Gaussian scale space, Difference of Gaussian scale space and Multiscale Retinex. Extensive experiments on three challenging and publicly available face anti-spoofing databases demonstrate the effectiveness of our proposed multiscale space representation in improving the performance of face spoofing detection based on gray-scale and color texture descriptors.

AI Reading Comprehension Assistants Integrating Visual Data for Enhanced Human Understanding

On the computation of a scale-space primal sketch

CSPFormer: A cross-spatial pyramid transformer for visual place recognition

Sparse representation has been demonstrated to be a powerful tool in classification of hyperspectral images (HSIs). The spatial context of an HSI can be exploited by first defining a local region for each test pixel and then jointly representing pixels within each region by a set of common training atoms (samples). However, the selection of the optimal region scale (size) for different HSIs with different types of structures is a nontrivial task. In this paper, considering that regions of different scales incorporate the complementary yet correlated information for classification, a multiscale adaptive sparse representation (MASR) model is proposed. The MASR effectively exploits spatial information at multiple scales via an adaptive sparse strategy. The adaptive sparse strategy not only restricts pixels from different scales to be represented by training atoms from a particular class but also allows the selected atoms for these pixels to be varied, thus providing an improved representation. Experiments on several real HSI data sets demonstrate the qualitative and quantitative superiority of the proposed MASR algorithm when compared to several well-known classifiers.

Pedestrian detection has achieved great improve-ments in recent years, while complex occlusion handling and high-accurate localization are still the most important problems. To take advantage of the body part semantic information and the contextual information for pedestrian detection, we propose the part and context network (PCN) in this paper. A PCN is composed of three branches: the basic branch; the part branch; and the context branch. It specially utilizes two branches to detect the pedestrians through the body part semantic information and the contextual information, respectively. In the part branch, the semantic information of body parts can communicate with each other via long short-term memory (LSTM). In the context branch, we adopt a local competition mechanism (maxout) for adaptive context scale selection. By combining the outputs of all branches, we develop a strong complementary pedestrian detector with a lower miss rate and higher localization accuracy, especially for the occlusion pedestrian. The combination of the body part semantic information and the contextual information in pedestrian detection is fully explored in this paper. Comprehensive evaluations on three challenging pedestrian detection datasets (i.e., Caltech, INRIA and KITTI) well demonstrate the effectiveness of our proposed PCN. Code for PCN is publicly available on GitHub https://github.com/sunnyxiaohu/pcn_pedestrian.

In this paper, we propose a new method to build a scale and rotation invariant descriptor for camera-based heterogeneous contents document image retrieval and spotting systems based on spatial information of keypoints. The descriptor is not only efficient to compute but also has low dimensionality. First, keypoints are extracted from an image using one of the dedicated detectors. And then, stable keypoints are sampled in order to compute descriptors based on geometric invariant from local organizations of the sampled keypoints via Delaunay triangulation graph. For sampling stable keypoints, we propose an approach which can deal with different scale level from scale space. The experimental results show that the proposed descriptor is promising for document image retrieval and spotting systems.

In this paper we analyze factors influencing the accuracy and precision of optical density measurement of light microscopical objects. The study is applied to the DNA content of Feulgen-stained cells using a lowresolution, TV-equipped microscope connected to a digital image processing system. Factors influencing the accuracy of density measurement include staining (not considered here), image formation (glare, focus, diffraction), image sampling (distribution, sampling density, noise), and computational accuracy. These factors are reviewed with respect to potential remedies. Evaluation of the measurement error contribution is performed on the level of the individual cell and on the specimen level. It is concluded that a coefficient of variation of 5% (in contrast to 3.5% using flow cytometry of the same specimen) in the measured values of normal cells of one specimen is attainable using adequate shading correction. With relatively simple computational methods, image cytometry may be well suited for pathology practice.

Multidimensional compound optimization is a new paradigm in the drug discovery process, yielding efficiencies during early stages and reducing attrition in the later stages of drug development. The success of this strategy relies heavily on understanding this multidimensional data and extracting useful information from it. This paper demonstrates how principled visualization algorithms can be used to understand and explore a large data set created in the early stages of drug discovery. The experiments presented are performed on a real-world data set comprising biological activity data and some whole-molecular physicochemical properties. Data visualization is a popular way of presenting complex data in a simpler form. We have applied powerful principled visualization methods, such as generative topographic mapping (GTM) and hierarchical GTM (HGTM), to help the domain experts (screening scientists, chemists, biologists, etc.) understand and draw meaningful decisions. We also benchmark these principled methods against relatively better known visualization approaches, principal component analysis (PCA), Sammon's mapping, and self-organizing maps (SOMs), to demonstrate their enhanced power to help the user visualize the large multidimensional data sets one has to deal with during the early stages of the drug discovery process. The results reported clearly show that the GTM and HGTM algorithms allow the user to cluster active compounds for different targets and understand them better than the benchmarks. An interactive software tool supporting these visualization algorithms was provided to the domain experts. The tool facilitates the domain experts by exploration of the projection obtained from the visualization algorithms providing facilities such as parallel coordinate plots, magnification factors, directional curvatures, and integration with industry standard software.

Small object detection, a critical technique for recognizing and localizing diminutive targets in visual data, plays a vital role in applications ranging from remote sensing and unmanned aerial vehicle (UAV) vision to autonomous driving. Current methodologies, however, face substantial challenges, including detection accuracy limitations, low‐resolution image processing difficulties, background noise interference, and target occlusion issues. To address these challenges, we propose FMF‐DETR, an innovative small object detection framework featuring frequency‐domain feature optimization through three key components: (1) High‐Low Frequency Fusion Model (HLFM), (2) Focused Diffusion Feature Pyramid Network (FDFPN), and (3) BiPathNet (BPNet). Specifically, the HLFM module enhances multiscale feature representation by emphasizing high‐frequency details while suppressing low‐frequency background noise. The FDFPN architecture improves detection performance in complex scenarios through multiscale feature fusion and saliency‐aware diffusion. BPNet introduces a dual‐path feature extraction mechanism that simultaneously enhances feature discriminability and reduces computational overhead. Through the synergistic integration of these components, the proposed framework enhances both detection accuracy and operational efficiency. Comprehensive evaluations on the VisDrone dataset demonstrate FMF‐DETR's superior performance, achieving a 2.2% accuracy improvement while reducing model parameters by 13.03M and computational complexity by 97.2G FLOPs compared to baseline methods. These results validate both the effectiveness and efficiency of our proposed framework.