10/25/2024


RGB-D based salient object detection (SOD) methods leverage the depth map as a valuable complementary information for better SOD performance. Previous methods mainly resort to exploit the correlation between RGB image and depth map in three fusion domains input images, extracted features, and output results. However, these fusion strategies cannot fully capture the complex correlation between the RGB image and depth map. Besides, these methods do not fully explore the cross-modal complementarity and the cross-level continuity of information, and treat information from different sources without discrimination. In this paper, to address these problems, we propose a novel Information Conversion Network (ICNet) for RGB-D based SOD by employing the siamese structure with encoder-decoder architecture. To fuse high-level RGB and depth features in an interactive and adaptive way, we propose a novel Information Conversion Module (ICM), which contains concatenation operations and correlation layers. Furthermore, we design a Cross-modal Depth-weighted Combination (CDC) block to discriminate the cross-modal features from different sources and to enhance RGB features with depth features at each level. Extensive experiments on five commonly tested datasets demonstrate the superiority of our ICNet over 15 state-of-theart RGB-D based SOD methods, and validate the effectiveness of the proposed ICM and CDC block.Block transform coded images usually suffer from annoying artifacts at low bit-rates, because of the independent quantization of DCT coefficients. Image prior models play an important role in compressed image reconstruction. Natural image patches in a small neighborhood of the high-dimensional image space usually exhibit an underlying sub-manifold structure. To model the distribution of signal, we extract sub-manifold structure as prior knowledge. We utilize graph Laplacian regularization to characterize the sub-manifold structure at patch level. And similar patches are exploited as samples to estimate distribution of a particular patch. Instead of using Euclidean distance as similarity metric, we propose to use graph-domain distance to measure the patch similarity. Then we perform low-rank regularization on the similar-patch group, and incorporate a non-convex lp penalty to surrogate matrix rank. Finally, an alternatively minimizing strategy is employed to solve the non-convex problem. Experimental results show that our proposed method is capable of achieving more accurate reconstruction than the state-of-the-art methods in both objective and perceptual qualities.In contrast with nature scenes, aerial scenes are often composed of many objects crowdedly distributed on the surface in bird's view, the description of which usually demands more discriminative features as well as local semantics. However, when applied to scene classification, most of the existing convolution neural networks (ConvNets) tend to depict global semantics of images, and the loss of low- and mid-level features can hardly be avoided, especially when the model goes deeper. To tackle these challenges, in this paper, we propose a multiple-instance densely-connected ConvNet (MIDC-Net) for aerial scene classification. It regards aerial scene classification as a multiple-instance learning problem so that local semantics can be further investigated. Our classification model consists of an instance-level classifier, a multiple instance pooling and followed by a bag-level classification layer. In the instance-level classifier, we propose a simplified dense connection structure to effectively preserve features from different levels. https://www.selleckchem.com/products/ag-221-enasidenib.html The extracted convolution features are further converted into instance feature vectors. Then, we propose a trainable attention-based multiple instance pooling. It highlights the local semantics relevant to the scene label and outputs the bag-level probability directly. Finally, with our bag-level classification layer, this multiple instance learning framework is under the direct supervision of bag labels. Experiments on three widely-utilized aerial scene benchmarks demonstrate that our proposed method outperforms many state-of-the-art methods by a large margin with much fewer parameters.Shear wave speed measurements can potentially be used to non-invasively measure myocardial stiffness in order to assess myocardial function. Several studies showed the feasibility of tracking natural mechanical waves induced by aortic valve closure in the interventricular septum, but different echocardiographic views have been used. This work systematically studied the wave propagation speeds measured in a parasternal long-axis and in an apical 4-chamber view in ten healthy volunteers. The apical and parasternal view are predominantly sensitive to longitudinal or transversal tissue motion respectively, and could therefore, theoretically, measure the speed of different wave modes. We found higher propagation speeds in apical than in parasternal view (median of 5.1 m/s vs 3.8 m/s, p less then 0.01, n=9). The results in the different views were not correlated (r=0.26, p=0.49), and an unexpectedly large variability among healthy volunteers was found in apical view compared to the parasternal view (3.5 - 8.7 vs 3.2 - 4.3 m/s, respectively). Complementary finite element simulations of Lamb waves in an elastic plate showed that different propagation speeds can be measured for different particle motion components when different wave modes are induced simultaneously. The in-vivo results cannot be fully explained with the theory of Lamb wave modes. Nonetheless, the results suggest that the parasternal long-axis view is a more suitable candidate for clinical diagnosis due to the lower variability in wave speeds.Double-parabolic-reflectors wave-guided ultrasonic transducers to realize wideband (0 to 2.5 MHz), multi-harmonic modes excitation (over 20 modes), and large mechanical/acoustic output were presented in this research. The double-parabolic-reflectors mechanism serves as a horn structure at low frequencies and acoustic focusing structure at high frequencies to enhance the energy density of the incident ultrasound. Combining simulation and experimental methods, we examined and verified the basic performance and working mechanisms of the double-parabolic-reflectors waveguide multi-modes excitation belongs to the harmonic modes from the thin waveguide; at megahertz range near the thickness mode of PZT, energy density of the incident ultrasound is enhanced by double parabolic reflections, and the amplification ranges from 10 to 40 times between 1 and 2.5 MHz; at burst excitation, the amplification performance is independent on the length of the thin waveguide. Compared with conventional Langevin transducers and HIFU transducers, our transducers possess a wide working frequency with large mechanical/acoustic output, large vibration velocity amplification.