Recently, deep learning-based cross-view gait recognition has become popular owing to the strong capacity of convolutional neural networks (CNNs). Current deep learning methods often rely on loss ...functions used widely in the task of face recognition, e.g., contrastive loss and triplet loss. These loss functions have the problem of hard negative mining. In this paper, a robust, effective, and gait-related loss function, called angle center loss (ACL), is proposed to learn discriminative gait features. The proposed loss function is robust to different local parts and temporal window sizes. Different from center loss which learns a center for each identity, the proposed loss function learns multiple sub-centers for each angle of the same identity. Only the largest distance between the anchor feature and the corresponding cross-view sub-centers is penalized, which achieves better intra-subject compactness. We also propose to extract discriminative spatial-temporal features by local feature extractors and a temporal attention model. A simplified spatial transformer network is proposed to localize the suitable horizontal parts of the human body. Local gait features for each horizontal part are extracted and then concatenated as the descriptor. We introduce long short-term memory (LSTM) units as the temporal attention model to learn the attention score for each frame, e.g., focusing more on discriminative frames and less on frames with bad quality. The temporal attention model shows better performance than the temporal average pooling or gait energy images (GEI). By combing the three aspects, we achieve state-of-the-art results on several cross-view gait recognition benchmarks.
Protein-peptide interactions mediate a wide variety of cellular and biological functions. Methods for predicting these interactions have garnered a lot of interest over the past few years, as ...witnessed by the rapidly growing number of peptide-based therapeutic molecules currently in clinical trials. The size and flexibility of peptides has shown to be challenging for existing automated docking software programs.
Here we present AutoDock CrankPep or ADCP in short, a novel approach to dock flexible peptides into rigid receptors. ADCP folds a peptide in the potential field created by the protein to predict the protein-peptide complex. We show that it outperforms leading peptide docking methods on two protein-peptide datasets commonly used for benchmarking docking methods: LEADS-PEP and peptiDB, comprised of peptides with up to 15 amino acids in length. Beyond these datasets, ADCP reliably docked a set of protein-peptide complexes containing peptides ranging in lengths from 16 to 20 amino acids. The robust performance of ADCP on these longer peptides enables accurate modeling of peptide-mediated protein-protein interactions and interactions with disordered proteins.
ADCP is distributed under the LGPL 2.0 open source license and is available at http://adcp.scripps.edu. The source code is available at https://github.com/ccsb-scripps/ADCP.
Supplementary data are available at Bioinformatics online.
This paper gives a comprehensive study on gait biometrics via a joint CNN-based method. Gait is a kind of behavioral biometric feature with unique advantages, e.g., long-distance, cross-view and ...non-cooperative perception and analysis. In this paper, the definition of gait analysis includes gait recognition and gait-based soft biometrics such as gender and age prediction. We propose to investigate these two problems in a joint CNN-based framework which has been seldom reported in the recent literature. The proposed method is efficient in terms of training time, testing time and storage. We achieve the state-of-the-art performance on several gait recognition and soft biometrics benchmarks. Also, we discuss which part of the human body is important and informative for a specific task by network visualization.
Relationships among objects play a crucial role in image understanding. Despite the great success of deep learning techniques in recognizing individual objects, reasoning about the relationships ...among objects remains a challenging task. Previous methods often treat this as a classification problem, considering each type of relationship (e.g. ride) or each distinct visual phrase (e.g. person-ride-horse) as a category. Such approaches are faced with significant difficulties caused by the high diversity of visual appearance for each kind of relationships or the large number of distinct visual phrases. We propose an integrated framework to tackle this problem. At the heart of this framework is the Deep Relational Network, a novel formulation designed specifically for exploiting the statistical dependencies between objects and their relationships. On two large data sets, the proposed method achieves substantial improvement over state-of-the-art.
Traditional photonic sensing based on the change of balanced reflection of photonic structures can hardly distinguish chemical species with similar refractive indices. Here a sensing method based on ...the dynamic reflection spectra (DRS) of photonic crystal gel has been developed to distinguish even homologues, isomers and solvents with similar structures and physical properties. There are inherent relationships between solvent properties, diffusion behaviour and evolution of reflection signals, so that the geometric characteristics of DRS pattern including ascending/descending, colour changes, splitting/merging and curvature of reflection band can be utilized to recognize different organic solvents. With adequate solvents being tested, a database of DRS patterns can be established, which provide a standard to identify an unknown solvent.
The cation channel of sperm (CatSper) is essential for sperm motility and fertility
. CatSper comprises the pore-forming proteins CATSPER1-4 and multiple auxiliary subunits, including CATSPERβ, γ, δ, ...ε, ζ, and EFCAB9
. Here we report the cryo-electron microscopy (cryo-EM) structure of the CatSper complex isolated from mouse sperm. In the extracellular view, CATSPER1-4 conform to the conventional domain-swapped voltage-gated ion channel fold
, following a counterclockwise arrangement. The auxiliary subunits CATSPERβ, γ, δ and ε-each of which contains a single transmembrane segment and a large extracellular domain-constitute a pavilion-like structure that stabilizes the entire complex through interactions with CATSPER4, 1, 3 and 2, respectively. Our EM map reveals several previously uncharacterized components, exemplified by the organic anion transporter SLCO6C1. We name this channel-transporter ultracomplex the CatSpermasome. The assembly and organization details of the CatSpermasome presented here lay the foundation for the development of CatSpermasome-related treatments for male infertility and non-hormonal contraceptives.
Most orogenic belts have experienced a complex accretionary process with multiple episodes of seafloor subduction and trench retreat. This accretionary process is important in continental development ...and growth .
In the age of artificial intelligence, the best approach to handling huge amounts of data is a tremendously motivating and hard problem. Among machine learning models, stochastic gradient descent ...(SGD) is not only simple but also very effective. This study provides a detailed analysis of contemporary state-of-the-art deep learning applications, such as natural language processing (NLP), visual data processing, and voice and audio processing. Following that, this study introduces several versions of SGD and its variant, which are already in the PyTorch optimizer, including SGD, Adagrad, adadelta, RMSprop, Adam, AdamW, and so on. Finally, we propose theoretical conditions under which these methods are applicable and discover that there is still a gap between theoretical conditions under which the algorithms converge and practical applications, and how to bridge this gap is a question for the future.
Brushless excitation systems are widely used for synchronous machines. As a critical part of the system, rotating rectifiers have a significant impact on the system behavior. This paper presents a ...numerical average-value model (AVM) for rotating rectifiers in brushless excitation systems, where the essential numerical functions are extracted from the detailed simulations and vary depending on the loading conditions. Open-circuit voltages of the brushless exciter armature are used to calculate the dynamic impedance that represents the loading condition. The model is validated by comparison with an experimentally validated detailed model of the brushless excitation system in three distinct cases. It has been demonstrated that the proposed AVM can provide accurate simulations in both transient and steady states with fewer time steps and less runtime compared with detailed models of such systems and that the proposed AVM can be combined with AVM models of other rectifiers in the system to reduce the overall computational cost.
Oceanic plateaus with high-Mg rocks in the present-day oceanic crust have attracted much attention for their proposed mantle-plume origins and abnormally high mantle potential temperatures (Tp). ...However, equivalent rocks in ancient oceanic environments are usually poorly preserved because of deformation and metamorphism. Here we present petrological, geochronological and geochemical data for pillow lavas from Cambrian ophiolites in the Lajishan and Yongjing regions of the South Qilian Accretionary Belt (SQAB), from the southern part of the Qilian Orogen, northern China. Three rock groups can be identified geochemically: (1) sub-alkaline basalts with enriched mid- ocean ridge basalt (E-MORB) affinity; (2) alkaline basalts with oceanic island basalt (OIB) features, probably derived from partial melting of an enriched mantle source; and (3) picrites with MgO (18–22wt%). Cr-numbers Cr#=Cr/(Cr+Al) of spinels from the picrites suggest 18–21% degree of partial melting at the estimated mantle potential temperature (Tp) of 1489–1600°C, equivalent to values of Cenozoic Hawaiian picrites (1500–1600°C). Zircons from one gabbro sample yielded a U–Pb Concordia age of 525±3Ma, suggesting the oceanic crust formed in the Cambrian. Available evidence suggests that Cambrian mantle plume activity is preserved in the South Qilian Accretionary Belt, and influenced the regional tectonics: “jamming” of the trench by thick oceanic crust explains the emplacement and preservation of the oceanic plateau, and gave rise to the generation of concomitant Ordovician inner-oceanic island arc basalts via re-organisation of the subduction zones in the region.
Display omitted
•We present plume-type ophiolites in an Early Paleozoic accretionary belt.•We confirm that they occurred as an oceanic plateau with a minimum age of 525Ma.•The rocks are mainly sub-alkaline, alkaline and picrites.•The subduction of oceanic plateau caused trench jam and continental accretion.