This paper presents a novel multiview gait recognition method that combines the enhanced Gabor (EG) representation of the gait energy image and the regularized local tensor discriminant analysis ...(RLTDA) method. EG first derives desirable gait features characterized by spatial frequency, spatial locality, and orientation selectivity to cope with the variations due to surface, shoe types, clothing, carrying conditions, and so on. Unlike traditional Gabor transformation, which does not consider the structural characteristics of the gait features, our representation method not only considers the statistical property of the input features but also adopts a nonlinear mapping to emphasize those important feature points. The dimensionality of the derivation of EG gait feature is further reduced by using RLTDA, which directly obtains a set of locally optimal tensor eigenvectors and can capture nonlinear manifolds of gait features that exhibit appearance changes due to variable viewing angles. An aggregation scheme is adopted to combine the complementary information from differently RLTDA recognizers at the matching score level. The proposed method achieves the best average Rank-1 recognition rates for multiview gait recognition based on image sequences from the USF HumanID gait challenge database and the CASIA gait database.
It is well recognized that gait is an important biometric feature to identify a person at a distance, such as in video surveillance application. However, in reality, a change of viewing angle causes ...a significant challenge for gait recognition. In this paper, a novel approach is proposed for multiview gait recognition with the view angle of a probe gait sequence unknown. We formulate a new patch distribution feature based classification framework to estimate the view angle of each probe gait sequence. In this method, each gait energy image is represented as a set of dual-tree complex wavelet transform (DTCWT) features derived from different scales and orientations together with the x-y coordinates. Then, a two-stage Gaussian mixture model is presented that can represent each DTCWT based gait feature with a set of patch distribution parameters. A simple nearest-neighbor classifier is employed for view classification. To measure the similarity of gait sequences, we also propose a sparse local discriminant canonical correlation analysis algorithm to model the correlation of gait features from different views and use the correlation strength as similarity measure. An uncorrelated multilinear SLDCCA (UMSLDCCA) framework is further presented that aims to extract uncorrelated discriminative features directly from multidimensional gait features through solving a tensor-to-vector projection. The solution consists of sequential iterative processes based on the alternating projection method. Different from existing approaches, UMSLDCCA considers the spatial structure information within each gait sample and local geometry information among multiple gait samples. Moreover, our approach does not need explicit reconstruction and is robust against feature noise. Extensive experiments have been performed on two benchmark gait databases. The results demonstrate that our method outperforms the state-of-the-art methods in terms of accuracy and efficiency.
We propose an efficient and robust solution, called sparse discriminative multimanifold Grassmannian analysis (SDMMGA), for face recognition based on image set (FRIS), where each set contains face ...images belonging to the same subject and typically covering large variations. In our work, linearity constrained hierarchical agglomerative clustering (LC-HAC) method is first employed to partition each image set into several local linear models (LLMs), each depicted as a point on the Grassmannian manifold using positive definite Gaussian kernel function. In contrast to the standard discriminative learning algorithms that assume that all data are sampled from one single manifold and only one projection is derived for feature extraction, we model all the LLMs of each person as a manifold and present SDMMGA model to seek multiple projection matrices, which can uncover the geometrical information of different manifolds. Aiming to better separate manifold margins in the low-dimensional feature space, we introduce the ℓ 1 and ℓ 2 norms penalty in the SDMMGA objective function. An efficient regression method is presented for finding the most discriminative features. Comprehensive experiments on three standard data sets show that our method consistently outperforms the state of the art.
The RNA-guided DNA editing technology CRISPRs (clustered regularly interspaced short palindrom- ic repeats)/Cas9 had been used to introduce double-stranded breaks into genomes and to direct sub- ...sequent site-specific insertions/deletions or the replacement of genetic material in bacteria, such as Escherichia coli, Streptococcus pneumonia, and Lactobacillus reuteri. In this study, we established a high-efficiency CRISPR/Cas9 genome editing plasmid pKCcas9dO for use in Streptomyces genetic manipulation, which comprises a target-specific guide RNA, a codon-optimized cas9, and two hom- ology-directed repair templates. By delivering pKCcas9dO series editing plasmids into the model strain Streptomyces coelicolor M145, through one-step intergeneric transfer, we achieved the gen- ome editing at different levels with high efficiencies of 60%-100%, including single gene deletion, such as actll-orf4, redD, and glnR, and single large-size gene cluster deletion, such as the antibiotic biosynthetic clusters of actinorhodin (ACT) (21.3 kb), undecylprodigiosin (RED) (31.6 kb), and Ca2+- dependent antibiotic (82.8 kb). Furthermore, we also realized simultaneous deletions of actll-orf4 and redD, and of the ACT and RED biosynthetic gene clusters with high efficiencies of 54% and 45%, respectively. Finally, we applied this system to introduce nucleotide point mutations into the rpsL gene, which conferred the mutants with resistance to streptomycin. Notably, using this system, the time required for one round of genome modification is reduced by one-third or one-half of those for conventional methods. These results clearly indicate that the established CRISPR/Cas9 genome editing system substantially improves the genome editing efficiency compared with the currently existing methods in Streptomyces, and it has promise for application to genome modification in other Actinomyces species.
This study presents a new dual-tree complex wavelet transform (DT-CWT)-based illumination normalisation approach for face recognition under varying lighting conditions. The method consists of three ...steps. First, the DT-CWT-based edge detection method is proposed which can obtain estimation for facial feature edges in different directionality and resolution level. Second, the DT-CWT-based denoising model is employed to obtain the multi-scale illumination invariant structures in the logarithm domain. Finally, by combining the obtained illumination invariant features and edge estimation information, the enhanced facial features are obtained which have more discriminating power for variable lighting face recognition. The effectiveness of the method is validated in comparative performance against many classical illumination compensation methods using the YaleB database and the CMU PIE database.
Vacancy defects in the porous ZnO nanoplates facilitate separation of charge carriers, and are in favor of adsorption and activation of CO2, resulting in greatly enhanced photocatalytic activity.
...Display omitted
•Porous ZnO nanoplates with VO defects are prepared by annealing precursor in air.•Amount of vacancy defects in ZnO can be tailored by changing heating temperature.•Different amount of defects lead to different performance for CO2 photoreduction.•VO defect can facilitate the separation of photogenerated electrons and holes.•VO defect is in favor of the adsorption and activation of CO2 on ZnO surface.
Photocatalytic conversion of CO2 into hydrocarbons by utilization of the solar energy is considered a promising approach to mitigate energy crisis and the environmental issues. Since the defects in a catalyst play an important role in CO2 reduction, herein, the porous ZnO nanoplates with vacancy defects are synthesized by annealing ZnS(en)0.5 precursor in air at different temperature. The defect amount in ZnO changes with the annealing temperature, resulting in different photocatalytic activity for CO2 reduction. The related mechanism has been studied both experimentally and theoretically. Raman spectra and chemical composition of the obtained catalysts are used to determine the defects. Transient techniques are used to investigate the separation of photogenerated charge carriers. CO2 adsorption capacity for different catalysts is also measured. First-principles calculation is used to study the adsorption and activation of CO2 on the ZnO surface. We envision that this work may afford an efficient approach to develop the semiconductor photocatalysts with superior activity via defects engineering.
The use of arginine deiminase (ADI) for arginine depletion therapy is an attractive anticancer approach. Combination strategies are needed to overcome the resistance of severe types of cancer cells ...to this monotherapy. In the current study, we report, for the first time, that the antioxidant N-acetylcysteine (NAC), which has been used in therapeutic practices for several decades, is a potent enhancer for targeted therapy that utilizes arginine deiminase. We demonstrated that pegylated arginine deiminase (ADI-PEG 20) induces apoptosis and G0/G1 phase arrest in murine MC38 colorectal cancer cells; ADI-PEG 20 induces Ca
overload and decreases the mitochondrial membrane potential in MC38 cells. ADI-PEG 20 induced the most important immunogenic cell death (ICD)-associated feature: cell surface exposure of calreticulin (CRT). The antioxidant NAC enhanced the antitumor activity of ADI-PEG 20 and strengthened its ICD-associated features including the secretion of high mobility group box 1 (HMGB1) and adenosine triphosphate (ATP). In addition, these regimens resulted in phagocytosis of treated MC38 cancer cells by bone marrow-derived dendritic cells (BMDCs). In conclusion, we describe, for the first time, that NAC in combination with ADI-PEG 20 not only possesses unique cytotoxic anticancer properties but also triggers the hallmarks of immunogenic cell death. Hence, ADI-PEG 20 in combination with NAC may represent a promising approach to treat ADI-sensitive tumors while preventing relapse and metastasis.
Abstract
The target of text‐based person re‐identification (Re‐ID) is to retrieve the corresponding image of a person through the given text information. However, due to the homogeneous variety and ...modality heterogeneity, it is challenging to simultaneously learn both global‐level and local‐level cross‐modal features and align them in the same embedding space without additional networks. To address these problems, an effective multi‐level cross‐modality learning (MCL) framework for language and vision person Re‐ID is proposed. More specifically, a multi‐branch feature extraction (MFE) module is designed to comprehensively map both global and partial semantic information for the visual and textual embedding at the same time, capturing the intra‐class semantic relationships in multi‐granularities. Besides, a cross‐modal alignment (CA) module is devised to match the multi‐grained representations and reduce the inter‐class gap from global‐level to partial‐level. Extensive experiments conducted on the CUHK‐PEDES and ICFG‐PEDES datasets suggest that this method outperforms the state‐of‐the‐art models.
Multimodal human sentiment comprehension refers to recognizing human affection from multiple modalities. There exist two key issues for this problem. First, it is difficult to explore time-dependent ...interactions between modalities and focus on the important time steps. Second, processing the long fused sequence of utterances is susceptible to the forgetting problem due to the long-term temporal dependency. In this article, we introduce a hierarchical learning architecture to classify utterance-level sentiment. To address the first issue, we perform time-step level fusion to generate fused features for each time step, which explicitly models time-restricted interactions by incorporating information across modalities at the same time step. Furthermore, based on the assumption that acoustic features directly reflect emotional intensity, we pioneer emotion intensity attention to focus on the time steps where emotion changes or intense affections take place. To handle the second issue, we propose Residual Memory Network (RMN) to process the fused sequence. RMN utilizes some techniques such as directly passing the previous state into the next time step, which helps to retain the information from many time steps ago. We show that our method achieves state-of-the-art performance on multiple datasets. Results also suggest that RMN yields competitive performance on sequence modeling tasks.
The accurate monitoring of blade vibration under operating conditions is essential in turbo-machinery testing. Blade tip timing (BTT) is a promising non-contact technique for the measurement of blade ...vibrations. However, the BTT sampling data are inherently under-sampled and contaminated with several measurement uncertainties. How to recover frequency spectra of blade vibrations though processing these under-sampled biased signals is a bottleneck problem. A novel method of BTT signal processing for alleviating measurement uncertainties in recovery of multi-mode blade vibration frequency spectrum is proposed in this paper. The method can be divided into four phases. First, a single measurement vector model is built by exploiting that the blade vibration signals are sparse in frequency spectra. Secondly, the uniqueness of the nonnegative sparse solution is studied to achieve the vibration frequency spectrum. Thirdly, typical sources of BTT measurement uncertainties are quantitatively analyzed. Finally, an improved vibration frequency spectra recovery method is proposed to get a guaranteed level of sparse solution when measurement results are biased. Simulations and experiments are performed to prove the feasibility of the proposed method. The most outstanding advantage is that this method can prevent the recovered multi-mode vibration spectra from being affected by BTT measurement uncertainties without increasing the probe number.