Search

Two new (1 and 2) meroterpenoids were isolated from the bark of Cinnamomum cassia. Their structures were determined by spectroscopic analyses and chemical methods. Antioxidant activities of 1 and 2 were evaluated by the ORAC and DPPH radical scavenging assays, and the results revealed that compound 2 displayed oxygen radical absorbance capacity. The discovery of compounds 1 and 2 added new members of this kind of natural product.

As one of the least understood aerosol processes, nucleation can be a dominant source of atmospheric aerosols. Sulfuric acid (SA)-amine binary nucleation with dimethylamine (DMA) has been recognized as a governing mechanism in the polluted continental boundary layer. Here we demonstrate the importance of trimethylamine (TMA) for nucleation in the complex atmosphere and propose a molecular-level SA-DMA-TMA ternary nucleation mechanism as an improvement upon the conventional binary mechanism. Using the proposed mechanism, we could connect the gaseous amines to the SA-amine cluster signals measured in the atmosphere of urban Beijing. Results show that TMA can accelerate the SA-DMA-based new particle formation in Beijing by 50–100%. Considering the global abundance of TMA and DMA, our findings imply comparable importance of TMA and DMA to nucleation in the polluted continental boundary layer, with probably higher contributions from TMA in polluted rural environments and future urban environments with controlled DMA emissions.

Video captioning requires that the model has the abilities of video understanding, video-text alignment, and text generation. Due to the semantic gap between vision and language, conducting video-text alignment is a crucial step to reduce the semantic gap, which maps the representations from the visual to the language domain. However, the existing methods often overlook this step, so the decoder has to directly take the visual representations as input, which increases the decoder’s workload and limits its ability to generate semantically correct captions. In this paper, we propose a video-text alignment module with a retrieval unit and an alignment unit to learn video-text aligned representations for video captioning. Specifically, we firstly propose a retrieval unit to retrieve sentences as additional input which is used as the semantic anchor between visual scene and language description. Then, we employ an alignment unit with the input of the video and retrieved sentences to conduct the video-text alignment. The representations of two modal inputs are aligned in a shared semantic space. The obtained video-text aligned representations are used to generate semantically correct captions. Moreover, retrieved sentences provide rich semantic concepts which are helpful for generating distinctive captions. Experiments on two public benchmarks, i.e., VATEX and MSR-VTT, demonstrate that our method outperforms state-of-the-art performances by a large margin. The qualitative analysis shows that our method generates correct and distinctive captions.

Domain generalization aims at generalizing the network trained on multiple domains to unknown but related domains. Under the assumption that different domains share the same classes, previous works can build relationships across domains. However, in realistic scenarios, the change of domains is always followed by the change of categories, which raises a difficulty for collecting sufficient aligned categories across domains. Bearing this in mind, this article introduces union domain generalization (UDG) as a new domain generalization scenario, in which the label space varies across domains, and the categories in unknown domains belong to the union of all given domain categories. The absence of categories in given domains is the main obstacle to aligning different domain distributions and obtaining domain-invariant information. To address this problem, we propose category-stitch learning (CSL), which aims at jointly learning the domain-invariant information and completing missing categories in all domains through an improved variational autoencoder and generators. The domain-invariant information extraction and sample generation cross-promote each other to better generalizability. Additionally, we decouple category and domain information and propose explicitly regularizing the semantic information by the classification loss with transferred samples. Thus our method can breakthrough the category limit and generate samples of missing categories in each domain. Extensive experiments and visualizations are conducted on MNIST, VLCS, PACS, Office-Home, and DomainNet datasets to demonstrate the effectiveness of our proposed method.

Sulfur-containing organophosphorus molecules have played a pivotal role in organic chemistry, thereby motivating researchers worldwide to establish S–P bonds from more environmentally friendly phosphorus sources.

Domain generalization aims to generalize a network trained on multiple domains to unknown yet related domains. Operating under the assumption that invariant information generalizes well to unknown domains, previous work has aimed to minimize the discrepancies amongst distributions across given domains. However, without prior regularization of feature distributions in unknown domains, the network in practice overfits the invariant information in the given domains. Moreover, if there are insufficient samples in given domains, then domain generalizability is limited, as diverse domain variations are not captured. To address these two drawbacks, we propose to explicitly map features in known and unknown domains onto latent space in a fixed Gaussian mixture distribution by variational coding. As a result, features in different classes follow Gaussian distributions with different mean values. The predefined latent space narrows discrepancies between known and unknown domains and effectively separates samples into different classes. Moreover, we propose to perturb sample features with gradients from the distribution regularized loss. This perturbation generates samples beyond but near the latent space of prior distributions, which has a profound impact on domain variations. Experiments and visualizations demonstrate the effectiveness of our proposed method.

A halotrimethylsilane (TMSX) accelerated cascade halophosphorylation and cycloisomerization of γ-hydroxyl ynones with diphenylphosphine oxides is presented. This methodology allows the one-step synthesis of practical polysubstituted halophosphorylated dihydrofuran derivatives. It is noteworthy that halotrimethylsilane functions as a halogenation reagent as well as a promoter to initiate this transformation. In addition, the reaction system can also be scaled up to gram quantities, and the produced halogenated compounds can undergo further derivatizations by Pd-catalyzed coupling reactions.

Volatile fatty acids (VFAs) derived from biomass are considered to be economical and environmentally friendly feedstocks for microbial fermentation. Converting VFAs to polyhydroxyalkanoate (PHA) could reduce the substrate cost and provide an economically viable route for the commercialization of PHA. The halophilic bacteria Salinivibrio spp. TGB4 and TGB19, newly isolated from salt fields, were found to accumulate poly-3-hydroxybutyrate (PHB) using acetate or butyrate as the substrate. Both strains exhibited considerable cell growth (OD

Low-dimensional ferroelectric tunnel junctions are appealing for the realization of nanoscale nonvolatile memory devices due to their inherent advantage of device miniaturization. Those based on current mechanisms still have restrictions including low tunneling electroresistance (TER) effects and complex heterostructures. Here, we introduce an entirely new TER mechanism to construct the nanotube ferroelectric tunnel junction with ferroelectric nanotubes as the tunneling region. When rolling a ferroelectric monolayer into a nanotube, due to the coexistence of its intrinsic ferroelectric polarization with the flexoelectric polarization induced by bending, there occurs metal-insulator transition depending on radiative polarization states. For the pristine monolayer, its out-of-plane polarization is tunable by an in-plane electric field, the conducting states of the ferroelectric nanotube can thus be tuned between metallic and insulating via axial electric means. Using {\alpha}-In2Se3 as an example, our first-principles density functional theory calculations and nonequilibrium Green's function formalism confirm the feasibility of the TER mechanism and indicate an ultrahigh TER ratio exceeding 9.9*10^10% of the proposed nanotube ferroelectric tunnel junctions. Our findings provide a promising approach based on simple homogeneous structures for high density ferroelectric microelectronic devices with excellent ON/OFF performance., Comment: 15 pages, 5 figures

Breast cancer (BC) remains the leading cause of cancer-related deaths worldwide. High recurrence risk Luminal BC receives adjuvant chemotherapy in addition to standard hormone therapy. Considering the heterogeneity of Luminal B BC, a more accurate classification model is urgently needed.In this study, we retrospectively reviewed the data of 1603 patients who were diagnosed with HER2-negative breast invasive ductal carcinoma. According to the expression level of PR and Ki-67 index, the Luminal B (HER2-negative) BCs were divided into three groups: ER+PR-Ki67The analysis results showed that there was a significant correlation between subtypes using this newly defined classification and overall survival (p 0.001) and disease-free survival (DFS) (p 0.001). Interestingly, patients in the ER+PR-Ki67

The structure of cellulolytic enzyme lignin (CEL) prepared from three bamboo species (Neosinocalamus affinis, Bambusa lapidea, and Dendrocalamus brandisii) has been characterized by different analytical methods. The chemical composition analysis revealed a higher lignin content, up to 32.6% of B. lapidea as compared to that of N. affinis (20.7%) and D. brandisii (23.8%). The results indicated that bamboo lignin was a p-hydroxyphenyl-guaiacyl-syringyl (H-G-S) lignin associated with p-coumarates and ferulates. Advanced NMR analyses displayed that the isolated CELs were extensively acylated at the γ-carbon of the lignin side chain (with either acetate and/or p-coumarate groups). Moreover, a predominance of S over G lignin moieties was found in CELs of N. affinis and B. lapidea, with the lowest S/G ratio observed in D. brandisii lignin. Catalytic hydrogenolysis of lignin demonstrated that 4-propyl-substituted syringol/guaiacol and propanol guaiacol/syringol derived from β-O-4′ moieties, and methyl coumarate/ferulate derived from hydroxycinnamic units were identified as the six major monomeric products. We anticipate that the insights of this work could shed light on the sufficient understanding of lignin, which could open a new avenue to facilitate the efficient utilization of bamboo.

Oilseed rape (Brassica napus L.) is an important cash crop, but transgenic oilseed rape has not been grown on a commercial scale in China. It is necessary to analyze the characteristics of transgenic oilseed rape before commercial cultivation. In our study, differential expression of total protein from the leaves in two transgenic lines of oilseed rape expressing foreign Bt Cry1Ac insecticidal toxin and their non-transgenic parent plant was analyzed using a proteomic approach. Only shared changes in both of the two transgenic lines were calculated. Fourteen differential protein spots were analyzed and identified, namely, eleven upregulated expressed protein spots and three downregulated protein spots. These proteins are involved in photosynthesis, transporter function, metabolism, protein synthesis, and cell growth and differentiation. The changes of these protein spots in transgenic oilseed rape may be attributable to the insertion of the foreign transgenes. However, the transgenic manipulation might not necessarily cause significant change in proteomes of the oilseed rape.

International audience; Broadcasting is an important routing strategy for message delivery in a VANET. However, the broadcast storm caused by loads of duplicate data packets can be severe, which leads to intense contention among vehicle nodes and a large number of dropped packets. In this case, the efficiency of message delivery is limited. This paper considers a broadcast routing protocol specially designed for urban areas with dense traffic and a huge amount of data traffic, and proposes a Preferred-Zone based broadcast (PreZcast) protocol. To alleviate the broadcast storm and improve the efficiency of message delivery, PreZcast only allows neighbors located within a Preferred Zone (PreZ) of a source node to rebroadcast a received packet. The PreZ is chosen based on the initial location and the distribution of two-hop neighbors of the source node. To further validate PreZcast in a more realistic and irregular topology, we evaluate PreZcast with real datasets issued from Bologna road traffic. Moreover, MultiPoint Relay (MPR) is introduced to further reduce duplicate packets in the network. Simulation results show that as compared with the Flooding protocol, PreZcast approximately improves 15% of broadcast efficiency and reduces 65% of packets transmitted with 5% more energy consumption, while PreZcast with MPR improves 10% of broadcast efficiency and reduces 70% of packets transmitted with only 0.5% more energy consumption.

We present DreamWaltz, a novel framework for generating and animating complex 3D avatars given text guidance and parametric human body prior. While recent methods have shown encouraging results for text-to-3D generation of common objects, creating high-quality and animatable 3D avatars remains challenging. To create high-quality 3D avatars, DreamWaltz proposes 3D-consistent occlusion-aware Score Distillation Sampling (SDS) to optimize implicit neural representations with canonical poses. It provides view-aligned supervision via 3D-aware skeleton conditioning which enables complex avatar generation without artifacts and multiple faces. For animation, our method learns an animatable and generalizable avatar representation which could map arbitrary poses to the canonical pose representation. Extensive evaluations demonstrate that DreamWaltz is an effective and robust approach for creating 3D avatars that can take on complex shapes and appearances as well as novel poses for animation. The proposed framework further enables the creation of complex scenes with diverse compositions, including avatar-avatar, avatar-object and avatar-scene interactions. See https://dreamwaltz3d.github.io/ for more vivid 3D avatar and animation results., project page at https://dreamwaltz3d.github.io/

With the development of ortho C-H functionalization in Pd/NBE chemistry, the catalytic systems used are becoming increasingly complex. The increasingly complex catalytic systems may have created technical barri-ers for researchers in other fields to apply Pd/NBE chemical methods. This report describes the use of a simple Pd/NBE catalytic system to achieve ortho C-H oxylation and phosphonylation and other functionalization of iodobenzene through templated conversion reactions. The key point of this method is to explore the previous-ly unknown step of introducing dimethylamine in the ortho position of iodobenzene through C-H amination. Aryl dimethylamine is quickly converted to methyl quaternary ammonium salt precipitation, and methyl qua-ternary ammonium salt effectively avoids Hofmann elimination in the subsequent functionalization.

Optical lattice plays an important role on stability and dynamics of quantum droplets. In this letter, we investigate the Bogoliubov excitation spectrum of quantum droplets in optical lattice in the thermodynamic limit. We classify the collective excitations as synchronous modes, Bloch phononic modes, and site-density imbalanced modes. For synchronous modes, we measure the dipole oscillation frequencies by quench dynamics with a sudden shift of the optical lattice, and the breathing frequencies by Floquet dynamics with a periodic change of the lattice depth. Bloch phononic modes are observable from the Landau critical velocity of the droplets. We further discuss the instability induced by the site-dependent density fluctuations, and calculate the critical filling of atoms where the growth of lattice vacancy breaks down the translational symmetry of the system. This work makes essential steps towards measuring the excitation spectrum and understanding the superfluid nature of quantum droplets in optical lattice., 5 figures

Deep Convolutional Neural Networks (CNNs) based methods have achieved significant breakthroughs in the task of single image shadow removal. However, the performance of these methods remains limited for several reasons. First, the existing shadow illumination model ignores the spatially variant property of the shadow images, hindering their further performance. Second, most deep CNNs based methods directly estimate the shadow free results from the input shadow images like a black box, thus losing the desired interpretability. To address these issues, we first propose a new shadow illumination model for the shadow removal task. This new shadow illumination model ensures the identity mapping among unshaded regions, and adaptively performs fine grained spatial mapping between shadow regions and their references. Then, based on the shadow illumination model, we reformulate the shadow removal task as a variational optimization problem. To effectively solve the variational problem, we design an iterative algorithm and unfold it into a deep network, naturally increasing the interpretability of the deep model. Experiments show that our method could achieve SOTA performance with less than half parameters, one-fifth of floating-point of operations (FLOPs), and over seventeen times faster than SOTA method (DHAN).

RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images. In this work, we propose a novel modality-adaptive mixup and invariant decomposition (MID) approach for RGB-infrared person re-identification towards learning modality-invariant and discriminative representations. MID designs a modality-adaptive mixup scheme to generate suitable mixed modality images between RGB and infrared images for mitigating the inherent modality discrepancy at the pixel-level. It formulates modality mixup procedure as Markov decision process, where an actor-critic agent learns dynamical and local linear interpolation policy between different regions of cross-modality images under a deep reinforcement learning framework. Such policy guarantees modality-invariance in a more continuous latent space and avoids manifold intrusion by the corrupted mixed modality samples. Moreover, to further counter modality discrepancy and enforce invariant visual semantics at the feature-level, MID employs modality-adaptive convolution decomposition to disassemble a regular convolution layer into modality-specific basis layers and a modality-shared coefficient layer. Extensive experimental results on two challenging benchmarks demonstrate superior performance of MID over state-of-the-art methods., 9 pages, 2 figures, AAAI 2022

Video captioning is a challenging task that aims to generate linguistic description based on video content. Most methods only incorporate visual features (2D/3D) as input for generating visual and non-visual words in the caption. However, generating non-visual words usually depends more on sentence-context than visual features. The wrong non-visual words can reduce the sentence fluency and even change the meaning of sentence. In this paper, we propose a syntax-guided hierarchical attention network (SHAN), which leverages semantic and syntax cues to integrate visual and sentence-context features for captioning. First, a globally-dependent context encoder is designed to extract the global sentence-context feature that facilitates generating non-visual words. Then, we introduce hierarchical content attention and syntax attention to adaptively integrate features in terms of temporality and feature characteristics respectively. Content attention helps focus on time intervals related to the semantic of current word, while cross-modal syntax attention uses syntax information to model importance of different features for target word’s generation. Moreover, such hierarchical attention can enhance the model interpretability for captioning. Experiments on MSVD and MSR-VTT datasets show the comparable performance of our method compared with current methods.

Iron dyshomeostasis is associated with hepatocellular carcinoma (HCC) development. However, the role of iron in HCC metastasis is unknown. This study aimed to elucidate the underlying mechanisms of iron’s enhancement activity on HCC metastasis. In addition to the HCC cell lines and clinical samples in vitro, iron deficient (ID) mouse models were generated using iron-free diet and transferrin receptor protein knock out, followed by administration of HCC tumors through either orthotopic or ectopic route. Clinical metastatic HCC samples showed significant ID status, accompanied by overexpression of sphingosine-1-phosphate transporter spinster homologue 2 (SPNS2). Mechanistically, ID increased SPNS2 expression, leading to HCC metastasis in both cell cultures and mouse models. ID not only altered the anti-tumor immunity, which was indicated by phenotypes of lymphatic subsets in the liver and lung of tumor-bearing mice, but also promoted HCC metastasis in a cancer cell autonomous manner through the SPNS2. Since germline knockout of globe SPNS2 showed significantly reduced HCC metastasis, we further developed hepatic-targeting recombinant adeno-associated virus vectors to knockdown SPNS2 expression and to inhibit iron-regulated HCC metastasis. Our observation indicates the role of iron in HCC pulmonary metastasis and suggests SPNS2 as a potential therapeutic target for the prevention of HCC pulmonary metastasis.

With the maturity of visual detection techniques, we are more ambitious in describing visual content with open-vocabulary, fine-grained and free-form language, i.e., the task of image captioning. In particular, we are interested in generating longer, richer and more fine-grained sentences and paragraphs as image descriptions. Image captioning can be translated to the task of sequential language prediction given visual content, where the output sequence forms natural language description with plausible grammar. However, existing image captioning methods focus only on language policy while not visual policy, and thus fail to capture visual context that are crucial for compositional reasoning such as object relationships (e.g., "man riding horse") and visual comparisons (e.g., "small(er) cat"). This issue is especially severe when generating longer sequences such as a paragraph. To fill the gap, we propose a Context-Aware Visual Policy network (CAVP) for fine-grained image-to-language generation: image sentence captioning and image paragraph captioning. During captioning, CAVP explicitly considers the previous visual attentions as context, and decides whether the context is used for the current word/sentence generation given the current visual attention. Compared against traditional visual attention mechanism that only fixes a single visual region at each step, CAVP can attend to complex visual compositions over time. The whole image captioning model -- CAVP and its subsequent language policy network -- can be efficiently optimized end-to-end by using an actor-critic policy gradient method. We have demonstrated the effectiveness of CAVP by state-of-the-art performances on MS-COCO and Stanford captioning datasets, using various metrics and sensible visualizations of qualitative visual context., Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI). Extended version of "Context-Aware Visual Policy Network for Sequence-Level Image Captioning", ACM MM 2018 (arXiv:1808.05864)

Benefiting from the popularity of deep learning theory, scene text detection algorithms have developed rapidly in recent years. Methods representing text region by text segmentation map are proved to capture arbitrary-shaped text in a more flexible and accurate way. However, such segmentation-based methods are prone to be disturbed by the text-like background patterns (like the fence, grass, etc.), which generally suffer from imprecise boundary detail problem. In this paper, LEMNet is proposed to handle the imprecise boundary problem by guiding the generation of text boundary based on a priori constraint. In the training stage, Boundary Segmentation Branch is firstly constructed to predict coarse boundary mask for each text instance. Then, through mapping pixels into an embedding space, the proposed Pixel Embedding Branch makes the embedding representation of boundary points learn to be more similar, meanwhile enlarging the characteristic distance between background points and boundary points. During inference, noise in the coarse boundary segmentation map can be effectively suppressed by a Noisy Point Suppression Algorithm among pixel embedding vectors. In this way, LEMNet can generate a more precise boundary description of text regions. To further enhance the distinguishability of boundary features, we propose a Context Enhancement Module to capture feature interactions in different representation subspaces, in which features are parallelly performed attention and concatenated to generate enhanced features. Extensive experiments are conducted over four challenging datasets, which demonstrate the effectiveness of LEMNet. Specifically, LEMNet achieves F-measure of 85.2%, 87.6% and 85.2% on CTW1500, Total-Text and MSRA-TD500 respectively, which is the latest SOTA.

Several species of novel marine bacteria from the genus Marinobacterium, including M. nitratireducens, M. sediminicola, and M. zhoushanense were found to be capable of producing polyhydroxyalkanoates (PHA) using sugars and volatile fatty acids (VFAs) as the carbon source. M. zhoushanense produced poly-3-hydroxybutytate (PHB) from sucrose, achieving a product titer and PHB content of 2.89 g/L and 64.05 wt%, respectively. By contrast, M. nitratireducens accumulated 3.38 g/L PHB and 66.80 wt% polymer content using butyrate as the substrate. A third species, M. sediminicola showed favorable tolerance to propionate, butyrate, and valerate. The use of 10 g/L valerate yielded 3.37 g/L poly(3-hydroxybutyrate-co-3-hydroxyvalerate) (PHBV), with a 3-hydroxyvalerate (3 HV) monomer content of 94.75 mol%. Moreover, M. sediminicola could be manipulated to produce PHBV with changeable polymer compositions by feeding different mixtures of VFAs. Our results indicate that M. sediminicola is a promising halophilic bacterium for the production of PHA.

In e-commerce platforms, there is an emerging type of content that tells a "story" about some merchandise in the form of multimedia (text, images, video), which is named storytelling. Well told stories, like advertisements, can inspire users to purchase the related products. Thus, e-commerce service provider is keen to disseminate storytelling items to potentially interested users. We address this requirement by a cross-domain personalized recommendation approach. Because storytelling is a new type of content, its related user actions are much less, more sparse than product-related user actions, thus we propose to use product-domain user actions to assist the identification of user preferences and to make storytelling recommendations. Our method has two technical contributions. First, since the user behavior patterns are different across the storytelling domain and the product domain, we propose an attentional domain-transfer network, which effectively selects the relevant items in the two domains to characterize user preferences. Second, although storytelling is about product, between the two domains there is a large gap: product description is objective and categorical, like "keywords," but storytelling is close to human language. To bridge the domain gap, we propose a dual-domain contrastive adversarial learning method to pre-train the feature extractors for storytelling and product simultaneously. We conduct experiments on two industrial datasets, and the results demonstrate the advantage of our proposed method that consistently outperforms the state-of-the-art methods. Besides, our method can be used to recommend storytelling to products, which is a desired functionality for product providers. Our code and models are publicly available.