Branch Extracts Research Articles

Aggregating transformers and CNNs for salient object detection in optical remote sensing images

Salient object detection (SOD) in optical remote sensing images (RSIs) plays a significant role in many areas such as agriculture, environmental protection, and the military. However, since the difference in imaging mode and image complexity between RSIs and natural scene images (NSIs), it is difficult to achieve remarkable results by directly extending the saliency method targeting NSIs to RSIs. Besides, we note that the convolutional neural networks (CNNs) based U-Net cannot effectively acquire the global long-range dependency, and the Transformer doesn’t adequately characterize the spatial local details of each patch. Therefore, to conduct salient object detection in RSIs, we propose a novel two-branch architecture based network for Aggregating the Transformers and CNNs, namely ATC-Net, where the local spatial details and the global semantic information are fused into the final high-quality saliency map. Specifically, our saliency model adopts an encoder-decoder architecture including two parallel encoder branches and a decoder. Firstly, the two parallel encoder branches extract global and local features by using Transformer and CNNs, respectively. Then, the decoder employs a series of feature-enhanced fusion (FF) modules to aggregate multi-level global and local features by interactive guidance and enhance the fused feature via attention mechanism. Finally, the decoder deploys the read out (RO) module to fuse the aggregated feature of FF module and the low-level CNN feature, steering the feature to focus more on spatial local details. Extensive experiments are performed on two public optical RSIs datasets, and the results show that our saliency model consistently outperforms 30 state-of-the-art methods.

Multi-Branch Deep Learning Framework for Land Scene Classification in Satellite Imagery

Land scene classification in satellite imagery has a wide range of applications in remote surveillance, environment monitoring, remote scene analysis, Earth observations and urban planning. Due to immense advantages of the land scene classification task, several methods have been proposed during recent years to automatically classify land scenes in remote sensing images. Most of the work focuses on designing and developing deep networks to identify land scenes from high-resolution satellite images. However, these methods face challenges in identifying different land scenes. Complex texture, cluttered background, extremely small size of objects and large variations in object scale are the common challenges that restrict the models to achieve high performance. To tackle these challenges, we propose a multi-branch deep learning framework that efficiently combines global contextual features with multi-scale features to identify complex land scenes. Generally, the framework consists of two branches. The first branch extracts global contextual information from different regions of the input image, and the second branch exploits a fully convolutional network (FCN) to extract multi-scale local features. The performance of the proposed framework is evaluated on three benchmark datasets, UC-Merced, SIRI-WHU, and EuroSAT. From the experiments, we demonstrate that the framework achieves superior performance compared to other similar models.

Virucidal antiviral activity of Maytenus quadrangulata extract against Mayaro virus: Evidence for the presence of catechins.

Mayaro virus (MAYV) is an arbovirus endemic to the Amazon region, which comprises the states of the North and Midwest region of Brazil and encompasses the largest tropical forest in the world, the Amazon Forest. The confirmation of its potential transmission by Aedes aegypti and recent cases in Brazil, mainly in large centers in the northern region, led to the classification of Mayaro fever as an emerging disease. Traditional medicine is commonly used to treat various diseases, mainly by local riverside populations. Some species of the genus Maytenus, which have similar morphologies, are popularly used to treat infections and inflammations. In this context, our research group has studied and confirmed the antiviral activity of several plant-derived compounds. However, several species of this same genus have not been studied and therefore deserve attention. This study aimed to demonstrate the effects of ethyl acetate extracts of leaves (LAE) and branches (TAE) of Maytenus quadrangulata against MAYV. Mammalian cells (Vero cells) were used to evaluate the cytotoxicity of the extracts. After cell infection by MAYV and the treatment with the extracts, we evaluated the selectivity index (SI), the virucidal effect, viral adsorption and internalization, and the effect on viral gene expression. The antiviral action was confirmed by quantifying the viral genome using RT-qPCR and by analyzing the effect on virus yield in infected cells. The treatment was performed based on the effective concentration protective for 50% of the infected cells (EC50). The leaves (LAE; EC50 12.0μg/mL) and branches (TAE; EC50 101.0μg/mL) extracts showed significative selectivity against the virus, with SI values of 79.21 and 9.91, respectively, which were considered safe. Phytochemical analysis revealed that the antiviral action was associated with the presence of catechins, mainly in LAE. This extract was chosen for the subsequent studies since it reduced the viral cytopathic effect and virus production, even at high viral loads [MOI (multiplicity of infection) 1 and 5]. The effects of LAE resulted in a marked reduction in viral gene expression. The viral title was drastically reduced when LAE was added to the virus before infection or during replication stages, reducing virus production up to 5-log units compared to infected and untreated cells. Through kinetic replication, MAYV was not detected in Vero cells treated with LAE throughout the viral cycle. The virucidal effect of LAE inactivates the viral particle and can intercept the virus at the end of the cycle when it gains the extracellular environment. Therefore, LAE is a promising source of antiviral agents.

Anti-Obesity Effects of Hovenia Dulcis Branches in Mouse Adipocytes, 3t3-l1 Cells, and High-Fat Diet Obese Mice.

Hovenia dulcis has been reported to have various pharmacological activities, but most studies were done with its fruits. However, from an economic point of view, the use of discarded leaves and branches as by-products is very valuable. In this study, thein vitro andin vivo anti-obesity activities of Hovenia dulcis branch extract (HDB) were investigated to evaluate the applicability of HDB as an anti-obesity agent. In differentiated 3T3-L1 cells, HDB inhibited lipid droplet accumulation. And HDB downregulated CEBPα, PPARγ, and perilipin-1, and upregulated ATGL, p-HSL, HSL, p-AMPK, UCP-1, PGC-1α, PRDM16, LC3-II, and p62/SQSTM1. In addition, HDB increased free glycerol content. In HFD-induced obese mice, HDB reduced body weight and total fat weight. In addition, HDB decreased blood LDL-cholesterol, blood total cholesterol, and blood triglyceride. These results indicate that HDB has anti-obesity activity and HDB can be used as a healthy functional food agent for weight reduction.

Branch information extraction from Norway spruce using handheld laser scanning point clouds in Nordic forests

We showed that a mobile handheld laser scanner (HHLS) provides useful features concerning the wood quality-influencing external structures of trees. When linked with wood properties measured at a sawmill utilizing state-of-the-art X-ray scanners, these data enable the training of various wood quality models for use in targeting and planning future wood procurement. A total of 457 Norway spruce sample trees (Picea abies (L.) H. Karst.) from 13 spruce-dominated stands in southeastern Finland were used in the study. All test sites were recorded with a ZEB Horizon HHLS, and the sample trees were tracked to a sawmill and subjected to X-rays. Two branch extraction techniques were applied to the HHLS point clouds: 1) a method developed in this study that was based on the density-based spatial clustering of applications with noise (DBSCAN) and 2) segmentation-based quantitative structure model (treeQSM). On average, the treeQSM method detected 46% more branches per tree than the DBSCAN did. However, compared with the X-rayed references, some of the branches detected by the treeQSM may either be false positives or so small in size that the X-rays are unable to detect them as knots, as the method overestimated the whorl count by 19% when compared with the X-rays. On the other hand, the DBSCAN method only detected larger branches and showed a −11% bias in whorl count. Overall, the DBSCAN underestimated knot volumes within trees by 6%, while the treeQSM overestimated them by 25%. When we input the HHLS features into a Random Forest model, the knottiness variables measured at the sawmill were predicted with R2s of 0.47–0.64. The results were comparable with previous results derived with the static terrestrial laser scanners. The obtained stem branching data are relevant for predicting wood quality attributes but do not provide data that are directly comparable with the X-ray features. Future work should combine terrestrial point clouds with dense above-canopy point clouds to overcome the limitations related to vertical coverage.

Testing a Method Based on an Improved UNet and Skeleton Thinning Algorithm to Obtain Branch Phenotypes of Tall and Valuable Trees Using Abies beshanzuensis as the Research Sample.

Sudden changes in the morphological characteristics of trees are closely related to plant health, and automated phenotypic measurements can help improve the efficiency of plant health monitoring, and thus aid in the conservation of old and valuable tress. The irregular distribution of branches and the influence of the natural environment make it very difficult to monitor the status of branches in the field. In order to solve the problem of branch phenotype monitoring of tall and valuable plants in the field environment, this paper proposes an improved UNet model to achieve accurate extraction of trunk and branches. This paper also proposes an algorithm that can measure the branch length and inclination angle by using the main trunk and branches separated in the previous stage, finding the skeleton line of a single branch via digital image morphological processing and the Zhang-Suen thinning algorithm, obtaining the number of pixel points as the branch length, and then using Euclidean distance to fit a straight line to calculate the inclination angle of each branch. These were carried out in order to monitor the change in branch length and inclination angle and to determine whether plant branch breakage or external stress events had occurred. We evaluated the method on video images of Abies beshanzuensis, and the experimental results showed that the present algorithm has more excellent performance at 94.30% MIoU as compared with other target segmentation algorithms. The coefficient of determination (R2) is higher than 0.89 for the calculation of the branch length and inclination angle. In summary, the algorithm proposed in this paper can effectively segment the branches of tall plants and measure their length and inclination angle in a field environment, thus providing an effective method to monitor the health of valuable plants.

TBDQN: A novel two-branch deep Q-network for crude oil and natural gas futures trading

Algorithmic trading plays a significant role in the trade of crude oil and natural gas futures. In this paper we propose a novel deep reinforcement learning (DRL) algorithm, dubbed two-branch deep Q-network (TBDQN), to automatically produce consistently profitable and robust trading signals in crude oil and natural gas futures markets. The first branch exploits long-short-term memory (LSTM) module to discover potential features hidden behind many technical indicators; the second branch extracts intrinsic features from futures contracts, trading positions and OHLCV using deep neural network. The extracted features are fused together to form the state vector of Q-leaning. In order to facilitate the training of the TBDQN model learning, we design a novel reward function by incorporating both immediate and long-term rewards. Compared to other popular methods, the proposed algorithm demonstrates excellent performance on the evaluation criteria of annualized return and Sharpe ratio in the oil and gas futures markets, which proves the effectiveness of our method.

A Multiscale Local–Global Feature Fusion Method for SAR Image Classification with Bayesian Hyperparameter Optimization Algorithm

In recent years, the advancement of deep learning technology has led to excellent performance in synthetic aperture radar (SAR) automatic target recognition (ATR) technology. However, due to the interference of speckle noise, the task of classifying SAR images remains challenging. To address this issue, a multi-scale local–global feature fusion network (MFN) integrating a convolution neural network (CNN) and a transformer network was proposed in this study. The proposed network comprises three branches: a CovNeXt-SimAM branch, a Swin Transformer branch, and a multi-scale feature fusion branch. The CovNeXt-SimAM branch extracts local texture detail features of the SAR images at different scales. By incorporating the SimAM attention mechanism to the CNN block, the feature extraction capability of the model was enhanced from the perspective of spatial and channel attention. Additionally, the Swin Transformer branch was employed to extract SAR image global semantic information at different scales. Finally, the multi-scale feature fusion branch was used to fuse local features and global semantic information. Moreover, to overcome the problem of poor accuracy and inefficiency of the model due to empirically determined model hyperparameters, the Bayesian hyperparameter optimization algorithm was used to determine the optimal model hyperparameters. The model proposed in this study achieved average recognition accuracies of 99.26% and 94.27% for SAR vehicle targets under standard operating conditions (SOCs) and extended operating conditions (EOCs), respectively, on the MSTAR dataset. Compared with the baseline model, the recognition accuracy has been improved by 12.74% and 25.26%, respectively. The results demonstrated that Bayes-MFN reduces the inter-class distance of the SAR images, resulting in more compact classification features and less interference from speckle noise. Compared with other mainstream models, the Bayes-MFN model exhibited the best classification performance.

Rethinking the necessity of image fusion in high-level vision tasks: A practical infrared and visible image fusion network based on progressive semantic injection and scene fidelity

Image fusion aims to integrate complementary characteristics of source images into a single fused image that better serves human visual observation and machine vision perception. However, most existing image fusion algorithms primarily focus on improving the visual appeal of fused images. Although there are some semantic-driven methods that consider semantic requirements of downstream applications, none of them have demonstrated the potential of image-level fusion compared to feature-level fusion, which fulfills high-level vision tasks directly on multi-modal features rather than on a fused image. To overcome these limitations, this paper presents a practical infrared and visible image fusion network based on progressive semantic injection and scene fidelity constraints, termed PSFusion. First of all, the sparse semantic perception branch extracts sufficient semantic features, which are then progressively integrated into the fusion network using the semantic injection module to fulfill the semantic requirements of high-level vision tasks. The scene fidelity path within the scene restoration branch is devised to ensure that the fusion features contain complete information for reconstructing the source images. Additionally, the contrast mask and salient target mask are employed to construct the fusion loss to maintain impressive visual effects of fusion results. In particular, we provide quantitative and qualitative analyses to demonstrate the potential of image-level fusion compared to feature-level fusion for high-level vision tasks. With the rapid advancement of large-scale models, image-level fusion can expeditiously leverage the advantages of multi-modal data and state-of-the-art (SOTA) unimodal segmentation to achieve superior performance. Furthermore, extensive comparative experiments demonstrate the superiority of our PSFusion over SOTA image-level fusion alternatives in terms of visual appeal and high-level semantics. Even under harsh circumstances, our method offers satisfactory fusion results to serve subsequent high-level vision applications. The source code is available at https://github.com/Linfeng-Tang/PSFusion.

Spatial complementary and self-repair learning for occluded person re-identification

Occluded person re-identification (ReID) is more challenging than holistic person ReID, as the appearance clues are insufficient and misaligned in cluttered scenarios. By digging pose/foreground priors, numerous previous methods focus on visible body regions to achieve alignment but they are complicated. To alleviate these issues, we present spatial complementary and self-repair learning (SCSRL), a simple yet effective approach that constructs holistic representations without extra priors. Specifically, SCSRL includes two learning branches, a spatial complementary learning (SCL) one and a self-repair learning (SRL) one. The SCL branch extracts aggregation features that reflect integral information of the human appearance. The SRL branch not only mines visible features for each input but also repairs missing/invisible appearance clues via a proposed repair loss. Moreover, we construct a large-scale occluded dataset namely Occluded-Market which contains more percentage of occlusion samples than existing datasets. The experiments show that our approach achieves state-of-the-art performance on Occluded-Market and other occluded datasets.

Relative estimation of beta-sitosterol in alcoholic extracts of roots and small branches of oroxylum indicum (L.) Kurz by HPTLC for plant part substitution, medicinal uses and conservation

Beta-sitosterol is a common and useful ‘phytosterol’, present in roots and small branches of Oroxylum indicum (L.) Kurz It has mainly cholesterol-lowering, anti-inflammatory, anti-cancer, and dietary properties. O. indicum is a rare medicinal plant in the traditional medicine system. This study comparatively identified and estimated beta-sitosterol in the methanolic extracts of roots and the small branches of O. indicum by the development of a validated HPTLC method. Chromatographic separation was performed on precoated TLC plates by toluene: ethyl acetate: formic acid: water (6:3:1:0.2, v/v/v/v) with standard procedures using HPTLC assembly. Marker was identified at RF 0.60 as prominent bands and quantified at 540 nm with sharp peaks corresponding to beta-sitosterol by calibration method. The method was validated as per ICH guidelines with a good linear relationship i.e. r2 = 0.9973 ± 0.000405 in 100 – 500 ng band−1 with respect to the peak area. The LOD and LOQ were calculated as 35.22 and 106.73 ng/band, respectively. The quantity of marker in extracts of roots and the small branches was found to be 268.7% w/w and 208.5% w/w respectively in 0.5 g of the sample. The method was simple, accurate, and reproducible for rapid screening and quantification of beta-sitosterol in roots and aerial parts of O. indicum. The study may helpful for plant part substitution study, medicinal practises, sustainability, and conservation of such vulnerable plant species. It may useful to establish the quality and efficacy of plant in traditional applications and in routine standardization (quality control) of different commercial preparations of O. indicum.

Five New Phenolic Glycosides from Viburnum luzonicum.

Viburnum luzonicum is widely distributed in China. Its branch extracts showed potential α-amylase and α-glucosidase inhibitory activities. In order to discover new bioactive constituents, five undescribed phenolic glycosides, viburozosides A-E (1-5), were obtained by bioassay-guided isolation coupled with HPLC-QTOF-MS/MS analysis. Their structures were elucidated by spectroscopic analyses, including 1D NMR, 2D NMR, ECD, and ORD. All compounds were tested for their α-amylase and α-glucosidase inhibitory potency. Compound 1 showed significantly competitive inhibition against α-amylase (IC50 =17.5 μM) and α-glucosidase (IC50 =13.6 μM).

Anti-inflammatory sesquiterpene polyol esters from the stem and branch of Tripterygium wilfordii.

The stem and branch extract of Tripterygium wilfordii (Celastraceae) afforded seven new dihydroagarofuran sesquiterpene polyesters [tripterysines A-G (1-7)] and eight known ones (8-15). The chemical structures of these new compounds were established based on combinational analysis of HR-ESI-MS and NMR techniques. The absolute configurations of tripterysines A-C (1-3) and E-G (5-7) were determined by X-ray crystallographic analysis and circular dichroism spectra. All the compounds were screened for their inhibitory effect on inflammation through determining their inhibitory effect on nitric oxide production in LPS-induced RAW 264.7 cells and the secretion of inflammatory cytokines TNF-α and IL-6 in LPS-induced BV2 macrophages. Compound 9 exhibited significant inhibitory activity on NO production with an IC50 value of 8.77 μmol·L-1. Moreover, compound 7 showed the strongest inhibitory effect with the secretion of IL-6 at 27.36%.

Ethyl Gallate Isolated from Castanopsis cuspidata var. sieboldii Branches Inhibits Melanogenesis and Promotes Autophagy in B16F10 Cells

The Castanopsis cuspidata var. sieboldii (CCS) plant grows predominantly in temperate regions of Asian countries, such as South Korea. Research on CCS has so far concentrated on the nutritional analysis, antioxidant activity, and anti-inflammation properties of its branches. However, the isolation of compounds and structural elucidation of effective single molecules remain unexplored, necessitating further exploration of CCS branches. Therefore, this study demonstrates the antioxidant and antimelanogenic activity of a single substance of ethyl gallate (EG) isolated from CCS branch extracts. Notably, the antimelanogenic (whitening) activity of EG extracted from CCS branches remains unexplored. Tyrosinase inhibition, kinetic enzyme assays, and molecular docking studies were conducted using mushroom tyrosinase in order to examine the antioxidant mechanism and antimelanin activity of EG in B16F10 melanoma cells. Nontoxic EG concentrations were found to be below 5 µg/mL. While EG significantly reduced the levels of whitening-associated proteins, p-CREB, and p-PKA, it dose-dependently inhibited the expression of TYR, TRP-1, TRP-2, and transcription factor (MITF). In addition, EG downregulated melanogenetic gene expression and activated autophagy signals. Therefore, EG extracted from CCS branches could serve as a novel functional cosmetic material with antimelanogenic and autophagy-enhancing activity.

QUALTITATIVE AND QUANTITATIVE ESTIMATION OF TERPENOID CONTENTS IN SOME IMPORTANT PLANTS OF PUNJAB, PAKISTAN


 
 
 Terpenoid contents of traditionally used ethnobotanically important plants (n=25) were determined. Ethanol extracts of seeds, fruits, pods, branches, bark, rhizome and whole plant parts were prepared and preliminary phytochemical investigation was carried out. Total terpenoid contents in ethanol extracts were determined through qualitative and quantitative analytical assay by Salkowski test. Results of qualitative analysis revealed that the seeds, pods and fruits were rich in terpenoid contents. Whereas the quantitative analysis of ethanol extract showed that fruit of Carissa carandas and Lodoicea maldivica seeds of Erysimum cheiri, whole plant of Fagonia arabica and branches of Withania somnifera had 80% of total terpenoids contents. While, seeds of Ceiba speciosa contained 77%, rhizome of Berberis lyceum, flower of Rosa indica and fruit of Diospyros peregrina had 70% of total terpenoids contents. Terpenoid contents in all other selected plants ranged from 60 to 40%. This study would be helpful in the determination of therapeutic bioactive terpenoids that could be isolated and used for mankind welfare.
 
 

Invitroanti-Staphylococcus aureusactivity of the methanol extract from Mitrephora thoreliiPierre’s branches and leavesin Lam Dong Province, Viet Nam

We demonstrated that the methanol extract of Mitrephora thoreliiPierre's branches and leavesin Lam Dong, Vietnam is anti-Staphylococcus aureusstrain (Sta1) of Phenikaa University, Hanoi, Viet Nam and Staphylococcus aureusATCC 29213strain(Sta2) from Thermo Fisher Scientific, USA. Invitro anti-Sta1 and Sta2 activity of the methanol extract of Mitrephora thoreliiPierre's branches and leaves were not significantly different. With a rise in extract content, the inhibitory zone's created diameter grew as well. The extract content of 100 mg/mL demonstrated the greatest antibacterial activity with a 25 mm inhibition zone diameter against Sta1 and 24mm inhibition zone diameter against Sta2. Bacteria were not resistant to the extract at concentrations of 20; 80 and 100 mg/mL after 48, 72, and 96 hours. The lowest inhibitory concentration (MIC) was between 312.5 and 625 μg/mL. The minimum bactericidal concentration was found to be 1.25mg/mL.

Bi-Branch Vision Transformer Network for EEG Emotion Recognition

Electroencephalogram (EEG) signals have emerged as an important tool for emotion research due to their objective reflection of real emotional states. Deep learning-based EEG emotion classification algorithms have made preliminary progress, but existing models struggle with capturing long-range dependence and integrating temporal, frequency, and spatial domain features to limit their classification ability. To address these challenges, this study proposes a Bi-branch Vision Transformer-based EEG emotion recognition model, Bi-ViTNet, that integrates spatial-temporal and spatial-frequency feature representations. Specifically, Bi-ViTNet is composed of spatial-frequency feature extraction branch and spatial-temporal feature extraction branch, which can fuse spatial-frequency-temporal features in a unified framework. Each branch is composed of Linear Embedding and Transformer Encoder, which is used to extract spatial-frequency features and spatial-temporal features. Finally, fusion and classification are performed by the Fusion and Classification layer. Experiments on SEED and SEED-IV datasets demonstrate that Bi-ViTNet outperforms state-of-the-art baselines.

Oxyresveratrol from mulberry branch extract protects HUVECs against oxidized Low-density Lipoprotein-induced oxidative injury via activation of the Nrf-2/HO-1 pathway

Oxyresveratrol from mulberry branch extract protects HUVECs against oxidized Low-density Lipoprotein-induced oxidative injury via activation of the Nrf-2/HO-1 pathway

Multiview Spatial–Spectral Two-Stream Network for Hyperspectral Image Unmixing

Linear spectral unmixing is an important technique in the analysis of mixed pixels in hyperspectral images. In recent years, deep learning-based methods have been garnering increasing attention in hyperspectral unmixing; especially, unsupervised autoencoder (AE) networks that have achieved excellent unmixing performance are a recent trend. While most approaches use spatial information, it is well known that hyperspectral data are characterized by a large number of narrow spectral bands. In order to take full advantage of the hyperspectral bands in unmixing and the spatial information, in this article, we explore multiview spectral and spatial information in an AE-based unmixing framework. We introduce multiview spectral information through spectral partitioning and propose a multiview spatial–spectral two-stream network, called MSSS-Net, which simultaneously learns a spatial stream network and a multiview spectral stream network in an end-to-end fashion for more efficient unmixing. The MSSS-Net is a two-stream deep unmixing network sharing a decoder, where its two AE networks employ recurrent neural networks (RNNs) to collaboratively utilize multiview spectral and spatial information. The spatial stream network branch extracts the spatial features of pixels and its neighbors, while the multiview spectral stream network branch exploits the multiview spectral bands of a pixel. Meanwhile, we design a cascaded bidirectional and unidirectional RNNs’ encoder structure for multiview spatial–spectral information to learn more discriminative deep patch-pixel features. Extensive ablation studies and experiments on both synthetic and real datasets demonstrate the superiority of the MSSS-Net over state-of-the-art unmixing methods.

Intra-Inter View Interaction Network for Light Field Image Super-Resolution

Light field (LF) cameras, which can record real-word scenes from multiple viewpoints in a single shot, are widely used in 3D reconstruction, re-focusing, and virtual reality <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">etc</i> . However, the inherent trade-off between spatial resolution and angular resolution of LF images hinders their applications for scenarios requiring high resolutions. In this paper, we propose a novel intra-inter view interaction network for LF image super-resolution, termed as LF-IINet, to exploit the correlations among all views and simultaneously preserve the parallax structure of LF views. The proposed LF-IINet consists of two parallel branches. Specifically, the top branch extracts global inter-view information, and the bottom branch first independently maps each view to deep representations and then models the correlations among all intra-view features via proposed multi-view context block (MCB). The two branches interact with each other by proposed inter-assist-intra feature updating module (IntraFUM, where the intra feature are updated with the assistance of the inter feature) and intra-assist-inter feature updating module (InterFUM, where the inter feature are updated with the assistance of the intra feature). In this way, our LF-IINet incorporates rich angular and spatial information for LF image super-resolution. Extensive comparison with state-of-the-art methods demonstrates that our method achieves superior performance visually and quantitatively. Furthermore, quantitative results also show that our method is effective for LF images with either small or large disparities. Our code is shared in <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/GaoshengLiu/LF-IINet</uri> .