Rotation-invariant recognition of shapes is a common challenge in computer vision. Recent approaches have significantly improved the accuracy of rotation-invariant recognition by encoding the rotational invariance of shapes as hand-crafted image features and introducing deep neural networks. However, the methods based on pixels have too much redundant information, and the critical geometric information is prone to early leakage, resulting in weak rotation-invariant recognition of fine-grained shapes. In this paper, we reconsider the shape recognition problem from the perspective of contour points rather than pixels. We propose an anti-noise rotation-invariant convolution module based on contour geometric aware for fine-grained shape recognition. The module divides the shape contour into multiple local geometric regions (LGA), where we implement finer-grained rotation-invariant coding in terms of point topological relations. We provide a deep network composed of five such cascaded modules for classification and retrieval experiments. The results show that our method exhibits excellent performance in rotation-invariant recognition of fine-grained shapes. In addition, we demonstrate that our method is robust to contour noise and the rotation centers.

Precise quantification of protein-ligand interaction is critical in early-stage drug discovery. Artificial intelligence (AI) has gained massive popularity in this area, with deep-learning models used to extract features from ligand and protein molecules. However, these models often fail to capture intermolecular non-covalent interactions, the primary factor influencing binding, leading to lower accuracy and interpretability. Moreover, such models overlook the spatial structure of protein-ligand complexes, resulting in weaker generalization. To address these issues, we propose Non-covalent Interaction-aware Graph Neural Network (NciaNet), a novel method that effectively utilizes intermolecular non-covalent interactions and 3D protein-ligand structure. Our approach achieves excellent predictive performance on multiple benchmark datasets and outperforms competitive baseline models in the binding affinity task, with the benchmark core set v.2016 achieving an RMSE of 1.208 and an R of 0.833, and the core set v.2013 achieving an RMSE of 1.409 and an R of 0.805, under the high-quality refined v.2016 training conditions. Importantly, NciaNet successfully learns vital features related to protein-ligand interactions, providing biochemical insights and demonstrating practical utility and reliability.

In recent years, large language models (LLMs) have shown rapid development, becoming one of the most popular topics in the field of artificial intelligence. LLMs have demonstrated powerful generalization and learning capabilities, and their performance on various language tasks has been remarkable. Despite their successes, LLMs face significant challenges, particularly in domain-specific tasks that require structured knowledge, often leading to issues such as hallucinations. To mitigate these challenges, we propose a novel system, SynaptiQA, which integrates LLMs with Knowledge Graphs (KGs) to answer more questions about knowledge. Our approach leverages the generative capabilities of LLMs to create and optimize KG queries, thereby improving the accuracy and contextual relevance of responses. Experimental results in an industrial data set demonstrate that SynaptiQA outperforms baseline models and naive retrieval-augmented generation (RAG) systems, demonstrating improved accuracy and reduced hallucinations. This integration of KGs with LLMs paves the way for more reliable and interpretable domain-specific question answering systems.

Driven by the complementary information fusion of optical and synthetic aperture radar (SAR) images, the optical-SAR image matching has drawn much attention. However, the significant radiometric differences between them imposes great challenges on accurate matching. Most existing approaches convert SAR and optical images into a shared feature space to perform the matching, but these methods often fail to achieve the robust matching since the feature spaces are unknown and uninterpretable. Motivated by the interpretable latent space of diffusion models, this paper formulates an optical-SAR image translation and matching framework via a dynamically conditioned diffusion model (DCDM) to achieve the interpretable and robust optical-SAR cross-modal image matching. Specifically, in the denoising process, to filter out outlier matching regions, a gated dynamic sparse cross-attention module is proposed to facilitate efficient and effective long-range interactions of multi-grained features between the cross-modal data. In addition, a spatial position consistency constraint is designed to promote the cross-attention features to perceive the spatial corresponding relation in different modalities, improving the matching precision. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods in terms of both the matching accuracy and the interpretability.

Weakly supervised object detection (WSOD) methods that trains an object detection network using image-level labels has attracted much attention due to its cost-effective annotation and broad applied requirement. However, applying such weak label to detect targets in infrared images is not trivial due to the less discriminative target information and interference of complex backgrounds. This article proposes a multi-grained and confidence-aware multiple instance network (MCMIN) to detect infrared targets given the imprecise labels. The multiscale multi-grained feature extraction module is designed to capture discriminative features from different receptive fields for dim-small targets. The hierarchical multiple instance target detection module first applies L1-sparsity regularization to encourage the model generate reliable pseudo ground truth (GT), and then leverages the confidence-aware instance adaptive weighting strategy to refine proposals with particular emphasis, achieving more accurate target detection. The experimental results on two infrared target detection datasets illustrate that the proposed MCMIN outperforms other state-of-the-art WSOD methods with higher average precision (AP). The proposed approach decreases the false alarms.

Tarim River Basin is located at the core area of The Belt and The Road at present and it once has been an essential transportation hub of the ancient Silk Road. However, Tarim River Basin belongs to arid and semi-arid region where water resource and vegetation cover are scarce, leading to soil erosion, desertification, and environmental degradation. So it is meaningful to study the variation of fractional vegetation cover (FVC) in Tarim River Basin. MODIS13Q1 data of Tarim River Basin from 2000 to 2018 were collected, and then, the pixel dichotomy model and Sen Mann-Kendall were applied in this research.The results were as follows: (1) The area ratio of different FVC types fluctuated with time, but the overall trend showed a slow growth trend. (2) In the trend analysis results, Significant improvement was concentrated in the low hills and oasis areas where the water resources in the basin are sufficient. In contrast, Severe degradation presented a feature of plaque-like sporadic distribution. (3)There are obvious seasonal differences FVC change. More specifically, FVC in spring and winter was considerably low, and yet FVC in summer and autumn was improved dramatically. Severe degradation and Significant improvement mainly occur in summer and autumn, and remain basically unchanged in spring and winter.

Using Landsat 8 OLI, GF-1, GF-2 and ALOS satellite images, the distribution of aquaculture in 2010-2018 in Sansha Bay were extracted through SVM and the spatial and temporal changes of aquaculture area were detected. Next, analyze the impact of the spatial changes on local water quality which was evaluated by CChl-a, CCOD, CDIP, CDIN. The results show that:(1). During 2010-2018, the area of cage culture remained stable while the algae culture's area has grown every year expect 2017 affected by algae growth time. (2). In 2010-2014, the algae culture was transferred from the western port area to the northeastern Dongwu Ocean and then move to the central sea area in the next three years. In 2017-2018, removal of large-scale culture from non-cultivation area of the central sea. (3). The distribution of culture is proportional to the concentration of Chl-a and COD, and CChl-aof algae aquaculture area is higher than that of cage area.

Land degradation is an important factor threatening human survival, social stability and sustainable development.This study aims to spatially analyse the land degradation sensitivity in Korla,Xinjiang in 2018, and provide a basis for identifying areas of land degradation.Based on the MEDALUS framework and the characteristics of the study area,four main factors of soil, climate, vegetation and management were considered, and several indicators affecting the quality of each factor were determined.The sensitivity of the areas to Land degradation risk was evaluated by LDSI(Land Degradation Sensitivity Index).As a whole, 84.4% of the districts in Korla have the possibility of land degradation. The ecological environment of Korla is relatively fragile.

Monitoring the marine aquaculture plays an important role in the management of marine fisheries, and also provides a valid method to evaluate the expansion intensity of the mariculture. In this context, different periods (2003, 2005, 2008, 2011, 2013, 2014 and 2016) of Landsat satellite data were collected and supervised classification method support vector machine (SVM) method was applied to extracted marine aquaculture in the Sansha Bay. Finally, different expansion indicators were used to evaluate the expansion intensity of mariculture in the study area. The results showed that: (1) the area of cage and algae culture increased rapidly, with the annual rates of expansion in 2.2×104km2and 9.3×104km2respectively from 2003 to 2016; (2) The total marine aquaculture reached 160×104km2in 2016, more than 21.2% of the planned mariculture; (3) Cage culture expanded from the coast of mainland and island to the deep sea, but the algae culture expanded more obviously and almost covered the sea, and the expansion intensity of cage and algae culture varied greatly at different periods.

In this study, we applied a process-based model, boreal ecosystem productivity simulator (BEPS) to simulate net primary productivity (NPP) over Fujian Province in 2015, and the responses of NPP to various environmental factors (e.g. temperature, elevation, slope, aspect) was analyzed. The results showed that: (1) the total NPP and mean NPP of Fujian province in 2015 are 43.13 × 106tC and 540.75gC m-2yr-1, and the rank of annual mean NPP of different forest types was as follows: Evergreen Broadleaf Forest(EBF)>Evergreen Needleleaf Forest (ENF)>Needle-Broadleaf Mixed Forest(NBMF)>Deciduous Needleleaf Forest (DNF)>Deciduous Broadleaf Forest(DBF), with the values of: 625.6gC m-2yr-1, 525.3gC m-2yr-1, 436.6gC m-2yr-1, 412.4gC m-2yr-1, 399.9gC m-2yr-1, respectively; (2) monthly mean NPP show “M” distribution temporally due to the high temperature in summer;(3)a significant correlation existed between NPP and terrain factors.