Search

This paper introduces the point-axis representation for oriented object detection, emphasizing its flexibility and geometrically intuitive nature with two key components: points and axes. 1) Points delineate the spatial extent and contours of objects, providing detailed shape descriptions. 2) Axes define the primary directionalities of objects, providing essential orientation cues crucial for precise detection. The point-axis representation decouples location and rotation, addressing the loss discontinuity issues commonly encountered in traditional bounding box-based approaches. For effective optimization without introducing additional annotations, we propose the max-projection loss to supervise point set learning and the cross-axis loss for robust axis representation learning. Further, leveraging this representation, we present the Oriented DETR model, seamlessly integrating the DETR framework for precise point-axis prediction and end-to-end detection. Experimental results demonstrate significant performance improvements in oriented object detection tasks., Comment: 19 pages,7 figures,accpeted by ECCV24!

Efficiently estimating the full-body pose with minimal wearable devices presents a worthwhile research direction. Despite significant advancements in this field, most current research neglects to explore full-body avatar estimation under low-quality signal conditions, which is prevalent in practical usage. To bridge this gap, we summarize three scenarios that may be encountered in real-world applications: standard scenario, instantaneous data-loss scenario, and prolonged data-loss scenario, and propose a new evaluation benchmark. The solution we propose to address data-loss scenarios is integrating the full-body avatar pose estimation problem with motion prediction. Specifically, we present \textit{ReliaAvatar}, a real-time, \textbf{relia}ble \textbf{avatar} animator equipped with predictive modeling capabilities employing a dual-path architecture. ReliaAvatar operates effectively, with an impressive performance rate of 109 frames per second (fps). Extensive comparative evaluations on widely recognized benchmark datasets demonstrate Relia\-Avatar's superior performance in both standard and low data-quality conditions. The code is available at \url{https://github.com/MIV-XJTU/ReliaAvatar}.

With the frequent occurrence of black swan events, global energy security situation has become increasingly complex and severe. Assessing the resilience of the international oil trade network (iOTN) is crucial for evaluating its ability to withstand extreme shocks and recover thereafter, ensuring energy security. We overcomes the limitations of discrete historical data by developing a simulation model for extreme event shock-recovery in the iOTNs. We introduce network efficiency indicator to measure oil resource allocation efficiency and evaluate network performance. Then, construct a resilience index to explore the resilience of the iOTNs from dimensions of resistance and recoverability. Our findings indicate that extreme events can lead to sharp declines in performance of the iOTNs, especially when economies with significant trading positions and relations suffer shocks. The upward trend in recoverability and resilience reflects the self-organizing nature of the iOTNs, demonstrating its capacity for optimizing its own structure and functionality. Unlike traditional energy security research based solely on discrete historical data or resistance indicators, our model evaluates resilience from multiple dimensions, offering insights for global energy governance systems while providing diverse perspectives for various economies to mitigate risks and uphold energy security.

Rapid advancements in Autonomous Driving (AD) tasks turned a significant shift toward end-to-end fashion, particularly in the utilization of vision-language models (VLMs) that integrate robust logical reasoning and cognitive abilities to enable comprehensive end-to-end planning. However, these VLM-based approaches tend to integrate 2D vision tokenizers and a large language model (LLM) for ego-car planning, which lack 3D geometric priors as a cornerstone of reliable planning. Naturally, this observation raises a critical concern: Can a 2D-tokenized LLM accurately perceive the 3D environment? Our evaluation of current VLM-based methods across 3D object detection, vectorized map construction, and environmental caption suggests that the answer is, unfortunately, NO. In other words, 2D-tokenized LLM fails to provide reliable autonomous driving. In response, we introduce DETR-style 3D perceptrons as 3D tokenizers, which connect LLM with a one-layer linear projector. This simple yet elegant strategy, termed Atlas, harnesses the inherent priors of the 3D physical world, enabling it to simultaneously process high-resolution multi-view images and employ spatiotemporal modeling. Despite its simplicity, Atlas demonstrates superior performance in both 3D detection and ego planning tasks on nuScenes dataset, proving that 3D-tokenized LLM is the key to reliable autonomous driving. The code and datasets will be released.

Most dataset distillation methods struggle to accommodate large-scale datasets due to their substantial computational and memory requirements. In this paper, we present a curriculum-based dataset distillation framework designed to harmonize scalability with efficiency. This framework strategically distills synthetic images, adhering to a curriculum that transitions from simple to complex. By incorporating curriculum evaluation, we address the issue of previous methods generating images that tend to be homogeneous and simplistic, doing so at a manageable computational cost. Furthermore, we introduce adversarial optimization towards synthetic images to further improve their representativeness and safeguard against their overfitting to the neural network involved in distilling. This enhances the generalization capability of the distilled images across various neural network architectures and also increases their robustness to noise. Extensive experiments demonstrate that our framework sets new benchmarks in large-scale dataset distillation, achieving substantial improvements of 11.1\% on Tiny-ImageNet, 9.0\% on ImageNet-1K, and 7.3\% on ImageNet-21K. The source code will be released to the community.

The current international landscape is turbulent and unstable, with frequent outbreaks of geopolitical conflicts worldwide. Geopolitical risk has emerged as a significant threat to regional and global peace, stability, and economic prosperity, causing serious disruptions to the global food system and food security. Focusing on the international food market, this paper builds different dimensions of geopolitical risk measures based on the random matrix theory and constructs single- and two-factor GJR-GARCH-MIDAS models with fixed time span and rolling window, respectively, to investigate the impact of geopolitical risk on food market volatility. The findings indicate that modeling based on rolling window performs better in describing the overall volatility of the wheat, maize, soybean, and rice markets, and the two-factor models generally exhibit stronger explanatory power in most cases. In terms of short-term fluctuations, all four staple food markets demonstrate obvious volatility clustering and high volatility persistence, without significant asymmetry. Regarding long-term volatility, the realized volatility of wheat, maize, and soybean significantly exacerbates their long-run market volatility. Additionally, geopolitical risks of different dimensions show varying directions and degrees of effects in explaining the long-term market volatility of the four staple food commodities. This study contributes to the understanding of the macro-drivers of food market fluctuations, provides useful information for investment using agricultural futures, and offers valuable insights into maintaining the stable operation of food markets and safeguarding global food security., Comment: 38 pages, 3 figures, 11 tables

Detecting anomaly patterns from images is a crucial artificial intelligence technique in industrial applications. Recent research in this domain has emphasized the necessity of a large volume of training data, overlooking the practical scenario where, post-deployment of the model, unlabeled data containing both normal and abnormal samples can be utilized to enhance the model's performance. Consequently, this paper focuses on addressing the challenging yet practical few-shot online anomaly detection and segmentation (FOADS) task. Under the FOADS framework, models are trained on a few-shot normal dataset, followed by inspection and improvement of their capabilities by leveraging unlabeled streaming data containing both normal and abnormal samples simultaneously. To tackle this issue, we propose modeling the feature distribution of normal images using a Neural Gas network, which offers the flexibility to adapt the topology structure to identify outliers in the data flow. In order to achieve improved performance with limited training samples, we employ multi-scale feature embedding extracted from a CNN pre-trained on ImageNet to obtain a robust representation. Furthermore, we introduce an algorithm that can incrementally update parameters without the need to store previous samples. Comprehensive experimental results demonstrate that our method can achieve substantial performance under the FOADS setting, while ensuring that the time complexity remains within an acceptable range on MVTec AD and BTAD datasets.

As networked control systems continue to evolve, ensuring the privacy of sensitive data becomes an increasingly pressing concern, especially in situations where the controller is physically separated from the plant. In this paper, we propose a secure control scheme for computing linear quadratic control in a networked control system utilizing two networked controllers, a privacy encoder and a control restorer. Specifically, the encoder generates two state signals blurred with random noise and sends them to the controllers, while the restorer reconstructs the correct control signal. The proposed design effectively preserves the privacy of the control system's state without sacrificing the control performance. We theoretically quantify the privacy-preserving performance in terms of the state estimation error of the controllers and the disclosure probability. Additionally, the proposed privacy-preserving scheme is also proven to satisfy differential privacy. Moreover, we extend the proposed privacy-preserving scheme and evaluation method to cases where collusion between two controllers occurs. Finally, we verify the validity of our proposed scheme through simulations.

The Russia-Ukraine conflict is a growing concern worldwide and poses serious threats to regional and global food security. Using monthly trade data for maize, rice, and wheat from 2016/1 to 2022/12, this paper constructs three international crop trade networks (iCTNs) and an aggregate international food trade network (iFTN). We aim to examine the structural changes following the occurrence of the Russia-Ukraine conflict. We find significant shifts in the number of edges, average degree, density, efficiency, and natural connectivity in the third quarter of 2022, particularly in the international wheat trade network. Additionally, we have shown that political reasons have caused more pronounced changes in the trade connections between the economies of the North Atlantic Treaty Organization and Russia than with Ukraine. This paper could provide insights into the negative impact of geopolitical conflicts on the global food system and encourage a series of effective strategies to mitigate the negative impact of the conflict on global food trade.

In real-world applications, dynamic scenarios require the models to possess the capability to learn new tasks continuously without forgetting the old knowledge. Experience-Replay methods store a subset of the old images for joint training. In the scenario of more strict privacy protection, storing the old images becomes infeasible, which leads to a more severe plasticity-stability dilemma and classifier bias. To meet the above challenges, we propose a new architecture, named continual expansion and absorption transformer~(CEAT). The model can learn the novel knowledge by extending the expanded-fusion layers in parallel with the frozen previous parameters. After the task ends, we losslessly absorb the extended parameters into the backbone to ensure that the number of parameters remains constant. To improve the learning ability of the model, we designed a novel prototype contrastive loss to reduce the overlap between old and new classes in the feature space. Besides, to address the classifier bias towards the new classes, we propose a novel approach to generate the pseudo-features to correct the classifier. We experiment with our methods on three standard Non-Exemplar Class-Incremental Learning~(NECIL) benchmarks. Extensive experiments demonstrate that our model gets a significant improvement compared with the previous works and achieves 5.38%, 5.20%, and 4.92% improvement on CIFAR-100, TinyImageNet, and ImageNet-Subset.

Agricultural products play a critical role in human development. With economic globalization and the financialization of agricultural products continuing to advance, the interconnections between different agricultural futures have become closer. We utilize a TVP-VAR-DY model combined with the quantile method to measure the risk spillover between 11 agricultural futures on the futures exchanges of US and China from July 9,2014, to December 31,2022. This study yielded several significant findings. Firstly, CBOT corn, soybean, and wheat were identified as the primary risk transmitters, with DCE corn and soybean as the main risk receivers. Secondly, sudden events or increased economic uncertainty can increase the overall risk spillovers. Thirdly, there is an aggregation of risk spillovers amongst agricultural futures based on the dynamic directional spillover results. Lastly, the central agricultural futures under the conditional mean are CBOT corn and soybean, while CZCE hard wheat and long-grained rice are the two risk spillover centers in extreme cases, as per the results of the spillover network and minimum spanning tree. Based on these results, decision-makers are advised to safeguard against the price risk of agricultural futures under sudden economic events, and investors can utilize the results to construct a superior investment portfolio by taking different agricultural product futures as risk-leading indicators according to various situations.

We study the magnetic and tidal interactions of a gas-giant exoplanet with its host star and with its exomoons, and focus on their retention. We briefly revisit the scaling law for planetary dynamo in terms of its mass, radius and luminosity. Based on the virial theorem, we construct an evolution law for planetary magnetic field and find that its initial entropy is important for the field evolution of a high-mass planet. We estimate the magnetic torques on orbit arising from the star-planet and planet-moon magnetic interactions, and find that it can compensate tidal torques and bypass frequency valleys where dynamical-tide response is ineffective. For exomoon's retention we consider two situations. In the presence of a circumplanetary disk (CPD), by comparison between CPD's inner and outer radii, we find that planets with too strong magnetic fields or too small distance from its host star tend not to host exomoons. During the subsequent CPD-free evolution, we find, by comparison between planet's spindown and moon's migration timescales, that hot Jupiters with periods of several days are unlikely to retain large exomoons, albeit they could be surrounded by rings from the debris of tidally disrupted moons. In contrast, moons, if formed around warm or cold Jupiters, can be preserved. Finally, we estimate the radio power and flux density due to the star-planet and planet-moon magnetic interactions and give the upper limit of detection distance by FAST.

Recently, the Floquet ${\rm Na_3Bi}$-type material has been proposed as an ideal platform for realizing various phases, i.e., the spin-degenerate Dirac semimetal (DSM) can be turned into the Weyl semimetal (WSM), and even to the Weyl half-metal (WHM). Instead of the conventional electrical methods, we use the RKKY interaction to characterize the topological phase transitions in this paper. It is found that detecting the Ising term $J_I$ is feasible for distinguishing the phase transition of DSM/WSM, since the emergence of $J_I$ is induced by the broken spin degeneracy. For the case with impurities deposited on $z$ axis (the line connecting the Weyl points), the Heisenberg term $J_H$ coexists with $J_I$ in the WSM, while $J_H$ is filtered out and only $J_I$ survives in the WHM. This magnetic filtering effect is a reflection of the fully spin-polarized property (one spin band is in the WSM phase while the other is gapped) of the WHM, and it can act a signal to capture the phase transition of WSM/WHM. This signal can not be disturbed unless the direction of the impurities greatly deviates from $z$ axis. Interestingly, as the impurities are moved into the $x$-$y$ plane, there arises another signal (a dip structure for $J_H$ at the phase boundary), which can also identify the phase transition of WSM/WHM. Furthermore, we have verified that all magnetic signals are robust to the term that breaks the electron-hole symmetry. Besides characterizing the phase transitions, our results also suggest that the Floquet DSMs are power platforms for controlling the magnetic interaction., Comment: 15 pages, 10 figures

We present ARTrackV2, which integrates two pivotal aspects of tracking: determining where to look (localization) and how to describe (appearance analysis) the target object across video frames. Building on the foundation of its predecessor, ARTrackV2 extends the concept by introducing a unified generative framework to "read out" object's trajectory and "retell" its appearance in an autoregressive manner. This approach fosters a time-continuous methodology that models the joint evolution of motion and visual features, guided by previous estimates. Furthermore, ARTrackV2 stands out for its efficiency and simplicity, obviating the less efficient intra-frame autoregression and hand-tuned parameters for appearance updates. Despite its simplicity, ARTrackV2 achieves state-of-the-art performance on prevailing benchmark datasets while demonstrating remarkable efficiency improvement. In particular, ARTrackV2 achieves AO score of 79.5\% on GOT-10k, and AUC of 86.1\% on TrackingNet while being $3.6 \times$ faster than ARTrack. The code will be released.

The ongoing Russia-Ukraine conflict between two major agricultural powers has posed significant threats and challenges to the global food system and world food security. Focusing on the impact of the conflict on the global agricultural market, we propose a new analytical framework for tail dependence, and combine the Copula-CoVaR method with the ARMA-GARCH-skewed Student-t model to examine the tail dependence structure and extreme risk spillover between agricultural futures and spots over the pre- and post-outbreak periods. Our results indicate that the tail dependence structures in the futures-spot markets of soybean, maize, wheat, and rice have all reacted to the Russia-Ukraine conflict. Furthermore, the outbreak of the conflict has intensified risks of the four agricultural markets in varying degrees, with the wheat market being affected the most. Additionally, all the agricultural futures markets exhibit significant downside and upside risk spillovers to their corresponding spot markets before and after the outbreak of the conflict, whereas the strengths of these extreme risk spillover effects demonstrate significant asymmetries at the directional (downside versus upside) and temporal (pre-outbreak versus post-outbreak) levels., Comment: 35 pages, 2 figures

This paper adopts the random matrix theory (RMT) to analyze the correlation structure of the global agricultural futures market from 2000 to 2020. It is found that the distribution of correlation coefficients is asymmetric and right skewed, and many eigenvalues of the correlation matrix deviate from the RMT prediction. The largest eigenvalue reflects a collective market effect common to all agricultural futures, the other largest deviating eigenvalues can be implemented to identify futures groups, and there are modular structures based on regional properties or agricultural commodities among the significant participants of their corresponding eigenvectors. Except for the smallest eigenvalue, other smallest deviating eigenvalues represent the agricultural futures pairs with highest correlations. This paper can be of reference and significance for using agricultural futures to manage risk and optimize asset allocation., Comment: 19 pages, 7 figures

1ES 1927+654 was known as a type 2 Seyfert galaxy, which exhibited drastic variability recently in ultraviolet (UV)/optical and X-ray bands. An UV/optical outburst was observed in the end of 2017, and it reached the peak luminosity $\sim 50$ days later. The high-cadence observations showed a rapid X-ray flux decline with complete disappearance of the power-law hard X-ray component when the soft X-ray thermal emission reached its lowest level about $150$ days after the UV/optical peak. The power law X-ray component reappeared with thermal X-ray emission brightening from its lowest flux within next $\sim$ 100~days. We assume an episodic accretion event taking place in the outer region of the disc surrounding a central black hole (BH), which is probably due to a red giant star tidally disrupted by the BH. The inner thin disc with corona is completely swept by the accretion event when the gas reaches the innermost circular stable orbit. The field threading the disrupted star is dragged inwards by the disc formed after the tidal disruption event, which accelerates outflows from the disc. The disc dimmed since a large fraction of the energy released in the disc is tapped into the outflows. The accretion rate of the episodic accretion event declines, and ultimately it turns out to be a thin disc, which is inefficient for field advection, and the outflows are switched off. A thin disc with corona reappears later after the outburst., Comment: 11 pages, 2023, MNRAS.526, 2331

This paper investigates the problem of sensor scheduling for remotely estimating the states of heterogeneous dynamical systems over resource-limited and lossy wireless channels. Considering the low time complexity and high versatility requirements of schedulers deployed on the transport layer, we propose a lightweight scheduler based on an Age of Information (AoI) function built with the tight scalar upper bound of the remote estimation error. We show that the proposed scheduler is indexable and sub-optimal. We derive an upper and a lower bound of the proposed scheduler and give stability conditions for estimation error. Numerical simulations demonstrate that, compared to existing policies, the proposed scheduler achieves estimation performance very close to the optimal at a much lower computation time.

Grains account for more than 50% of the calories consumed by people worldwide, and military conflicts, pandemics, climate change, and soaring grain prices all have vital impacts on food security. However, the complex price behavior of the global grain spot markets has not been well understood. A recent study performed multifractal moving average analysis (MF-DMA) of the Grains & Oilseeds Index (GOI) and its sub-indices of wheat, maize, soyabeans, rice, and barley and found that only the maize and barley sub-indices exhibit an intrinsic multifractal nature with convincing evidence. Here, we utilize multifractal fluctuation analysis (MF-DFA) to investigate the same problem. Extensive statistical tests confirm the presence of intrinsic multifractality in the maize and barley sub-indices and the absence of intrinsic multifractality in the wheat and rice sub-indices. Different from the MF-DMA results, the MF-DFA results suggest that there is also intrinsic multifractality in the GOI and soyabeans sub-indices. Our comparative analysis does not provide conclusive information about the GOI and soyabeans and highlights the high complexity of the global grain spot markets., Comment: 23 pages including 14 figures

This report introduces the 1st place winning solution for the Autonomous Driving Challenge 2023 - Online HD-map Construction. By delving into the vectorization pipeline, we elaborate an effective architecture, termed as MachMap, which formulates the task of HD-map construction as the point detection paradigm in the bird-eye-view space with an end-to-end manner. Firstly, we introduce a novel map-compaction scheme into our framework, leading to reducing the number of vectorized points by 93% without any expression performance degradation. Build upon the above process, we then follow the general query-based paradigm and propose a strong baseline with integrating a powerful CNN-based backbone like InternImage, a temporal-based instance decoder and a well-designed point-mask coupling head. Additionally, an extra optional ensemble stage is utilized to refine model predictions for better performance. Our MachMap-tiny with IN-1K initialization achieves a mAP of 79.1 on the Argoverse2 benchmark and the further improved MachMap-huge reaches the best mAP of 83.5, outperforming all the other online HD-map construction approaches on the final leaderboard with a distinct performance margin (> 9.8 mAP at least)., Comment: The Outstanding Champion and Innovation Award in the Online HD Map Construction Challenge (CVPR2023 Workshop)

N-nutrients in nitrogen fertilizers are a critical resource for modern agricultural production, with most economies relying on imports to secure adequate supplies. The N-nutrient trade system is vital for global food security and ecological safety. We analyzed the N-nutrient trade network from 1991 to 2020, using the perspective of the temporal rich club (TRC), to identify the core functional groups of global N-nutrient trade. Our analysis revealed that the Netherlands, US, France, China, UK, Belgium, Germany, and Spain form the stable cornerstone group from which other economies derive the complete trade network. We found that simply increasing the volume of import and export trade is insufficient to create an extensive and stable trade structure. Instead, the most effective way to enter the core of the trade network is to increase upstream and downstream trade partners and enhance its own importance and reputation. Our mathematical model suggests that the generation mechanism of the TRC phenomenon in the N-nutrient trade network is due to the coexistence of the attraction of reputation in supply and demand and the path-dependence mechanism. By understanding these mechanisms, we can provide a new perspective on the evolution of the trade network and the stability of the system.

The Grains and Oilseeds Index (GOI) and its sub-indices of wheat, maize, soyabeans, rice, and barley are daily price indexes reflect the price changes of the global spot markets of staple agro-food crops. In this paper, we carry out a visibility graph (VG) analysis of the GOI and its five sub-indices. Maximum likelihood estimation shows that the degree distributions of the VGs display power-law tails, except for rice. The average clustering coefficients of the six VGs are quite large (>0.5) and exhibit a nice power-law relation with respect to the average degrees of the VGs. For each VG, the clustering coefficients of nodes are inversely proportional to their degrees for large degrees and are correlated to their degrees as a power law for small degrees. All the six VGs exhibit small-world characteristics to some extent. The degree-degree correlation coefficients shows that the VGs for maize and soyabeans indices exhibit weak assortative mixing patterns, while the other four VGs are weakly disassortative. The average nearest neighbor degree functions have similar patterns, and each function shows a more complex mixing pattern which decreases for small degrees, increases for mediate degrees, and decreases again for large degrees., Comment: 14 pages, 43 figures

This paper combines the Copula-CoVaR approach with the ARMA-GARCH-skewed Student-t model to investigate the tail dependence structure and extreme risk spillover effects between the international agricultural futures and spot markets, taking four main agricultural commodities, namely soybean, maize, wheat, and rice as examples. The empirical results indicate that the tail dependence structures for the four futures-spot pairs are quite different, and each of them exhibits a certain degree of asymmetry. In addition, the futures market for each agricultural commodity has significant and robust extreme downside and upside risk spillover effects on the spot market, and the downside risk spillover effects for both soybeans and maize are significantly stronger than their corresponding upside risk spillover effects, while there is no significant strength difference between the two risk spillover effects for wheat, and rice. This study provides a theoretical basis for strengthening global food cooperation and maintaining global food security, and has practical significance for investors to use agricultural commodities for risk management and portfolio optimization., Comment: 37 pages, 7 figures

Energy security and energy trade are the cornerstones of global economic and social development. The structural robustness of the international oil trade network (iOTN) plays an important role in the global economy. We integrate the machine learning optimization algorithm, game theory, and utility theory for learning an oil trade decision-making model which contains the benefit endowment and cost endowment of economies in international oil trades. We have reconstructed the network degree, clustering coefficient, and closeness of the iOTN well to verify the effectiveness of the model. In the end, policy simulations based on game theory and agent-based model are carried out in a more realistic environment. We find that the export-oriented economies are more vulnerable to be affected than import-oriented economies after receiving external shocks. Moreover, the impact of the increase and decrease of trade friction costs on the international oil trade is asymmetrical and there are significant differences between international organizations., Comment: 14 pages, 5 figures

Pesticides are a kind of agricultural input, whose use can greatly reduce yield loss, regulate plant growth, effectively liberate agricultural productivity, and improve food security. The availability of pesticides in economies all over the world is ensured by pesticide redistribution through international trade and economies play different roles in this process. In this work, we measure and rank the importance of economies using nine node metrics in an evolutionary way. It is found that the clustering coefficient is correlated negatively with the other eight node metrics, while the other eight node metrics are positively correlated with each other and can be grouped into three communities (betweenness; in-degree, PageRank, authority, and in-closeness; out-degree, hub, and out-closeness). We further investigate the structural robustness of the international pesticide trade networks proxied by the giant component size under three types of shocks to economies (node removal in descending order, randomly, and in ascending order). The results show that, except for the clustering coefficient, the international pesticide trade networks are relatively robust under shocks to economies in ascending orders and randomly, but fragile under shocks to economies in descending order. In contrast, removing nodes with the clustering coefficient in ascending and descending orders gives similar robustness curves. Moreover, the structural robustness related to the giant component size evolves over time and exhibits an inverse U-shaped pattern., Comment: 17 pages, 14 figures

Ensuring food supply stability is key to food security for economies, and food imports become increasingly important to safeguard food supplies in economies with inadequate food production. Food import shocks have significant impacts on targeted economies. Using import trade data of four staple crops (maize, rice, soybean, and wheat) from 1986 to 2018, this paper identifies food import trade shocks that occurred to economies during the period of 1995--2018. We compare the temporal evolution and spatial distribution of import shocks occurring to different crops and analyze the shock intensity and shock recovery in various continents based on locally weighted polynomial regression and Cook's distance. The results reveal higher frequencies during the 2007/2008 food crisis and relatively higher shock frequencies in North America, Africa, and Asia. Meanwhile, there are regional differences in shock recovery, with the majority of shocks in Asia recovering in the short term. We also find that high import diversity and a low import dependency ratio buffer economies against import shocks, resulting in a low shock rate and a high recovery rate. These results contribute to our understanding of the external supply risks of food, placing emphasis on accessibility issues in food security.

International food trade is a growing complement to gaps in domestic food supply and demand, but it is vulnerable to disruptions due to some unforeseen shocks. This paper assembles the international crop trade networks using maize, rice, soybean, and wheat trade data sets from 1986 to 2020. We assess the importance of economies using multidimensional node importance metrics. We analyze the correlation structure of different node important metrics based on the random matrix theory and incorporate 20 metrics into a single metric. We find that some metrics have many similarities and dissimilarities, especially for metrics based on the same trade flow directions. We also find that European economies have a significant impact on the iCTNs. Additionally, economies with poor crop production play a major role in import trade, whereas economies with higher food production or smaller populations are crucial to export trade. Our findings have practical implications for identifying key economies in the international crop trade networks, preventing severe damage to the food trade system caused by trade disruptions in some economies, maintaining the stability of the food supply, and ensuring food security.

Pesticides are important agricultural inputs to increase agricultural productivity and improve food security. The availability of pesticides is partially achieved through international trade. However, economies involved in the international trade of pesticides are impacted by internal and external shocks from time to time, which influence the redistribution efficiency of pesticides all over the world. In this work, we adopt simulations to quantify the efficiency and robustness of the international pesticide trade networks under shocks to economies. Shocks are simulated based on nine node metrics, and three strategies are utilized based on descending, random, and ascending node removal. It is found that the efficiency and robustness of the international trade networks of pesticides increased for all the node metrics except the clustering coefficient. Moreover, the international pesticide trade networks are more fragile when import-oriented economies are affected by shocks., Comment: 12 pages, 5 figures

Current class-incremental learning research mainly focuses on single-label classification tasks while multi-label class-incremental learning (MLCIL) with more practical application scenarios is rarely studied. Although there have been many anti-forgetting methods to solve the problem of catastrophic forgetting in class-incremental learning, these methods have difficulty in solving the MLCIL problem due to label absence and information dilution. In this paper, we propose a knowledge restore and transfer (KRT) framework for MLCIL, which includes a dynamic pseudo-label (DPL) module to restore the old class knowledge and an incremental cross-attention(ICA) module to save session-specific knowledge and transfer old class knowledge to the new model sufficiently. Besides, we propose a token loss to jointly optimize the incremental cross-attention module. Experimental results on MS-COCO and PASCAL VOC datasets demonstrate the effectiveness of our method for improving recognition performance and mitigating forgetting on multi-label class-incremental learning tasks.