Search

For channel and spatial feature map C×W×H in object detection task, its information fusion usually relies on attention mechanism, that is, all C channels and the entire space W×H are all compressed respectively via average/max pooling, and then their attention weight masks are obtained based on correlation calculation. This coarse-grained global operation ignores the differences among multiple channels and diverse spatial regions, resulting in inaccurate attention weights. In addition, how to mine the contextual information in the space W×H is also a challenge for object recognition and localization. To this end, we propose a Fine-Grained Dual Level Attention Mechanism joint Spacial Context Information Fusion module for object detection (FGDLAM&SCIF). It is a cascaded structure, firstly, we subdivide the feature space W×H into n (optimized as n = 4 in experiments) subspaces and construct a global adaptive pooling and one-dimensional convolution algorithm to effectively extract the feature channel weights on each subspace respectively. Secondly, the C feature channels are divided into n (n = 4) sub-channels, and then a multi-scale module is constructed in the feature space W×H to mine context information. Finally, row and column coding is used to fuse them orthogonally to obtain enhanced features. This module is embeddable, which can be transplanted into any object detection network, such as YOLOv4/v5, PPYOLOE, YOLOX and MobileNet, ResNet as well. Experiments are conducted on the MS COCO 2017 and Pascal VOC 2007 datasets to verify its effectiveness and good portability. [ABSTRACT FROM AUTHOR]

Maximizing the advantages of different views and mitigating their respective disadvantages in fine-grained segmentation tasks are an important challenge in the field of point cloud multi-view fusion. Traditional multi-view fusion methods ignore two fatal problems: 1. the loss of depth and quantization information due to mapping and voxelization operations, resulting in "anomalies" in the extracted features; 2. how to pay attention to the large differences in object sizes among different views during point cloud learning, and fine-tune the fusion efficiency in order to improve the performance of network. In this paper, we propose a new algorithm that uses channel self-attention to fuse range-point-voxel, abbreviated as RPV-CASNet. RPV-CASNet integrates the three different views: range, point and voxel in a more subtle way through an interactive structure (range-point-voxel cross-adaptive layer known as RPVLayer for short), to take full advantage of the differences among them. The RPVLayer contains two key designs: the Feature Refinement Module (FRM) and the Multi-Fine-Grained Feature Self-Attention Module(MFGFSAM). Specifically, the FRM allows for a re-inference representation of points with entrained anomalous features, correcting the features. The MFGFSAM addresses two challenges: efficiently aggregating tokens from distant regions and preserving multiscale features within a single attention layer. In addition, we design a Dynamic Feature Pyramid Extractor (DFPE) for network deployment, which is used to extract rich features from spherical range images. Our method achieves impressive mIoU scores of 69.8% and 77.1% on the SemanticKITTI and nuScenes datasets, respectively. [ABSTRACT FROM AUTHOR]

Exploring spatial-temporal interactions among group members is crucial for group activity recognition. However, most existing approaches cannot jointly consider it from multi-level cross-relations, which results in an incomplete representation. To address this issue, we propose a relational complementary module that comprehensively learns the interactions among members from both time-space and space-time perspectives. To suppress the information redundancy caused by this all-view interaction description, we introduce NH-Softmax to impose sparsity on the few relevant attention weights to generate robust and differentiated feature representations. In addition, to fully explore individual contextual interaction information, relaxed attention (RAT) is designed to enhance the feature information of each individual in a relaxed manner. It fleshes out individual representations by highlighting the most salient features and eases the computational burden. Our experiments on Volleyball dataset and Collective Activity dataset show significant improvements over previous state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper focuses on the adverse impact of outlier points and the ambiguity of candidate localizations in 3D object detection in terms of point cloud dataset. First, outlier points can disperse real feature extracting and mislead object detection, we propose an outlier weakening strategy. The neighborhood points of each point in the point set can be established via multi-directional search algorithm, and the correlations among points in the neighborhood are figured out via self-attention mechanism, then each point representation can be enhanced with the key information from its neighborhood, thus the negative impact of outlier points will be weakened due to obtaining real knowledge of object from neighborhood context. Second, multiple proposed boxes for object localization usually containing the same sampling points, this causes vagueness in differing them from each other and leads to incorrect object positioning. This paper proposes a voxel coding strategy with adaptive pooling, the candidate boxes are divided into voxels, and each voxel is further divided into multiple columns, then they are weighted and aggregated according to the importance of each column, thus can pop out the most confident spatial voxel encodings as reliable object localization nominees. This algorithm achieves an average accuracy of 82.98% and 93.2% on the KITTI dataset Car category and ModelNet40 dataset, respectively. [ABSTRACT FROM AUTHOR]

The community structure and co-occurrence pattern of eukaryotic algae in Yuncheng Salt Lake were analyzed based on marker gene analysis of the 18S rRNA V4 region to understand the species composition and their synergistic adaptations to the environmental factors in different salinity waters. The results showed indicated that the overall algal composition of Yuncheng Salt Lake showed a Chlorophyta-Pyrrophyta-Bacillariophyta type structure. Chlorophyta showed an absolute advantage in all salinity waters. In addition, Cryptophyta dominated in the least saline waters; Pyrrophyta and Bacillariophyta were the dominant phyla in the waters with salinity ranging from 13.2 to 18%. Picochlorum, Nannochloris, Ulva, and Tetraselmis of Chlorophyta, Biecheleria and Oxyrrhis of Pyrrophyta, Halamphora, Psammothidium, and Navicula of Bacillariophyta, Guillardia and Rhodomonas of Cryptophyta were not observed in previous surveys of the Yuncheng Salt Lake, suggesting that the algae are undergoing a constant turnover as the water environment of the Salt Lake continues to change. The network diagram demonstrated that the algae were strongly influenced by salinity, NO3−, and pH, changes in these environmental factors would lead to changes in the algal community structure, thus affecting the stability of the network structure. [ABSTRACT FROM AUTHOR]

With the advancement of new energy vehicles, power battery recycling has gained prominence. We examine a power battery closed-loop supply chain, taking subsidy decisions and battery supplier channel encroachment into account. We investigate optimal prices, collected quantities and predicted revenues under various channel encroachment and subsidy decision. It analyzes the effects of channel costs and subsidy levels on predicted revenues and social welfare. We discover that when the channel encroachment is under a particular threshold, it can accomplish a "win–win." Both the channel encroachment and subsidy strategies are conducive to promoting battery recycling, where the channel cost and the subsidy level are key factors affecting enterprise profits and social welfare. And high subsidies are always conducive to battery recycling, but this will undoubtedly bring severe fiscal stress to the government. In addition, if the government's goal is to reduce environmental impacts and subsidies, the government will adopt a subsidy strategy to reduce environmental pollution when the recycling revenue is significantly small. Otherwise, the government will not provide subsidies. Furthermore, we further examine the equilibrium decisions of enterprises and governments under risk-averse conditions to demonstrate the robustness of the results. [ABSTRACT FROM AUTHOR]

Under the background of the green maritime transportation, green investment and vertical alliances between port and shipping enterprises are effective ways to reduce maritime emissions. In this paper, we consider a maritime supply chain consisting of a port, a shipping company, and a forwarder. The port and shipping company determine individual green investment to reduce emission pollution. There are three vertical alliance strategies for the shipping company under green investment: no alliance, alliance with the port, and alliance with the forwarder. We obtain the optimal alliance strategy under the same green investment entity and the optimal choice for the investment entity under the same alliance strategy. In addition, we analyze the impacts of different alliance strategies and investment entities on consumer surplus and social welfare. The results show that whether the port implements the green investment or the shipping company implements green investment, when all three alliance strategies are feasible, there is always a higher green investment level, a higher demand, and a lower shipping service charge, and alliance strategies lead to greater profits for the maritime supply chain. Under the same alliance strategy, the choice of investment entity is affected by the green investment cost coefficient. If the green investment cost coefficient of the investor is too high, then the enterprise's green investment cannot improve the maritime supply chain profit. Therefore, port and shipping enterprises should reasonably set green input according to their own conditions to maximize the profit of maritime supply chain. Vertical alliances can improve environmental performance as well as increase consumer surplus and social welfare. In particular, under the shipping company green investment, alliance between the shipping company and downstream forwarder can precisely grasp the market demand and achieve the optimal social welfare. [ABSTRACT FROM AUTHOR]

Green financing is an effective means to encourage small and medium-sized enterprises (SMEs) to improve environmental efficiency in their operations. This paper studies two financing strategies of a carbon-dependent manufacturer in an e-commerce supply chain, which are called bank credit and cost-sharing with third-party platform that provides a marketplace. The optimal carbon emission reduction (CER) level, selling price, and service level are investigated. It turns out that the participants' profits and environmental benefit under two financing strategies are higher than those without financing. In addition, when the commission provided by the platform is low, the manufacturer is more inclined to bank credit, and when the commission is high, it is more sensible to share CER cost with the platform. The impact of government service supervision policies on corporate decision-making is further explored. The results prove that setting an appropriate service threshold and reward-penalty factor is not only conducive to incentivizing the platform to improve service level but also beneficial to the environment and overall social welfare. This paper provides cooperation strategies for manufacturers in green financing in the e-commerce supply chain and provides policy recommendations for the government to implement e-commerce service regulation and promote CER. [ABSTRACT FROM AUTHOR]

Considering the adverse impacts of pollutant emissions from port areas on the environment, an analytical model is developed to investigate optimal decisions for two port-based supply chains with or without governmental pollution tax. When the governmental pollution tax is introduced, the impacts of local governments independently determining pollution tax and jointly determining pollution tax on the environment and transport chains are investigated, respectively. The results show that the enterprises will not pay attention to the pollution if the governmental pollution tax is not introduced, which will result in the higher pollution level than the optimal level. It is interesting to note that negative pollution tax (i.e., subsidies) is more likely to occur when local governments set pollution tax separately. When local governments cooperate with each other to determine pollution tax, the pollution spillover problem can be solved, and optimal social welfare can be achieved. Thus, cooperation between local governments is more effective. Furthermore, a numerical example is given to analyze the influences of the local pollution damage coefficient and the spillover pollution damage coefficient on the optimal strategies of all participants. [ABSTRACT FROM AUTHOR]

The development of sharing economy has effectively changed the gap between market participants and promoted the emergence of new business modes, which has also brought enlightenment to the operation of shipping e-commerce. In this paper, we develop a liner shipping system consisting of one ship space booking platform and two Non-Vessel Operating Common Carriers (NVOCCs). Under two rental modes proposed by platform, the NVOCCs separately determine the order quantity of ship spaces and then consider whether to share the remaining idle ship spaces on the platform before the start of voyage. Introducing multi-party game theory, the optimal sharing strategy and ship space rental mode are obtained. The results reveal that both NVOCCs choosing sharing strategy will achieve a win–win situation, which is also beneficial for the platform. Furthermore, we find the most appropriate operation mode of the platform is to provide differentiated rentals, and this choice is independent of NVOCCs' sharing strategies. The differential rentals mode is also more beneficial to the NVOCC with larger potential demand, but adverse for the NVOCC with less potential demand, so the latter is more inclined to share remaining spaces under the same rental mode. We also extend the model to multiple NVOCCs and present numerical analysis to verify the validity of the conclusions. [ABSTRACT FROM AUTHOR]

Considering the influence of carbon emissions trading, the fuzzy stochastic programming model was established to cut back the total cost of carbon trading balance. Modeling this chain is carried out by accounting for carbon cap-and-trade considerations and total cost optimization. In this paper, we analyze the low-carbon integrated forward/reverse logistics network and made relevant simulation tests. The results show that the changes of the confidence level and carbon emission limits have obvious influences on logistics costs. If the emission limit is large, carbon trading mechanism has little effect on the total logistics cost in the same scenario. Therefore, the government needs to use the appropriate emission limits to guide enterprises to reduce carbon emissions, and enterprises can make coping strategies according to the different limit at the same time. Therefore, the fuzzy random programming model proposed in this paper is practical. Its decision making applying the proposed algorithm is reasonable and applicable and could provide decision basis for enterprise managers. [ABSTRACT FROM AUTHOR]

Under the environment of technological spillover, carbon abatement investment has become one of key factors on cutting reducing carbon emission, which includes production costs in the components and products. Based on demand with price elastic, we study a dyadic supply chain consisting of a retailer and a manufacturer to explore a two-echelon Stackelberg model for obtaining the optimal decisions of decentralized and centralized supply chain within the dominated manufacturer. With the coordination contract through revenue-cost sharing, setting the decentralized profits of players as the disagreement points, the manufacturer and the retailer can achieve the goal of centralized scenario, which can promote the members to increase the carbon abatement investment and decrease the retail pricing. Finally, by theoretical comparison and numerical analysis, the results show that technological spillovers amplify the impact of 'free-ride' behavior, which the supplier always has incentives to reduce carbon emission, but the cooperation of players will achieve as well as improves the profits only when technological spillovers are large. [ABSTRACT FROM AUTHOR]

Graph convolutional network is apt for feature extraction in terms of non-Euclidian human skeleton data, but its adjacency matrix is fixed and the receptive field is small, which results in bias representation for skeleton intrinsic information. In addition, the operation of mean pooling on spatio-temporal features in classification layer will result in losing information and degrade recognition accuracy. To this end, the Decoupled Adaptive Graph Convolutional Network (DAGCN) is proposed. Specifically, a multi-level adaptive adjacency matrix is designed, which can dynamically obtain the rich correlation information among the skeleton nodes by a non-local adaptive algorithm. Whereafter, a new Residual Multi-scale Temporal Convolution Network (RMTCN) is proposed to fully extract temporal feature of the above decoupled skeleton dada. For the second problem in classification, we decompose the spatio-temporal features into three parts as spatial, temporal, spatio-temporal information, they are averagely pooled respectively, and added together for classification, denoted as STMP (spatio-temporal mean pooling) module. Experimental results show that our algorithm achieves accuracy of 96.5%, 90.6%, 96.4% on NTU-RGB+D60, NTU-RGB+D120 and NW-UCLA data sets respectively. [ABSTRACT FROM AUTHOR]