The field of remote sensing information processing places significant research emphasis on object detection (OD) in high-spatial-resolution remote sensing images (HSRIs). The OD task in HSRIs poses additional challenges compared to conventional natural images. These challenges include variations in object scales, complex backgrounds, dense arrangement, and uncertain orientations. These factors contribute to the increased difficulty of OD in HSRIs as compared to conventional images. To tackle the aforementioned challenges, this paper introduces an innovative OD algorithm that builds upon enhancements made to the YOLOv5 framework. The incorporation of RepConv, Transformer Encoder, and BiFPN modules into the original YOLOv5 network leads to improved detection accuracy, particularly for objects of varying scales. The C3GAM module is designed by introducing the GAM attention mechanism to address the interference caused by complex background regions. To achieve precise localization of densely arranged objects, the SIoU loss function is integrated into YOLOv5. The circular smooth label method is used to detect objects with uncertain directions. The effectiveness of the suggested algorithm is confirmed through its application to two commonly utilized datasets, specifically HRSC2016 and UCAS-AOD. The average detection accuracies achieved on these datasets are 90.29% and 90.06% respectively, surpassing the performance of other compared OD algorithms for HSRIs.

During feature-level data fusion in 3D object detection, the correlation between different modal data is destroyed by the misalignment problem, which leads to inaccurate localization of small targets at long distances. For the problem, a Transformer Fusion Information Enhancement Network(TFIENet) is proposed. Firstly, the original point cloud and color images are taken as input. Besides, the standard backbone network of feature extraction is passed to obtain LiDAR point cloud features and image features, respectively. Secondly, a region proposal network of Transformer dual-fusion feature is designed, which uses a deformable Transformer-decoder to double fuse the extracted LiDAR point cloud features and image features based on a deformed attention mechanism. Moreover, the dual domain feature information of LiDAR camera is aggregated to generate the initial candidate frames. Then, the enhancement module of feature information is used to further refine the frame, which predicts the dense depth feature information using a depth complementation mechanism. The corresponding dense depth information and feature semantic information are extracted to complete the box refinement. Finally, for aligning and fusing feature information from different modalities effectively, a multimodal feature cross-attention module is designed. Moreover, a dynamic cross-attention mechanism is applied to obtain the correlation between different modalities. Experimental results on the KITTI, NuScenes and Waymo datasets demonstrate the generality and effectiveness of the proposed TFIENet method. Extensive ablation experiments demonstrate the efficiency of each individual modules. Experimental results on a real road dataset show that the TFIENet algorithm has strong robustness in complex real road environments.

This paper proposes a new classification method for spatial data by adjusting prior class probabilities according to local spatial patterns. First, the proposed method uses a classical statistical classifier to model training data. Second, the prior class probabilities are estimated according to the local spatial pattern and the classifier for each unseen object is adapted using the estimated prior probability. Finally, each unseen object is classified using its adapted classifier. Because the new method can be coupled with both generative and discriminant statistical classifiers, it performs generally more accurately than other methods for a variety of different spatial datasets. Experimental results show that this method has a lower prediction error than statistical classifiers that take no spatial information into account. Moreover, in the experiments, the new method also outperforms spatial auto-logistic regression and Markov random field-based methods when an appropriate estimate of local prior class distribution is used.

Most recommender systems rely on user and item attributes or their interaction records to find similar neighbors for collaborative filtering. Existing methods focus on developing collaborative signals from only one type of neighbors and ignore the unique contributions of different types of neighbor views. This paper proposes a multiscale neighbor-aware attention network for collaborative filtering (MSNAN). First, attribute-view neighbor embedding is modeled to extract the features of different types of neighbors with co-occurrence attributes, and interaction-view neighbor embedding is leveraged to describe the fine-grained neighborhood behaviors of ratings. Then, a matched attention network is used to identify different contributions of multiscale neighbors and capture multiple types of collaborative signals for overcoming sparse recommendations. Finally, we make the rating prediction by a joint learning of multi-task loss and verify the positive effect of the proposed MSNAN on three datasets. Compared with traditional methods, the experimental results of the proposed MSNAN not only improve the accuracy in MAE and RMSE indexes, but also solve the problem of poor performance for recommendation in sparse data scenarios.