In recent years, Transformer has been widely used in the crossing task of computer vision (CV) and natural language processing (NLP), e.g., image captioning. The prior works of image captioning based on Transformer have achieved remarkable ...

Display Omitted

Image captioning is a task that involves understanding scenes by combining computer vision (CV) and natural language processing (NLP). While many advanced image captioning models only focus on extracting visual features for sentence generation, ...

Achieving precise semantic segmentation for traffic scenes relies on adopting multi-spectral image fusion techniques to attain high-quality images. Many existing fusion solutions often aim to enhance the similarity between the input and fusion ...

The discriminative correlation filter (DCF) is commonly used in aerial object tracking due to its high tracking accuracy and computing speed. However, when similar object disturbances emerge in the background, the response map will generate sub-...

• Proposing a novel correlation filter algorithm for real-time UAV tracking.
• Suggesting a novel strategy to accurately suppress the spatial disturbance.
• Presenting an object saliency-aware strategy to focus more on the tracked ...

Lower resolution and fewer feature details appear in small objects, so achieving small object detection is a challenging task. To improve the detection ability in the case of low-resolution object details, we propose to exploit 3D features with ...

• We propose a GS-Block based on 3D features in the network for extracting shallow features that can accurately capture the spatial relationship between the context and the objects of interest while effectively exploiting the appearance ...

The capturing of images with poor exposures remains a major source of errors in camera-based photography. Under- or over-exposure problems greatly reduce contrast and naturalness, and the disappearance of detailed content affects the ...

In the past few years, self-attention in Transformer has been widely used in natural language processing (NLP) and computer vision (CV) due to its excellent ability to capture global information, especially in image captioning, where the use of self-...

• Discussing limitations of IoU-based and center-point assignment strategies and revealing their inconsistencies in the open world.
• Weight IoU score with the normalized center-distance for better alignment of anchor-object named the ...

Recent CNN-based methods for object detection largely focus on training the backbone of the object detector, neglecting the key part of selecting positive/negative samples. Instead, based on our analyses about the limitations and inconsistency of ...

To enhance the expression ability of deep features and improve the tracking performance of the fully convolutional siamese network (SiamFC) in the UAV scene, we propose a UAV visual tracking algorithm based on feature fusion of the attention mechanism. ...

To improve the feature representation ability of the YOLOX algorithm and obtain better detection performance, an object detection algorithm based on second-order pooling network and gaussian mixture attention is proposed. Firstly, the second-order ...

Discriminative correlation filters (DCFs) have shown promising tracking performance in recent years thanks to the powerful representation ability of deep features. However, a large number of target‐irrelevant channels in deep features limits the ...

In this paper, a novel transverse-flux machine with dual-tooth-slot core configuration is proposed for direct-drive applications, which is characterized by high-torque density and high utilization rate of motor space. Firstly, the structure and working ...

In this paper, a novel linear double-side permanent magnet vernier motor(LPMVM) is proposed. The advantages of high thrust density, low thrust ripple, normal force elimination and stable structure are introduced in detail. The novelty of the proposed ...

In this paper, a dual-side excited transverse flux permanent magnet linear machine was investigated. In consideration of the doubly salient structure caused by the primary and secondary cores, the permeance distribution in the air gap is established ...

To investigate the relationship between waiting duration and cyclist violation, cyclists' street-crossing behavior was examined by modeling the waiting duration at signalized intersections. Violation waiting duration was collected by video cameras and ...