A Novel Multi-Scale Transformer for Object Detection in Aerial Scenes by Guanlin Lu, Xiaohui He, Qiang Wang, Faming Shao, Hongwei Wang, Jinkang Wang

“…DFCformer is mainly composed of three parts: the backbone network DMViT, which introduces deformation patch embedding and multi-scale adaptive self-attention to capture sufficient features of the objects; FRGC guides feature interaction layer by layer to break the barriers between feature layers and improve the information discrimination and processing ability of multi-scale critical features; CAIM adopts an attention mechanism to fuse multi-scale features to perform hierarchical reasoning on the relationship between different levels and fully utilize the complementary information in multi-scale features. …”
Get full text

GCMTN: Low-Overlap Point Cloud Registration Network Combining Dense Graph Convolution and Multilevel Interactive Transformer by Xuchu Wang, Yue Yuan

“…To make pointwise features more discriminative, a multilevel interaction Transformer module combining Multihead Offset Attention and Multihead Cross Attention is proposed to refine the internal features of the point cloud and perform feature interaction. To filter out the undesirable effects of outliers, an overlap prediction module containing overlap factor and matching factor is also proposed for determining the match ability of points and predicting the overlap region. …”
Get full text

Mirror complementary transformer network for RGB‐thermal salient object detection by Xiurong Jiang, Yifan Hou, Hui Tian, Lin Zhu

“…Moreover, the attention‐based feature interaction and serial multiscale dilated convolution (SDC)‐based feature fusion modules are introduced to make the two modalities complement and adjust each other flexibly. …”
Get full text

Attention-Aware Heterogeneous Graph Neural Network by Jintao Zhang, Quan Xu

“…Finally, the semantic-level neural network is proposed to extract the feature interaction relationships on different meta-paths and learn the final embedding of nodes. …”
Get full text

Fine-Grained Visual Categorization: Deep Pairwise Feature Comparison Interaction Algorithm by WANG Min, ZHAO Peng, GUO Xinping, MIN Fan

“…Secondly, a deep pairwise feature interaction mechanism is established to realize global information learning, depth comparison and depth adaptive interaction of paired depth features. …”
Get full text

Combinatorial interaction testing of software product lines: a mapping study by Sahid, Mohd Zanes, Md Sultan, Abu Bakar, Abdul Ghani, Abdul Azim, Baharom, Salmi

“…The motivation of SPL testing is to anticipate the feature interaction problem, in which the majority of the works were reported to leverage test configuration selection approach, while some employed test configuration prioritization approach. …”
Get full text

Taguchi's T-method with nearest integer-based binary bat algorithm for prediction by Marlan, Zulkifli Marlah, Jamaludin, Khairur Rijal, Ramlie, Faizir, Harudin, Nolia

“…This, however, resulted in a sub-optimal prediction accuracy due to its fixed and limited feature combination offered for evaluation and lack of higher-order feature interaction. In this paper, a swarm-based binary bat optimization algorithm with a nearest integer discretization approach is integrated with the Taguchi’s T-method. …”
Get full text

An Improved 3D-2D Convolutional Neural Network Based on Feature Optimization for Hyperspectral Image Classification by Yamei Ma, Shuangting Wang, Weibing Du, Xiaoqian Cheng

“…Then, we construct a spatial multi-scale interactive attention (SMIA) module in the spatial feature enhancement phase, which can refine the multi-scale features through the attention weights of multi-scale feature interaction, and further improve the quality of spatial features. …”
Get full text

Legal Document Similarity Matching Based on Ensemble Learning by Aman Fan, Shaoxi Wang, Yanchuan Wang

“…Furthermore, the binary classification judgment sub-network integrates sample pairs to facilitate feature interaction between text pairs during extraction. …”
Get full text

Hierarchical and Multiple-Perspective Interaction Network for Long Text Matching by Zhuozhang Zou, Zhidan Huang, Wei Yang, Longlong Pang, Chen Liang, Quangao Liu

“…Existing long text matching methods generally do not fully use the rich local features embedded in text information, and focus more on encoding long text as fixed length vectors to calculate the semantic distance, disregarding the importance of feature interaction in the text matching process. Therefore, the performance of the relevant models needs to be improved. …”
Get full text

Click-through rate prediction model integrating user interest and multi-head attention mechanism by Wei Zhang, Yahui Han, Baolin Yi, Zhaoli Zhang

“…The multi-head self-attention mechanism with residual network is then employed to get feature interaction, which enhances the degree of effect of significant characteristics on the estimation result as well as its accuracy. …”
Get full text

HP3D-V2V: High-Precision 3D Object Detection Vehicle-to-Vehicle Cooperative Perception Algorithm by Hongmei Chen, Haifeng Wang, Zilong Liu, Dongbing Gu, Wen Ye

“…In addition, we design a feature extraction network based on the fusion of voxels and PointPillars and encode it to generate BEV features, which solves the spatial feature interaction problem lacking in the PointPillars approach and enhances the semantic information of the extracted features. …”
Get full text

A Fast Attention-Guided Hierarchical Decoding Network for Real-Time Semantic Segmentation by Xuegang Hu, Jing Feng

“…In the decoder, the global attention (GA) module is used to process the feature map of the encoder, enhance the feature interaction in the channel and spatial dimensions, and enhance the ability to mine feature information. …”
Get full text

Crossed Dual-Branch U-Net for Hyperspectral Image Super-Resolution by Jingyi Zhang, Jianjun Liu, Jinlong Yang, Zebin Wu

“…In specific, we adopt U-Net architecture and introduce a spectral–spatial feature interaction module to capture cross-modality interaction information between two input images. …”
Get full text

A Multi-level Mesh Mutual Attention Model for Visual Question Answering by Zhi Lei, Guixian Zhang, Lijuan Wu, Kui Zhang, Rongjiao Liang

“…Therefore, how to deal with the feature interaction and multimodal feature fusion between the critical regions in the image and the keywords in the question is an important issue. …”
Get full text

CGR-Block: Correlated Feature Extractor and Geometric Feature Fusion for Point Cloud Analysis by Fan Wang, Yingxiang Zhao, Gang Shi, Qing Cui, Tengfei Cao, Xian Jiang, Yongjie Hou, Rujun Zhuang, Yunfei Mei

“…However, previous networks failed to simultaneously extract inter-feature interaction and geometric information. In this paper, we propose a novel point cloud analysis module, CGR-block, which mainly uses two units to learn point cloud features: correlated feature extractor and geometric feature fusion. …”
Get full text

DOPNet: Achieving Accurate and Efficient Point Cloud Registration Based on Deep Learning and Multi-Level Features by Rongbin Yi, Jinlong Li, Lin Luo, Yu Zhang, Xiaorong Gao, Jianqiang Guo

“…To enhance the information interaction between the two branches, the feature interaction module is inserted into the feature extraction pipeline to implement early data association. …”
Get full text

DSGEM: Dual scene graph enhancement module‐based visual question answering by Boyue Wang, Yujian Ma, Xiaoyan Li, Heng Liu, Yongli Hu, Baocai Yin

“…Then, two scene graph enhancement modules are proposed to propagate the involved external and structural knowledge to explicitly guide the feature interaction between objects (nodes). Finally, the authors embed such two scene graph enhancement modules to existing VQA models to introduce the explicit relation reasoning ability. …”
Get full text

Vehicle Multi-Object Detection and Tracking Algorithm Based on Improved You Only Look Once 5s Version and DeepSORT by Thioanh Bui, Guihao Wang, Geng Wei, Qian Zeng

“…Firstly, in the detection model of YOLOv5s, the Attention-based Intra-scale Feature Interaction (AIFI) module is introduced to detect vehicles more quickly and accurately. …”
Get full text

PIDFusion: Fusing Dense LiDAR Points and Camera Images at Pixel-Instance Level for 3D Object Detection by Zheng Zhang, Ruyu Xu, Qing Tian

“…Finally, an instance-level fusion module is proposed to enhance semantic consistency through cross-modal feature interaction. Experiments show that PIDFusion is far ahead of existing 3D object detection methods, especially for small and long-range objects, with 70.8 mAP and 73.5 NDS on the nuScenes test set.…”
Get full text