In the neck part of a two-stage object detection network, feature fusion is generally carried out in either top-down or bottom-up manner. However, two types imbalance may exist: model and gradient region interest extraction layer due to scale changes objects. The deeper network is, more abstract learned features are, that say, semantic information can be extracted. extracted image background, s...

We address the problem of multi-modal object tracking in video and explore various options available for fusing complementary information conveyed by visible (RGB) thermal infrared (TIR) modalities, including pixel-level, feature-level decision-level fusion. Specifically, contrast to existing approaches, we propose develop paradigm combining image fusion at pixel level. At feature level, two di...

Recently, existing FCNs-based methods have shown their advantages in processing object boundaries. However, these still suffer from false interference, which appears saliency predictions. To solve this problem, an edge-interior feature fusion (EIFF) framework is proposed, consists of internal-boundary decoupled generation structure with receptive field enlargement and attention mechanism enhanc...

While many RGB-based saliency detection algorithms have recently shown the capability of segmenting salient objects from an image, they still suffer unsatisfactory performance when dealing with complex scenarios, insufficient illumination or occluded appearances. To overcome this problem, article studies RGB-T detection, where we take advantage thermal modality's robustness against and occlusio...

The task of classifying small objects is still challenging for current deep learning classification models [such as convolutional neural networks (CNNs) and vision transformers (ViTs)]. We believe that these algorithms are not designed specifically targets, so their feature extraction abilities targets insufficient. To improve the capabilities CNN-based ViT-based objects, two multidomain fusion...