How to perform effective information fusion of different modalities is a core
factor in boosting the performance of RGBT tracking. This paper presents a
novel deep fusion algorithm based on the representations from an end-to-end
trained convolutional neural network. To deploy the complementarity of features
of all layers, we propose a recursive strategy to densely aggregate these
features that yield robust representations of target objects in each modality.
In different modalities, we propose to prune the densely aggregated features of
all modalities in a collaborative way. In a specific, we employ the operations
of global average pooling and weighted random selection to perform channel
scoring and selection, which could remove redundant and noisy features to
achieve more robust feature representation. Experimental results on two RGBT
tracking benchmark datasets suggest that our tracker achieves clear
state-of-the-art against other RGB and RGBT tracking methods.

本文提出一种基于深度融合和递归策略的算法用于多模态追踪，该算法利用端到端训练的卷积神经网络的特征表示强化在所有模态中的物体表示，采用全局平均池化和加权随机选择分数进行通道评分和选择，并通过剪枝去除冗余和噪声特征以实现更强的特征表示。在两个 RGBT 追踪基准数据集上的实验结果表明，该算法在 RGB 和 RGBT 追踪方法中实现了明显的最新技术水平。