Visible and Infrared Object Tracking via Convolution-Transformer Network With Joint Multimodal Feature Learning
Jiazhu Qiu, Rui Yao, Yong Zheng Zhou, Peng Wang, Yanning Zhang, Hancheng Zhu · IEEE Geoscience and Remote Sensing Letters · 2023
The existing Transformer-based RGBT tracker mainly focus on the enhancement of features extracted by Convolutional Neural Network (CNN). The potential of Transformer in representation learning remains under-explored. In this paper, we propose a Convolution-Transformer network with joint multimodal feature learning, in which both representation learning and feature fusion leverage Transformer. Specifically, we use the multi-branch Convolution-Transformer feature extraction network to process the extraction task of local modality-independent features and global modality-shared features respectively. Several simplified Transformer encoder layers form the Transformer backbone network, which is more suitable for the real-time object tracking. Besides, we found that inter-modality correlation is an important factor for modality interactions and mutual exploitation. Therefore, we propose a Joint Multimodal Feature Learning (JMFL) module, which uses cross-attention to capture the dependencies of cross-modal and enhance multimodal fusion by bidirectional guidance of multimodal information. The proposed method is fully experimented on two large benchmark datasets and compared with some current well-performing methods. The experimental results show that the proposed method performs well in terms of tracking accuracy and speed.