The goal of RGB-Thermal (RGB-T) tracking is to utilize the synergistic and complementary strengths of RGB and TIR modalities to enhance tracking in diverse situations, with cross-modal interaction being a crucial element. Earlier methods often simply combine the features of the RGB and TIR search frames, leading to a coarse interaction that also introduced unnecessary background noise. Many other approaches sample candidate boxes from search frames and apply different fusion techniques to individual pairs of RGB and TIR boxes, which confines cross-modal interactions to local areas and results in insufficient context modeling. Additionally, mining video temporal contexts is also under-explored in RGB-T tracking. To alleviate these limitations, we propose a novel Template-Bridged Search region Interaction (TBSI) module that exploits templates as the medium to bridge the cross-modal interaction between RGB and TIR search regions by gathering and distributing target-relevant object and environment contexts. An Illumination Guided Fusion (IGF) module is designed to adaptively fuse RGB and TIR search region tokens with a global illumination factor. Furthermore, in the inference stage, we also propose an efficient Target-Preserved Template Updating (TPTU) strategy, leveraging the temporal context within video sequences to accommodate the target's appearance change. Our proposed modules are integrated into a ViT backbone for joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three popular RGB-T tracking benchmarks demonstrate our method achieves new state-of-the-art performances.

Existing pan-sharpening methods focus more on the processing of spatial domain features, which is difficult to balance for multiresolution performance, and prone to difficulties such as edge blurring or artifacts. In this paper, we propose an Attention-guided Progressive Frequency-decoupled Network, termed APFNN, to improve the performance of fused images in terms of spatial enhancement and spectral fidelity. The decoupling and fusion of the frequency-domain features are used as the main body, and the two-stage progressive network framework is built with the auxiliary correction by the spatial domain features, realizing fine-grained interactive fusion of dual-domain features. To optimize the APFNN, spatial feature characteristics processed with Cascading Interactive Attention (CIAtt) are used as guidance information, combined with the features of the high-resolution panchromatic image and low-resolution multispectral image for high-frequency and low-frequency decoupling, embedded into the residual dense module to form a new feature extraction component and perform subtle frequency feature fusion. Extensive qualitative and quantitative experiments have been conducted on a variety of datasets, verifying that the proposed APFNN outperforms state-of-the-art methods both in reduced-resolution and full-resolution image pan-sharpening.

RGB-T tracking aims to leverage the mutual enhancement and complement ability of RGB and TIR modalities for improving the tracking process in various scenarios, where cross-modal interaction is the key component. Some previous methods concatenate the RGB and TIR search region features directly to perform a coarse interaction process with redundant background noises introduced. Many other methods sample candidate boxes from search frames and conduct various fusion approaches on isolated pairs of RGB and TIR boxes, which limits the cross-modal interaction within local regions and brings about inadequate context modeling. To alleviate these limitations, we propose a novel Template-Bridged Search region Interaction (TBSI) module which exploits templates as the medium to bridge the cross-modal interaction between RGB and TIR search regions by gathering and distributing target-relevant object and environment contexts. Original templates are also updated with enriched multimodal contexts from the template medium. Our TBSI module is inserted into a ViT backbone for joint feature extraction, search-template matching, and cross-modal interaction. Extensive experiments on three popular RGB-T tracking benchmarks demonstrate our method achieves new state-of-the-art performances. Code is available at https://github.com/RyanHTR/TBSI.