English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Many RGB-T trackers attempt to attain robust feature representation byutilizing an adaptive weighting scheme (or attention mechanism). Different fromthese works, we propose a new dynamic modality-aware filter generation module(named MFGNet) to boost the message communication between visible and thermaldata by adaptively adjusting the convolutional kernels for various input imagesin practical tracking. Given the image pairs as input, we first encode theirfeatures with the backbone network. Then, we concatenate these feature maps andgenerate dynamic modality-aware filters with two independent networks. Thevisible and thermal filters will be used to conduct a dynamic convolutionaloperation on their corresponding input feature maps respectively. Inspired byresidual connection, both the generated visible and thermal feature maps willbe summarized with input feature maps. The augmented feature maps will be fedinto the RoI align module to generate instance-level features for subsequentclassification. To address issues caused by heavy occlusion, fast motion andout-of-view, we propose to conduct a joint local and global search byexploiting a new direction-aware target driven attention mechanism. The spatialand temporal recurrent neural network is used to capture the direction-awarecontext for accurate global attention prediction. Extensive experiments onthree large-scale RGB-T tracking benchmark datasets validated the effectivenessof our proposed algorithm. The source code of this paper is available at\textcolor{magenta}{\url{https://github.com/wangxiao5791509/MFG_RGBT_Tracking_PyTorch}}.

MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking