2023/07/09 by Zhiyu Zhu, Junhui Hou, Zhu, Zhiyu +3 · 3 citations
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Optical Imaging and Spectroscopy Techniques #Video Surveillance and Tracking Methods #Visual Attention and Saliency Detection
paper · pdf · doi:10.48550/arxiv.2307.04129
openalex publication_date 2023/07/09 · openalex created_date 2023/07/13 · openalex updated_date 2026/07/28
This paper addresses the problem of cross-modal object tracking from RGB videos and event data. Rather than constructing a complex cross-modal fusion network, we explore the great potential of a pre-trained vision Transformer (ViT). Particularly, we delicately investigate plug-and-play training augmentations that encourage the ViT to bridge the vast distribution gap between the two modalities, enabling comprehensive cross-modal information interaction and thus enhancing its ability. Specifically, we propose a mask modeling strategy that randomly masks a specific modality of some tokens to enforce the interaction between tokens from different modalities interacting proactively. To mitigate network oscillations resulting from the masking strategy and further amplify its positive effect, we then theoretically propose an orthogonal high-rank loss to regularize the attention matrix. Extensive experiments demonstrate that our plug-and-play training augmentation techniques can significantly boost state-of-the-art one-stream and twostream trackers to a large extent in terms of both tracking precision and success rate. Our new perspective and findings will potentially bring insights to the field of leveraging powerful pre-trained ViTs to model cross-modal data. The code will be publicly available.