Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

View graph of relations

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF International Conference on Computer Vision (ICCV 2023)
PublisherIEEE
Pages21988-21998
ISBN (Electronic)979-8-3503-0718-4
Publication statusPublished - Oct 2023

Conference

TitleIEEE International Conference on Computer Vision 2023 (ICCV 2023)
LocationParis Convention Center
PlaceFrance
CityParis
Period2 - 6 October 2023

Abstract

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 two-stream 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 is publicly available at https://github.com/ZHU-Zhiyu/High-Rank_RGB-Event_Tracker.

© 2023 IEEE

Citation Format(s)

Cross-modal Orthogonal High-rank Augmentation for RGB-Event Transformer-trackers. / Zhu, Zhiyu; Hou, Junhui; Wu, Dapeng Oliver.
Proceedings - 2023 IEEE/CVF International Conference on Computer Vision (ICCV 2023). IEEE, 2023. p. 21988-21998.

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review