Transformer meets remote sensing video detection and tracking: A comprehensive survey

L Jiao, X Zhang, X Liu, F Liu, S Yang… - IEEE Journal of …, 2023 - ieeexplore.ieee.org
Transformer has shown excellent performance in remote sensing field with long-range
modeling capabilities. Remote sensing video (RSV) moving object detection and tracking …

EANTrack: An efficient attention network for visual tracking

F Gu, J Lu, C Cai, Q Zhu, Z Ju - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Recently, Siamese trackers have gained widespread attention in visual tracking due to their
exceptional performance. However, many trackers still suffer from limitations in challenging …

Repformer: a robust shared-encoder dual-pipeline transformer for visual tracking

F Gu, J Lu, C Cai, Q Zhu, Z Ju - Neural Computing and Applications, 2023 - Springer
Siamese-based trackers have achieved outstanding tracking performance. However, these
trackers in complex scenarios struggle to adequately integrate the valuable target feature …

Glt-t: Global-local transformer voting for 3d single object tracking in point clouds

J Nie, Z He, Y Yang, M Gao, J Zhang - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Current 3D single object tracking methods are typically based on VoteNet, a 3D region
proposal network. Despite the success, using a single seed point feature as the cue for offset …

Learning spatial-frequency transformer for visual object tracking

C Tang, X Wang, Y Bai, Z Wu, J Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Recently, some researchers have begun to adopt the Transformer to combine or replace the
widely used ResNet as their new backbone network. As the Transformer captures the long …

Learning localization-aware target confidence for siamese visual tracking

J Nie, Z He, Y Yang, M Gao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Siamese tracking paradigm has achieved great success, providing effective appearance
discrimination and size estimation by classification and regression. While such a paradigm …

Memory network with pixel-level spatio-temporal learning for visual object tracking

Z Zhou, X Zhou, Z Chen, P Guo, QY Liu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Making full use of temporal and spatial information is critical to cope with the appearance
changes of objects in visual object tracking. However, existing methods in the tracking field …

FAML-RT: Feature alignment-based multi-level similarity metric learning network for a two-stage robust tracker

J Nie, Z Dong, Z He, H Wu, M Gao - Information Sciences, 2023 - Elsevier
Existing multi-stage trackers treat visual object tracking as a multiple feature extraction and
similarity metric process. However, the similarity metric methods used in them are typically …

OSP2B: One-stage point-to-box network for 3D siamese tracking

J Nie, Z He, Y Yang, Z Bao, M Gao, J Zhang - arxiv preprint arxiv …, 2023 - arxiv.org
Two-stage point-to-box network acts as a critical role in the recent popular 3D Siamese
tracking paradigm, which first generates proposals and then predicts corresponding …

MSA-MOT: Multi-stage association for 3D multimodality multi-object tracking

Z Zhu, J Nie, H Wu, Z He, M Gao - Sensors, 2022 - mdpi.com
Three-dimensional multimodality multi-object tracking has attracted great attention due to
the use of complementary information. However, such a framework generally adopts a one …