Learning target-aware vision transformers for real-time UAV tracking
In recent years, the field of unmanned aerial vehicle (UAV) tracking has grown rapidly,
finding numerous applications across various industries. While the discriminative correlation …
finding numerous applications across various industries. While the discriminative correlation …
Enhancing small object tracking with reversible rescaling networks
Y Zha, X Guo, F Li, H Li - Image and Vision Computing, 2024 - Elsevier
In the rapidly evolving domain of visual tracking, the accurate identification and tracking of
small objects pose significant challenges due to their minimal pixel presence and detail …
small objects pose significant challenges due to their minimal pixel presence and detail …
Enhancing UAV tracking: a focus on discriminative representations using contrastive instances
Addressing the core challenges of achieving both high efficiency and precision in UAV
tracking is crucial due to limitations in computing resources, battery capacity, and maximum …
tracking is crucial due to limitations in computing resources, battery capacity, and maximum …
Efficient Template Distinction Modeling Tracker with Temporal Contexts for Aerial Tracking
H Zhang, W Xing, H Lin, H Liu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
In recent years, trackers based on neural networks have demonstrated excellent tracking
performance. Compared to general tracking tasks, aerial tracking tasks require more …
performance. Compared to general tracking tasks, aerial tracking tasks require more …
Learning motion blur robust vision transformers with dynamic early exit for real-time UAV tracking
Recently, the surge in the adoption of single-stream architectures utilizing pre-trained ViT
backbones represents a promising advancement in the field of generic visual tracking. By …
backbones represents a promising advancement in the field of generic visual tracking. By …
BSTrack: Robust UAV tracking using feature extraction of bilateral filters and sparse attention mechanism
K Wang, Z Wang, X Zhang, M Liu - Expert Systems with Applications, 2025 - Elsevier
In UAV tracking tasks, detailed object information and key features are critical for enhancing
tracking performance. The AlexNet feature extraction network relies predominantly on …
tracking performance. The AlexNet feature extraction network relies predominantly on …
Learning Adaptive and View-Invariant Vision Transformer with Multi-Teacher Knowledge Distillation for Real-Time UAV Tracking
Y Wu, Y Li, M Liu, X Wang, X Yang, H Ye… - arXiv preprint arXiv …, 2024 - arxiv.org
Visual tracking has made significant strides due to the adoption of transformer-based
models. Most state-of-the-art trackers struggle to meet real-time processing demands on …
models. Most state-of-the-art trackers struggle to meet real-time processing demands on …
Spatio-Temporal Feature Aware Vision Transformers for Real-Time Unmanned Aerial Vehicle Tracking
H Zhang, H Ye, X Guo, X Zhang, Y Rong, S Li - Drones, 2025 - mdpi.com
Driven by the rapid advancement of Unmanned Aerial Vehicle (UAV) technology, the field of
UAV object tracking has witnessed significant progress. This study introduces an innovative …
UAV object tracking has witnessed significant progress. This study introduces an innovative …
Learning Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking
Harnessing transformer-based models, visual tracking has made substantial strides.
However, the sluggish performance of current trackers limits their practicality on devices with …
However, the sluggish performance of current trackers limits their practicality on devices with …