Hierarchical memory-guided long-term tracking with meta transformer inquiry network

X Wang, G Nie, B Li, Y Zhao, M Kang, B Liu - Knowledge-Based Systems, 2023 - Elsevier
Long-term tracking is a critical and rapidly develo** field in visual object tracking research.
The tracking target's appearance can change over time due to its motion or environmental …

Residual memory inference network for regression tracking with weighted gradient harmonized loss

H Zhang, J Zhang, G Nie, J Hu, WJC Zhang - Information Sciences, 2022 - Elsevier
Recently, the memory mechanism has been widely implemented in target tracking.
However, these trackers hardly balance the stability of long-term memory with the plasticity …

Temporal relation transformer for robust visual tracking with dual-memory learning

G Nie, X Wang, Z Yan, X Xu, B Liu - Applied Soft Computing, 2024 - Elsevier
Recently, transformer trackers mostly associate multiple reference images with the search
area to adapt to the changing appearance of the target. However, they ignore the learned …

Learning soft mask based feature fusion with channel and spatial attention for robust visual object tracking

M Fiaz, A Mahmood, SK Jung - Sensors, 2020 - mdpi.com
We propose to improve the visual object tracking by introducing a soft mask based low-level
feature fusion technique. The proposed technique is further strengthened by integrating …

DMV: visual object tracking via part-level dense memory and voting-based retrieval

G Nam, SW Oh, JY Lee, SJ Kim - arxiv preprint arxiv:2003.09171, 2020 - arxiv.org
We propose a novel memory-based tracker via part-level dense memory and voting-based
retrieval, called DMV. Since deep learning techniques have been introduced to the tracking …

[CITAZIONE][C] Task-Adaptive Meta-Learning for Few-Shot Learning

백성용 - 2022 - 서울대학교 대학원