Hierarchical memory-guided long-term tracking with meta transformer inquiry network
Long-term tracking is a critical and rapidly developing field in visual object tracking research. The tracking target’s appearance can change over time due to its motion or environmental factors, resulting in various appearance patterns. Those factors, such as dense distractors, confusing background...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8227 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-9230 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-92302023-10-13T09:18:03Z Hierarchical memory-guided long-term tracking with meta transformer inquiry network WANG, Xingmei NIE, Guohao LI, Boquan ZHAO, Yilin KANG, Minyang LIU, Bo Long-term tracking is a critical and rapidly developing field in visual object tracking research. The tracking target’s appearance can change over time due to its motion or environmental factors, resulting in various appearance patterns. Those factors, such as dense distractors, confusing backgrounds, and motion blurs, make it difficult to track objects. Existing tracking algorithms typically rely on online learning to adapt to such long-term variations. However, obtaining reliable training samples and implementing effective updating schemes can be difficult, particularly when the target object frequently disappears and reappears. Therefore, in this paper, we propose a Hierarchical Memory-guided Long-term Tracker (HMLT) with a Meta Transformer Inquiry Network (MTIN) that refines online learning. Our method introduces a hierarchical memory strategy that considers simple and trustworthy updating of long-term tracking components using multiple target memories. We also devise MTIN to identify available memory based on the long-term variation pattern of the target, so as to avoid the risk of updating from incorrect samples. In addition, we devise a memory attention network to perform robust redetection based on long-term memory. Based on the hierarchical memory strategy, we construct a complete and learnable long-term tracking framework that uses a validator learned from memory to reconcile local and global searches. Our experimental results on several benchmarks, including LaSOT, VOT-LT2018, VOT-LT2019, TLP, OTB-2015, and UAV123, demonstrate that our proposed method achieves comparable performance to the state-of-the-art long-term tracking algorithms. 2023-06-07T07:00:00Z text https://ink.library.smu.edu.sg/sis_research/8227 info:doi/10.1016/j.knosys.2023.110504 Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University visual tracking long-term tracking memory tracking transformer meta-learning Artificial Intelligence and Robotics |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
visual tracking long-term tracking memory tracking transformer meta-learning Artificial Intelligence and Robotics |
spellingShingle |
visual tracking long-term tracking memory tracking transformer meta-learning Artificial Intelligence and Robotics WANG, Xingmei NIE, Guohao LI, Boquan ZHAO, Yilin KANG, Minyang LIU, Bo Hierarchical memory-guided long-term tracking with meta transformer inquiry network |
description |
Long-term tracking is a critical and rapidly developing field in visual object tracking research. The tracking target’s appearance can change over time due to its motion or environmental factors, resulting in various appearance patterns. Those factors, such as dense distractors, confusing backgrounds, and motion blurs, make it difficult to track objects. Existing tracking algorithms typically rely on online learning to adapt to such long-term variations. However, obtaining reliable training samples and implementing effective updating schemes can be difficult, particularly when the target object frequently disappears and reappears. Therefore, in this paper, we propose a Hierarchical Memory-guided Long-term Tracker (HMLT) with a Meta Transformer Inquiry Network (MTIN) that refines online learning. Our method introduces a hierarchical memory strategy that considers simple and trustworthy updating of long-term tracking components using multiple target memories. We also devise MTIN to identify available memory based on the long-term variation pattern of the target, so as to avoid the risk of updating from incorrect samples. In addition, we devise a memory attention network to perform robust redetection based on long-term memory. Based on the hierarchical memory strategy, we construct a complete and learnable long-term tracking framework that uses a validator learned from memory to reconcile local and global searches. Our experimental results on several benchmarks, including LaSOT, VOT-LT2018, VOT-LT2019, TLP, OTB-2015, and UAV123, demonstrate that our proposed method achieves comparable performance to the state-of-the-art long-term tracking algorithms. |
format |
text |
author |
WANG, Xingmei NIE, Guohao LI, Boquan ZHAO, Yilin KANG, Minyang LIU, Bo |
author_facet |
WANG, Xingmei NIE, Guohao LI, Boquan ZHAO, Yilin KANG, Minyang LIU, Bo |
author_sort |
WANG, Xingmei |
title |
Hierarchical memory-guided long-term tracking with meta transformer inquiry network |
title_short |
Hierarchical memory-guided long-term tracking with meta transformer inquiry network |
title_full |
Hierarchical memory-guided long-term tracking with meta transformer inquiry network |
title_fullStr |
Hierarchical memory-guided long-term tracking with meta transformer inquiry network |
title_full_unstemmed |
Hierarchical memory-guided long-term tracking with meta transformer inquiry network |
title_sort |
hierarchical memory-guided long-term tracking with meta transformer inquiry network |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2023 |
url |
https://ink.library.smu.edu.sg/sis_research/8227 |
_version_ |
1781793937030119424 |