2020
DOI: 10.1007/978-981-15-4818-5_13
|View full text |Cite
|
Sign up to set email alerts
|

Adaptive Feature Selection Siamese Networks for Visual Tracking

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
3
3

Relationship

3
3

Authors

Journals

citations
Cited by 6 publications
(6 citation statements)
references
References 38 publications
0
6
0
Order By: Relevance
“…This mechanism is widely used in several fields of computer vision, including image classification [16], object detection [27], segmentation [28], and person reidentification [29]. Similarly, visual tracking frameworks [10,11,[13][14][15] adopt attention mechanisms to highlight the target features. This technique enables the model to handle challenges in tracking.…”
Section: Tracking With Attention Networkmentioning
confidence: 99%
See 1 more Smart Citation
“…This mechanism is widely used in several fields of computer vision, including image classification [16], object detection [27], segmentation [28], and person reidentification [29]. Similarly, visual tracking frameworks [10,11,[13][14][15] adopt attention mechanisms to highlight the target features. This technique enables the model to handle challenges in tracking.…”
Section: Tracking With Attention Networkmentioning
confidence: 99%
“…However, techniques relying on template matching using metric learning extract the target template and choose the most similar candidate patch at the current frame. Siamese-based trackers [9][10][11][12][13][14][15] follow the template-matching strategy, which uses cross-correlation to reduce computational overhead and solve the tracking problem effectively. Siamese-based tracker, SiamFC [9], gains immense popularity to the tracking community.…”
Section: Introductionmentioning
confidence: 99%
“…CSRDCF [ 48 ] constructs a unique spatial reliability map to impose constraints on correlation filters within a correlation tracking framework. AFS-Siam [ 49 ] selects the discriminative kernels from different convolutional layers. Choi et al [ 24 ] proposed ACFN and used spatial attention to select a subset of correlation filters for visual object tracking.…”
Section: Related Workmentioning
confidence: 99%
“…It uses cross-correlation to match the template patch with the current frame of the video, which utilizes fewer operations and increases the network computational power. Due to its efficient computational ability, several trackers [11][12][13][14][15] are developed recently to solve the tracking problems using the Siamese network. However, they suffer a lack of robustness to handle challenging sequences, particularly background clutter, occlusion, and appearance changes because of offline training on the large dataset without considering the most discriminative features that reduce the performances.…”
Section: Introductionmentioning
confidence: 99%