Non-sparse linear representations for visual tracking with online reservoir metric learning

Li, Xi; Shen, Chunhua; Shi, Qinfeng; Dick, Anthony; Hengel, Anton van den

doi:10.1109/cvpr.2012.6247872

Cited by 20 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Performance evaluations of representative generative [1–30], discriminative [31–65] and combined methods [66–75] are summarised, and the results are shown in Tables 9 and 10. In visual tracking field, according to most literatures, the number of successfully tracked frames and the average position errors is commonly used as evaluation standards to quantitatively evaluate tracking performance.…”

Section: Discussionmentioning

confidence: 99%

“…To capture information on the correlation between different feature dimensions, Li et al [64] incorporated an online metric learning into a tracking algorithm based on the non-sparse linear representation. Moreover, in order to prevent unbounded growth in the number of training samples for the metric learning, they designed a time-weighted reservoir sampling method to balance sample diversity and adaptability.…”

Section: Methods Based On Online Metric Learningmentioning

confidence: 99%

See 1 more Smart Citation

Survey of single‐target visual tracking methods based on online learning

Liu

Zhao

Hou

2014

IET Computer Vision

View full text Add to dashboard Cite

Visual tracking is a popular and challenging topic in computer vision and robotics. Owing to changes in the appearance of the target and complicated variations that may occur in various scenes, online learning scheme is necessary for advanced visual tracking framework to adopt. This paper briefly introduces the challenges and applications of visual tracking and focuses on discussing the state‐of‐the‐art online‐learning‐based tracking methods by category. We provide detail descriptions of representative methods in each category, and examine their pros and cons. Moreover, several most representative algorithms are implemented to provide quantitative reference. At last, we outline several trends for future visual tracking research.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methods Based On Online Metric Learningmentioning

confidence: 99%