2019 IEEE 23rd International Conference on Computer Supported Cooperative Work in Design (CSCWD) 2019
DOI: 10.1109/cscwd.2019.8791907
|View full text |Cite
|
Sign up to set email alerts
|

A Collaborative Feature Learning Method for Accurate and Robust Tracking

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2022
2022
2022
2022

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 21 publications
0
2
0
Order By: Relevance
“…is result demonstrates that it is the collaborative representation that plays an important role in the effectiveness of SRC. (4) e matrix-based methods usually surpass the vector-based methods (e.g., NMRP and our SMEDP method, which make use of the structural information outperform SPP). Notably, they enhance the performance of intraclass clustering.…”
Section: Experiments On Coil-20 Objectmentioning
confidence: 94%
See 1 more Smart Citation
“…is result demonstrates that it is the collaborative representation that plays an important role in the effectiveness of SRC. (4) e matrix-based methods usually surpass the vector-based methods (e.g., NMRP and our SMEDP method, which make use of the structural information outperform SPP). Notably, they enhance the performance of intraclass clustering.…”
Section: Experiments On Coil-20 Objectmentioning
confidence: 94%
“…Big data analytics as the premise and the foundation of arti cial intelligence can easily cause the problem of "curse of dimensionality" [1], high storage cost, and heavy computation burden [2]. How to deal with such high-dimensional data is always a vital issue in many applications, including machine intelligence, data mining, pattern recognition, and image processing [3][4][5]. Feature extraction can e ectively solve the above problems by reducing the size of a data set while preserving relevant information.…”
Section: Introductionmentioning
confidence: 99%