A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Robust Visual Tracking via Implicit Low-Rank Constraints and Structural Color Histograms
[article]
2019
arXiv
pre-print
The experimental results on standard benchmarks demonstrate that our Implicit Low-Rank Constraints and Structural Color Histograms (ILRCSCH) tracker outperforms state-of-the-art methods. ...
To encourage temporal continuity and to explore the smooth variation of target appearance, we propose to enhance low-rank structure of the learned filters, which can be realized by constraining the successive ...
In this work, we propose Implicit Low-Rank Constraints and Structural Color Histograms (ILRCSCH), which is based on three handcrafted features (HOG, CN [17] , and Structural Color Histogram) in order ...
arXiv:1912.11343v1
fatcat:3pb25zcxibe7rct4tv7ty7l7fy
Curvilinear Structure Tracking by Low Rank Tensor Approximation with Model Propagation
2014
2014 IEEE Conference on Computer Vision and Pattern Recognition
Tracking of such anatomical structures and devices is very challenging due to large degrees of appearance changes, low visibility of X-ray images and the deformable nature of the underlying motion field ...
Specifically, the deformable tracking is formulated as a multi-dimensional assignment problem which is solved by rank-1 1 tensor approximation. ...
Low visibility and poor image quality due to a low dose of radiations in interventional imaging make the deformable tracking more difficult. ...
doi:10.1109/cvpr.2014.391
dblp:conf/cvpr/ChengPZYL14
fatcat:vmym364t5bdspfpaknv635jxlu
A Simplified Low Rank and Sparse Model for Visual Tracking
2017
Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods
Sparsity always pursues a sparse enough solution that ignores the low-rank structure and vice versa. Therefore, this paper replaces the low-rank and sparse constraints with 2,1 l norm. ...
Numerous tracking methods using low-rank and sparse constraints perform well in visual tracking. However, these methods cannot reasonably balance the two characteristics. ...
the low-rank structure of Z. ...
doi:10.5220/0006117003010308
dblp:conf/icpram/WangXLXZ17
fatcat:xedfnx5ktjc7thuusfmegomtmi
Better Feature Tracking through Subspace Constraints
2014
2014 IEEE Conference on Computer Vision and Pattern Recognition
Our approach does not require direct modeling of the structure or the motion of the scene, and runs in real time on a single CPU core. ...
While this approach works quite well when dealing with high-quality video and "strong" features, it often falters when faced with dark and noisy video containing low-quality features. ...
Low Rank Regularization Framework If we want to encourage a low rank structure in the trajectories, we cannot view the tracking of different features as separate problems. ...
doi:10.1109/cvpr.2014.441
dblp:conf/cvpr/PolingLS14
fatcat:jaiksn3ibfdtdfyujlagb23zta
Page 803 of Journal of Sedimentary Petrology Vol. 45, Issue 4
[page]
1975
Journal of Sedimentary Petrology
—Structural prisms arranged according to rank from flutes (low) to oscillation ripples (high). Each point designates an outcrop containing the structure. ...
For our pur- poses the former is referred to as low rank and latter as high rank.
As expected, the sedimentary structures show a definite relationship with lithology. ...
Background subtraction in high-contrast imaging
2020
Zenodo
• usually not a major effort if derotator can be accessed
LESSON #2: LOW-RANK APPROXIMATIONS
๏ Efficient way to disentangle rotating field from quasi-static
background features (in pupil tracking) ...
๏ Most appropriate for point sources -known to affect images
of extended sources
• self-subtraction: source partly captured in low-rank subspace
• over-subtraction: source projection onto low-rank ...
doi:10.5281/zenodo.4249860
fatcat:ceyousg2ife7xhjei3m2noiuwm
Low-Rank Representation with Graph Constraints for Robust Visual Tracking
2017
IEICE transactions on information and systems
In this paper, we propose a novel subspace representation algorithm for robust visual tracking by using low-rank representation with graph constraints (LRGC). ...
In this paper, we aim to exploit benefits from both low-rank representation and graph constraint, and deploy it to handle challenging visual tracking problems. ...
CLRST represents particles as sparse linear combinations of dictionary templates to capture the low-rank structure of data. ...
doi:10.1587/transinf.2016edp7422
fatcat:uxfvwz2kqzcfbcvvbx2of2jzca
Robust visual tracking via efficient manifold ranking with low-dimensional compressive features
2015
Pattern Recognition
Due to the outstanding ability of the manifold ranking algorithm in discovering the underlying geometrical structure of a given image database, our tracker is more robust to overcome tracking drift. ...
Meanwhile, we adopt non-adaptive random projections to preserve the structure of original image space, and a very sparse measurement matrix is used to efficiently extract low-dimensional compressive features ...
Due to a low complexity for computing the ranking function r * , we can reconstruct graph in each tracking round efficiently. ...
doi:10.1016/j.patcog.2015.03.008
fatcat:ieosuimeqrheveimktp3xb6rqq
Low-Rank Representation-Based Object Tracking Using Multitask Feature Learning with Joint Sparsity
2014
Abstract and Applied Analysis
We address object tracking problem as a multitask feature learning process based on low-rank representation of features with joint sparsity. ...
Since the proposed method attempts to perform the feature learning problem in both multitask and low-rank manner, it can not only reduce the dimension but also improve the tracking performance without ...
The low-rank sparse tracking (LRST) was proposed by representing all samples using only a few templates [17] . ...
doi:10.1155/2014/147353
fatcat:dwuh6xpzmrahpmr5ki7uzut334
Visual tracking via graph-based efficient manifold ranking with low-dimensional compressive features
2014
2014 IEEE International Conference on Multimedia and Expo (ICME)
In this paper, a novel and robust tracking method based on efficient manifold ranking is proposed. ...
Meanwhile, we adopt non-adaptive random projections to preserve the structure of original image space, and a very sparse measurement matrix is used to efficiently extract low-dimensional compressive features ...
Due to a low complexity for computing the ranking function r * , we can reconstruct graph in each tracking round efficiently. ...
doi:10.1109/icme.2014.6890194
dblp:conf/icmcs/ZhouHXFZY14
fatcat:bipafeenofbatla47sfti3gs6y
Moving Object Detection in Dynamic Environment via Weighted Low-Rank Structured Sparse RPCA and Kalman Filtering
2022
Mathematical Problems in Engineering
Besides, the weighted low-rank and structured sparse RPCA model is efficiently solved by the Alternating Direction Method of Multipliers (ADMM) optimization algorithm. ...
Therefore, a real-time MOD framework (LSRPCA_KF) is proposed for the dynamic background, where a weighted low-rank and structured sparse RPCA algorithm is used to achieve background modeling for history ...
Offline Analysis of Weighted Low-Rank and Structured Sparsity RPCA-Based Object Detection. ...
doi:10.1155/2022/7087130
doaj:8b5645a158854e57aacf5538c4416676
fatcat:qopjf5mv2re7lpclhf4lrrv3ly
Covariance tracking from sketches of rapid data streams
2015
2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Estimating and tracking the covariance matrix of high-dimensional data streams with low complexities in acquisition, storage and computation are of great interest in modern data-intensive applications. ...
In particular, we devise a discounting mechanism in the aggregation procedure to enable faster tracking when the covariance structure changes over time. ...
structures such as sparsity and low rank. ...
doi:10.1109/icassp.2015.7179017
dblp:conf/icassp/JiangC15
fatcat:lj2bjv4yqnfz5avbaymxewaifq
Robust Object Tracking via Reverse Low-Rank Sparse Learning and Fractional-Order Variation Regularization
2020
Mathematical Problems in Engineering
In this paper, we propose a novel tracking algorithm via reverse low-rank sparse learning and fractional-order variation regularization. ...
Object tracking based on low-rank sparse learning usually makes the drift phenomenon occur when the target faces severe occlusion and fast motion. ...
Low-rank constraint [1] [2] [3] [4] on the candidate particles can reflect the subspace structure feature of the object appearance. is subspace representation is robust to handle the global appearance ...
doi:10.1155/2020/8640724
fatcat:6kkkuj2mqbgvzdq2uduljocrhm
Non-Rigid Structure-From-Motion With Uniqueness Constraint and Low Rank Matrix Fitting Factorization
2014
IEEE transactions on multimedia
Index Terms Non-rigid structure-from-motion, uniqueness constraint, low rank matrix fitting, least squares estimation. ...
A framework for occluded and incomplete measured data is also proposed using low rank matrix fitting which is a robust factorization scheme for the matrix completion problem. ...
(SVD) into two low-rank matricesM 2F ×3K ,Ŝ 3K×P and is defined as, W = UΣV T = (UΣ 1 2 )(UΣ 1 2 ) =dot(M 2F ×3KŜ3K×P ), so this model eventually decomposes W as the product of two low-rank matricesM ...
doi:10.1109/tmm.2014.2308415
fatcat:f7qhbozgprbkjezvzfoymyzvpe
UCD IIRG at TREC 2011 Medical Track
2011
Text Retrieval Conference
For both these approaches query expansion and concept re-ranking are applied. ...
and developing a method to create a ranking of visits given the retrieved reports. ...
This method of calculating the relevancy score for a visit reduces the impact of very low ranking reports while maintaining the importance of those with high ranks. ...
dblp:conf/trec/CogleySDC11
fatcat:72jaaicgc5bvdlctlwr3a674ty
« Previous
Showing results 1 — 15 out of 365,297 results