Maximum weight cliques with mutex constraints for video object segmentation

Ma, Tianyang; Latecki, Longin Jan

doi:10.1109/cvpr.2012.6247735

Cited by 49 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally, graph-based approaches [15] are among the top-performing methods for the task of segmentation. In [23], authors transform the problem of video target segmentation into the task to find a maximum weight clique in a weighted region graph. Lee et al [20] introduce a method to estimate a pixel-level target segmentation based on a series of binary partitions among some key segments.…”

Section: Related Workmentioning

confidence: 99%

Multiple cues-based active contours for target contour tracking under sophisticated background

Zhao

Chen

et al. 2016

Vis Comput

View full text Add to dashboard Cite

In this paper, we propose a novel target contour tracking method under sophisticated background using the multiple cues-based active contour model. To locate the target position, a contour-based mean-shift tracker is designed which combines both color and texture information. To reduce the adverse impact of sophisticated background and also accelerate the curve motion, we propose a twolayer-based target appearance model that combines both discriminative pre-learned-based global layer and votingbased local layer. The proposed appearance model is able to extract rough target region from the complex background, which provides important target region information for our active contour model. We subsequently introduce a dynamical shape model to provide prior target shape information for more stable segmentation. To obtain accurate target boundaries, we design a new multiple cues-based active contour model which integrates with target edge, discriminative region, and shape information. The experimental results on 30 video sequences demonstrate that the proposed method outperforms other competitive contour tracking methods under various tracking environment. Electronic supplementary materialThe online version of this article (

show abstract

Section: Related Workmentioning

confidence: 99%

Multiple cues-based active contours for target contour tracking under sophisticated background

Zhao

Chen

et al. 2016

Vis Comput

View full text Add to dashboard Cite

show abstract

“…This leads to a problem of finding maximal weighted cliques in a graph, which is a tough problem (NP-Hard) and to date no known algorithm exist which can guarantee the solution quality for this problem [39]. Approaches such as [36], [29] have looked into solving clique problems using heuristic optimization techniques which have no stability guarantees for output, and are typically run many times for obtaining a usable solution. However since the diverse solution space is much smaller as compared to the clique space in the base model, we can employ global clique criterion and find solutions better than MAP in a painless manner.…”

Section: Expressing the Quality Of A Trajectorymentioning

confidence: 99%

Pose tracking by efficiently exploiting global features

Kumar¹,

Batra

2016

2016 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Typical pose tracking algorithms first obtain a set of plausible pose hypotheses in all image frames of a video and subsequently stitch compatible detections across time to form a pose-track. This approach to tracking is commonly termed tracking-by-detections, and has been very successful in other areas such as multiple object tracking, video segmentation using object proposals. Often models in this category can only incorporate local spatio-temporal evidence due to exponentially increased cost when using global information. Local spatio-temporal evidence can be ambiguous, thus leading to an inferior objective modeling. To deal with ambiguities in local information it is necessary to incorporate global information over multiple frames into a model.Based on the recent advances in generating multiple solutions from a probabilistic model, we first generate multiple plausible pose-track hypotheses, and subsequently employ a mixture of local and global features to express the quality of these solutions with high fidelity. We perform extensive experiments and competitive results across varied datasets demonstrate the robustness of our approach. Chain CRF for tracking-by-detectionsA pose estimator (detector) is used to obtain a plausible set of pose hypotheses for all frames of a video batch. A

show abstract

“…In this paper, we focus on MEWCP. Because of edge weights, MEWCP is more flexible than MCP in modeling problems arising in different fields, such as material science (Agapito et al 2016), bioinformatics (Butenko and Wilhelm 2006;Li et al 2010;Tomita, Akutsu, and Matsunaga 2011), computer vision and pattern recognition (Ma and Latecki 2012;San Segundo and Artieda 2015), robotics (San Segundo and Rodriguez-Losada 2013), and so on. Though important, MEWCP is less studied compared to MVWCP, and most existing algorithms for MVWCP cannot be directly applied to MEWCP.…”

Section: Introductionmentioning

confidence: 99%

A Fast Exact Solver with Theoretical Analysis for the Maximum Edge-Weighted Clique Problem

Liu,

Xiao,

Zhou

2024

AAAI

View full text Add to dashboard Cite

The maximum vertex-weighted clique problem (MVWCP) and the maximum edge-weighted clique problem (MEWCP) are two natural extensions of the fundamental maximum clique problem. In this paper, we systematically study MEWCP and make the following major contributions: (1) We show that MEWCP is NP-hard even when the minimum degree of the graph is n-2, in contrast to MVWCP which is polynomial-time solvable when the minimum degree of the graph is at least n-3. This result distinguishes the complexity of the two problems for the first time. (2) To address MEWCP, we develop an efficient branch-and-bound algorithm called MEWCat with both practical and theoretical performance guarantees. In practice, MEWCat utilizes a new upper bound tighter than existing ones, which allows for more efficient pruning of branches. In theory, we prove a running-time bound of O*(1.4423^n) for MEWCat, which breaks the trivial bound of O*(2^n) in the research line of practical exact MEWCP solvers for the first time. (3) Empirically, we evaluate the performance of MEWCat on various benchmark instances. The experiments demonstrate that MEWCat outperforms state-of-the-art exact solvers significantly. For instance, on 16 DIMACS graphs that the state-of-the-art solver BBEWC fails to solve within 7200 seconds, MEWCat solves all of them with an average time of less than 1000 seconds. On real-world graphs, MEWCat achieves an average speedup of over 36x.

show abstract

Maximum weight cliques with mutex constraints for video object segmentation

Cited by 49 publications

References 24 publications

Multiple cues-based active contours for target contour tracking under sophisticated background

Multiple cues-based active contours for target contour tracking under sophisticated background

Pose tracking by efficiently exploiting global features

A Fast Exact Solver with Theoretical Analysis for the Maximum Edge-Weighted Clique Problem

Contact Info

Product

Resources

About