Beyond Pairwise Shape Similarity Analysis

Kontschieder, Peter; Donoser, Michael; Bischof, Horst

doi:10.1007/978-3-642-12297-2_63

Cited by 81 publications

(79 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, to comment that if we use a context-sensitive learning approach, in particular [19] Bold entries show the best results.…”

Section: Retrieval Ratesmentioning

confidence: 99%

“…This global information is very discriminant as its results have shown. The current state-of-the-art shape retrieval is based on the analysis of the distances that these methods offer to produce other distances that increase the discriminability between different shape groups, what is called context-sensitive learning [16,17,18,19]. In general, all of these research accepts that in order to obtain a good starting point there must be a cyclic alignment, but they use 40 brute force cyclic alignment which has a O(n 3 ) computational cost (where n is the size of both sequences).…”

Section: Introductionmentioning

confidence: 99%

“…Finally, to mention that in the context-sensitive learning methods [16,17,18,19], in a shape retrieval task, for a given query shape, in a first stage we need to compute the distances over the entire database and then, based on these distances, we can obtain with these methods the 325 improved distances. Our algorithm can be used to speed up the computation of the distances in this first stage.…”

mentioning

confidence: 99%

See 2 more Smart Citations

On the dynamic time warping of cyclic sequences for shape retrieval

Palazón-González

Marzal

2012

Image and Vision Computing

View full text Add to dashboard Cite

In the last years, in shape retrieval, methods based on Dynamic Time Warping and sequences where each point of the contour is represented by elements of several dimensions have had a significant presence. In this approach each point of the closed contour contains information with respect to the other ones, this global information is very discriminant. The current state-of-the-art shape retrieval is based on the analysis of these distances to learn better ones.These methods are robust to noise and invariant to transformations, but, they obtain the invariance to the starting point with a brute force cyclic alignment which has a high computational time. In this work, we present the Cyclic Dynamic Time Warping. It can obtain the cyclic alignment in O(n 2 log n) time, where n is the size of both sequences. Experimental results show that our proposal is a better alternative than the brute force cyclic alignment and other heuristics for obtaining this invariance.

show abstract

“…Finally, to comment that if we use a context-sensitive learning approach, in particular [19] Bold entries show the best results.…”

Section: Retrieval Ratesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

On the dynamic time warping of cyclic sequences for shape retrieval

Palazón-González

Marzal

2012

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…Recent work clearly demonstrated that adding context information to direct pairwise shape similarity can substantially improver shape retrieval [40,15,41]. Under context of a given shape we understand here its first K nearest neighbors.…”

Section: Beyond Pairwise Shape Similaritymentioning

confidence: 99%

“…Under context of a given shape we understand here its first K nearest neighbors. However, these methods [40,15,41] mainly focus on improving the transduction algorithms. We demonstrate that a 'better' original distance matrix is also very crucial for the shape retrieval with context information.…”

Section: Beyond Pairwise Shape Similaritymentioning

confidence: 99%

Balancing Deformability and Discriminability for Shape Matching

Ling

Yang

Latecki

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We propose a novel framework, aspect space, to balance deformability and discriminability, which are often two competing factors in shape and image representations. In this framework, an object is embedded as a surface in a higher dimensional space with a parameter named aspect weight, which controls the importance of intensity in the embedding. We show that this framework naturally unifies existing important shape and image representations by adjusting the aspect weight and the embedding. More importantly, we find that the aspect weight implicitly controls the degree to which a representation handles deformation. Based on this idea, we present the aspect shape context, which extends shape context-based descriptors and adaptively selects the "best" aspect weight for shape comparison. Another observation we have is the proposed descriptor nicely fits context-sensitive shape retrieval. The proposed methods are evaluated on two public datasets, MPEG7-CE-Shape-1 and Tari 1000, in comparison to state-of-the-art solutions. In the standard shape retrieval experiment using the MPEG7 CE-Shape-1 database, the new descriptor with context information achieves a bull's eye score of 95.96%, which surpassed all previous results. In the Tari 1000 dataset, our methods significantly outperform previous tested methods as well.

show abstract

A unified model for accelerating unsupervised iterative re‐ranking algorithms

Pisani

Valem

Pedronette

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Re-ranking algorithms are used to improve the effectiveness of multimedia retrieval systems. However, they are usually very computationally costly, and therefore demand the specification and implementation of efficient and effective big multimedia analysis approaches.Recently proposed unsupervised iterative re-ranking methods present good accuracy and significant potential for parallelization, leading us to explore efficiency vs. effectiveness trade-offs. In this paper, we introduce a class of unsupervised iterative re-ranking algorithms and present a model that can be used to guide their implementation for parallel architectures. We also analyze the impact of the parallelization on the performance of three algorithms that belong to the proposed class: Contextual Spaces, RL-Sim, and Contextual Re-Ranking. The experiments show speedups that reach up to 6.0× for Contextual Spaces Re-Ranking, 16.1× for RL-Sim Re-Ranking, and 3.3× for Contextual Re-Ranking. These results demonstrate that the proposed parallel programming model can be successfully applied to improve the scalability of multimedia retrieval systems.

show abstract

Beyond Pairwise Shape Similarity Analysis

Cited by 81 publications

References 18 publications

On the dynamic time warping of cyclic sequences for shape retrieval

On the dynamic time warping of cyclic sequences for shape retrieval

Balancing Deformability and Discriminability for Shape Matching

A unified model for accelerating unsupervised iterative re‐ranking algorithms

Contact Info

Product

Resources

About