RECORD
3D Shape Retrieval via Irrelevance Filtering and Similarity Ranking (IF/SR)
Computer Vision and Pattern Recognition · Submitted 30 Jan 2017
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim The superior performance of the proposed IF/SR method is demonstrated by extensive experiments conducted on the popular SHREC12 dataset.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
A novel solution for the content-based 3D shape retrieval problem using an unsupervised clustering approach, which does not need any label information of 3D shapes, is presented in this work. The proposed shape retrieval system consists of two modules in cascade: the irrelevance filtering (IF) module and the similarity ranking (SR) module. The IF module attempts to cluster gallery shapes that are similar to each other by examining global and local features simultaneously. However, shapes that are close in the local feature space can be distant in the global feature space, and vice versa. To resolve this issue, we propose a joint cost function that strikes a balance between two distances. Irrelevant samples that are close in the local feature space but distant in the global feature space can be removed in this stage. The remaining gallery samples are ranked in the SR module using the local feature. The superior performance of the proposed IF/SR method is demonstrated by extensive experiments conducted on the popular SHREC12 dataset.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | A novel solution for the content-based 3D shape retrieval problem using an unsupervised clustering approach, which does not need any label information of 3D shapes, is presented in this work. | contribution 1.00 | 0.88 | 0.15 | asserted 0.99 |
| s1 | The proposed shape retrieval system consists of two modules in cascade: the irrelevance filtering (IF) module and the similarity ranking (SR) module. | method 0.92 | 0.78 | 0.04 | asserted 1.00 |
| s2 | The IF module attempts to cluster gallery shapes that are similar to each other by examining global and local features simultaneously. | method 0.99 | 0.68 | 0.03 | asserted 0.96 |
| s3 | However, shapes that are close in the local feature space can be distant in the global feature space, and vice versa. | background 0.72 | 0.23 | 0.02 | asserted 0.98 |
| s4 | To resolve this issue, we propose a joint cost function that strikes a balance between two distances. | method 0.64 | 0.88 | 0.04 | asserted 1.00 |
| s5 | Irrelevant samples that are close in the local feature space but distant in the global feature space can be removed in this stage. | method 0.96 | 0.72 | 0.05 | asserted 0.82 |
| s6 | The remaining gallery samples are ranked in the SR module using the local feature. | method 1.00 | 0.68 | 0.03 | asserted 0.98 |
| s7 | The superior performance of the proposed IF/SR method is demonstrated by extensive experiments conducted on the popular SHREC12 dataset. | result 0.99 | 0.95 | 0.83 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
A novel solution for the content-based 3D shape retrieval problem using an unsupervised clustering approach, which does not need any label information of 3D shapes, is presented in this work. The proposed shape retrieval system consists of two modules in cascade: the irrelevance filtering (IF) module and the similarity ranking (SR) module. The IF module attempts to cluster gallery shapes that are similar to each other by examining global and local features simultaneously. However, shapes that are close in the local feature space can be distant in the global feature space, and vice versa. To resolve this issue, we propose a joint cost function that strikes a balance between two distances. Irrelevant samples that are close in the local feature space but distant in the global feature space can be removed in this stage. The remaining gallery samples are ranked in the SR module using the local feature. The superior performance of the proposed IF/SR method is demonstrated by extensive experiments conducted on the popular SHREC12 dataset.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites
Cites as background 1 paper
-
Recently, convolutional neural-network (CNN) based solutions achieved impressive performance by training a network using either multiple views of 3D shapes [ref] or the 3D volumetric data [ref] .
Volumetric and Multi-View CNNs for Object Classification on 3D Data · Introduction · 0.89
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.