Iterative 3D shape classification by online metric learning

Song, Mofei; Sun, Zhengxing; Liu, Kai; Lang, Xufeng

doi:10.1016/j.cagd.2015.03.009

Cited by 10 publications

(7 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The determination of interactive content of students' online PAEL is the core content for the analysis on the interactive behavior of students' online PAEL [8]. Therefore, from the perspectives of learning community and knowledge construction, this paper constructed the interactive content system of PAEL [9], as shown in Figure 1.…”

Section: Construction Of the Interactive Content System Of Paelmentioning

confidence: 99%

Evaluation of Factors Affecting Student Participation in Peer-Assisted English Learning Based on Online Education Platform

Hong

Wang

Zhai

et al. 2021

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

Through a questionnaire survey, this study explored the factors affecting student participation in peer-assisted English learning (PAEL) based on online education platforms. Specifically, the authors constructed the system of PAEL contents, analyzed the online PAEL behaviors of students, and evaluated the student participation in online PAEL from both surface participation and deep participation. On this basis, the influencing factors of student participation in online PAEL were evaluated thoroughly. In the end, several countermeasures were presented to solve the problems with student participation in online PAEL. The results show that: the online PAEL face such problems like low-level knowledge structure and poor interaction quality, weak intensity of interaction, and inactive atmosphere of collaboration; In general, the students are not actively participating in online PAEL; the student participation in online PAEL is greatly affected by teachers, students, teaching contents, and online education platforms; the low participation in online PAEL mainly arises from the weak motives of students for online PAEL, the inadequate teaching design and supervision of teachers, and the imperfect functions of online education platform. The research enriches the theoretical and practical results on the factors affecting student participation in online PAEL.

show abstract

Section: Construction Of the Interactive Content System Of Paelmentioning

confidence: 99%

Evaluation of Factors Affecting Student Participation in Peer-Assisted English Learning Based on Online Education Platform

Hong

Wang

Zhai

et al. 2021

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

show abstract

“…Yi et al [15] enriched the semantic region annotations of 3D shape datasets, which was achieved by propagating the manual annotations of a few shapes across the whole shape set under an active learning framework. Song et al [16], [17] learned a customized classifier for 3D shapes in an interactive way, where the Figure 1. The pipeline of our framework.…”

Section: Active Learning In 3dmentioning

confidence: 99%

Active Arrangement of Small Objects in 3D Indoor Scenes

Zhang

Han

Lai

et al. 2021

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Small object arrangement is very important for creating detailed and realistic 3D indoor scenes. In this paper, we present an interactive framework based on active learning to help users create customized arrangements for small objects according to their preferences. To achieve this with minimal user effort, we first learn the prior knowledge about small object arrangement from a 3D indoor scene dataset through a probability mining method, which forms the initial guidance for arranging small objects. Then, users are able to express their preferences on a few small object categories, which are automatically propagated to all the other categories via a novel active learning approach. In the propagation process, we introduce a novel metric to obtain the propagation weights, which measures the degree of interchangeability between two small object categories, and is calculated based on a spatial embedding model learned from the small object neighborhood information extracted from the 3D indoor scene dataset. Experiments show that our framework is able to help users effectively create customized small object arrangements with little effort.

show abstract

“…Each of these methods uses as input a combination shape and color information to generate a descriptor vector. Song et al introduced a framework which combined unsupervised learning, metric learning, and user intervention which used minimal input from users to validate proposed model groupings [25]. These descriptor methods rely on a domain expert to recognize and quantify the aspects of input which best suit the specified task (e.g.…”

Section: Descriptor Machine Based Learningmentioning

confidence: 99%

A Convolutional Neural Network Model for Predicting a Product's Function, Given Its Form

Dering

Tucker

2017

Journal of Mechanical Design

View full text Add to dashboard Cite

Quantifying the ability of a digital design concept to perform a function currently requires the use of costly and intensive solutions such as Computational Fluid Dynamics. To mitigate these challenges, the authors of this work propose a deep learning approach based on 3-Dimensional Convolutions that predicts Functional Quantities of digital design concepts. This work defines the term Functional Quantity to mean a quantitative measure of an artifact's ability to perform a function. Several research questions are derived from this work: i) Are learned 3D Convolutions able to accurately calculate these quantities, as measured by rank, magnitude and accuracy? ii) What do the latent features (that is, internal values in the model) discovered by this network mean? iii) Does this work perform better than other deep learning approaches at calculating Functional Quantities? In the case study, a proposed network design is tested for its ability to predict several functions (Sitting, Storing Liquid, Emitting Sound, Displaying Images, and Providing Conveyance) based on test form classes distinct from training class. This study evaluates several approaches to this problem based on a common architecture, with the best approach achieving F Scores of > 0.9 in 3 of the 5 functions identified. Testing trained models on novel input also yields accuracy as high as 98% for estimating rank of these functional quantities. This method is also employed to differentiate between decorative and functional head-wear, which yields an 84.4% accuracy and 0.786 precision.Dering MD-17-1178 1 3-D scanners, or RGB-D Sensors such as the Microsoft Kinect) has further enabled the capture, sharing, and production of such artifacts around the world [1, 2].However, just because a design "looks good" does not mean that it will achieve its intended functions or behaviors.While simulation models such as CFD use advanced numerical methods and algorithms to evaluate the feasibility of designs, they require extensive modeling expertise, advanced computing resources and are time consuming [3,4]. While some of these publicly-available digital design models are decorative in nature, many of these artifacts are meant to serve a specific purpose or function that may be implied or explicitly stated by the designer. Formally, a function is defined as a purpose intended for an object. This work proposes a method that uses as input, a model file representing a possible artifact. A neural network analyzes this artifact, and as output, predicts how well it will perform each intended function. For example, some objects can be used for sitting. This network will predict how much force it will be able to withstand, when sat upon. These trained predictive models will provide insight from their latent variables as well. A latent variable is a variable contained within the model whose value may describe the forms and patterns that have the most predictive power.Typically, design defines a product by its form, function, and behavior [5]. However, this work is limited to a stud...

show abstract

Iterative 3D shape classification by online metric learning

Cited by 10 publications

References 36 publications

Evaluation of Factors Affecting Student Participation in Peer-Assisted English Learning Based on Online Education Platform

Evaluation of Factors Affecting Student Participation in Peer-Assisted English Learning Based on Online Education Platform

Active Arrangement of Small Objects in 3D Indoor Scenes

A Convolutional Neural Network Model for Predicting a Product's Function, Given Its Form

Contact Info

Product

Resources

About