Journal ArticleDOI
Learning High-Level Feature by Deep Belief Networks for 3-D Model Retrieval and Recognition
TLDR
This paper proposes a multi-level 3-D shape feature extraction framework by using deep learning, where low-level shape descriptors are first encoded into geometric bag-of-words, from which middle-level patterns are discovered to explore geometric relationships among words.Abstract:
3-D shape analysis has attracted extensive research efforts in recent years, where the major challenge lies in designing an effective high-level 3-D shape feature. In this paper, we propose a multi-level 3-D shape feature extraction framework by using deep learning. The low-level 3-D shape descriptors are first encoded into geometric bag-of-words, from which middle-level patterns are discovered to explore geometric relationships among words. After that, high-level shape features are learned via deep belief networks, which are more discriminative for the tasks of shape classification and retrieval. Experiments on 3-D shape recognition and retrieval demonstrate the superior performance of the proposed method in comparison to the state-of-the-art methods.read more
Citations
More filters
Journal ArticleDOI
Deep Learning Advances in Computer Vision with 3D Data: A Survey
TL;DR: It is concluded that systems employing 2D views of 3D data typically surpass voxel-based (3D) deep models, which however, can perform better with more layers and severe data augmentation, therefore, larger-scale datasets and increased resolutions are required.
Journal ArticleDOI
Multi-Modal Clique-Graph Matching for View-Based 3D Model Retrieval
TL;DR: The proposed MCG provides the following benefits: 1) preserves the local and global attributes of a graph with the designed structure; 2) eliminates redundant and noisy information by strengthening inliers while suppressing outliers; and 3) avoids the difficulty of defining high-order attributes and solving hyper-graph matching.
Journal ArticleDOI
Learning Multi-View Representation With LSTM for 3-D Shape Recognition and Retrieval
TL;DR: A novel multiview-based network architecture that combines convolutional neural networks with long short-term memory (LSTM) to exploit the correlative information from multiple views for 3-D shape recognition and retrieval is proposed.
Journal ArticleDOI
Surface EMG based continuous estimation of human lower limb joint angles by using deep belief networks
TL;DR: The results show that the features extracted from multichannel surface EMG signals using DBN method proposed in this paper outperform principal components analysis (PCA), and the root mean square error (RMSE) between the estimated joint angles and calculated ones during human walking is reduced by about 50%.
Journal ArticleDOI
GLA: Global–Local Attention for Image Description
TL;DR: The proposed GLA method can generate more relevant image description sentences and achieve the state-of-the-art performance on the well-known Microsoft COCO caption dataset with several popular evaluation metrics.
References
More filters
Journal ArticleDOI
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Journal ArticleDOI
A fast learning algorithm for deep belief nets
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Book
Learning Deep Architectures for AI
TL;DR: The motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer modelssuch as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks are discussed.
Journal ArticleDOI
Training products of experts by minimizing contrastive divergence
TL;DR: A product of experts (PoE) is an interesting candidate for a perceptual system in which rapid inference is vital and generation is unnecessary because it is hard even to approximate the derivatives of the renormalization term in the combination rule.
Proceedings ArticleDOI
Multi-column deep neural networks for image classification
TL;DR: In this paper, a biologically plausible, wide and deep artificial neural network architectures was proposed to match human performance on tasks such as the recognition of handwritten digits or traffic signs, achieving near-human performance.