The PASCAL Visual Object Classes Challenge

https://bura.brunel.ac.uk/bitstream/2438/14221/1/FullText.pdf

A survey of deep neural network architectures and their applications

In modern industrial processes, soft sensors have played an important role for effective process control, optimization, and monitoring. Feature representation is one of the core factors to construct accurate soft sensors. Recently, deep learning techniques have been developed for high-level abstract feature extraction in pattern recognition areas, which also have great potential for soft sensing applications. Hence, deep stacked autoencoder (SAE) is introduced for soft sensor in this paper. As for output prediction purpose, traditional deep learning algorithms cannot extract high-level output-related features. Thus, a novel variable-wise weighted stacked autoencoder (VW-SAE) is proposed for hierarchical output-related feature representation layer by layer. By correlation analysis with the output variable, important variables are identified from other ones in the input layer of each autoencoder. The variables are assigned with different weights accordingly. Then, variable-wise weighted autoencoders are designed and stacked to form deep networks. An industrial application shows that the proposed VW-SAE can give better prediction performance than the traditional multilayer neural networks and SAE.

Deep Learning-Based Feature Representation and Its Application for Soft Sensor Modeling With Variable-Wise Weighted SAE

Most existing zero-shot learning approaches exploit transfer learning via an intermediate semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A projection from a low-level feature space to the semantic representation space is learned from the auxiliary dataset and applied without adaptation to the target dataset. In this paper we identify two inherent limitations with these approaches. First, due to having disjoint and potentially unrelated classes, the projection functions learned from the auxiliary dataset/domain are biased when applied directly to the target dataset/domain. We call this problem the projection domain shift problem and propose a novel framework, transductive multi-view embedding , to solve it. The second limitation is the prototype sparsity problem which refers to the fact that for each target class, only a single prototype is available for zero-shot learning given a semantic representation. To overcome this problem, a novel heterogeneous multi-view hypergraph label propagation method is formulated for zero-shot learning in the transductive embedding space. It effectively exploits the complementary information offered by different semantic representations and takes advantage of the manifold structures of multiple representation spaces in a coherent manner. We demonstrate through extensive experiments that the proposed approach (1) rectifies the projection shift between the auxiliary and target domains, (2) exploits the complementarity of multiple semantic representations, (3) significantly outperforms existing methods for both zero-shot and N-shot recognition on three image and video benchmark datasets, and (4) enables novel cross-view annotation tasks.

/pdf/transductive-multi-view-zero-shot-learning-1m2j4n2g31.pdf

Transductive Multi-View Zero-Shot Learning

Deep learning has exploded in the public consciousness, primarily as predictive and analytical products suffuse our world, in the form of numerous human-centered smart-world systems, including targeted advertisements, natural language assistants and interpreters, and prototype self-driving vehicle systems. Yet to most, the underlying mechanisms that enable such human-centered smart products remain obscure. In contrast, researchers across disciplines have been incorporating deep learning into their research to solve problems that could not have been approached before. In this paper, we seek to provide a thorough investigation of deep learning in its applications and mechanisms. Specifically, as a categorical collection of state of the art in deep learning research, we hope to provide a broad reference for those seeking a primer on deep learning and its various implementations, platforms, algorithms, and uses in a variety of smart-world systems. Furthermore, we hope to outline recent key advancements in the technology, and provide insight into areas, in which deep learning can improve investigation, as well as highlight new areas of research that have yet to see the application of deep learning, but could nonetheless benefit immensely. We hope this survey provides a valuable reference for new deep learning practitioners, as well as those seeking to innovate in the application of deep learning.

https://ieeexplore.ieee.org/ielaam/6287639/8274985/8351898-aam.pdf

A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends

Video-based human pose recovery is usually conducted by retrieving relevant poses using image features. In the retrieving process, the mapping between 2D images and 3D poses is assumed to be linear in most of the traditional methods. However, their relationships are inherently non-linear, which limits recovery performance of these methods. In this paper, we propose a novel pose recovery method using non-linear mapping with multi-layered deep neural network. It is based on feature extraction with multimodal fusion and back-propagation deep learning. In multimodal fusion, we construct hypergraph Laplacian with low-rank representation. In this way, we obtain a unified feature description by standard eigen-decomposition of the hypergraph Laplacian matrix. In back-propagation deep learning, we learn a non-linear mapping from 2D images to 3D poses with parameter fine-tuning. The experimental results on three data sets show that the recovery error has been reduced by 20%–25%, which demonstrates the effectiveness of the proposed method.

Multimodal Deep Autoencoder for Human Pose Recovery

Image-based 3-D human pose recovery is usually conducted by retrieving relevant poses with image features. However, it suffers from the high dimensionality of image features and the low efficiency of the retrieving process. Particularly for multiview data, the integration of different types of features is difficult. In this paper, a novel approach is proposed to recover 3-D human poses from silhouettes. This approach improves traditional methods by adopting multiview locality-sensitive sparse coding in the retrieving process. First, it incorporates a local similarity preserving term into the objective of sparse coding, which groups similar silhouettes to alleviate the instability of sparse codes. Second, the objective function of sparse coding is improved by integrating multiview data. The experimental results show that the retrieval error has been reduced by 20% to 50%, which demonstrate the effectiveness of the proposed method.

Image-Based Three-Dimensional Human Pose Recovery by Multiview Locality-Sensitive Sparse Retrieval

Human pose recovery in videos is usually conducted by matching 2-D image features and retrieving relevant 3-D human poses. In the retrieving process, the mapping between images and poses is critical. Traditional methods assume this mapping relationship as local joint detection or global joint localization, which limits recovery performance of these methods since this two tasks are actually unified. In this paper, we propose a novel pose recovery framework by simultaneously learning the tasks of joint localization and joint detection. To obtain this framework, multiple manifold learning is used and the shared parameter is calculated. With them, multiple manifold regularizers are integrated and generalized eigendecomposition is utilized to achieve parameter optimization. In this way, pose recovery is boosted by both global mapping and local refinement. Experimental results on two popular datasets demonstrates that the recovery error has been reduced by 10%–20%, which proves the performance improvement of the proposed method.

Multitask Autoencoder Model for Recovering Human Poses

Multi-view ensemble manifold regularization for 3D object recognition

In many real-world applications, data are represented by high-dimensional features. Despite the simplicity, existing K-means subspace clustering algorithms often employ eigenvalue decomposition to generate an approximate solution, which makes the model less efficiency. Besides, their loss functions are either sensitive to outliers or small loss errors. In this paper, we propose a fast adaptive K-means (FAKM) type subspace clustering model, where an adaptive loss function is designed to provide a flexible cluster indicator calculation mechanism, thereby suitable for datasets under different distributions. To find the optimal feature subset, FAKM performs clustering and feature selection simultaneously without the eigenvalue decomposition, therefore efficient for real-world applications. We exploit an efficient alternative optimization algorithm to solve the proposed model, together with theoretical analyses on its convergence and computational complexity. Finally, extensive experiments on several benchmark datasets demonstrate the advantages of FAKM compared to state-of-the-art clustering algorithms.

/pdf/fast-adaptive-k-means-subspace-clustering-for-high-3fe7rjs8dl.pdf

Chaoqun Hong

Papers

Multimodal Deep Autoencoder for Human Pose Recovery

Image-Based Three-Dimensional Human Pose Recovery by Multiview Locality-Sensitive Sparse Retrieval

Multitask Autoencoder Model for Recovering Human Poses

Multi-view ensemble manifold regularization for 3D object recognition

Fast Adaptive K-Means Subspace Clustering for High-Dimensional Data