Paper Group ANR 1518
Advanced Variations of Two-Dimensional Principal Component Analysis for Face Recognition. Penalized-likelihood PET Image Reconstruction Using 3D Structural Convolutional Sparse Coding. A Hierarchical Location Prediction Neural Network for Twitter User Geolocation. Thoth: Improved Rapid Serial Visual Presentation using Natural Language Processing. S …
Advanced Variations of Two-Dimensional Principal Component Analysis for Face Recognition
| Title | Advanced Variations of Two-Dimensional Principal Component Analysis for Face Recognition |
| Authors | Meixiang Zhao, Zhigang Jia, Yunfeng Cai, Xiao Chen, Dunwei Gong |
| Abstract | The two-dimensional principal component analysis (2DPCA) has become one of the most powerful tools of artificial intelligent algorithms. In this paper, we review 2DPCA and its variations, and propose a general ridge regression model to extract features from both row and column directions. To enhance the generalization ability of extracted features, a novel relaxed 2DPCA (R2DPCA) is proposed with a new ridge regression model. R2DPCA generates a weighting vector with utilizing the label information, and maximizes a relaxed criterion with applying an optimal algorithm to get the essential features. The R2DPCA-based approaches for face recognition and image reconstruction are also proposed and the selected principle components are weighted to enhance the role of main components. Numerical experiments on well-known standard databases indicate that R2DPCA has high generalization ability and can achieve a higher recognition rate than the state-of-the-art methods, including in the deep learning methods such as CNNs, DBNs, and DNNs. |
| Tasks | Face Recognition, Image Reconstruction |
| Published | 2019-12-19 |
| URL | https://arxiv.org/abs/1912.09970v1 |
| https://arxiv.org/pdf/1912.09970v1.pdf | |
| PWC | https://paperswithcode.com/paper/advanced-variations-of-two-dimensional |
| Repo | |
| Framework | |
Penalized-likelihood PET Image Reconstruction Using 3D Structural Convolutional Sparse Coding
| Title | Penalized-likelihood PET Image Reconstruction Using 3D Structural Convolutional Sparse Coding |
| Authors | Nuobei Xie, Kuang Gong, Ning Guo, Zhixin Qin, Zhifang Wu, Huafeng Liu, Quanzheng Li |
| Abstract | Positron emission tomography (PET) is widely used for clinical diagnosis. As PET suffers from low resolution and high noise, numerous efforts try to incorporate anatomical priors into PET image reconstruction, especially with the development of hybrid PET/CT and PET/MRI systems. In this work, we proposed a novel 3D structural convolutional sparse coding (CSC) concept for penalized-likelihood PET image reconstruction, named 3D PET-CSC. The proposed 3D PET-CSC takes advantage of the convolutional operation and manages to incorporate anatomical priors without the need of registration or supervised training. As 3D PET-CSC codes the whole 3D PET image, instead of patches, it alleviates the staircase artifacts commonly presented in traditional patch-based sparse coding methods. Moreover, we developed the residual-image and order-subset mechanisms to further reduce the computational cost and accelerate the convergence for the proposed 3D PET-CSC method. Experiments based on computer simulations and clinical datasets demonstrate the superiority of 3D PET-CSC compared with other reference methods. |
| Tasks | Image Reconstruction |
| Published | 2019-12-16 |
| URL | https://arxiv.org/abs/1912.07180v1 |
| https://arxiv.org/pdf/1912.07180v1.pdf | |
| PWC | https://paperswithcode.com/paper/penalized-likelihood-pet-image-reconstruction |
| Repo | |
| Framework | |
A Hierarchical Location Prediction Neural Network for Twitter User Geolocation
| Title | A Hierarchical Location Prediction Neural Network for Twitter User Geolocation |
| Authors | Binxuan Huang, Kathleen M. Carley |
| Abstract | Accurate estimation of user location is important for many online services. Previous neural network based methods largely ignore the hierarchical structure among locations. In this paper, we propose a hierarchical location prediction neural network for Twitter user geolocation. Our model first predicts the home country for a user, then uses the country result to guide the city-level prediction. In addition, we employ a character-aware word embedding layer to overcome the noisy information in tweets. With the feature fusion layer, our model can accommodate various feature combinations and achieves state-of-the-art results over three commonly used benchmarks under different feature settings. It not only improves the prediction accuracy but also greatly reduces the mean error distance. |
| Tasks | |
| Published | 2019-10-28 |
| URL | https://arxiv.org/abs/1910.12941v1 |
| https://arxiv.org/pdf/1910.12941v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-hierarchical-location-prediction-neural |
| Repo | |
| Framework | |
Thoth: Improved Rapid Serial Visual Presentation using Natural Language Processing
| Title | Thoth: Improved Rapid Serial Visual Presentation using Natural Language Processing |
| Authors | David Awad |
| Abstract | Thoth is a tool designed to combine many different types of speed reading technology. The largest insight is using natural language parsing for more optimal rapid serial visual presentation and more effective reading information. |
| Tasks | |
| Published | 2019-08-05 |
| URL | https://arxiv.org/abs/1908.01699v1 |
| https://arxiv.org/pdf/1908.01699v1.pdf | |
| PWC | https://paperswithcode.com/paper/thoth-improved-rapid-serial-visual |
| Repo | |
| Framework | |
Self-supervised classification of dynamic obstacles using the temporal information provided by videos
| Title | Self-supervised classification of dynamic obstacles using the temporal information provided by videos |
| Authors | Sid Ali Hamideche, Florent Chiaroni, Mohamed-Cherif Rahal |
| Abstract | Nowadays, autonomous driving systems can detect, segment, and classify the surrounding obstacles using a monocular camera. However, state-of-the-art methods solving these tasks generally perform a fully supervised learning process and require a large amount of training labeled data. On another note, some self-supervised learning approaches can deal with detection and segmentation of dynamic obstacles using the temporal information available in video sequences. In this work, we propose in addition to classifiy the detected obstacles depending on their motion pattern. We present a novel self-supervised framework consisting of learning offline clusters from temporal patch sequences and using these clusters as pseudo labels to train a real-time image classifier. The presented model outperforms state-of-the-art unsupervised image classification methods on BDD100K dataset. |
| Tasks | Autonomous Driving, Image Classification, Unsupervised Image Classification |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09094v1 |
| https://arxiv.org/pdf/1910.09094v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-classification-of-dynamic |
| Repo | |
| Framework | |
On the Robustness of Median Sampling in Noisy Evolutionary Optimization
| Title | On the Robustness of Median Sampling in Noisy Evolutionary Optimization |
| Authors | Chao Bian, Chao Qian, Yang Yu |
| Abstract | In real-world optimization tasks, the objective (i.e., fitness) function evaluation is often disturbed by noise due to a wide range of uncertainties. Evolutionary algorithms (EAs) have been widely applied to tackle noisy optimization, where reducing the negative effect of noise is a crucial issue. One popular strategy to cope with noise is sampling, which evaluates the fitness multiple times and uses the sample average to approximate the true fitness. In this paper, we introduce median sampling as a noise handling strategy into EAs, which uses the median of the multiple evaluations to approximate the true fitness instead of the mean. We theoretically show that median sampling can reduce the expected running time of EAs from exponential to polynomial by considering the (1+1)-EA on OneMax under the commonly used one-bit noise. We also compare mean sampling with median sampling by considering two specific noise models, suggesting that when the 2-quantile of the noisy fitness increases with the true fitness, median sampling can be a better choice. The results provide us with some guidance to employ median sampling efficiently in practice. |
| Tasks | |
| Published | 2019-07-28 |
| URL | https://arxiv.org/abs/1907.13100v1 |
| https://arxiv.org/pdf/1907.13100v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-robustness-of-median-sampling-in-noisy |
| Repo | |
| Framework | |
Multi-Label Graph Convolutional Network Representation Learning
| Title | Multi-Label Graph Convolutional Network Representation Learning |
| Authors | Min Shi, Yufei Tang, Xingquan Zhu, Jianxun Liu |
| Abstract | Knowledge representation of graph-based systems is fundamental across many disciplines. To date, most existing methods for representation learning primarily focus on networks with simplex labels, yet real-world objects (nodes) are inherently complex in nature and often contain rich semantics or labels, e.g., a user may belong to diverse interest groups of a social network, resulting in multi-label networks for many applications. The multi-label network nodes not only have multiple labels for each node, such labels are often highly correlated making existing methods ineffective or fail to handle such correlation for node representation learning. In this paper, we propose a novel multi-label graph convolutional network (ML-GCN) for learning node representation for multi-label networks. To fully explore label-label correlation and network topology structures, we propose to model a multi-label network as two Siamese GCNs: a node-node-label graph and a label-label-node graph. The two GCNs each handle one aspect of representation learning for nodes and labels, respectively, and they are seamlessly integrated under one objective function. The learned label representations can effectively preserve the inner-label interaction and node label properties, and are then aggregated to enhance the node representation learning under a unified training framework. Experiments and comparisons on multi-label node classification validate the effectiveness of our proposed approach. |
| Tasks | Node Classification, Representation Learning |
| Published | 2019-12-26 |
| URL | https://arxiv.org/abs/1912.11757v1 |
| https://arxiv.org/pdf/1912.11757v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-label-graph-convolutional-network |
| Repo | |
| Framework | |
Complete Scene Reconstruction by Merging Images and Laser Scans
| Title | Complete Scene Reconstruction by Merging Images and Laser Scans |
| Authors | Xiang Gao, Shuhan Shen, Lingjie Zhu, Tianxin Shi, Zhiheng Wang, Zhanyi Hu |
| Abstract | Image based modeling and laser scanning are two commonly used approaches in large-scale architectural scene reconstruction nowadays. In order to generate a complete scene reconstruction, an effective way is to completely cover the scene using ground and aerial images, supplemented by laser scanning on certain regions with low texture and complicated structure. Thus, the key issue is to accurately calibrate cameras and register laser scans in a unified framework. To this end, we proposed a three-step pipeline for complete scene reconstruction by merging images and laser scans. First, images are captured around the architecture in a multi-view and multi-scale way and are feed into a structure-from-motion (SfM) pipeline to generate SfM points. Then, based on the SfM result, the laser scanning locations are automatically planned by considering textural richness, structural complexity of the scene and spatial layout of the laser scans. Finally, the images and laser scans are accurately merged in a coarse-to-fine manner. Experimental evaluations on two ancient Chinese architecture datasets demonstrate the effectiveness of our proposed complete scene reconstruction pipeline. |
| Tasks | |
| Published | 2019-04-21 |
| URL | https://arxiv.org/abs/1904.09568v4 |
| https://arxiv.org/pdf/1904.09568v4.pdf | |
| PWC | https://paperswithcode.com/paper/complete-scene-reconstruction-by-merging |
| Repo | |
| Framework | |
TCDCaps: Visual Tracking via Cascaded Dense Capsules
| Title | TCDCaps: Visual Tracking via Cascaded Dense Capsules |
| Authors | Ding Ma, Xiangqian Wu |
| Abstract | The critical challenge in tracking-by-detection framework is how to avoid drift problem during online learning, where the robust features for a variety of appearance changes are difficult to be learned and a reasonable intersection over union (IoU) threshold that defines the true/false positives is hard to set. This paper presents the TCDCaps method to address the problems above via a cascaded dense capsule architecture. To get robust features, we extend original capsules with dense-connected routing, which are referred as DCaps. Depending on the preservation of part-whole relationships in the Capsule Networks, our dense-connected capsules can capture a variety of appearance variations. In addition, to handle the issue of IoU threshold, a cascaded DCaps model (CDCaps) is proposed to improve the quality of candidates, it consists of sequential DCaps trained with increasing IoU thresholds so as to sequentially improve the quality of candidates. Extensive experiments on 3 popular benchmarks demonstrate the robustness of the proposed TCDCaps. |
| Tasks | Visual Tracking |
| Published | 2019-02-26 |
| URL | https://arxiv.org/abs/1902.10054v2 |
| https://arxiv.org/pdf/1902.10054v2.pdf | |
| PWC | https://paperswithcode.com/paper/tcdcaps-visual-tracking-via-cascaded-dense |
| Repo | |
| Framework | |
Community Detection and Growth Potential Prediction from Patent Citation Networks
| Title | Community Detection and Growth Potential Prediction from Patent Citation Networks |
| Authors | Asahi Hentona, Takeshi Sakumoto, Hugo Alberto Mendoza España, Hirofumi Nonaka, Shotaro Kataoka, Toru Hiraoka, Kensei Nakai, Elisa Claire Alemán Carreón, Masaharu Hirota |
| Abstract | The scoring of patents is useful for technology management analysis. Therefore, a necessity of developing citation network clustering and prediction of future citations for practical patent scoring arises. In this paper, we propose a community detection method using the Node2vec. And in order to analyze growth potential we compare three ‘‘time series analysis methods’', the Long Short-Term Memory (LSTM), ARIMA model, and Hawkes Process. The results of our experiments, we could find common technical points from those clusters by Node2vec. Furthermore, we found that the prediction accuracy of the ARIMA model was higher than that of other models. |
| Tasks | Community Detection, Time Series, Time Series Analysis |
| Published | 2019-04-23 |
| URL | http://arxiv.org/abs/1904.12040v1 |
| http://arxiv.org/pdf/1904.12040v1.pdf | |
| PWC | https://paperswithcode.com/paper/190412040 |
| Repo | |
| Framework | |
A Systematic Literature Review about the impact of Artificial Intelligence on Autonomous Vehicle Safety
| Title | A Systematic Literature Review about the impact of Artificial Intelligence on Autonomous Vehicle Safety |
| Authors | A. M. Nascimento, L. F. Vismari, C. B. S. T. Molina, P. S. Cugnasca, J. B. Camargo Jr., J. R. de Almeida Jr., R. Inam, E. Fersman, M. V. Marquezini, A. Y. Hata |
| Abstract | Autonomous Vehicles (AV) are expected to bring considerable benefits to society, such as traffic optimization and accidents reduction. They rely heavily on advances in many Artificial Intelligence (AI) approaches and techniques. However, while some researchers in this field believe AI is the core element to enhance safety, others believe AI imposes new challenges to assure the safety of these new AI-based systems and applications. In this non-convergent context, this paper presents a systematic literature review to paint a clear picture of the state of the art of the literature in AI on AV safety. Based on an initial sample of 4870 retrieved papers, 59 studies were selected as the result of the selection criteria detailed in the paper. The shortlisted studies were then mapped into six categories to answer the proposed research questions. An AV system model was proposed and applied to orient the discussions about the SLR findings. As a main result, we have reinforced our preliminary observation about the necessity of considering a serious safety agenda for the future studies on AI-based AV systems. |
| Tasks | Autonomous Vehicles |
| Published | 2019-04-04 |
| URL | http://arxiv.org/abs/1904.02697v1 |
| http://arxiv.org/pdf/1904.02697v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-systematic-literature-review-about-the |
| Repo | |
| Framework | |
Integration and Evaluation of Quantum Accelerators for Data-Driven User Functions
| Title | Integration and Evaluation of Quantum Accelerators for Data-Driven User Functions |
| Authors | Thomas Hubregtsen, Christoph Segler, Josef Pichlmeier, Aritra Sarkar, Thomas Gabor, Koen Bertels |
| Abstract | Quantum computers hold great promise for accelerating computationally challenging algorithms on noisy intermediate-scale quantum (NISQ) devices in the upcoming years. Much attention of the current research is directed to algorithmic research on artificial data that is disconnected from live systems, such as optimization of systems or training of learning algorithms. In this paper we investigate the integration of quantum systems into industry-grade system architectures. In this work we propose a system architecture for the integration of quantum accelerators. In order to evaluate our proposed system architecture we implemented various algorithms including a classical system, a gate-based quantum accelerator and a quantum annealer. This algorithm automates user habits using data-driven functions trained on real-world data. This also includes an evaluation of the quantum enhanced kernel, that previously was only evaluated on artificial data. In our evaluation, we showed that the quantum-enhanced kernel performs at least equally well to a classical state-of-the-art kernel. We also showed a low reduction in accuracy and latency numbers within acceptable bounds when running on the gate-based IBM quantum accelerator. We, therefore, conclude it is feasible to integrate NISQ-era devices in industry-grade system architecture in preparation for future hardware improvements. |
| Tasks | |
| Published | 2019-12-12 |
| URL | https://arxiv.org/abs/1912.06032v2 |
| https://arxiv.org/pdf/1912.06032v2.pdf | |
| PWC | https://paperswithcode.com/paper/integration-and-evaluation-of-quantum |
| Repo | |
| Framework | |
Nonparametric Independence Testing for Right-Censored Data using Optimal Transport
| Title | Nonparametric Independence Testing for Right-Censored Data using Optimal Transport |
| Authors | David Rindt, Dino Sejdinovic, David Steinsaltz |
| Abstract | We propose a nonparametric test of independence, termed OPT-HSIC, between a covariate and a right-censored lifetime. Because the presence of censoring creates a challenge in applying the standard permutation-based testing approaches, we use optimal transport to transform the censored dataset into an uncensored one, while preserving the relevant dependencies. We then apply a permutation test using the kernel-based dependence measure as a statistic to the transformed dataset. The type 1 error is proven to be correct in the case where censoring is independent of the covariate. Experiments indicate that OPT-HSIC has power against a much wider class of alternatives than Cox proportional hazards regression and that it has the correct type 1 control even in the challenging cases where censoring strongly depends on the covariate. |
| Tasks | |
| Published | 2019-06-10 |
| URL | https://arxiv.org/abs/1906.03866v2 |
| https://arxiv.org/pdf/1906.03866v2.pdf | |
| PWC | https://paperswithcode.com/paper/nonparametric-independence-testing-for-right |
| Repo | |
| Framework | |
Data Augmentation by AutoEncoders for Unsupervised Anomaly Detection
| Title | Data Augmentation by AutoEncoders for Unsupervised Anomaly Detection |
| Authors | Kasra Babaei, ZhiYuan Chen, Tomas Maul |
| Abstract | This paper proposes an autoencoder (AE) that is used for improving the performance of once-class classifiers for the purpose of detecting anomalies. Traditional one-class classifiers (OCCs) perform poorly under certain conditions such as high-dimensionality and sparsity. Also, the size of the training set plays an important role on the performance of one-class classifiers. Autoencoders have been widely used for obtaining useful latent variables from high-dimensional datasets. In the proposed approach, the AE is capable of deriving meaningful features from high-dimensional datasets while doing data augmentation at the same time. The augmented data is used for training the OCC algorithms. The experimental results show that the proposed approach enhance the performance of OCC algorithms and also outperforms other well-known approaches. |
| Tasks | Anomaly Detection, Data Augmentation, Unsupervised Anomaly Detection |
| Published | 2019-12-21 |
| URL | https://arxiv.org/abs/1912.13384v1 |
| https://arxiv.org/pdf/1912.13384v1.pdf | |
| PWC | https://paperswithcode.com/paper/data-augmentation-by-autoencoders-for |
| Repo | |
| Framework | |
A comparative study of estimating articulatory movements from phoneme sequences and acoustic features
| Title | A comparative study of estimating articulatory movements from phoneme sequences and acoustic features |
| Authors | Abhayjeet Singh, Aravind Illa, Prasanta Kumar Ghosh |
| Abstract | Unlike phoneme sequences, movements of speech articulators (lips, tongue, jaw, velum) and the resultant acoustic signal are known to encode not only the linguistic message but also carry para-linguistic information. While several works exist for estimating articulatory movement from acoustic signals, little is known to what extent articulatory movements can be predicted only from linguistic information, i.e., phoneme sequence. In this work, we estimate articulatory movements from three different input representations: R1) acoustic signal, R2) phoneme sequence, R3) phoneme sequence with timing information. While an attention network is used for estimating articulatory movement in the case of R2, BLSTM network is used for R1 and R3. Experiments with ten subjects’ acoustic-articulatory data reveal that the estimation techniques achieve an average correlation coefficient of 0.85, 0.81, and 0.81 in the case of R1, R2, and R3 respectively. This indicates that attention network, although uses only phoneme sequence (R2) without any timing information, results in an estimation performance similar to that using rich acoustic signal (R1), suggesting that articulatory motion is primarily driven by the linguistic message. The correlation coefficient is further improved to 0.88 when R1 and R3 are used together for estimating articulatory movements. |
| Tasks | |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1910.14375v2 |
| https://arxiv.org/pdf/1910.14375v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-comparative-study-of-estimating |
| Repo | |
| Framework | |
