January 27, 2020

3094 words 15 mins read

Paper Group ANR 1144

Estimation of crowd density applying wavelet transform and machine learning. NeuroPod: a real-time neuromorphic spiking CPG applied to robotics. Discriminative Video Representation Learning Using Support Vector Classifiers. Water Supply Prediction Based on Initialized Attention Residual Network. Recent Trends in Deep Learning Based Personality Dete …

Estimation of crowd density applying wavelet transform and machine learning


Title	Estimation of crowd density applying wavelet transform and machine learning
Authors	Koki Nagao, Daichi Yanagisawa, Katsuhiro Nishinari
Abstract	We conducted a simple experiment in which one pedestrian passed through a crowded area and measured the body-rotational angular velocity with commercial tablets. Then, we developed a new method for predicting crowd density by applying the continuous wavelet transform and machine learning to the data obtained in the experiment. We found that the accuracy of prediction using angular velocity data was as high as that using raw velocity data. Therefore, we concluded that angular velocity has relationship with crowd density and we could estimate crowd density by angular velocity. Our research will contribute to management of safety and comfort of pedestrians by developing an easy way to measure crowd density.
Tasks
Published	2019-03-19
URL	http://arxiv.org/abs/1903.07806v1
PDF	http://arxiv.org/pdf/1903.07806v1.pdf
PWC	https://paperswithcode.com/paper/estimation-of-crowd-density-applying-wavelet
Repo
Framework

NeuroPod: a real-time neuromorphic spiking CPG applied to robotics


Title	NeuroPod: a real-time neuromorphic spiking CPG applied to robotics
Authors	Daniel Gutierrez-Galan, Juan Pedro Dominguez-Morales, Fernando Perez-Pena, Alejandro Linares-Barranco
Abstract	Initially, robots were developed with the aim of making our life easier, carrying out repetitive or dangerous tasks for humans. Although they were able to perform these tasks, the latest generation of robots are being designed to take a step further, by performing more complex tasks that have been carried out by smart animals or humans up to date. To this end, inspiration needs to be taken from biological examples. For instance, insects are able to optimally solve complex environment navigation problems, and many researchers have started to mimic how these insects behave. Recent interest in neuromorphic engineering has motivated us to present a real-time, neuromorphic, spike-based Central Pattern Generator of application in neurorobotics, using an arthropod-like robot. A Spiking Neural Network was designed and implemented on SpiNNaker. The network models a complex, online-change capable Central Pattern Generator which generates three gaits for a hexapod robot locomotion. Reconfigurable hardware was used to manage both the motors of the robot and the real-time communication interface with the Spiking Neural Networks. Real-time measurements confirm the simulation results, and locomotion tests show that NeuroPod can perform the gaits without any balance loss or added delay.
Tasks
Published	2019-04-25
URL	http://arxiv.org/abs/1904.11243v1
PDF	http://arxiv.org/pdf/1904.11243v1.pdf
PWC	https://paperswithcode.com/paper/neuropod-a-real-time-neuromorphic-spiking-cpg
Repo
Framework

Discriminative Video Representation Learning Using Support Vector Classifiers


Title	Discriminative Video Representation Learning Using Support Vector Classifiers
Authors	Jue Wang, Anoop Cherian
Abstract	Most popular deep models for action recognition in videos generate independent predictions for short clips, which are then pooled heuristically to assign an action label to the full video segment. As not all frames may characterize the underlying action—many are common across multiple actions—pooling schemes that impose equal importance on all frames might be unfavorable. In an attempt to tackle this problem, we propose discriminative pooling, based on the notion that among the deep features generated on all short clips, there is at least one that characterizes the action. To identify these useful features, we resort to a negative bag consisting of features that are known to be irrelevant, for example, they are sampled either from datasets that are unrelated to our actions of interest or are CNN features produced via random noise as input. With the features from the video as a positive bag and the irrelevant features as the negative bag, we cast an objective to learn a (nonlinear) hyperplane that separates the unknown useful features from the rest in a multiple instance learning formulation within a support vector machine setup. We use the parameters of this separating hyperplane as a descriptor for the full video segment. Since these parameters are directly related to the support vectors in a max-margin framework, they can be treated as a weighted average pooling of the features from the bags, with zero weights given to non-support vectors. Our pooling scheme is end-to-end trainable within a deep learning framework. We report results from experiments on eight computer vision benchmark datasets spanning a variety of video-related tasks and demonstrate state-of-the-art performance across these tasks.
Tasks	Action Recognition In Videos, Multiple Instance Learning, Representation Learning
Published	2019-09-05
URL	https://arxiv.org/abs/1909.02856v1
PDF	https://arxiv.org/pdf/1909.02856v1.pdf
PWC	https://paperswithcode.com/paper/discriminative-video-representation-learning
Repo
Framework

Water Supply Prediction Based on Initialized Attention Residual Network


Title	Water Supply Prediction Based on Initialized Attention Residual Network
Authors	Yuhao Long, Jingcheng Wang, Jingyi Wang
Abstract	Real-time and accurate water supply forecast is crucial for water plant. However, most existing methods are likely affected by factors such as weather and holidays, which lead to a decline in the reliability of water supply prediction. In this paper, we address a generic artificial neural network, called Initialized Attention Residual Network (IARN), which is combined with an attention module and residual modules. Specifically, instead of continuing to use the recurrent neural network (RNN) in time-series tasks, we try to build a convolution neural network (CNN)to recede the disturb from other factors, relieve the limitation of memory size and get a more credible results. Our method achieves state-of-the-art performance on several data sets, in terms of accuracy, robustness and generalization ability.
Tasks	Time Series
Published	2019-12-17
URL	https://arxiv.org/abs/1912.13497v1
PDF	https://arxiv.org/pdf/1912.13497v1.pdf
PWC	https://paperswithcode.com/paper/water-supply-prediction-based-on-initialized
Repo
Framework

Recent Trends in Deep Learning Based Personality Detection


Title	Recent Trends in Deep Learning Based Personality Detection
Authors	Yash Mehta, Navonil Majumder, Alexander Gelbukh, Erik Cambria
Abstract	Recently, the automatic prediction of personality traits has received a lot of attention. Specifically, personality trait prediction from multimodal data has emerged as a hot topic within the field of affective computing. In this paper, we review significant machine learning models which have been employed for personality detection, with an emphasis on deep learning-based methods. This review paper provides an overview of the most popular approaches to automated personality detection, various computational datasets, its industrial applications, and state-of-the-art machine learning models for personality detection with specific focus on multimodal approaches. Personality detection is a very broad and diverse topic: this survey only focuses on computational approaches and leaves out psychological studies on personality detection.
Tasks
Published	2019-08-07
URL	https://arxiv.org/abs/1908.03628v2
PDF	https://arxiv.org/pdf/1908.03628v2.pdf
PWC	https://paperswithcode.com/paper/recent-trends-in-deep-learning-based
Repo
Framework

Fairness in Deep Learning: A Computational Perspective


Title	Fairness in Deep Learning: A Computational Perspective
Authors	Mengnan Du, Fan Yang, Na Zou, Xia Hu
Abstract	Deep learning is increasingly being used in high-stake decision making applications that affect individual lives. However, deep learning models might exhibit algorithmic discrimination behaviors with respect to protected groups, potentially posing negative impacts on individuals and society. Therefore, fairness in deep learning has attracted tremendous attention recently. We provide a review covering recent progresses to tackle algorithmic fairness problems of deep learning from the computational perspective. Specifically, we show that interpretability can serve as a useful ingredient to diagnose the reasons that lead to algorithmic discrimination. We also discuss fairness mitigation approaches categorized according to three stages of deep learning life-cycle, aiming to push forward the area of fairness in deep learning and build genuinely fair and reliable deep learning systems.
Tasks	Decision Making
Published	2019-08-23
URL	https://arxiv.org/abs/1908.08843v2
PDF	https://arxiv.org/pdf/1908.08843v2.pdf
PWC	https://paperswithcode.com/paper/fairness-in-deep-learning-a-computational
Repo
Framework

Capacity Preserving Mapping for High-dimensional Data Visualization


Title	Capacity Preserving Mapping for High-dimensional Data Visualization
Authors	Rongrong Wang, Xiaopeng Zhang
Abstract	We provide a rigorous mathematical treatment to the crowding issue in data visualization when high dimensional data sets are projected down to low dimensions for visualization. By properly adjusting the capacity of high dimensional balls, our method makes right enough room to prepare for the embedding. A key component of the proposed method is an estimation of the correlation dimension at various scales which reflects the data density variation. The proposed adjustment to the capacity applies to any distance (Euclidean, geodesic, diffusion) and can potentially be used in many existing methods to mitigate the crowding during the dimension reduction. We demonstrate the effectiveness of the new method using synthetic and real datasets.
Tasks	Dimensionality Reduction
Published	2019-09-29
URL	https://arxiv.org/abs/1909.13322v1
PDF	https://arxiv.org/pdf/1909.13322v1.pdf
PWC	https://paperswithcode.com/paper/capacity-preserving-mapping-for-high
Repo
Framework

Unsupervised Deep Transfer Feature Learning for Medical Image Classification


Title	Unsupervised Deep Transfer Feature Learning for Medical Image Classification
Authors	Euijoon Ahn, Ashnil Kumar, Dagan Feng, Michael Fulham, Jinman Kim
Abstract	The accuracy and robustness of image classification with supervised deep learning are dependent on the availability of large-scale, annotated training data. However, there is a paucity of annotated data available due to the complexity of manual annotation. To overcome this problem, a popular approach is to use transferable knowledge across different domains by: 1) using a generic feature extractor that has been pre-trained on large-scale general images (i.e., transfer-learned) but which not suited to capture characteristics from medical images; or 2) fine-tuning generic knowledge with a relatively smaller number of annotated images. Our aim is to reduce the reliance on annotated training data by using a new hierarchical unsupervised feature extractor with a convolutional auto-encoder placed atop of a pre-trained convolutional neural network. Our approach constrains the rich and generic image features from the pre-trained domain to a sophisticated representation of the local image characteristics from the unannotated medical image domain. Our approach has a higher classification accuracy than transfer-learned approaches and is competitive with state-of-the-art supervised fine-tuned methods.
Tasks	Image Classification
Published	2019-03-15
URL	http://arxiv.org/abs/1903.06342v2
PDF	http://arxiv.org/pdf/1903.06342v2.pdf
PWC	https://paperswithcode.com/paper/unsupervised-deep-transfer-feature-learning
Repo
Framework


Title	Do Cross Modal Systems Leverage Semantic Relationships?
Authors	Shah Nawaz, Muhammad Kamran Janjua, Ignazio Gallo, Arif Mahmood, Alessandro Calefati, Faisal Shafait
Abstract	Current cross-modal retrieval systems are evaluated using R@K measure which does not leverage semantic relationships rather strictly follows the manually marked image text query pairs. Therefore, current systems do not generalize well for the unseen data in the wild. To handle this, we propose a new measure, SemanticMap, to evaluate the performance of cross-modal systems. Our proposed measure evaluates the semantic similarity between the image and text representations in the latent embedding space. We also propose a novel cross-modal retrieval system using a single stream network for bidirectional retrieval. The proposed system is based on a deep neural network trained using extended center loss, minimizing the distance of image and text descriptions in the latent space from the class centers. In our system, the text descriptions are also encoded as images which enabled us to use a single stream network for both text and images. To the best of our knowledge, our work is the first of its kind in terms of employing a single stream network for cross-modal retrieval systems. The proposed system is evaluated on two publicly available datasets including MSCOCO and Flickr30K and has shown comparable results to the current state-of-the-art methods.
Tasks	Cross-Modal Retrieval, Semantic Similarity, Semantic Textual Similarity
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01976v1
PDF	https://arxiv.org/pdf/1909.01976v1.pdf
PWC	https://paperswithcode.com/paper/do-cross-modal-systems-leverage-semantic
Repo
Framework

Consistent Feature Construction with Constrained Genetic Programming for Experimental Physics


Title	Consistent Feature Construction with Constrained Genetic Programming for Experimental Physics
Authors	Noëlie Cherrier, Jean-Philippe Poli, Maxime Defurne, Franck Sabatié
Abstract	A good feature representation is a determinant factor to achieve high performance for many machine learning algorithms in terms of classification. This is especially true for techniques that do not build complex internal representations of data (e.g. decision trees, in contrast to deep neural networks). To transform the feature space, feature construction techniques build new high-level features from the original ones. Among these techniques, Genetic Programming is a good candidate to provide interpretable features required for data analysis in high energy physics. Classically, original features or higher-level features based on physics first principles are used as inputs for training. However, physicists would benefit from an automatic and interpretable feature construction for the classification of particle collision events. Our main contribution consists in combining different aspects of Genetic Programming and applying them to feature construction for experimental physics. In particular, to be applicable to physics, dimensional consistency is enforced using grammars. Results of experiments on three physics datasets show that the constructed features can bring a significant gain to the classification accuracy. To the best of our knowledge, it is the first time a method is proposed for interpretable feature construction with units of measurement, and that experts in high-energy physics validate the overall approach as well as the interpretability of the built features.
Tasks
Published	2019-08-17
URL	https://arxiv.org/abs/1908.08005v1
PDF	https://arxiv.org/pdf/1908.08005v1.pdf
PWC	https://paperswithcode.com/paper/190808005
Repo
Framework

Multiple instance dense connected convolution neural network for aerial image scene classification


Title	Multiple instance dense connected convolution neural network for aerial image scene classification
Authors	Qi Bi, Kun Qin, Zhili Li, Han Zhang, Kai Xu
Abstract	With the development of deep learning, many state-of-the-art natural image scene classification methods have demonstrated impressive performance. While the current convolution neural network tends to extract global features and global semantic information in a scene, the geo-spatial objects can be located at anywhere in an aerial image scene and their spatial arrangement tends to be more complicated. One possible solution is to preserve more local semantic information and enhance feature propagation. In this paper, an end to end multiple instance dense connected convolution neural network (MIDCCNN) is proposed for aerial image scene classification. First, a 23 layer dense connected convolution neural network (DCCNN) is built and served as a backbone to extract convolution features. It is capable of preserving middle and low level convolution features. Then, an attention based multiple instance pooling is proposed to highlight the local semantics in an aerial image scene. Finally, we minimize the loss between the bag-level predictions and the ground truth labels so that the whole framework can be trained directly. Experiments on three aerial image datasets demonstrate that our proposed methods can outperform current baselines by a large margin.
Tasks	Scene Classification
Published	2019-08-22
URL	https://arxiv.org/abs/1908.08156v1
PDF	https://arxiv.org/pdf/1908.08156v1.pdf
PWC	https://paperswithcode.com/paper/multiple-instance-dense-connected-convolution
Repo
Framework

On conducting better validation studies of automatic metrics in natural language generation evaluation


Title	On conducting better validation studies of automatic metrics in natural language generation evaluation
Authors	Johnny Tian-Zheng Wei
Abstract	Natural language generation (NLG) has received increasing attention, which has highlighted evaluation as a central methodological concern. Since human evaluations for these systems are costly, automatic metrics have broad appeal in NLG. Research in language generation often finds situations where it is appropriate to apply existing metrics or propose new ones. The application of these metrics are entirely dependent on validation studies - studies that determine a metric’s correlation to human judgment. However, there are many details and considerations in conducting strong validation studies. This document is intended for those validating existing metrics or proposing new ones in the broad context of NLG: we 1) begin with a write-up of best practices in validation studies, 2) outline how to adopt these practices, 3) conduct analyses in the WMT’17 metrics shared task\footnote{Our jupyter notebook containing the analyses is available at \url{https://github.com}}, and 4) highlight promising approaches to NLG metrics 5) conclude with our opinions on the future of this area.
Tasks	Text Generation
Published	2019-07-31
URL	https://arxiv.org/abs/1907.13362v1
PDF	https://arxiv.org/pdf/1907.13362v1.pdf
PWC	https://paperswithcode.com/paper/on-conducting-better-validation-studies-of
Repo
Framework

Easy-to-Hard: Leveraging Simple Questions for Complex Question Generation


Title	Easy-to-Hard: Leveraging Simple Questions for Complex Question Generation
Authors	Jie Zhao, Xiang Deng, Huan Sun
Abstract	This paper makes one of the first efforts toward automatically generating complex questions from knowledge graphs. Particularly, we study how to leverage existing simple question datasets for this task, under two separate scenarios: using either sub-questions of the target complex questions, or distantly related pseudo sub-questions when the former are unavailable. First, a competitive base model named CoG2Q is designed to map complex query qraphs to natural language questions. Afterwards, we propose two extension models, namely CoGSub2Q and CoGSub^m2Q, respectively for the above two scenarios. The former encodes and copies from a sub-question, while the latter further scores and aggregates multiple pseudo sub-questions. Experiment results show that the extension models significantly outperform not only base CoG2Q, but also its augmented variant using simple questions as additional training examples. This demonstrates the importance of instance-level connections between simple and corresponding complex questions, which may be underexploited by straightforward data augmentation of CoG2Q that builds model-level connections through learned parameters.
Tasks	Data Augmentation, Knowledge Graphs, Question Generation
Published	2019-12-05
URL	https://arxiv.org/abs/1912.02367v2
PDF	https://arxiv.org/pdf/1912.02367v2.pdf
PWC	https://paperswithcode.com/paper/easy-to-hard-leveraging-simple-questions-for
Repo
Framework

Realtime Simulation of Thin-Shell Deformable Materials using CNN-Based Mesh Embedding


Title	Realtime Simulation of Thin-Shell Deformable Materials using CNN-Based Mesh Embedding
Authors	Qingyang Tan, Zherong Pan, Lin Gao, Dinesh Manocha
Abstract	We address the problem of accelerating thin-shell deformable object simulations by dimension reduction. We present a new algorithm to embed a high-dimensional configuration space of deformable objects in a low-dimensional feature space, where the configurations of objects and feature points have approximate one-to-one mapping. Our key technique is a graph-based convolutional neural network (CNN) defined on meshes with arbitrary topologies and a new mesh embedding approach based on physics-inspired loss term. We have applied our approach to accelerate high-resolution thin shell simulations corresponding to cloth-like materials, where the configuration space has tens of thousands of degrees of freedom. We show that our physics-inspired embedding approach leads to higher accuracy compared with prior mesh embedding methods. Finally, we show that the temporal evolution of the mesh in the feature space can also be learned using a recurrent neural network (RNN) leading to fully learnable physics simulators. After training our learned simulator runs $500-10000\times$ faster and the accuracy is high enough for robot manipulation tasks.
Tasks	Dimensionality Reduction
Published	2019-09-26
URL	https://arxiv.org/abs/1909.12354v4
PDF	https://arxiv.org/pdf/1909.12354v4.pdf
PWC	https://paperswithcode.com/paper/realtime-simulation-of-thin-shell-deformable
Repo
Framework

Adapting SQuaRE for Quality Assessment of Artificial Intelligence Systems


Title	Adapting SQuaRE for Quality Assessment of Artificial Intelligence Systems
Authors	Hiroshi Kuwajima, Fuyuki Ishikawa
Abstract	More and more software practitioners are tackling towards industrial applications of artificial intelligence (AI) systems, especially those based on machine learning (ML). However, many of existing principles and approaches to traditional systems do not work effectively for the system behavior obtained by training not by logical design. In addition, unique kinds of requirements are emerging such as fairness and explainability. To provide clear guidance to understand and tackle these difficulties, we present an analysis on what quality concepts we should evaluate for AI systems. We base our discussion on ISO/IEC 25000 series, known as SQuaRE, and identify how it should be adapted for the unique nature of ML and $\textit{Ethics guidelines for trustworthy AI}$ from European Commission. We thus provide holistic insights for quality of AI systems by incorporating the ML nature and AI ethics to the traditional software quality concepts.
Tasks
Published	2019-07-31
URL	https://arxiv.org/abs/1908.02134v1
PDF	https://arxiv.org/pdf/1908.02134v1.pdf
PWC	https://paperswithcode.com/paper/adapting-square-for-quality-assessment-of
Repo
Framework