July 28, 2019

2968 words 14 mins read

Paper Group ANR 325

An Efficient Method for online Detection of Polychronous Patterns in Spiking Neural Network. Weighted Tensor Decomposition for Learning Latent Variables with Partial Data. Generative Cooperative Net for Image Generation and Data Augmentation. An Evolutionary Computing Enriched RS Attack Resilient Medical Image Steganography Model for Telemedicine A …

An Efficient Method for online Detection of Polychronous Patterns in Spiking Neural Network


Title	An Efficient Method for online Detection of Polychronous Patterns in Spiking Neural Network
Authors	Joseph Chrol-Cannon, Yaochu Jin, André Grüning
Abstract	Polychronous neural groups are effective structures for the recognition of precise spike-timing patterns but the detection method is an inefficient multi-stage brute force process that works off-line on pre-recorded simulation data. This work presents a new model of polychronous patterns that can capture precise sequences of spikes directly in the neural simulation. In this scheme, each neuron is assigned a randomized code that is used to tag the post-synaptic neurons whenever a spike is transmitted. This creates a polychronous code that preserves the order of pre-synaptic activity and can be registered in a hash table when the post-synaptic neuron spikes. A polychronous code is a sub-component of a polychronous group that will occur, along with others, when the group is active. We demonstrate the representational and pattern recognition ability of polychronous codes on a direction selective visual task involving moving bars that is typical of a computation performed by simple cells in the cortex. The computational efficiency of the proposed algorithm far exceeds existing polychronous group detection methods and is well suited for online detection.
Tasks
Published	2017-02-20
URL	http://arxiv.org/abs/1702.05939v1
PDF	http://arxiv.org/pdf/1702.05939v1.pdf
PWC	https://paperswithcode.com/paper/an-efficient-method-for-online-detection-of
Repo
Framework

Weighted Tensor Decomposition for Learning Latent Variables with Partial Data


Title	Weighted Tensor Decomposition for Learning Latent Variables with Partial Data
Authors	Omer Gottesman, Weiwei Pan, Finale Doshi-Velez
Abstract	Tensor decomposition methods are popular tools for learning latent variables given only lower-order moments of the data. However, the standard assumption is that we have sufficient data to estimate these moments to high accuracy. In this work, we consider the case in which certain dimensions of the data are not always observed—common in applied settings, where not all measurements may be taken for all observations—resulting in moment estimates of varying quality. We derive a weighted tensor decomposition approach that is computationally as efficient as the non-weighted approach, and demonstrate that it outperforms methods that do not appropriately leverage these less-observed dimensions.
Tasks
Published	2017-10-18
URL	http://arxiv.org/abs/1710.06818v1
PDF	http://arxiv.org/pdf/1710.06818v1.pdf
PWC	https://paperswithcode.com/paper/weighted-tensor-decomposition-for-learning
Repo
Framework

Generative Cooperative Net for Image Generation and Data Augmentation


Title	Generative Cooperative Net for Image Generation and Data Augmentation
Authors	Qiangeng Xu, Zengchang Qin, Tao Wan
Abstract	How to build a good model for image generation given an abstract concept is a fundamental problem in computer vision. In this paper, we explore a generative model for the task of generating unseen images with desired features. We propose the Generative Cooperative Net (GCN) for image generation. The idea is similar to generative adversarial networks except that the generators and discriminators are trained to work accordingly. Our experiments on hand-written digit generation and facial expression generation show that GCN’s two cooperative counterparts (the generator and the classifier) can work together nicely and achieve promising results. We also discovered a usage of such generative model as an data-augmentation tool. Our experiment of applying this method on a recognition task shows that it is very effective comparing to other existing methods. It is easy to set up and could help generate a very large synthesized dataset.
Tasks	Data Augmentation, Image Generation
Published	2017-05-08
URL	http://arxiv.org/abs/1705.02887v3
PDF	http://arxiv.org/pdf/1705.02887v3.pdf
PWC	https://paperswithcode.com/paper/generative-cooperative-net-for-image
Repo
Framework

An Evolutionary Computing Enriched RS Attack Resilient Medical Image Steganography Model for Telemedicine Applications


Title	An Evolutionary Computing Enriched RS Attack Resilient Medical Image Steganography Model for Telemedicine Applications
Authors	Romany F. Mansour, Elsaid MD. Abdelrahim
Abstract	The recent advancement in computing technologies and resulting vision based applications have gives rise to a novel practice called telemedicine that requires patient diagnosis images or allied information to recommend or even perform diagnosis practices being located remotely. However, to ensure accurate and optimal telemedicine there is the requirement of seamless or flawless biomedical information about patient. On the contrary, medical data transmitted over insecure channel often remains prone to get manipulated or corrupted by attackers. The existing cryptosystems alone are not sufficient to deal with these issues and hence in this paper a highly robust reversible image steganography model has been developed for secret information hiding. Unlike traditional wavelet transform techniques, we incorporated Discrete Ripplet Transformation (DRT) technique for message embedding in the medical cover images. In addition, to assure seamless communication over insecure channel, a dual cryptosystem model containing proposed steganography scheme and RSA cryptosystem has been developed. One of the key novelties of the proposed research work is the use of adaptive genetic algorithm (AGA) for optimal pixel adjustment process (OPAP) that enriches data hiding capacity as well as imperceptibility features. The performance assessment reveals that the proposed steganography model outperforms other wavelet transformation based approaches in terms of high PSNR, embedding capacity, imperceptibility etc.
Tasks	Image Steganography
Published	2017-09-25
URL	http://arxiv.org/abs/1709.08362v2
PDF	http://arxiv.org/pdf/1709.08362v2.pdf
PWC	https://paperswithcode.com/paper/an-evolutionary-computing-enriched-rs-attack
Repo
Framework

Learning Inference Models for Computer Vision


Title	Learning Inference Models for Computer Vision
Authors	Varun Jampani
Abstract	Computer vision can be understood as the ability to perform inference on image data. Breakthroughs in computer vision technology are often marked by advances in inference techniques. This thesis proposes novel inference schemes and demonstrates applications in computer vision. We propose inference techniques for both generative and discriminative vision models. The use of generative models in vision is often hampered by the difficulty of posterior inference. We propose techniques for improving inference in MCMC sampling and message-passing inference. Our inference strategy is to learn separate discriminative models that assist Bayesian inference in a generative model. Experiments on a range of generative models show that the proposed techniques accelerate the inference process and/or converge to better solutions. A main complication in the design of discriminative models is the inclusion of prior knowledge. We concentrate on CNN models and propose a generalization of standard spatial convolutions to bilateral convolutions. We generalize the existing use of bilateral filters and then propose new neural network architectures with learnable bilateral filters, which we call `Bilateral Neural Networks’. Experiments demonstrate the use of the bilateral networks on a wide range of image and video tasks and datasets. In summary, we propose techniques for better inference in several vision models ranging from inverse graphics to freely parameterized neural networks. In generative models, our inference techniques alleviate some of the crucial hurdles in Bayesian posterior inference, paving new ways for the use of model based machine learning in vision. In discriminative CNN models, the proposed filter generalizations aid in the design of new neural network architectures that can handle sparse high-dimensional data as well as provide a way to incorporate prior knowledge into CNNs. \|
Tasks	Bayesian Inference
Published	2017-08-31
URL	http://arxiv.org/abs/1709.00069v1
PDF	http://arxiv.org/pdf/1709.00069v1.pdf
PWC	https://paperswithcode.com/paper/learning-inference-models-for-computer-vision
Repo
Framework

Hibikino-Musashi@Home 2017 Team Description Paper


Title	Hibikino-Musashi@Home 2017 Team Description Paper
Authors	Sansei Hori, Yutaro Ishida, Yuta Kiyama, Yuichiro Tanaka, Yuki Kuroda, Masataka Hisano, Yuto Imamura, Tomotaka Himaki, Yuma Yoshimoto, Yoshiya Aratani, Kouhei Hashimoto, Gouki Iwamoto, Hiroto Fujita, Takashi Morie, Hakaru Tamukoh
Abstract	Our team Hibikino-Musashi@Home was founded in 2010. It is based in Kitakyushu Science and Research Park, Japan. Since 2010, we have participated in the RoboCup@Home Japan open competition open-platform league every year. Currently, the Hibikino-Musashi@Home team has 24 members from seven different laboratories based in the Kyushu Institute of Technology. Our home-service robots are used as platforms for both education and implementation of our research outcomes. In this paper, we introduce our team and the technologies that we have implemented in our robots.
Tasks
Published	2017-11-15
URL	http://arxiv.org/abs/1711.05457v1
PDF	http://arxiv.org/pdf/1711.05457v1.pdf
PWC	https://paperswithcode.com/paper/hibikino-musashihome-2017-team-description
Repo
Framework

The CARESSES EU-Japan project: making assistive robots culturally competent


Title	The CARESSES EU-Japan project: making assistive robots culturally competent
Authors	Barbara Bruno, Nak Young Chong, Hiroko Kamide, Sanjeev Kanoria, Jaeryoung Lee, Yuto Lim, Amit Kumar Pandey, Chris Papadopoulos, Irena Papadopoulos, Federico Pecora, Alessandro Saffiotti, Antonio Sgorbissa
Abstract	The nursing literature shows that cultural competence is an important requirement for effective healthcare. We claim that personal assistive robots should likewise be culturally competent, that is, they should be aware of general cultural characteristics and of the different forms they take in different individuals, and take these into account while perceiving, reasoning, and acting. The CARESSES project is an Europe-Japan collaborative effort that aims at designing, developing and evaluating culturally competent assistive robots. These robots will be able to adapt the way they behave, speak and interact to the cultural identity of the person they assist. This paper describes the approach taken in the CARESSES project, its initial steps, and its future plans.
Tasks
Published	2017-08-21
URL	http://arxiv.org/abs/1708.06276v1
PDF	http://arxiv.org/pdf/1708.06276v1.pdf
PWC	https://paperswithcode.com/paper/the-caresses-eu-japan-project-making
Repo
Framework

Improving Interpretability of Deep Neural Networks with Semantic Information


Title	Improving Interpretability of Deep Neural Networks with Semantic Information
Authors	Yinpeng Dong, Hang Su, Jun Zhu, Bo Zhang
Abstract	Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose and correct potential problems. However, it is challenging to reason about what a DNN actually does due to its opaque or black-box nature. To address this issue, we propose a novel technique to improve the interpretability of DNNs by leveraging the rich semantic information embedded in human descriptions. By concentrating on the video captioning task, we first extract a set of semantically meaningful topics from the human descriptions that cover a wide range of visual concepts, and integrate them into the model with an interpretive loss. We then propose a prediction difference maximization algorithm to interpret the learned features of each neuron. Experimental results demonstrate its effectiveness in video captioning using the interpretable features, which can also be transferred to video action recognition. By clearly understanding the learned features, users can easily revise false predictions via a human-in-the-loop procedure.
Tasks	Temporal Action Localization, Video Captioning
Published	2017-03-12
URL	http://arxiv.org/abs/1703.04096v2
PDF	http://arxiv.org/pdf/1703.04096v2.pdf
PWC	https://paperswithcode.com/paper/improving-interpretability-of-deep-neural
Repo
Framework

Activity Recognition based on a Magnitude-Orientation Stream Network


Title	Activity Recognition based on a Magnitude-Orientation Stream Network
Authors	Carlos Caetano, Victor H. C. de Melo, Jefersson A. dos Santos, William Robson Schwartz
Abstract	The temporal component of videos provides an important clue for activity recognition, as a number of activities can be reliably recognized based on the motion information. In view of that, this work proposes a novel temporal stream for two-stream convolutional networks based on images computed from the optical flow magnitude and orientation, named Magnitude-Orientation Stream (MOS), to learn the motion in a better and richer manner. Our method applies simple nonlinear transformations on the vertical and horizontal components of the optical flow to generate input images for the temporal stream. Experimental results, carried on two well-known datasets (HMDB51 and UCF101), demonstrate that using our proposed temporal stream as input to existing neural network architectures can improve their performance for activity recognition. Results demonstrate that our temporal stream provides complementary information able to improve the classical two-stream methods, indicating the suitability of our approach to be used as a temporal video representation.
Tasks	Activity Recognition, Optical Flow Estimation
Published	2017-08-22
URL	http://arxiv.org/abs/1708.06637v1
PDF	http://arxiv.org/pdf/1708.06637v1.pdf
PWC	https://paperswithcode.com/paper/activity-recognition-based-on-a-magnitude
Repo
Framework

Credible Review Detection with Limited Information using Consistency Analysis


Title	Credible Review Detection with Limited Information using Consistency Analysis
Authors	Subhabrata Mukherjee, Sourav Dutta, Gerhard Weikum
Abstract	Online reviews provide viewpoints on the strengths and shortcomings of products/services, influencing potential customers’ purchasing decisions. However, the proliferation of non-credible reviews – either fake (promoting/ demoting an item), incompetent (involving irrelevant aspects), or biased – entails the problem of identifying credible reviews. Prior works involve classifiers harnessing rich information about items/users – which might not be readily available in several domains – that provide only limited interpretability as to why a review is deemed non-credible. This paper presents a novel approach to address the above issues. We utilize latent topic models leveraging review texts, item ratings, and timestamps to derive consistency features without relying on item/user histories, unavailable for “long-tail” items/users. We develop models, for computing review credibility scores to provide interpretable evidence for non-credible reviews, that are also transferable to other domains – addressing the scarcity of labeled data. Experiments on real-world datasets demonstrate improvements over state-of-the-art baselines.
Tasks	Topic Models
Published	2017-05-07
URL	http://arxiv.org/abs/1705.02668v1
PDF	http://arxiv.org/pdf/1705.02668v1.pdf
PWC	https://paperswithcode.com/paper/credible-review-detection-with-limited
Repo
Framework

Interactive Reinforcement Learning for Object Grounding via Self-Talking


Title	Interactive Reinforcement Learning for Object Grounding via Self-Talking
Authors	Yan Zhu, Shaoting Zhang, Dimitris Metaxas
Abstract	Humans are able to identify a referred visual object in a complex scene via a few rounds of natural language communications. Success communication requires both parties to engage and learn to adapt for each other. In this paper, we introduce an interactive training method to improve the natural language conversation system for a visual grounding task. During interactive training, both agents are reinforced by the guidance from a common reward function. The parametrized reward function also cooperatively updates itself via interactions, and contribute to accomplishing the task. We evaluate the method on GuessWhat?! visual grounding task, and significantly improve the task success rate. However, we observe language drifting problem during training and propose to use reward engineering to improve the interpretability for the generated conversations. Our result also indicates evaluating goal-ended visual conversation tasks require semantic relevant metrics beyond task success rate.
Tasks
Published	2017-12-02
URL	http://arxiv.org/abs/1712.00576v1
PDF	http://arxiv.org/pdf/1712.00576v1.pdf
PWC	https://paperswithcode.com/paper/interactive-reinforcement-learning-for-object
Repo
Framework

Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis


Title	Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis
Authors	Dat Thanh Tran, Alexandros Iosifidis, Juho Kanniainen, Moncef Gabbouj
Abstract	Financial time-series forecasting has long been a challenging problem because of the inherently noisy and stochastic nature of the market. In the High-Frequency Trading (HFT), forecasting for trading purposes is even a more challenging task since an automated inference system is required to be both accurate and fast. In this paper, we propose a neural network layer architecture that incorporates the idea of bilinear projection as well as an attention mechanism that enables the layer to detect and focus on crucial temporal information. The resulting network is highly interpretable, given its ability to highlight the importance and contribution of each temporal instance, thus allowing further analysis on the time instances of interest. Our experiments in a large-scale Limit Order Book (LOB) dataset show that a two-hidden-layer network utilizing our proposed layer outperforms by a large margin all existing state-of-the-art results coming from much deeper architectures while requiring far fewer computations.
Tasks	Time Series, Time Series Forecasting
Published	2017-12-04
URL	http://arxiv.org/abs/1712.00975v1
PDF	http://arxiv.org/pdf/1712.00975v1.pdf
PWC	https://paperswithcode.com/paper/temporal-attention-augmented-bilinear-network
Repo
Framework

Find the Conversation Killers: a Predictive Study of Thread-ending Posts


Title	Find the Conversation Killers: a Predictive Study of Thread-ending Posts
Authors	Yunhao Jiao, Cheng Li, Fei Wu, Qiaozhu Mei
Abstract	How to improve the quality of conversations in online communities has attracted considerable attention recently. Having engaged, urbane, and reactive online conversations has a critical effect on the social life of Internet users. In this study, we are particularly interested in identifying a post in a multi-party conversation that is unlikely to be further replied to, which therefore kills that thread of the conversation. For this purpose, we propose a deep learning model called the ConverNet. ConverNet is attractive due to its capability of modeling the internal structure of a long conversation and its appropriate encoding of the contextual information of the conversation, through effective integration of attention mechanisms. Empirical experiments on real-world datasets demonstrate the effectiveness of the proposal model. For the widely concerned topic, our analysis also offers implications for improving the quality and user experience of online conversations.
Tasks
Published	2017-12-22
URL	http://arxiv.org/abs/1712.08636v1
PDF	http://arxiv.org/pdf/1712.08636v1.pdf
PWC	https://paperswithcode.com/paper/find-the-conversation-killers-a-predictive
Repo
Framework

Hierarchical Embeddings for Hypernymy Detection and Directionality


Title	Hierarchical Embeddings for Hypernymy Detection and Directionality
Authors	Kim Anh Nguyen, Maximilian Köper, Sabine Schulte im Walde, Ngoc Thang Vu
Abstract	We present a novel neural model HyperVec to learn hierarchical embeddings for hypernymy detection and directionality. While previous embeddings have shown limitations on prototypical hypernyms, HyperVec represents an unsupervised measure where embeddings are learned in a specific order and capture the hypernym$-$hyponym distributional hierarchy. Moreover, our model is able to generalize over unseen hypernymy pairs, when using only small sets of training data, and by mapping to other languages. Results on benchmark datasets show that HyperVec outperforms both state$-$of$-$the$-$art unsupervised measures and embedding models on hypernymy detection and directionality, and on predicting graded lexical entailment.
Tasks
Published	2017-07-23
URL	http://arxiv.org/abs/1707.07273v1
PDF	http://arxiv.org/pdf/1707.07273v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-embeddings-for-hypernymy
Repo
Framework

Time Series Prediction : Predicting Stock Price


Title	Time Series Prediction : Predicting Stock Price
Authors	Aaron Elliot, Cheng Hua Hsu
Abstract	Time series forecasting is widely used in a multitude of domains. In this paper, we present four models to predict the stock price using the SPX index as input time series data. The martingale and ordinary linear models require the strongest assumption in stationarity which we use as baseline models. The generalized linear model requires lesser assumptions but is unable to outperform the martingale. In empirical testing, the RNN model performs the best comparing to other two models, because it will update the input through LSTM instantaneously, but also does not beat the martingale. In addition, we introduce an online to batch algorithm and discrepancy measure to inform readers the newest research in time series predicting method, which doesn’t require any stationarity or non mixing assumptions in time series data. Finally, to apply these forecasting to practice, we introduce basic trading strategies that can create Win win and Zero sum situations.
Tasks	Time Series, Time Series Forecasting, Time Series Prediction
Published	2017-10-16
URL	http://arxiv.org/abs/1710.05751v2
PDF	http://arxiv.org/pdf/1710.05751v2.pdf
PWC	https://paperswithcode.com/paper/time-series-prediction-predicting-stock-price
Repo
Framework