October 19, 2019

3023 words 15 mins read

Paper Group ANR 119

Cross-Database Micro-Expression Recognition: A Benchmark. InfyNLP at SMM4H Task 2: Stacked Ensemble of Shallow Convolutional Neural Networks for Identifying Personal Medication Intake from Twitter. Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering. Probabilistic Tools for the Analysis of Randomized Optimization Heur …

Cross-Database Micro-Expression Recognition: A Benchmark


Title	Cross-Database Micro-Expression Recognition: A Benchmark
Authors	Yuan Zong, Tong Zhang, Wenming Zheng, Xiaopeng Hong, Chuangao Tang, Zhen Cui, Guoying Zhao
Abstract	Cross-database micro-expression recognition (CDMER) is one of recently emerging and interesting problem in micro-expression analysis. CDMER is more challenging than the conventional micro-expression recognition (MER), because the training and testing samples in CDMER come from different micro-expression databases, resulting in the inconsistency of the feature distributions between the training and testing sets. In this paper, we contribute to this topic from three aspects. First, we establish a CDMER experimental evaluation protocol aiming to allow the researchers to conveniently work on this topic and provide a standard platform for evaluating their proposed methods. Second, we conduct benchmark experiments by using NINE state-of-the-art domain adaptation (DA) methods and SIX popular spatiotemporal descriptors for respectively investigating CDMER problem from two different perspectives. Third, we propose a novel DA method called region selective transfer regression (RSTR) to deal with the CDMER task. Our RSTR takes advantage of one important cue for recognizing micro-expressions, i.e., the different contributions of the facial local regions in MER. The overall superior performance of RSTR demonstrates that taking into consideration the important cues benefiting MER, e.g., the facial local region information, contributes to develop effective DA methods for dealing with CDMER problem.
Tasks	Domain Adaptation
Published	2018-12-19
URL	https://arxiv.org/abs/1812.07742v2
PDF	https://arxiv.org/pdf/1812.07742v2.pdf
PWC	https://paperswithcode.com/paper/cross-database-micro-expression-recognition-a
Repo
Framework

InfyNLP at SMM4H Task 2: Stacked Ensemble of Shallow Convolutional Neural Networks for Identifying Personal Medication Intake from Twitter


Title	InfyNLP at SMM4H Task 2: Stacked Ensemble of Shallow Convolutional Neural Networks for Identifying Personal Medication Intake from Twitter
Authors	Jasper Friedrichs, Debanjan Mahata, Shubham Gupta
Abstract	This paper describes Infosys’s participation in the “2nd Social Media Mining for Health Applications Shared Task at AMIA, 2017, Task 2”. Mining social media messages for health and drug related information has received significant interest in pharmacovigilance research. This task targets at developing automated classification models for identifying tweets containing descriptions of personal intake of medicines. Towards this objective we train a stacked ensemble of shallow convolutional neural network (CNN) models on an annotated dataset provided by the organizers. We use random search for tuning the hyper-parameters of the CNN and submit an ensemble of best models for the prediction task. Our system secured first place among 9 teams, with a micro-averaged F-score of 0.693.
Tasks
Published	2018-03-21
URL	http://arxiv.org/abs/1803.07718v1
PDF	http://arxiv.org/pdf/1803.07718v1.pdf
PWC	https://paperswithcode.com/paper/infynlp-at-smm4h-task-2-stacked-ensemble-of
Repo
Framework

Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering


Title	Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering
Authors	Zhuoqian Yang, Zengchang Qin, Jing Yu, Yue Hu
Abstract	One of the key issues of Visual Question Answering (VQA) is to reason with semantic clues in the visual content under the guidance of the question, how to model relational semantics still remains as a great challenge. To fully capture visual semantics, we propose to reason over a structured visual representation - scene graph, with embedded objects and inter-object relationships. This shows great benefit over vanilla vector representations and implicit visual relationship learning. Based on existing visual relationship models, we propose a visual relationship encoder that projects visual relationships into a learned deep semantic space constrained by visual context and language priors. Upon the constructed graph, we propose a Scene Graph Convolutional Network (SceneGCN) to jointly reason the object properties and relational semantics for the correct answer. We demonstrate the model’s effectiveness and interpretability on the challenging GQA dataset and the classical VQA 2.0 dataset, remarkably achieving state-of-the-art 54.56% accuracy on GQA compared to the existing best model.
Tasks	Cross-Modal Information Retrieval, Information Retrieval, Question Answering, Visual Question Answering
Published	2018-12-23
URL	https://arxiv.org/abs/1812.09681v2
PDF	https://arxiv.org/pdf/1812.09681v2.pdf
PWC	https://paperswithcode.com/paper/multi-modal-learning-with-prior-visual
Repo
Framework

Probabilistic Tools for the Analysis of Randomized Optimization Heuristics


Title	Probabilistic Tools for the Analysis of Randomized Optimization Heuristics
Authors	Benjamin Doerr
Abstract	This chapter collects several probabilistic tools that proved to be useful in the analysis of randomized search heuristics. This includes classic material like Markov, Chebyshev and Chernoff inequalities, but also lesser known topics like stochastic domination and coupling or Chernoff bounds for geometrically distributed random variables and for negatively correlated random variables. Most of the results presented here have appeared previously, some, however, only in recent conference publications. While the focus is on collecting tools for the analysis of randomized search heuristics, many of these may be useful as well in the analysis of classic randomized algorithms or discrete random structures.
Tasks
Published	2018-01-20
URL	https://arxiv.org/abs/1801.06733v4
PDF	https://arxiv.org/pdf/1801.06733v4.pdf
PWC	https://paperswithcode.com/paper/probabilistic-tools-for-the-analysis-of
Repo
Framework

Hyperspectral Imaging Technology and Transfer Learning Utilized in Identification Haploid Maize Seeds


Title	Hyperspectral Imaging Technology and Transfer Learning Utilized in Identification Haploid Maize Seeds
Authors	Wen-Xuan Liao, Xuan-Yu Wang, Dong An, Yao-Guang Wei
Abstract	It is extremely important to correctly identify the cultivars of maize seeds in the breeding process of maize. In this paper, the transfer learning as a method of deep learning is adopted to establish a model by combining with the hyperspectral imaging technology. The haploid seeds can be recognized from large amount of diploid maize ones with great accuracy through the model. First, the information of maize seeds on each wave band is collected using the hyperspectral imaging technology, and then the recognition model is built on VGG-19 network, which is pre-trained by large-scale computer vision database (Image-Net). The correct identification rate of model utilizing seed spectral images containing 256 wave bands (862.5-1704.2nm) reaches 96.32%, and the correct identification rate of the model utilizing the seed spectral images containing single-band reaches 95.75%. The experimental results show that, CNN model which is pre-trained by visible light image database can be applied to the near-infrared hyperspectral imaging-based identification of maize seeds, and high accurate identification rate can be achieved. Meanwhile, when there is small amount of data samples, it can still realize high recognition by using transfer learning. The model not only meets the requirements of breeding recognition, but also greatly reduce the cost occurred in sample collection.
Tasks	Transfer Learning
Published	2018-05-30
URL	http://arxiv.org/abs/1805.11784v1
PDF	http://arxiv.org/pdf/1805.11784v1.pdf
PWC	https://paperswithcode.com/paper/hyperspectral-imaging-technology-and-transfer
Repo
Framework

DN-ResNet: Efficient Deep Residual Network for Image Denoising


Title	DN-ResNet: Efficient Deep Residual Network for Image Denoising
Authors	Haoyu Ren, Mostafa El-Khamy, Jungwon Lee
Abstract	A deep learning approach to blind denoising of images without complete knowledge of the noise statistics is considered. We propose DN-ResNet, which is a deep convolutional neural network (CNN) consisting of several residual blocks (ResBlocks). With cascade training, DN-ResNet is more accurate and more computationally efficient than the state of art denoising networks. An edge-aware loss function is further utilized in training DN-ResNet, so that the denoising results have better perceptive quality compared to conventional loss function. Next, we introduce the depthwise separable DN-ResNet (DS-DN-ResNet) utilizing the proposed Depthwise Seperable ResBlock (DS-ResBlock) instead of standard ResBlock, which has much less computational cost. DS-DN-ResNet is incrementally evolved by replacing the ResBlocks in DN-ResNet by DS-ResBlocks stage by stage. As a result, high accuracy and good computational efficiency are achieved concurrently. Whereas previous state of art deep learning methods focused on denoising either Gaussian or Poisson corrupted images, we consider denoising images having the more practical Poisson with additive Gaussian noise as well. The results show that DN-ResNets are more efficient, robust, and perform better denoising than current state of art deep learning methods, as well as the popular variants of the BM3D algorithm, in cases of blind and non-blind denoising of images corrupted with Poisson, Gaussian or Poisson-Gaussian noise. Our network also works well for other image enhancement task such as compressed image restoration.
Tasks	Denoising, Image Denoising, Image Enhancement, Image Restoration
Published	2018-10-16
URL	http://arxiv.org/abs/1810.06766v1
PDF	http://arxiv.org/pdf/1810.06766v1.pdf
PWC	https://paperswithcode.com/paper/dn-resnet-efficient-deep-residual-network-for
Repo
Framework

Improving Sequential Determinantal Point Processes for Supervised Video Summarization


Title	Improving Sequential Determinantal Point Processes for Supervised Video Summarization
Authors	Aidean Sharghi, Ali Borji, Chengtao Li, Tianbao Yang, Boqing Gong
Abstract	It is now much easier than ever before to produce videos. While the ubiquitous video data is a great source for information discovery and extraction, the computational challenges are unparalleled. Automatically summarizing the videos has become a substantial need for browsing, searching, and indexing visual content. This paper is in the vein of supervised video summarization using sequential determinantal point process (SeqDPP), which models diversity by a probabilistic distribution. We improve this model in two folds. In terms of learning, we propose a large-margin algorithm to address the exposure bias problem in SeqDPP. In terms of modeling, we design a new probabilistic distribution such that, when it is integrated into SeqDPP, the resulting model accepts user input about the expected length of the summary. Moreover, we also significantly extend a popular video summarization dataset by 1) more egocentric videos, 2) dense user annotations, and 3) a refined evaluation scheme. We conduct extensive experiments on this dataset (about 60 hours of videos in total) and compare our approach to several competitive baselines.
Tasks	Point Processes, Supervised Video Summarization, Video Summarization
Published	2018-07-28
URL	http://arxiv.org/abs/1807.10957v2
PDF	http://arxiv.org/pdf/1807.10957v2.pdf
PWC	https://paperswithcode.com/paper/improving-sequential-determinantal-point
Repo
Framework

How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization


Title	How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization
Authors	Yandong Li, Liqiang Wang, Tianbao Yang, Boqing Gong
Abstract	The large volume of video content and high viewing frequency demand automatic video summarization algorithms, of which a key property is the capability of modeling diversity. If videos are lengthy like hours-long egocentric videos, it is necessary to track the temporal structures of the videos and enforce local diversity. The local diversity refers to that the shots selected from a short time duration are diverse but visually similar shots are allowed to co-exist in the summary if they appear far apart in the video. In this paper, we propose a novel probabilistic model, built upon SeqDPP, to dynamically control the time span of a video segment upon which the local diversity is imposed. In particular, we enable SeqDPP to learn to automatically infer how local the local diversity is supposed to be from the input video. The resulting model is extremely involved to train by the hallmark maximum likelihood estimation (MLE), which further suffers from the exposure bias and non-differentiable evaluation metrics. To tackle these problems, we instead devise a reinforcement learning algorithm for training the proposed model. Extensive experiments verify the advantages of our model and the new learning algorithm over MLE-based methods.
Tasks	Point Processes, Supervised Video Summarization, Video Summarization
Published	2018-07-11
URL	http://arxiv.org/abs/1807.04219v4
PDF	http://arxiv.org/pdf/1807.04219v4.pdf
PWC	https://paperswithcode.com/paper/how-local-is-the-local-diversity-reinforcing
Repo
Framework

Data-driven Discovery of Cyber-Physical Systems


Title	Data-driven Discovery of Cyber-Physical Systems
Authors	Ye Yuan, Xiuchuan Tang, Wei Pan, Xiuting Li, Wei Zhou, Hai-Tao Zhang, Han Ding, Jorge Goncalves
Abstract	Cyber-physical systems (CPSs) embed software into the physical world. They appear in a wide range of applications such as smart grids, robotics, intelligent manufacture and medical monitoring. CPSs have proved resistant to modeling due to their intrinsic complexity arising from the combination of physical components and cyber components and the interaction between them. This study proposes a general framework for reverse engineering CPSs directly from data. The method involves the identification of physical systems as well as the inference of transition logic. It has been applied successfully to a number of real-world examples ranging from mechanical and electrical systems to medical applications. The novel framework seeks to enable researchers to make predictions concerning the trajectory of CPSs based on the discovered model. Such information has been proven essential for the assessment of the performance of CPS, the design of failure-proof CPS and the creation of design guidelines for new CPSs.
Tasks
Published	2018-10-01
URL	http://arxiv.org/abs/1810.00697v1
PDF	http://arxiv.org/pdf/1810.00697v1.pdf
PWC	https://paperswithcode.com/paper/data-driven-discovery-of-cyber-physical
Repo
Framework

Optimizing Answer Set Computation via Heuristic-Based Decomposition


Title	Optimizing Answer Set Computation via Heuristic-Based Decomposition
Authors	Francesco Calimeri, Simona Perri, Jessica Zangari
Abstract	Answer Set Programming (ASP) is a purely declarative formalism developed in the field of logic programming and nonmonotonic reasoning: computational problems are encoded by logic programs whose answer sets, corresponding to solutions, are computed by an ASP system. Different, semantically equivalent, programs can be defined for the same problem; however, performance of systems evaluating them might significantly vary. We propose an approach for automatically transforming an input logic program into an equivalent one that can be evaluated more efficiently. One can make use of existing tree-decomposition techniques for rewriting selected rules into a set of multiple ones; the idea is to guide and adaptively apply them on the basis of proper new heuristics, to obtain a smart rewriting algorithm to be integrated into an ASP system. The method is rather general: it can be adapted to any system and implement different preference policies. Furthermore, we define a set of new heuristics tailored at optimizing grounding, one of the main phases of the ASP computation; we use them in order to implement the approach into the ASP system DLV, in particular into its grounding subsystem I-DLV, and carry out an extensive experimental activity for assessing the impact of the proposal. Under consideration in Theory and Practice of Logic Programming (TPLP).
Tasks
Published	2018-12-23
URL	http://arxiv.org/abs/1812.09718v2
PDF	http://arxiv.org/pdf/1812.09718v2.pdf
PWC	https://paperswithcode.com/paper/optimizing-answer-set-computation-via
Repo
Framework

Lingke: A Fine-grained Multi-turn Chatbot for Customer Service


Title	Lingke: A Fine-grained Multi-turn Chatbot for Customer Service
Authors	Pengfei Zhu, Zhuosheng Zhang, Jiangtong Li, Yafang Huang, Hai Zhao
Abstract	Traditional chatbots usually need a mass of human dialogue data, especially when using supervised machine learning method. Though they can easily deal with single-turn question answering, for multi-turn the performance is usually unsatisfactory. In this paper, we present Lingke, an information retrieval augmented chatbot which is able to answer questions based on given product introduction document and deal with multi-turn conversations. We will introduce a fine-grained pipeline processing to distill responses based on unstructured documents, and attentive sequential context-response matching for multi-turn conversations.
Tasks	Chatbot, Information Retrieval, Question Answering
Published	2018-08-10
URL	http://arxiv.org/abs/1808.03430v1
PDF	http://arxiv.org/pdf/1808.03430v1.pdf
PWC	https://paperswithcode.com/paper/lingke-a-fine-grained-multi-turn-chatbot-for
Repo
Framework

R3Net: Random Weights, Rectifier Linear Units and Robustness for Artificial Neural Network


Title	R3Net: Random Weights, Rectifier Linear Units and Robustness for Artificial Neural Network
Authors	Arun Venkitaraman, Alireza M. Javid, Saikat Chatterjee
Abstract	We consider a neural network architecture with randomized features, a sign-splitter, followed by rectified linear units (ReLU). We prove that our architecture exhibits robustness to the input perturbation: the output feature of the neural network exhibits a Lipschitz continuity in terms of the input perturbation. We further show that the network output exhibits a discrimination ability that inputs that are not arbitrarily close generate output vectors which maintain distance between each other obeying a certain lower bound. This ensures that two different inputs remain discriminable while contracting the distance in the output feature space.
Tasks
Published	2018-03-12
URL	http://arxiv.org/abs/1803.04186v1
PDF	http://arxiv.org/pdf/1803.04186v1.pdf
PWC	https://paperswithcode.com/paper/r3net-random-weights-rectifier-linear-units
Repo
Framework

Overlapping Sliced Inverse Regression for Dimension Reduction


Title	Overlapping Sliced Inverse Regression for Dimension Reduction
Authors	Ning Zhang, Zhou Yu, Qiang Wu
Abstract	Sliced inverse regression (SIR) is a pioneer tool for supervised dimension reduction. It identifies the effective dimension reduction space, the subspace of significant factors with intrinsic lower dimensionality. In this paper, we propose to refine the SIR algorithm through an overlapping slicing scheme. The new algorithm, called overlapping sliced inverse regression (OSIR), is able to estimate the effective dimension reduction space and determine the number of effective factors more accurately. We show that such overlapping procedure has the potential to identify the information contained in the derivatives of the inverse regression curve, which helps to explain the superiority of OSIR. We also prove that OSIR algorithm is $\sqrt n $-consistent and verify its effectiveness by simulations and real applications.
Tasks	Dimensionality Reduction
Published	2018-06-23
URL	http://arxiv.org/abs/1806.08911v1
PDF	http://arxiv.org/pdf/1806.08911v1.pdf
PWC	https://paperswithcode.com/paper/overlapping-sliced-inverse-regression-for
Repo
Framework


Title	Deep Curiosity Loops in Social Environments
Authors	Jonatan Barkan, Goren Gordon
Abstract	Inspired by infants’ intrinsic motivation to learn, which values informative sensory channels contingent on their immediate social environment, we developed a deep curiosity loop (DCL) architecture. The DCL is composed of a learner, which attempts to learn a forward model of the agent’s state-action transition, and a novel reinforcement-learning (RL) component, namely, an Action-Convolution Deep Q-Network, which uses the learner’s prediction error as reward. The environment for our agent is composed of visual social scenes, composed of sitcom video streams, thereby both the learner and the RL are constructed as deep convolutional neural networks. The agent’s learner learns to predict the zero-th order of the dynamics of visual scenes, resulting in intrinsic rewards proportional to changes within its social environment. The sources of these socially informative changes within the sitcom are predominantly motions of faces and hands, leading to the unsupervised curiosity-based learning of social interaction features. The face and hand detection is represented by the value function and the social interaction optical-flow is represented by the policy. Our results suggest that face and hand detection are emergent properties of curiosity-based learning embedded in social environments.
Tasks	Optical Flow Estimation
Published	2018-06-10
URL	http://arxiv.org/abs/1806.03645v1
PDF	http://arxiv.org/pdf/1806.03645v1.pdf
PWC	https://paperswithcode.com/paper/deep-curiosity-loops-in-social-environments
Repo
Framework

Fast variational Bayes for heavy-tailed PLDA applied to i-vectors and x-vectors


Title	Fast variational Bayes for heavy-tailed PLDA applied to i-vectors and x-vectors
Authors	Anna Silnova, Niko Brummer, Daniel Garcia-Romero, David Snyder, Lukas Burget
Abstract	The standard state-of-the-art backend for text-independent speaker recognizers that use i-vectors or x-vectors, is Gaussian PLDA (G-PLDA), assisted by a Gaussianization step involving length normalization. G-PLDA can be trained with both generative or discriminative methods. It has long been known that heavy-tailed PLDA (HT-PLDA), applied without length normalization, gives similar accuracy, but at considerable extra computational cost. We have recently introduced a fast scoring algorithm for a discriminatively trained HT-PLDA backend. This paper extends that work by introducing a fast, variational Bayes, generative training algorithm. We compare old and new backends, with and without length-normalization, with i-vectors and x-vectors, on SRE’10, SRE’16 and SITW.
Tasks
Published	2018-03-24
URL	http://arxiv.org/abs/1803.09153v1
PDF	http://arxiv.org/pdf/1803.09153v1.pdf
PWC	https://paperswithcode.com/paper/fast-variational-bayes-for-heavy-tailed-plda
Repo
Framework