Paper Group ANR 778
An End-to-End Network for Generating Social Relationship Graphs. Generative Graph Convolutional Network for Growing Graphs. c-TextGen: Conditional Text Generation for Harmonious Human-Machine Interaction. TransSent: Towards Generation of Structured Sentences with Discourse Marker. AppsPred: Predicting Context-Aware Smartphone Apps using Random Fore …
An End-to-End Network for Generating Social Relationship Graphs
| Title | An End-to-End Network for Generating Social Relationship Graphs |
| Authors | Arushi Goel, Keng Teck Ma, Cheston Tan |
| Abstract | Socially-intelligent agents are of growing interest in artificial intelligence. To this end, we need systems that can understand social relationships in diverse social contexts. Inferring the social context in a given visual scene not only involves recognizing objects, but also demands a more in-depth understanding of the relationships and attributes of the people involved. To achieve this, one computational approach for representing human relationships and attributes is to use an explicit knowledge graph, which allows for high-level reasoning. We introduce a novel end-to-end-trainable neural network that is capable of generating a Social Relationship Graph - a structured, unified representation of social relationships and attributes - from a given input image. Our Social Relationship Graph Generation Network (SRG-GN) is the first to use memory cells like Gated Recurrent Units (GRUs) to iteratively update the social relationship states in a graph using scene and attribute context. The neural network exploits the recurrent connections among the GRUs to implement message passing between nodes and edges in the graph, and results in significant improvement over previous methods for social relationship recognition. |
| Tasks | Graph Generation, Visual Social Relationship Recognition |
| Published | 2019-03-23 |
| URL | http://arxiv.org/abs/1903.09784v1 |
| http://arxiv.org/pdf/1903.09784v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-end-to-end-network-for-generating-social |
| Repo | |
| Framework | |
Generative Graph Convolutional Network for Growing Graphs
| Title | Generative Graph Convolutional Network for Growing Graphs |
| Authors | Da Xu, Chuanwei Ruan, Kamiya Motwani, Evren Korpeoglu, Sushant Kumar, Kannan Achan |
| Abstract | Modeling generative process of growing graphs has wide applications in social networks and recommendation systems, where cold start problem leads to new nodes isolated from existing graph. Despite the emerging literature in learning graph representation and graph generation, most of them can not handle isolated new nodes without nontrivial modifications. The challenge arises due to the fact that learning to generate representations for nodes in observed graph relies heavily on topological features, whereas for new nodes only node attributes are available. Here we propose a unified generative graph convolutional network that learns node representations for all nodes adaptively in a generative model framework, by sampling graph generation sequences constructed from observed graph data. We optimize over a variational lower bound that consists of a graph reconstruction term and an adaptive Kullback-Leibler divergence regularization term. We demonstrate the superior performance of our approach on several benchmark citation network datasets. |
| Tasks | Graph Generation, Recommendation Systems |
| Published | 2019-03-06 |
| URL | http://arxiv.org/abs/1903.02640v1 |
| http://arxiv.org/pdf/1903.02640v1.pdf | |
| PWC | https://paperswithcode.com/paper/generative-graph-convolutional-network-for |
| Repo | |
| Framework | |
c-TextGen: Conditional Text Generation for Harmonious Human-Machine Interaction
| Title | c-TextGen: Conditional Text Generation for Harmonious Human-Machine Interaction |
| Authors | Bin Guo, Hao Wang, Yasan Ding, Shaoyang Hao, Yueqi Sun, Zhiwen Yu |
| Abstract | In recent years, with the development of deep learning technology, text generation technology has undergone great changes and provided many kinds of services for human beings, such as restaurant reservation and daily communication. The automatically generated text is becoming more and more fluent so researchers begin to consider more anthropomorphic text generation technology, that is the conditional text generation, including emotional text generation, personalized text generation, and so on. Conditional text generation (c-TextGen) has thus become a research hotspot. As a promising research field, we find that many efforts have been paid to researches of c-TextGen. Therefore, we aim to give a comprehensive review of the new research trends of c-TextGen. We first give a brief literature review of text generation technology, based on which we formalize the concept model of c-TextGen. We further make an investigation of several different c-TextGen techniques, and illustrate the advantages and disadvantages of commonly used neural network models. Finally, we discuss the open issues and promising research directions of c-TextGen. |
| Tasks | Text Generation |
| Published | 2019-09-08 |
| URL | https://arxiv.org/abs/1909.03409v1 |
| https://arxiv.org/pdf/1909.03409v1.pdf | |
| PWC | https://paperswithcode.com/paper/c-textgen-conditional-text-generation-for |
| Repo | |
| Framework | |
TransSent: Towards Generation of Structured Sentences with Discourse Marker
| Title | TransSent: Towards Generation of Structured Sentences with Discourse Marker |
| Authors | Xing Wu, Tao Zhang, Liangjun Zang, Jizhong Han, Songlin Hu |
| Abstract | This paper focuses on the task of generating long structured sentences with explicit discourse markers, by proposing a new task Sentence Transfer and a novel model architecture TransSent. Previous works on text generation fused semantic and structure information in one mixed hidden representation. However, the structure was difficult to maintain properly when the generated sentence became longer. In this work, we explicitly separate the modeling process of semantic information and structure information. Intuitively, humans produce long sentences by directly connecting discourses with discourse markers like and, but, etc. We thus define a new task called Sentence Transfer. This task represents a long sentence as (head discourse, discourse marker, tail discourse) and aims at tail discourse generation based on head discourse and discourse marker. Then, by connecting original head discourse and generated tail discourse with a discourse marker, we generate a long structured sentence. We also propose a model architecture called TransSent, which models relations between two discourses by interpreting them as transferring from one discourse to the other in the embedding space. Experiment results show that our model achieves better performance in automatic evaluations, and can generate structured sentences with high quality. The datasets can be accessed by https://github.com/1024er/TransSent dataset. |
| Tasks | Text Generation |
| Published | 2019-09-05 |
| URL | https://arxiv.org/abs/1909.05364v1 |
| https://arxiv.org/pdf/1909.05364v1.pdf | |
| PWC | https://paperswithcode.com/paper/transsent-towards-generation-of-structured |
| Repo | |
| Framework | |
AppsPred: Predicting Context-Aware Smartphone Apps using Random Forest Learning
| Title | AppsPred: Predicting Context-Aware Smartphone Apps using Random Forest Learning |
| Authors | Iqbal H. Sarker, Khaled Salah |
| Abstract | Due to the popularity of context-awareness in the Internet of Things (IoT) and the recent advanced features in the most popular IoT device, i.e., smartphone, modeling and predicting personalized usage behavior based on relevant contexts can be highly useful in assisting them to carry out daily routines and activities. Usage patterns of different categories smartphone apps such as social networking, communication, entertainment, or daily life services related apps usually vary greatly between individuals. People use these apps differently in different contexts, such as temporal context, spatial context, individual mood and preference, work status, Internet connectivity like Wifi? status, or device related status like phone profile, battery level etc. Thus, we consider individuals’ apps usage as a multi-class context-aware problem for personalized modeling and prediction. Random Forest learning is one of the most popular machine learning techniques to build a multi-class prediction model. Therefore, in this paper, we present an effective context-aware smartphone apps prediction model, and name it “AppsPred” using random forest machine learning technique that takes into account optimal number of trees based on such multi-dimensional contexts to build the resultant forest. The effectiveness of this model is examined by conducting experiments on smartphone apps usage datasets collected from individual users. The experimental results show that our AppsPred significantly outperforms other popular machine learning classification approaches like ZeroR, Naive Bayes, Decision Tree, Support Vector Machines, Logistic Regression while predicting smartphone apps in various context-aware test cases. |
| Tasks | |
| Published | 2019-08-26 |
| URL | https://arxiv.org/abs/1909.12949v1 |
| https://arxiv.org/pdf/1909.12949v1.pdf | |
| PWC | https://paperswithcode.com/paper/appspred-predicting-context-aware-smartphone |
| Repo | |
| Framework | |
Efficient structure learning with automatic sparsity selection for causal graph processes
| Title | Efficient structure learning with automatic sparsity selection for causal graph processes |
| Authors | Théophile Griveau-Billion, Ben Calderhead |
| Abstract | We propose a novel algorithm for efficiently computing a sparse directed adjacency matrix from a group of time series following a causal graph process. Our solution is scalable for both dense and sparse graphs and automatically selects the LASSO coefficient to obtain an appropriate number of edges in the adjacency matrix. Current state-of-the-art approaches rely on sparse-matrix-computation libraries to scale, and either avoid automatic selection of the LASSO penalty coefficient or rely on the prediction mean squared error, which is not directly related to the correct number of edges. Instead, we propose a cyclical coordinate descent algorithm that employs two new non-parametric error metrics to automatically select the LASSO coefficient. We demonstrate state-of-the-art performance of our algorithm on simulated stochastic block models and a real dataset of stocks from the S&P$500$. |
| Tasks | Time Series |
| Published | 2019-06-11 |
| URL | https://arxiv.org/abs/1906.04479v2 |
| https://arxiv.org/pdf/1906.04479v2.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-structure-learning-with-automatic |
| Repo | |
| Framework | |
Hybrid-Learning approach toward situation recognition and handling
| Title | Hybrid-Learning approach toward situation recognition and handling |
| Authors | Hossein Rajaby Faghihi, Mohammad Amin Fazli, Jafar Habibi |
| Abstract | The success of smart environments largely depends on their smartness of understanding the environments’ ongoing situations. Accordingly, this task is an essence to smart environment central processors. Obtaining knowledge from the environment is often through sensors, and the response to a particular circumstance is offered by actuators. This can be improved by getting user feedback, and capturing environmental changes. Machine learning techniques and semantic reasoning tools are widely used in this area to accomplish the goal of interpretation. In this paper, we have proposed a hybrid approach utilizing both machine learning and semantic reasoning tools to derive a better understanding from sensors. This method uses situation templates jointly with a decision tree to adapt the system knowledge to the environment. To test this approach we have used a simulation process which has resulted in a better precision for detecting situations in an ongoing environment involving living agents while capturing its dynamic nature. |
| Tasks | |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.09816v1 |
| https://arxiv.org/pdf/1906.09816v1.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-learning-approach-toward-situation |
| Repo | |
| Framework | |
CvxNet: Learnable Convex Decomposition
| Title | CvxNet: Learnable Convex Decomposition |
| Authors | Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey Hinton, Andrea Tagliasacchi |
| Abstract | Any solid object can be decomposed into a collection of convex polytopes (in short, convexes). When a small number of convexes are used, such a decomposition can bethought of as a piece-wise approximation of the geometry.This decomposition is fundamental to real-time physics simulation in computer graphics, where it creates a unified representation of dynamic geometry for collision detection. A convex object also has the property of being simultaneously an explicit and implicit representation: one can interpret it explicitly as a mesh derived by computing the vertices of a convex hull, or implicitly as the collection of half-space constraints or support functions. Their implicit representation makes them particularly well suited for neural net-work training, as they abstract away from the topology of the geometry they need to represent. We introduce a net-work architecture to represent a low dimensional family of convexes. This family is automatically derived via an auto-encoding process. We investigate the applications of this architecture including automatic convex decomposition, image to 3D reconstruction, and part-based shape retrieval. |
| Tasks | 3D Reconstruction |
| Published | 2019-09-12 |
| URL | https://arxiv.org/abs/1909.05736v3 |
| https://arxiv.org/pdf/1909.05736v3.pdf | |
| PWC | https://paperswithcode.com/paper/cvxnets-learnable-convex-decomposition |
| Repo | |
| Framework | |
Self-supervised Dense 3D Reconstruction from Monocular Endoscopic Video
| Title | Self-supervised Dense 3D Reconstruction from Monocular Endoscopic Video |
| Authors | Xingtong Liu, Ayushi Sinha, Masaru Ishii, Gregory D. Hager, Russell H. Taylor, Mathias Unberath |
| Abstract | We present a self-supervised learning-based pipeline for dense 3D reconstruction from full-length monocular endoscopic videos without a priori modeling of anatomy or shading. Our method only relies on unlabeled monocular endoscopic videos and conventional multi-view stereo algorithms, and requires neither manual interaction nor patient CT in both training and application phases. In a cross-patient study using CT scans as groundtruth, we show that our method is able to produce photo-realistic dense 3D reconstructions with submillimeter mean residual errors from endoscopic videos from unseen patients and scopes. |
| Tasks | 3D Reconstruction |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.03101v1 |
| https://arxiv.org/pdf/1909.03101v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-dense-3d-reconstruction-from |
| Repo | |
| Framework | |
Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits
| Title | Training Neural Networks as Learning Data-adaptive Kernels: Provable Representation and Approximation Benefits |
| Authors | Xialiang Dou, Tengyuan Liang |
| Abstract | Consider the problem: given the data pair $(\mathbf{x}, \mathbf{y})$ drawn from a population with $f_*(x) = \mathbf{E}[\mathbf{y} \mathbf{x} = x]$, specify a neural network model and run gradient flow on the weights over time until reaching any stationarity. How does $f_t$, the function computed by the neural network at time $t$, relate to $f_*$, in terms of approximation and representation? What are the provable benefits of the adaptive representation by neural networks compared to the pre-specified fixed basis representation in the classical nonparametric literature? We answer the above questions via a dynamic reproducing kernel Hilbert space (RKHS) approach indexed by the training process of neural networks. Firstly, we show that when reaching any local stationarity, gradient flow learns an adaptive RKHS representation and performs the global least-squares projection onto the adaptive RKHS, simultaneously. Secondly, we prove that as the RKHS is data-adaptive and task-specific, the residual for $f_*$ lies in a subspace that is potentially much smaller than the orthogonal complement of the RKHS. The result formalizes the representation and approximation benefits of neural networks. Lastly, we show that the neural network function computed by gradient flow converges to the kernel ridgeless regression with an adaptive kernel, in the limit of vanishing regularization. The adaptive kernel viewpoint provides new angles of studying the approximation, representation, generalization, and optimization advantages of neural networks. |
| Tasks | |
| Published | 2019-01-21 |
| URL | https://arxiv.org/abs/1901.07114v2 |
| https://arxiv.org/pdf/1901.07114v2.pdf | |
| PWC | https://paperswithcode.com/paper/training-neural-networks-as-learning-data |
| Repo | |
| Framework | |
Losing Confidence in Quality: Unspoken Evolution of Computer Vision Services
| Title | Losing Confidence in Quality: Unspoken Evolution of Computer Vision Services |
| Authors | Alex Cummaudo, Rajesh Vasa, John Grundy, Mohamed Abdelrazek, Andrew Cain |
| Abstract | Recent advances in artificial intelligence (AI) and machine learning (ML), such as computer vision, are now available as intelligent services and their accessibility and simplicity is compelling. Multiple vendors now offer this technology as cloud services and developers want to leverage these advances to provide value to end-users. However, there is no firm investigation into the maintenance and evolution risks arising from use of these intelligent services; in particular, their behavioural consistency and transparency of their functionality. We evaluated the responses of three different intelligent services (specifically computer vision) over 11 months using 3 different data sets, verifying responses against the respective documentation and assessing evolution risk. We found that there are: (1) inconsistencies in how these services behave; (2) evolution risk in the responses; and (3) a lack of clear communication that documents these risks and inconsistencies. We propose a set of recommendations to both developers and intelligent service providers to inform risk and assist maintainability. |
| Tasks | |
| Published | 2019-06-18 |
| URL | https://arxiv.org/abs/1906.07328v2 |
| https://arxiv.org/pdf/1906.07328v2.pdf | |
| PWC | https://paperswithcode.com/paper/losing-confidence-in-quality-unspoken |
| Repo | |
| Framework | |
Statistical Descriptors-based Automatic Fingerprint Identification: Machine Learning Approaches
| Title | Statistical Descriptors-based Automatic Fingerprint Identification: Machine Learning Approaches |
| Authors | Hamid Jan, Amjad Ali, Shahid Mahmood, Gautam Srivastava |
| Abstract | Identification of a person from fingerprints of good quality has been used by commercial applications and law enforcement agencies for many years, however identification of a person from latent fingerprints is very difficult and challenging. A latent fingerprint is a fingerprint left on a surface by deposits of oils and/or perspiration from the finger. It is not usually visible to the naked eye but may be detected with special techniques such as dusting with fine powder and then lifting the pattern of powder with transparent tape. We have evaluated the quality of machine learning techniques that has been implemented in automatic fingerprint identification. In this paper, we use fingerprints of low quality from database DB1 of Fingerprint Verification Competition (FVC 2002) to conduct our experiments. Fingerprints are processed to find its core point using Poincare index and carry out enhancement using Diffusion coherence filter whose performance is known to be good in the high curvature regions of fingerprints. Grey-level Co-Occurrence Matrix (GLCM) based seven statistical descriptors with four different inter pixel distances are then extracted as features and put forward to train and test REPTree, RandomTree, J48, Decision Stump and Random Forest Machine Learning techniques for personal identification. Experiments are conducted on 80 instances and 28 attributes. Our experiments proved that Random Forests and J48 give good results for latent fingerprints as compared to other machine learning techniques and can help improve the identification accuracy. |
| Tasks | |
| Published | 2019-07-18 |
| URL | https://arxiv.org/abs/1907.12741v1 |
| https://arxiv.org/pdf/1907.12741v1.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-descriptors-based-automatic |
| Repo | |
| Framework | |
A Machine-Synesthetic Approach To DDoS Network Attack Detection
| Title | A Machine-Synesthetic Approach To DDoS Network Attack Detection |
| Authors | Yuri Monakhov, Oleg Nikitin, Anna Kuznetsova, Alexey Kharlamov, Alexandr Amochkin |
| Abstract | In the authors’ opinion, anomaly detection systems, or ADS, seem to be the most perspective direction in the subject of attack detection, because these systems can detect, among others, the unknown (zero-day) attacks. To detect anomalies, the authors propose to use machine synesthesia. In this case, machine synesthesia is understood as an interface that allows using image classification algorithms in the problem of detecting network anomalies, making it possible to use non-specialized image detection methods that have recently been widely and actively developed. The proposed approach is that the network traffic data is “projected” into the image. It can be seen from the experimental results that the proposed method for detecting anomalies shows high results in the detection of attacks. On a large sample, the value of the complex efficiency indicator reaches 97%. |
| Tasks | Anomaly Detection, Image Classification |
| Published | 2019-01-13 |
| URL | http://arxiv.org/abs/1901.04017v2 |
| http://arxiv.org/pdf/1901.04017v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-machine-synesthetic-approach-to-ddos |
| Repo | |
| Framework | |
A Survey on Why-Type Question Answering Systems
| Title | A Survey on Why-Type Question Answering Systems |
| Authors | Manvi Breja, Sanjay Kumar Jain |
| Abstract | Search engines such as Google, Yahoo and Baidu yield information in the form of a relevant set of web pages according to the need of the user. Question Answering Systems reduce the time taken to get an answer, to a query asked in natural language by providing the one most relevant answer. To the best of our knowledge, major research in Why-type questions began in early 2000’s and our work on Why-type questions can help explore newer avenues for fact-finding and analysis. The paper presents a survey on Why-type Question Answering System, details the architecture, the processes involved in the system and suggests further areas of research. |
| Tasks | Question Answering |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.04879v1 |
| https://arxiv.org/pdf/1911.04879v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-on-why-type-question-answering |
| Repo | |
| Framework | |
DeepLocalization: Landmark-based Self-Localization with Deep Neural Networks
| Title | DeepLocalization: Landmark-based Self-Localization with Deep Neural Networks |
| Authors | Nico Engel, Stefan Hoermann, Markus Horn, Vasileios Belagiannis, Klaus Dietmayer |
| Abstract | We address the problem of vehicle self-localization from multi-modal sensor information and a reference map. The map is generated off-line by extracting landmarks from the vehicle’s field of view, while the measurements are collected similarly on the fly. Our goal is to determine the autonomous vehicle’s pose from the landmark measurements and map landmarks. To learn this mapping, we propose DeepLocalization, a deep neural network that regresses the vehicle’s translation and rotation parameters from unordered and dynamic input landmarks. The proposed network architecture is robust to changes of the dynamic environment and can cope with a small number of extracted landmarks. During the training process we rely on synthetically generated ground-truth. In our experiments, we evaluate two inference approaches in real-world scenarios. We show that DeepLocalization can be combined with regular GPS signals and filtering algorithms such as the extended Kalman filter. Our approach achieves state-of-the-art accuracy and is about ten times faster than the related work. |
| Tasks | |
| Published | 2019-04-18 |
| URL | https://arxiv.org/abs/1904.09007v2 |
| https://arxiv.org/pdf/1904.09007v2.pdf | |
| PWC | https://paperswithcode.com/paper/deeplocalization-landmark-based-self |
| Repo | |
| Framework | |
