Paper Group ANR 451
Automated essay scoring with string kernels and word embeddings. Predicting Effective Control Parameters for Differential Evolution using Cluster Analysis of Objective Function Features. The algorithm of the impulse noise filtration in images based on an algorithm of community detection in graphs. Pre-training Graph Neural Networks with Kernels. Fe …
Automated essay scoring with string kernels and word embeddings
| Title | Automated essay scoring with string kernels and word embeddings |
| Authors | Mădălina Cozma, Andrei M. Butnaru, Radu Tudor Ionescu |
| Abstract | In this work, we present an approach based on combining string kernels and word embeddings for automatic essay scoring. String kernels capture the similarity among strings based on counting common character n-grams, which are a low-level yet powerful type of feature, demonstrating state-of-the-art results in various text classification tasks such as Arabic dialect identification or native language identification. To our best knowledge, we are the first to apply string kernels to automatically score essays. We are also the first to combine them with a high-level semantic feature representation, namely the bag-of-super-word-embeddings. We report the best performance on the Automated Student Assessment Prize data set, in both in-domain and cross-domain settings, surpassing recent state-of-the-art deep learning approaches. |
| Tasks | Language Identification, Native Language Identification, Text Classification, Word Embeddings |
| Published | 2018-04-21 |
| URL | http://arxiv.org/abs/1804.07954v2 |
| http://arxiv.org/pdf/1804.07954v2.pdf | |
| PWC | https://paperswithcode.com/paper/automated-essay-scoring-with-string-kernels |
| Repo | |
| Framework | |
Predicting Effective Control Parameters for Differential Evolution using Cluster Analysis of Objective Function Features
| Title | Predicting Effective Control Parameters for Differential Evolution using Cluster Analysis of Objective Function Features |
| Authors | Sean P. Walton, M. Rowan Brown |
| Abstract | A methodology is introduced which uses three simple objective function features to predict effective control parameters for differential evolution. This is achieved using cluster analysis techniques to classify objective functions using these features. Information on prior performance of various control parameters for each classification is then used to determine which control parameters to use in future optimisations. Our approach is compared to state-of-the-art adaptive and non-adaptive techniques. Two accepted bench mark suites are used to compare performance and in all cases we show that the improvement resulting from our approach is statistically significant. The majority of the computational effort of this methodology is performed off-line, however even when taking into account the additional on-line cost our approach outperforms other adaptive techniques. We also investigate the key tuning parameters of our methodology, such as number of clusters, which further support the finding that the simple features selected are predictors of effective control parameters. The findings presented in this paper are significant because they show that simple to calculate features of objective functions can help to select control parameters for optimisation algorithms. This can have an immediate positive impact on the application of these optimisation algorithms on real world problems, where it is often difficult to select effective control parameters. |
| Tasks | |
| Published | 2018-06-25 |
| URL | https://arxiv.org/abs/1806.09432v2 |
| https://arxiv.org/pdf/1806.09432v2.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-effective-control-parameters-for |
| Repo | |
| Framework | |
The algorithm of the impulse noise filtration in images based on an algorithm of community detection in graphs
| Title | The algorithm of the impulse noise filtration in images based on an algorithm of community detection in graphs |
| Authors | S. V. Belim, S. B. Larionov |
| Abstract | This article suggests an algorithm of impulse noise filtration, based on the community detection in graphs. The image is representing as non-oriented weighted graph. Each pixel of an image is corresponding to a vertex of the graph. Community detection algorithm is running on the given graph. Assumed that communities that contain only one pixel are corresponding to noised pixels of an image. Suggested method was tested with help of computer experiment. This experiment was conducted on grayscale, and on colored images, on artificial images and on photos. It is shown that the suggested method is better than median filter by 20% regardless of noise percent. Higher efficiency is justified by the fact that most of filters are changing all of image pixels, but suggested method is finding and restoring only noised pixels. The dependence of the effectiveness of the proposed method on the percentage of noise in the image is shown. |
| Tasks | Community Detection |
| Published | 2018-12-25 |
| URL | http://arxiv.org/abs/1812.10098v1 |
| http://arxiv.org/pdf/1812.10098v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-algorithm-of-the-impulse-noise-filtration |
| Repo | |
| Framework | |
Pre-training Graph Neural Networks with Kernels
| Title | Pre-training Graph Neural Networks with Kernels |
| Authors | Nicolò Navarin, Dinh V. Tran, Alessandro Sperduti |
| Abstract | Many machine learning techniques have been proposed in the last few years to process data represented in graph-structured form. Graphs can be used to model several scenarios, from molecules and materials to RNA secondary structures. Several kernel functions have been defined on graphs that coupled with kernelized learning algorithms, have shown state-of-the-art performances on many tasks. Recently, several definitions of Neural Networks for Graph (GNNs) have been proposed, but their accuracy is not yet satisfying. In this paper, we propose a task-independent pre-training methodology that allows a GNN to learn the representation induced by state-of-the-art graph kernels. Then, the supervised learning phase will fine-tune this representation for the task at hand. The proposed technique is agnostic on the adopted GNN architecture and kernel function, and shows consistent improvements in the predictive performance of GNNs in our preliminary experimental results. |
| Tasks | |
| Published | 2018-11-16 |
| URL | http://arxiv.org/abs/1811.06930v1 |
| http://arxiv.org/pdf/1811.06930v1.pdf | |
| PWC | https://paperswithcode.com/paper/pre-training-graph-neural-networks-with |
| Repo | |
| Framework | |
Feature-based groupwise registration of historical aerial images to present-day ortho-photo maps
| Title | Feature-based groupwise registration of historical aerial images to present-day ortho-photo maps |
| Authors | Sebastian Zambanini |
| Abstract | In this paper, we address the registration of historical WWII images to present-day ortho-photo maps for the purpose of geolocalization. Due to the challenging nature of this problem, we propose to register the images jointly as a group rather than in a step-by-step manner. To this end, we exploit Hough Voting spaces as pairwise registration estimators and show how they can be integrated into a probabilistic groupwise registration framework that can be efficiently optimized. The feature-based nature of our registration framework allows to register images with a-priori unknown translational and rotational relations, and is also able to handle scale changes of up to 30% in our test data due to a final geometrically guided matching step. The superiority of the proposed method over existing pairwise and groupwise registration methods is demonstrated on eight highly challenging sets of historical images with corresponding ortho-photo maps. |
| Tasks | |
| Published | 2018-11-22 |
| URL | http://arxiv.org/abs/1811.09081v1 |
| http://arxiv.org/pdf/1811.09081v1.pdf | |
| PWC | https://paperswithcode.com/paper/feature-based-groupwise-registration-of |
| Repo | |
| Framework | |
Higher-Order Spectral Clustering under Superimposed Stochastic Block Model
| Title | Higher-Order Spectral Clustering under Superimposed Stochastic Block Model |
| Authors | Subhadeep Paul, Olgica Milenkovic, Yuguo Chen |
| Abstract | Higher-order motif structures and multi-vertex interactions are becoming increasingly important in studies that aim to improve our understanding of functionalities and evolution patterns of networks. To elucidate the role of higher-order structures in community detection problems over complex networks, we introduce the notion of a Superimposed Stochastic Block Model (SupSBM). The model is based on a random graph framework in which certain higher-order structures or subgraphs are generated through an independent hyperedge generation process, and are then replaced with graphs that are superimposed with directed or undirected edges generated by an inhomogeneous random graph model. Consequently, the model introduces controlled dependencies between edges which allow for capturing more realistic network phenomena, namely strong local clustering in a sparse network, short average path length, and community structure. We proceed to rigorously analyze the performance of a number of recently proposed higher-order spectral clustering methods on the SupSBM. In particular, we prove non-asymptotic upper bounds on the misclustering error of spectral community detection for a SupSBM setting in which triangles or 3-uniform hyperedges are superimposed with undirected edges. As part of our analysis, we also derive new bounds on the misclustering error of higher-order spectral clustering methods for the standard SBM and the 3-uniform hypergraph SBM. Furthermore, for a non-uniform hypergraph SBM model in which one directly observes both edges and 3-uniform hyperedges, we obtain a criterion that describes when to perform spectral clustering based on edges and when on hyperedges, based on a function of hyperedge density and observation quality. |
| Tasks | Community Detection |
| Published | 2018-12-16 |
| URL | http://arxiv.org/abs/1812.06515v1 |
| http://arxiv.org/pdf/1812.06515v1.pdf | |
| PWC | https://paperswithcode.com/paper/higher-order-spectral-clustering-under |
| Repo | |
| Framework | |
Automatic Adaptation of Person Association for Multiview Tracking in Group Activities
| Title | Automatic Adaptation of Person Association for Multiview Tracking in Group Activities |
| Authors | Minh Vo, Ersin Yumer, Kalyan Sunkavalli, Sunil Hadap, Yaser Sheikh, Srinivasa Narasimhan |
| Abstract | Reliable markerless motion tracking of multiple people participating in complex group activity from multiple handheld cameras is challenging due to frequent occlusions, strong viewpoint and appearance variations, and asynchronous video streams. The key to solving this problem is to reliably associate the same person across distant viewpoint and temporal instances. In this work, we combine motion tracking, mutual exclusion constraints, and multiview geometry in a multitask learning framework to automatically adapt a generic person appearance descriptor to the domain videos. Tracking is formulated as a spatiotemporally constrained clustering using the adapted person descriptor. Physical human constraints are exploited to reconstruct accurate and consistent 3D skeletons for every person across the entire sequence. We show significant improvement in association accuracy (up to 18%) in events with up to 60 people and 3D human skeleton reconstruction (5 to 10 times) over the baseline for events captured “in the wild”. |
| Tasks | |
| Published | 2018-05-22 |
| URL | http://arxiv.org/abs/1805.08717v2 |
| http://arxiv.org/pdf/1805.08717v2.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-adaptation-of-person-association |
| Repo | |
| Framework | |
Jet Charge and Machine Learning
| Title | Jet Charge and Machine Learning |
| Authors | Katherine Fraser, Matthew D. Schwartz |
| Abstract | Modern machine learning techniques, such as convolutional, recurrent and recursive neural networks, have shown promise for jet substructure at the Large Hadron Collider. For example, they have demonstrated effectiveness at boosted top or W boson identification or for quark/gluon discrimination. We explore these methods for the purpose of classifying jets according to their electric charge. We find that both neural networks that incorporate distance within the jet as an input and boosted decision trees including radial distance information can provide significant improvement in jet charge extraction over current methods. Specifically, convolutional, recurrent, and recursive networks can provide the largest improvement over traditional methods, in part by effectively utilizing distance within the jet or clustering history. The advantages of using a fixed-size input representation (as with the CNN) or a small input representation (as with the RNN) suggest that both convolutional and recurrent networks will be essential to the future of modern machine learning at colliders. |
| Tasks | |
| Published | 2018-03-21 |
| URL | http://arxiv.org/abs/1803.08066v2 |
| http://arxiv.org/pdf/1803.08066v2.pdf | |
| PWC | https://paperswithcode.com/paper/jet-charge-and-machine-learning |
| Repo | |
| Framework | |
Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool
| Title | Inverse Visual Question Answering: A New Benchmark and VQA Diagnosis Tool |
| Authors | Feng Liu, Tao Xiang, Timothy M. Hospedales, Wankou Yang, Changyin Sun |
| Abstract | In recent years, visual question answering (VQA) has become topical. The premise of VQA’s significance as a benchmark in AI, is that both the image and textual question need to be well understood and mutually grounded in order to infer the correct answer. However, current VQA models perhaps understand' less than initially hoped, and instead master the easier task of exploiting cues given away in the question and biases in the answer distribution. In this paper we propose the inverse problem of VQA (iVQA). The iVQA task is to generate a question that corresponds to a given image and answer pair. We propose a variational iVQA model that can generate diverse, grammatically correct and content correlated questions that match the given answer. Based on this model, we show that iVQA is an interesting benchmark for visuo-linguistic understanding, and a more challenging alternative to VQA because an iVQA model needs to understand the image better to be successful. As a second contribution, we show how to use iVQA in a novel reinforcement learning framework to diagnose any existing VQA model by way of exposing its belief set: the set of question-answer pairs that the VQA model would predict true for a given image. This provides a completely new window into what VQA models believe’ about images. We show that existing VQA models have more erroneous beliefs than previously thought, revealing their intrinsic weaknesses. Suggestions are then made on how to address these weaknesses going forward. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2018-03-16 |
| URL | http://arxiv.org/abs/1803.06936v1 |
| http://arxiv.org/pdf/1803.06936v1.pdf | |
| PWC | https://paperswithcode.com/paper/inverse-visual-question-answering-a-new |
| Repo | |
| Framework | |
Unrepresentative video data: A review and evaluation
| Title | Unrepresentative video data: A review and evaluation |
| Authors | Georgios Mastorakis |
| Abstract | It is well known that the quality and quantity of training data are significant factors which affect the development and performance of machine intelligence algorithms. Without representative data, neither scientists nor algorithms would be able to accurately capture the visual details of objects, actions or scenes. An evaluation methodology which filters data quality does not yet exist, and currently, the validation of the data depends solely on human factor. This study reviews several public datasets and discusses their limitations and issues regarding quality, feasibility, adaptation and availability of training data. A simple approach to evaluate (i.e. automatically “clean” samples) training data is proposed with the use of real events recorded on the YouTube platform. This study focuses on action recognition data and particularly on human fall detection datasets. However, the limitations described in this paper apply in virtually all datasets. |
| Tasks | Temporal Action Localization |
| Published | 2018-11-28 |
| URL | http://arxiv.org/abs/1811.11815v2 |
| http://arxiv.org/pdf/1811.11815v2.pdf | |
| PWC | https://paperswithcode.com/paper/unrepresentative-video-data-a-review-and |
| Repo | |
| Framework | |
Short-Term Wind-Speed Forecasting Using Kernel Spectral Hidden Markov Models
| Title | Short-Term Wind-Speed Forecasting Using Kernel Spectral Hidden Markov Models |
| Authors | Shunsuke Tsuzuki, Yu Nishiyama |
| Abstract | In machine learning, a nonparametric forecasting algorithm for time series data has been proposed, called the kernel spectral hidden Markov model (KSHMM). In this paper, we propose a technique for short-term wind-speed prediction based on KSHMM. We numerically compared the performance of our KSHMM-based forecasting technique to other techniques with machine learning, using wind-speed data offered by the National Renewable Energy Laboratory. Our results demonstrate that, compared to these methods, the proposed technique offers comparable or better performance. |
| Tasks | Time Series |
| Published | 2018-11-15 |
| URL | http://arxiv.org/abs/1811.06210v1 |
| http://arxiv.org/pdf/1811.06210v1.pdf | |
| PWC | https://paperswithcode.com/paper/short-term-wind-speed-forecasting-using |
| Repo | |
| Framework | |
Learning to Generate Music with BachProp
| Title | Learning to Generate Music with BachProp |
| Authors | Florian Colombo, Johanni Brea, Wulfram Gerstner |
| Abstract | As deep learning advances, algorithms of music composition increase in performance. However, most of the successful models are designed for specific musical structures. Here, we present BachProp, an algorithmic composer that can generate music scores in many styles given sufficient training data. To adapt BachProp to a broad range of musical styles, we propose a novel representation of music and train a deep network to predict the note transition probabilities of a given music corpus. In this paper, new music scores generated by BachProp are compared with the original corpora as well as with different network architectures and other related models. We show that BachProp captures important features of the original datasets better than other models and invite the reader to a qualitative comparison on a large collection of generated songs. |
| Tasks | |
| Published | 2018-12-17 |
| URL | https://arxiv.org/abs/1812.06669v2 |
| https://arxiv.org/pdf/1812.06669v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-generate-music-with-bachprop |
| Repo | |
| Framework | |
Document classification using a Bi-LSTM to unclog Brazil’s supreme court
| Title | Document classification using a Bi-LSTM to unclog Brazil’s supreme court |
| Authors | Fabricio Ataides Braz, Nilton Correia da Silva, Teofilo Emidio de Campos, Felipe Borges S. Chaves, Marcelo H. S. Ferreira, Pedro Henrique Inazawa, Victor H. D. Coelho, Bernardo Pablo Sukiennik, Ana Paula Goncalves Soares de Almeida, Flavio Barros Vidal, Davi Alves Bezerra, Davi B. Gusmao, Gabriel G. Ziegler, Ricardo V. C. Fernandes, Roberta Zumblick, Fabiano Hartmann Peixoto |
| Abstract | The Brazilian court system is currently the most clogged up judiciary system in the world. Thousands of lawsuit cases reach the supreme court every day. These cases need to be analyzed in order to be associated to relevant tags and allocated to the right team. Most of the cases reach the court as raster scanned documents with widely variable levels of quality. One of the first steps for the analysis is to classify these documents. In this paper we present a Bidirectional Long Short-Term Memory network (Bi-LSTM) to classify these pieces of legal document. |
| Tasks | Document Classification |
| Published | 2018-11-27 |
| URL | http://arxiv.org/abs/1811.11569v1 |
| http://arxiv.org/pdf/1811.11569v1.pdf | |
| PWC | https://paperswithcode.com/paper/document-classification-using-a-bi-lstm-to |
| Repo | |
| Framework | |
Breaking Reversibility Accelerates Langevin Dynamics for Global Non-Convex Optimization
| Title | Breaking Reversibility Accelerates Langevin Dynamics for Global Non-Convex Optimization |
| Authors | Xuefeng Gao, Mert Gurbuzbalaban, Lingjiong Zhu |
| Abstract | Langevin dynamics (LD) has been proven to be a powerful technique for optimizing a non-convex objective as an efficient algorithm to find local minima while eventually visiting a global minimum on longer time-scales. LD is based on the first-order Langevin diffusion which is reversible in time. We study two variants that are based on non-reversible Langevin diffusions: the underdamped Langevin dynamics (ULD) and the Langevin dynamics with a non-symmetric drift (NLD). Adopting the techniques of Tzen, Liang and Raginsky (2018) for LD to non-reversible diffusions, we show that for a given local minimum that is within an arbitrary distance from the initialization, with high probability, either the ULD trajectory ends up somewhere outside a small neighborhood of this local minimum within a recurrence time which depends on the smallest eigenvalue of the Hessian at the local minimum or they enter this neighborhood by the recurrence time and stay there for a potentially exponentially long escape time. The ULD algorithms improve upon the recurrence time obtained for LD in Tzen, Liang and Raginsky (2018) with respect to the dependency on the smallest eigenvalue of the Hessian at the local minimum. Similar result and improvement are obtained for the NLD algorithm. We also show that non-reversible variants can exit the basin of attraction of a local minimum faster in discrete time when the objective has two local minima separated by a saddle point and quantify the amount of improvement. Our analysis suggests that non-reversible Langevin algorithms are more efficient to locate a local minimum as well as exploring the state space. Our analysis is based on the quadratic approximation of the objective around a local minimum. As a by-product of our analysis, we obtain optimal mixing rates for quadratic objectives in the 2-Wasserstein distance for two non-reversible Langevin algorithms we consider. |
| Tasks | |
| Published | 2018-12-19 |
| URL | https://arxiv.org/abs/1812.07725v3 |
| https://arxiv.org/pdf/1812.07725v3.pdf | |
| PWC | https://paperswithcode.com/paper/breaking-reversibility-accelerates-langevin |
| Repo | |
| Framework | |
Real-Time Visual Tracking and Identification for a Team of Homogeneous Humanoid Robots
| Title | Real-Time Visual Tracking and Identification for a Team of Homogeneous Humanoid Robots |
| Authors | Hafez Farazi, Sven Behnke |
| Abstract | The use of a team of humanoid robots to collaborate in completing a task is an increasingly important field of research. One of the challenges in achieving collaboration, is mutual identification and tracking of the robots. This work presents a real-time vision-based approach to the detection and tracking of robots of known appearance, based on the images captured by a stationary robot. A Histogram of Oriented Gradients descriptor is used to detect the robots and the robot headings are estimated by a multiclass classifier. The tracked robots report their own heading estimate from magnetometer readings. For tracking, a cost function based on position and heading is applied to each of the tracklets, and a globally optimal labeling of the detected robots is found using the Hungarian algorithm. The complete identification and tracking system was tested using two igus Humanoid Open Platform robots on a soccer field. We expect that a similar system can be used with other humanoid robots, such as Nao and DARwIn-OP |
| Tasks | Real-Time Visual Tracking, Visual Tracking |
| Published | 2018-10-15 |
| URL | http://arxiv.org/abs/1810.06411v2 |
| http://arxiv.org/pdf/1810.06411v2.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-visual-tracking-and-identification |
| Repo | |
| Framework | |
