October 16, 2019

3181 words 15 mins read

Paper Group ANR 1129

Time series clustering based on the characterisation of segment typologies. DuPLO: A DUal view Point deep Learning architecture for time series classificatiOn. IIIDYT at SemEval-2018 Task 3: Irony detection in English tweets. Fault Area Detection in Leaf Diseases using k-means Clustering. From BOP to BOSS and Beyond: Time Series Classification with …

Time series clustering based on the characterisation of segment typologies


Title	Time series clustering based on the characterisation of segment typologies
Authors	David Guijo-Rubio, Antonio Manuel Durán-Rosal, Pedro Antonio Gutiérrez, Alicia Troncoso, César Hervás-Martínez
Abstract	Time series clustering is the process of grouping time series with respect to their similarity or characteristics. Previous approaches usually combine a specific distance measure for time series and a standard clustering method. However, these approaches do not take the similarity of the different subsequences of each time series into account, which can be used to better compare the time series objects of the dataset. In this paper, we propose a novel technique of time series clustering based on two clustering stages. In a first step, a least squares polynomial segmentation procedure is applied to each time series, which is based on a growing window technique that returns different-length segments. Then, all the segments are projected into same dimensional space, based on the coefficients of the model that approximates the segment and a set of statistical features. After mapping, a first hierarchical clustering phase is applied to all mapped segments, returning groups of segments for each time series. These clusters are used to represent all time series in the same dimensional space, after defining another specific mapping process. In a second and final clustering stage, all the time series objects are grouped. We consider internal clustering quality to automatically adjust the main parameter of the algorithm, which is an error threshold for the segmenta- tion. The results obtained on 84 datasets from the UCR Time Series Classification Archive have been compared against two state-of-the-art methods, showing that the performance of this methodology is very promising.
Tasks	Time Series, Time Series Classification, Time Series Clustering
Published	2018-10-27
URL	http://arxiv.org/abs/1810.11624v1
PDF	http://arxiv.org/pdf/1810.11624v1.pdf
PWC	https://paperswithcode.com/paper/time-series-clustering-based-on-the
Repo
Framework

DuPLO: A DUal view Point deep Learning architecture for time series classificatiOn


Title	DuPLO: A DUal view Point deep Learning architecture for time series classificatiOn
Authors	Roberto Interdonato, Dino Ienco, Raffaele Gaetano, Kenji Ose
Abstract	Nowadays, modern Earth Observation systems continuously generate huge amounts of data. A notable example is represented by the Sentinel-2 mission, which provides images at high spatial resolution (up to 10m) with high temporal revisit period (every 5 days), which can be organized in Satellite Image Time Series (SITS). While the use of SITS has been proved to be beneficial in the context of Land Use/Land Cover (LULC) map generation, unfortunately, machine learning approaches commonly leveraged in remote sensing field fail to take advantage of spatio-temporal dependencies present in such data. Recently, new generation deep learning methods allowed to significantly advance research in this field. These approaches have generally focused on a single type of neural network, i.e., Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs), which model different but complementary information: spatial autocorrelation (CNNs) and temporal dependencies (RNNs). In this work, we propose the first deep learning architecture for the analysis of SITS data, namely \method{} (DUal view Point deep Learning architecture for time series classificatiOn), that combines Convolutional and Recurrent neural networks to exploit their complementarity. Our hypothesis is that, since CNNs and RNNs capture different aspects of the data, a combination of both models would produce a more diverse and complete representation of the information for the underlying land cover classification task. Experiments carried out on two study sites characterized by different land cover characteristics (i.e., the \textit{Gard} site in France and the \textit{Reunion Island} in the Indian Ocean), demonstrate the significance of our proposal.
Tasks	Time Series, Time Series Classification
Published	2018-09-20
URL	http://arxiv.org/abs/1809.07589v1
PDF	http://arxiv.org/pdf/1809.07589v1.pdf
PWC	https://paperswithcode.com/paper/duplo-a-dual-view-point-deep-learning
Repo
Framework

IIIDYT at SemEval-2018 Task 3: Irony detection in English tweets


Title	IIIDYT at SemEval-2018 Task 3: Irony detection in English tweets
Authors	Edison Marrese-Taylor, Suzana Ilic, Jorge A. Balazs, Yutaka Matsuo, Helmut Prendinger
Abstract	In this paper we introduce our system for the task of Irony detection in English tweets, a part of SemEval 2018. We propose representation learning approach that relies on a multi-layered bidirectional LSTM, without using external features that provide additional semantic information. Although our model is able to outperform the baseline in the validation set, our results show limited generalization power over the test set. Given the limited size of the dataset, we think the usage of more pre-training schemes would greatly improve the obtained results.
Tasks	Representation Learning
Published	2018-04-22
URL	http://arxiv.org/abs/1804.08094v1
PDF	http://arxiv.org/pdf/1804.08094v1.pdf
PWC	https://paperswithcode.com/paper/iiidyt-at-semeval-2018-task-3-irony-detection
Repo
Framework

Fault Area Detection in Leaf Diseases using k-means Clustering


Title	Fault Area Detection in Leaf Diseases using k-means Clustering
Authors	Subhajit Maity, Sujan Sarkar, Avinaba Tapadar, Ayan Dutta, Sanket Biswas, Sayon Nayek, Pritam Saha
Abstract	With increasing population the crisis of food is getting bigger day by day.In this time of crisis,the leaf disease of crops is the biggest problem in the food industry.In this paper, we have addressed that problem and proposed an efficient method to detect leaf disease.Leaf diseases can be detected from sample images of the leaf with the help of image processing and segmentation.Using k-means clustering and Otsu’s method the faulty region in a leaf is detected which helps to determine proper course of action to be taken.Further the ratio of normal and faulty region if calculated would be able to predict if the leaf can be cured at all.
Tasks
Published	2018-10-24
URL	http://arxiv.org/abs/1810.10188v1
PDF	http://arxiv.org/pdf/1810.10188v1.pdf
PWC	https://paperswithcode.com/paper/fault-area-detection-in-leaf-diseases-using-k
Repo
Framework

From BOP to BOSS and Beyond: Time Series Classification with Dictionary Based Classifiers


Title	From BOP to BOSS and Beyond: Time Series Classification with Dictionary Based Classifiers
Authors	James Large, Anthony Bagnall, Simon Malinowski, Romain Tavenard
Abstract	A family of algorithms for time series classification (TSC) involve running a sliding window across each series, discretising the window to form a word, forming a histogram of word counts over the dictionary, then constructing a classifier on the histograms. A recent evaluation of two of this type of algorithm, Bag of Patterns (BOP) and Bag of Symbolic Fourier Approximation Symbols (BOSS) found a significant difference in accuracy between these seemingly similar algorithms. We investigate this phenomenon by deconstructing the classifiers and measuring the relative importance of the four key components between BOP and BOSS. We find that whilst ensembling is a key component for both algorithms, the effect of the other components is mixed and more complex. We conclude that BOSS represents the state of the art for dictionary based TSC. Both BOP and BOSS can be classed as bag of words approaches. These are particularly popular in Computer Vision for tasks such as image classification. Converting approaches from vision requires careful engineering. We adapt three techniques used in Computer Vision for TSC: Scale Invariant Feature Transform; Spatial Pyramids; and Histrogram Intersection. We find that using Spatial Pyramids in conjunction with BOSS (SP) produces a significantly more accurate classifier. SP is significantly more accurate than standard benchmarks and the original BOSS algorithm. It is not significantly worse than the best shapelet based approach, and is only outperformed by HIVE-COTE, an ensemble that includes BOSS as a constituent module.
Tasks	Image Classification, Time Series, Time Series Classification
Published	2018-09-18
URL	http://arxiv.org/abs/1809.06751v1
PDF	http://arxiv.org/pdf/1809.06751v1.pdf
PWC	https://paperswithcode.com/paper/from-bop-to-boss-and-beyond-time-series
Repo
Framework

MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM


Title	MID-Fusion: Octree-based Object-Level Multi-Instance Dynamic SLAM
Authors	Binbin Xu, Wenbin Li, Dimos Tzoumanikas, Michael Bloesch, Andrew Davison, Stefan Leutenegger
Abstract	We propose a new multi-instance dynamic RGB-D SLAM system using an object-level octree-based volumetric representation. It can provide robust camera tracking in dynamic environments and at the same time, continuously estimate geometric, semantic, and motion properties for arbitrary objects in the scene. For each incoming frame, we perform instance segmentation to detect objects and refine mask boundaries using geometric and motion information. Meanwhile, we estimate the pose of each existing moving object using an object-oriented tracking method and robustly track the camera pose against the static scene. Based on the estimated camera pose and object poses, we associate segmented masks with existing models and incrementally fuse corresponding colour, depth, semantic, and foreground object probabilities into each object model. In contrast to existing approaches, our system is the first system to generate an object-level dynamic volumetric map from a single RGB-D camera, which can be used directly for robotic tasks. Our method can run at 2-3 Hz on a CPU, excluding the instance segmentation part. We demonstrate its effectiveness by quantitatively and qualitatively testing it on both synthetic and real-world sequences.
Tasks	Instance Segmentation, Semantic Segmentation
Published	2018-12-19
URL	http://arxiv.org/abs/1812.07976v4
PDF	http://arxiv.org/pdf/1812.07976v4.pdf
PWC	https://paperswithcode.com/paper/mid-fusion-octree-based-object-level-multi
Repo
Framework

Explainable time series tweaking via irreversible and reversible temporal transformations


Title	Explainable time series tweaking via irreversible and reversible temporal transformations
Authors	Isak Karlsson, Jonathan Rebane, Panagiotis Papapetrou, Aristides Gionis
Abstract	Time series classification has received great attention over the past decade with a wide range of methods focusing on predictive performance by exploiting various types of temporal features. Nonetheless, little emphasis has been placed on interpretability and explainability. In this paper, we formulate the novel problem of explainable time series tweaking, where, given a time series and an opaque classifier that provides a particular classification decision for the time series, we want to find the minimum number of changes to be performed to the given time series so that the classifier changes its decision to another class. We show that the problem is NP-hard, and focus on two instantiations of the problem, which we refer to as reversible and irreversible time series tweaking. The classifier under investigation is the random shapelet forest classifier. Moreover, we propose two algorithmic solutions for the two problems along with simple optimizations, as well as a baseline solution using the nearest neighbor classifier. An extensive experimental evaluation on a variety of real datasets demonstrates the usefulness and effectiveness of our problem formulation and solutions.
Tasks	Time Series, Time Series Classification
Published	2018-09-13
URL	http://arxiv.org/abs/1809.05183v1
PDF	http://arxiv.org/pdf/1809.05183v1.pdf
PWC	https://paperswithcode.com/paper/explainable-time-series-tweaking-via
Repo
Framework

3D Interpreter Networks for Viewer-Centered Wireframe Modeling


Title	3D Interpreter Networks for Viewer-Centered Wireframe Modeling
Authors	Jiajun Wu, Tianfan Xue, Joseph J. Lim, Yuandong Tian, Joshua B. Tenenbaum, Antonio Torralba, William T. Freeman
Abstract	Understanding 3D object structure from a single image is an important but challenging task in computer vision, mostly due to the lack of 3D object annotations to real images. Previous research tackled this problem by either searching for a 3D shape that best explains 2D annotations, or training purely on synthetic data with ground truth 3D information. In this work, we propose 3D INterpreter Networks (3D-INN), an end-to-end trainable framework that sequentially estimates 2D keypoint heatmaps and 3D object skeletons and poses. Our system learns from both 2D-annotated real images and synthetic 3D data. This is made possible mainly by two technical innovations. First, heatmaps of 2D keypoints serve as an intermediate representation to connect real and synthetic data. 3D-INN is trained on real images to estimate 2D keypoint heatmaps from an input image; it then predicts 3D object structure from heatmaps using knowledge learned from synthetic 3D shapes. By doing so, 3D-INN benefits from the variation and abundance of synthetic 3D objects, without suffering from the domain difference between real and synthesized images, often due to imperfect rendering. Second, we propose a Projection Layer, mapping estimated 3D structure back to 2D. During training, it ensures 3D-INN to predict 3D structure whose projection is consistent with the 2D annotations to real images. Experiments show that the proposed system performs well on both 2D keypoint estimation and 3D structure recovery. We also demonstrate that the recovered 3D information has wide vision applications, such as image retrieval.
Tasks	Image Retrieval
Published	2018-04-03
URL	https://arxiv.org/abs/1804.00782v2
PDF	https://arxiv.org/pdf/1804.00782v2.pdf
PWC	https://paperswithcode.com/paper/3d-interpreter-networks-for-viewer-centered
Repo
Framework

Horizontal Pyramid Matching for Person Re-identification


Title	Horizontal Pyramid Matching for Person Re-identification
Authors	Yang Fu, Yunchao Wei, Yuqian Zhou, Honghui Shi, Gao Huang, Xinchao Wang, Zhiqiang Yao, Thomas Huang
Abstract	Despite the remarkable recent progress, person re-identification (Re-ID) approaches are still suffering from the failure cases where the discriminative body parts are missing. To mitigate such cases, we propose a simple yet effective Horizontal Pyramid Matching (HPM) approach to fully exploit various partial information of a given person, so that correct person candidates can be still identified even even some key parts are missing. Within the HPM, we make the following contributions to produce a more robust feature representation for the Re-ID task: 1) we learn to classify using partial feature representations at different horizontal pyramid scales, which successfully enhance the discriminative capabilities of various person parts; 2) we exploit average and max pooling strategies to account for person-specific discriminative information in a global-local manner. To validate the effectiveness of the proposed HPM, extensive experiments are conducted on three popular benchmarks, including Market-1501, DukeMTMC-ReID and CUHK03. In particular, we achieve mAP scores of 83.1%, 74.5% and 59.7% on these benchmarks, which are the new state-of-the-arts. Our code is available on Github
Tasks	Person Re-Identification
Published	2018-04-14
URL	http://arxiv.org/abs/1804.05275v4
PDF	http://arxiv.org/pdf/1804.05275v4.pdf
PWC	https://paperswithcode.com/paper/horizontal-pyramid-matching-for-person-re
Repo
Framework

Self-Paced Multi-Task Clustering


Title	Self-Paced Multi-Task Clustering
Authors	Yazhou Ren, Xiaofan Que, Dezhong Yao, Zenglin Xu
Abstract	Multi-task clustering (MTC) has attracted a lot of research attentions in machine learning due to its ability in utilizing the relationship among different tasks. Despite the success of traditional MTC models, they are either easy to stuck into local optima, or sensitive to outliers and noisy data. To alleviate these problems, we propose a novel self-paced multi-task clustering (SPMTC) paradigm. In detail, SPMTC progressively selects data examples to train a series of MTC models with increasing complexity, thus highly decreases the risk of trapping into poor local optima. Furthermore, to reduce the negative influence of outliers and noisy data, we design a soft version of SPMTC to further improve the clustering performance. The corresponding SPMTC framework can be easily solved by an alternating optimization method. The proposed model is guaranteed to converge and experiments on real data sets have demonstrated its promising results compared with state-of-the-art multi-task clustering methods.
Tasks
Published	2018-08-24
URL	http://arxiv.org/abs/1808.08068v1
PDF	http://arxiv.org/pdf/1808.08068v1.pdf
PWC	https://paperswithcode.com/paper/self-paced-multi-task-clustering
Repo
Framework

Local Linear Forests


Title	Local Linear Forests
Authors	Rina Friedberg, Julie Tibshirani, Susan Athey, Stefan Wager
Abstract	Random forests are a powerful method for non-parametric regression, but are limited in their ability to fit smooth signals, and can show poor predictive performance in the presence of strong, smooth effects. Taking the perspective of random forests as an adaptive kernel method, we pair the forest kernel with a local linear regression adjustment to better capture smoothness. The resulting procedure, local linear forests, enables us to improve on asymptotic rates of convergence for random forests with smooth signals, and provides substantial gains in accuracy on both real and simulated data. We prove a central limit theorem valid under regularity conditions on the forest and smoothness constraints, and propose a computationally efficient construction for confidence intervals. Moving to a causal inference application, we discuss the merits of local regression adjustments for heterogeneous treatment effect estimation, and give an example on a dataset exploring the effect word choice has on attitudes to the social safety net. Last, we include simulation results on real and generated data.
Tasks	Causal Inference
Published	2018-07-30
URL	https://arxiv.org/abs/1807.11408v3
PDF	https://arxiv.org/pdf/1807.11408v3.pdf
PWC	https://paperswithcode.com/paper/local-linear-forests
Repo
Framework

Motorcycle Classification in Urban Scenarios using Convolutional Neural Networks for Feature Extraction


Title	Motorcycle Classification in Urban Scenarios using Convolutional Neural Networks for Feature Extraction
Authors	Jorge E. Espinosa, Sergio A. Velastin, John W. Branch
Abstract	This paper presents a motorcycle classification system for urban scenarios using Convolutional Neural Network (CNN). Significant results on image classification has been achieved using CNNs at the expense of a high computational cost for training with thousands or even millions of examples. Nevertheless, features can be extracted from CNNs already trained. In this work AlexNet, included in the framework CaffeNet, is used to extract features from frames taken on a real urban scenario. The extracted features from the CNN are used to train a support vector machine (SVM) classifier to discriminate motorcycles from other road users. The obtained results show a mean accuracy of 99.40% and 99.29% on a classification task of three and five classes respectively. Further experiments are performed on a validation set of images showing a satisfactory classification.
Tasks	Image Classification
Published	2018-08-28
URL	http://arxiv.org/abs/1808.09273v1
PDF	http://arxiv.org/pdf/1808.09273v1.pdf
PWC	https://paperswithcode.com/paper/motorcycle-classification-in-urban-scenarios
Repo
Framework

Leveraging translations for speech transcription in low-resource settings


Title	Leveraging translations for speech transcription in low-resource settings
Authors	Antonis Anastasopoulos, David Chiang
Abstract	Recently proposed data collection frameworks for endangered language documentation aim not only to collect speech in the language of interest, but also to collect translations into a high-resource language that will render the collected resource interpretable. We focus on this scenario and explore whether we can improve transcription quality under these extremely low-resource settings with the assistance of text translations. We present a neural multi-source model and evaluate several variations of it on three low-resource datasets. We find that our multi-source model with shared attention outperforms the baselines, reducing transcription character error rate by up to 12.3%.
Tasks
Published	2018-03-23
URL	http://arxiv.org/abs/1803.08991v2
PDF	http://arxiv.org/pdf/1803.08991v2.pdf
PWC	https://paperswithcode.com/paper/leveraging-translations-for-speech
Repo
Framework

SCORE+ for Network Community Detection


Title	SCORE+ for Network Community Detection
Authors	Jiashun Jin, Zheng Tracy Ke, Shengming Luo
Abstract	SCORE is a recent approach to network community detection proposed by Jin (2015). In this note, we propose a simple improvement of SCORE, called SCORE+, and compare its performance with several other methods, using 10 different network data sets. For 7 of these data sets, the performances of SCORE and SCORE+ are similar, but for the other 3 data sets (Polbooks, Simmons, Caltech), SCORE+ provides a significant improvement.
Tasks	Community Detection
Published	2018-11-14
URL	http://arxiv.org/abs/1811.05927v1
PDF	http://arxiv.org/pdf/1811.05927v1.pdf
PWC	https://paperswithcode.com/paper/score-for-network-community-detection
Repo
Framework

Adaptive strategy for superpixel-based region-growing image segmentation


Title	Adaptive strategy for superpixel-based region-growing image segmentation
Authors	Mahaman Sani Chaibou, Pierre-Henri Conze, Karim Kalti, Basel Solaiman, Mohamed Ali Mahjoub
Abstract	This work presents a region-growing image segmentation approach based on superpixel decomposition. From an initial contour-constrained over-segmentation of the input image, the image segmentation is achieved by iteratively merging similar superpixels into regions. This approach raises two key issues: (1) how to compute the similarity between superpixels in order to perform accurate merging and (2) in which order those superpixels must be merged together. In this perspective, we firstly introduce a robust adaptive multi-scale superpixel similarity in which region comparisons are made both at content and common border level. Secondly, we propose a global merging strategy to efficiently guide the region merging process. Such strategy uses an adpative merging criterion to ensure that best region aggregations are given highest priorities. This allows to reach a final segmentation into consistent regions with strong boundary adherence. We perform experiments on the BSDS500 image dataset to highlight to which extent our method compares favorably against other well-known image segmentation algorithms. The obtained results demonstrate the promising potential of the proposed approach.
Tasks	Semantic Segmentation
Published	2018-03-17
URL	http://arxiv.org/abs/1803.06541v1
PDF	http://arxiv.org/pdf/1803.06541v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-strategy-for-superpixel-based-region
Repo
Framework