Paper Group ANR 552
Multi-Stage Feature Selection Based Intelligent Classifier for Classification of Incipient Stage Fire in Building. Detecting the Moment of Completion: Temporal Models for Localising Action Completion. Counterfactual Causality from First Principles?. Picasso, Matisse, or a Fake? Automated Analysis of Drawings at the Stroke Level for Attribution and …
Multi-Stage Feature Selection Based Intelligent Classifier for Classification of Incipient Stage Fire in Building
| Title | Multi-Stage Feature Selection Based Intelligent Classifier for Classification of Incipient Stage Fire in Building |
| Authors | Allan Melvin Andrew, Ammar Zakaria, Shaharil Mad Saad, Ali Yeon Md Shakaff |
| Abstract | In this study, an early fire detection algorithm has been proposed based on low cost array sensing system, utilizing gas sensors, dust particles and ambient sensors such as temperature and humidity sensor. The odor or smell-print emanated from various fire sources and building construction materials at early stage are measured. For this purpose, odor profile data from five common fire sources and three common building construction materials were used to develop the classification model. Normalized feature extractions of the smell print data were performed before subjected to prediction classifier. These features represent the odor signals in the time domain. The obtained features undergo the proposed multi-stage feature selection technique and lastly, further reduced by Principal Component Analysis (PCA), a dimension reduction technique. The hybrid PCA-PNN based approach has been applied on different datasets from in-house developed system and the portable electronic nose unit. Experimental classification results show that the dimension reduction process performed by PCA has improved the classification accuracy and provided high reliability, regardless of ambient temperature and humidity variation, baseline sensor drift, the different gas concentration level and exposure towards different heating temperature range. |
| Tasks | Dimensionality Reduction, Feature Selection |
| Published | 2017-08-12 |
| URL | http://arxiv.org/abs/1708.08750v1 |
| http://arxiv.org/pdf/1708.08750v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-stage-feature-selection-based |
| Repo | |
| Framework | |
Detecting the Moment of Completion: Temporal Models for Localising Action Completion
| Title | Detecting the Moment of Completion: Temporal Models for Localising Action Completion |
| Authors | Farnoosh Heidarivincheh, Majid Mirmehdi, Dima Damen |
| Abstract | Action completion detection is the problem of modelling the action’s progression towards localising the moment of completion - when the action’s goal is confidently considered achieved. In this work, we assess the ability of two temporal models, namely Hidden Markov Models (HMM) and Long-Short Term Memory (LSTM), to localise completion for six object interactions: switch, plug, open, pull, pick and drink. We use a supervised approach, where annotations of pre-completion and post-completion frames are available per action, and fine-tuned CNN features are used to train temporal models. Tested on the Action-Completion-2016 dataset, we detect completion within 10 frames of annotations for ~75% of completed action sequences using both temporal models. Results show that fine-tuned CNN features outperform hand-crafted features for localisation, and that observing incomplete instances is necessary when incomplete sequences are also present in the test set. |
| Tasks | |
| Published | 2017-10-06 |
| URL | http://arxiv.org/abs/1710.02310v1 |
| http://arxiv.org/pdf/1710.02310v1.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-the-moment-of-completion-temporal |
| Repo | |
| Framework | |
Counterfactual Causality from First Principles?
| Title | Counterfactual Causality from First Principles? |
| Authors | Gregor Gössler, Oleg Sokolsky, Jean-Bernard Stefani |
| Abstract | In this position paper we discuss three main shortcomings of existing approaches to counterfactual causality from the computer science perspective, and sketch lines of work to try and overcome these issues: (1) causality definitions should be driven by a set of precisely specified requirements rather than specific examples; (2) causality frameworks should support system dynamics; (3) causality analysis should have a well-understood behavior in presence of abstraction. |
| Tasks | |
| Published | 2017-10-10 |
| URL | http://arxiv.org/abs/1710.03393v1 |
| http://arxiv.org/pdf/1710.03393v1.pdf | |
| PWC | https://paperswithcode.com/paper/counterfactual-causality-from-first |
| Repo | |
| Framework | |
Picasso, Matisse, or a Fake? Automated Analysis of Drawings at the Stroke Level for Attribution and Authentication
| Title | Picasso, Matisse, or a Fake? Automated Analysis of Drawings at the Stroke Level for Attribution and Authentication |
| Authors | Ahmed Elgammal, Yan Kang, Milko Den Leeuw |
| Abstract | This paper proposes a computational approach for analysis of strokes in line drawings by artists. We aim at developing an AI methodology that facilitates attribution of drawings of unknown authors in a way that is not easy to be deceived by forged art. The methodology used is based on quantifying the characteristics of individual strokes in drawings. We propose a novel algorithm for segmenting individual strokes. We designed and compared different hand-crafted and learned features for the task of quantifying stroke characteristics. We also propose and compare different classification methods at the drawing level. We experimented with a dataset of 300 digitized drawings with over 80 thousands strokes. The collection mainly consisted of drawings of Pablo Picasso, Henry Matisse, and Egon Schiele, besides a small number of representative works of other artists. The experiments shows that the proposed methodology can classify individual strokes with accuracy 70%-90%, and aggregate over drawings with accuracy above 80%, while being robust to be deceived by fakes (with accuracy 100% for detecting fakes in most settings). |
| Tasks | |
| Published | 2017-11-08 |
| URL | http://arxiv.org/abs/1711.03536v1 |
| http://arxiv.org/pdf/1711.03536v1.pdf | |
| PWC | https://paperswithcode.com/paper/picasso-matisse-or-a-fake-automated-analysis |
| Repo | |
| Framework | |
Automated Diagnosis of Epilepsy Employing Multifractal Detrended Fluctuation Analysis Based Features
| Title | Automated Diagnosis of Epilepsy Employing Multifractal Detrended Fluctuation Analysis Based Features |
| Authors | S Pratiher, S Chatterjee, R Bose |
| Abstract | This contribution reports an application of MultiFractal Detrended Fluctuation Analysis, MFDFA based novel feature extraction technique for automated detection of epilepsy. In fractal geometry, Multifractal Detrended Fluctuation Analysis MFDFA is a popular technique to examine the self-similarity of a nonlinear, chaotic and noisy time series. In the present research work, EEG signals representing healthy, interictal (seizure free) and ictal activities (seizure) are acquired from an existing available database. The acquired EEG signals of different states are at first analyzed using MFDFA. To requisite the time series singularity quantification at local and global scales, a novel set of fourteen different features. Suitable feature ranking employing students t-test has been done to select the most statistically significant features which are henceforth being used as inputs to a support vector machines (SVM) classifier for the classification of different EEG signals. Eight different classification problems have been presented in this paper and it has been observed that the overall classification accuracy using MFDFA based features are reasonably satisfactory for all classification problems. The performance of the proposed method are also found to be quite commensurable and in some cases even better when compared with the results published in existing literature studied on the similar data set. |
| Tasks | EEG, Time Series |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01297v1 |
| http://arxiv.org/pdf/1704.01297v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-diagnosis-of-epilepsy-employing |
| Repo | |
| Framework | |
A Proof of Orthogonal Double Machine Learning with $Z$-Estimators
| Title | A Proof of Orthogonal Double Machine Learning with $Z$-Estimators |
| Authors | Vasilis Syrgkanis |
| Abstract | We consider two stage estimation with a non-parametric first stage and a generalized method of moments second stage, in a simpler setting than (Chernozhukov et al. 2016). We give an alternative proof of the theorem given in (Chernozhukov et al. 2016) that orthogonal second stage moments, sample splitting and $n^{1/4}$-consistency of the first stage, imply $\sqrt{n}$-consistency and asymptotic normality of second stage estimates. Our proof is for a variant of their estimator, which is based on the empirical version of the moment condition (Z-estimator), rather than a minimization of a norm of the empirical vector of moments (M-estimator). This note is meant primarily for expository purposes, rather than as a new technical contribution. |
| Tasks | |
| Published | 2017-04-12 |
| URL | http://arxiv.org/abs/1704.03754v2 |
| http://arxiv.org/pdf/1704.03754v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-proof-of-orthogonal-double-machine-learning |
| Repo | |
| Framework | |
A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe
| Title | A Unified Optimization View on Generalized Matching Pursuit and Frank-Wolfe |
| Authors | Francesco Locatello, Rajiv Khanna, Michael Tschannen, Martin Jaggi |
| Abstract | Two of the most fundamental prototypes of greedy optimization are the matching pursuit and Frank-Wolfe algorithms. In this paper, we take a unified view on both classes of methods, leading to the first explicit convergence rates of matching pursuit methods in an optimization sense, for general sets of atoms. We derive sublinear ($1/t$) convergence for both classes on general smooth objectives, and linear convergence on strongly convex objectives, as well as a clear correspondence of algorithm variants. Our presented algorithms and rates are affine invariant, and do not need any incoherence or sparsity assumptions. |
| Tasks | |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06457v2 |
| http://arxiv.org/pdf/1702.06457v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-optimization-view-on-generalized |
| Repo | |
| Framework | |
Learning Where to Look: Data-Driven Viewpoint Set Selection for 3D Scenes
| Title | Learning Where to Look: Data-Driven Viewpoint Set Selection for 3D Scenes |
| Authors | Kyle Genova, Manolis Savva, Angel X. Chang, Thomas Funkhouser |
| Abstract | The use of rendered images, whether from completely synthetic datasets or from 3D reconstructions, is increasingly prevalent in vision tasks. However, little attention has been given to how the selection of viewpoints affects the performance of rendered training sets. In this paper, we propose a data-driven approach to view set selection. Given a set of example images, we extract statistics describing their contents and generate a set of views matching the distribution of those statistics. Motivated by semantic segmentation tasks, we model the spatial distribution of each semantic object category within an image view volume. We provide a search algorithm that generates a sampling of likely candidate views according to the example distribution, and a set selection algorithm that chooses a subset of the candidates that jointly cover the example distribution. Results of experiments with these algorithms on SUNCG indicate that they are indeed able to produce view distributions similar to an example set from NYUDv2 according to the earth mover’s distance. Furthermore, the selected views improve performance on semantic segmentation compared to alternative view selection algorithms. |
| Tasks | Semantic Segmentation |
| Published | 2017-04-07 |
| URL | http://arxiv.org/abs/1704.02393v1 |
| http://arxiv.org/pdf/1704.02393v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-where-to-look-data-driven-viewpoint |
| Repo | |
| Framework | |
The Zero Resource Speech Challenge 2017
| Title | The Zero Resource Speech Challenge 2017 |
| Authors | Ewan Dunbar, Xuan Nga Cao, Juan Benjumea, Julien Karadayi, Mathieu Bernard, Laurent Besacier, Xavier Anguera, Emmanuel Dupoux |
| Abstract | We describe a new challenge aimed at discovering subword and word units from raw speech. This challenge is the followup to the Zero Resource Speech Challenge 2015. It aims at constructing systems that generalize across languages and adapt to new speakers. The design features and evaluation metrics of the challenge are presented and the results of seventeen models are discussed. |
| Tasks | |
| Published | 2017-12-12 |
| URL | http://arxiv.org/abs/1712.04313v1 |
| http://arxiv.org/pdf/1712.04313v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-zero-resource-speech-challenge-2017 |
| Repo | |
| Framework | |
k-FFNN: A priori knowledge infused Feed-forward Neural Networks
| Title | k-FFNN: A priori knowledge infused Feed-forward Neural Networks |
| Authors | Sri Harsha Dumpala, Rupayan Chakraborty, Sunil Kumar Kopparapu |
| Abstract | Recurrent neural network (RNN) are being extensively used over feed-forward neural networks (FFNN) because of their inherent capability to capture temporal relationships that exist in the sequential data such as speech. This aspect of RNN is advantageous especially when there is no a priori knowledge about the temporal correlations within the data. However, RNNs require large amount of data to learn these temporal correlations, limiting their advantage in low resource scenarios. It is not immediately clear (a) how a priori temporal knowledge can be used in a FFNN architecture (b) how a FFNN performs when provided with this knowledge about temporal correlations (assuming available) during training. The objective of this paper is to explore k-FFNN, namely a FFNN architecture that can incorporate the a priori knowledge of the temporal relationships within the data sequence during training and compare k-FFNN performance with RNN in a low resource scenario. We evaluate the performance of k-FFNN and RNN by extensive experimentation on MediaEval 2016 audio data (“Emotional Impact of Movies” task). Experimental results show that the performance of k-FFNN is comparable to RNN, and in some scenarios k-FFNN performs better than RNN when temporal knowledge is injected into FFNN architecture. The main contributions of this paper are (a) fusing a priori knowledge into FFNN architecture to construct a k-FFNN and (b) analyzing the performance of k-FFNN with respect to RNN for different size of training data. |
| Tasks | |
| Published | 2017-04-24 |
| URL | http://arxiv.org/abs/1704.07055v1 |
| http://arxiv.org/pdf/1704.07055v1.pdf | |
| PWC | https://paperswithcode.com/paper/k-ffnn-a-priori-knowledge-infused-feed |
| Repo | |
| Framework | |
Specifying Non-Markovian Rewards in MDPs Using LDL on Finite Traces (Preliminary Version)
| Title | Specifying Non-Markovian Rewards in MDPs Using LDL on Finite Traces (Preliminary Version) |
| Authors | Ronen Brafman, Giuseppe De Giacomo, Fabio Patrizi |
| Abstract | In Markov Decision Processes (MDPs), the reward obtained in a state depends on the properties of the last state and action. This state dependency makes it difficult to reward more interesting long-term behaviors, such as always closing a door after it has been opened, or providing coffee only following a request. Extending MDPs to handle such non-Markovian reward function was the subject of two previous lines of work, both using variants of LTL to specify the reward function and then compiling the new model back into a Markovian model. Building upon recent progress in the theories of temporal logics over finite traces, we adopt LDLf for specifying non-Markovian rewards and provide an elegant automata construction for building a Markovian model, which extends that of previous work and offers strong minimality and compositionality guarantees. |
| Tasks | |
| Published | 2017-06-25 |
| URL | http://arxiv.org/abs/1706.08100v1 |
| http://arxiv.org/pdf/1706.08100v1.pdf | |
| PWC | https://paperswithcode.com/paper/specifying-non-markovian-rewards-in-mdps |
| Repo | |
| Framework | |
Deep Automated Multi-task Learning
| Title | Deep Automated Multi-task Learning |
| Authors | Davis Liang, Yan Shu |
| Abstract | Multi-task learning (MTL) has recently contributed to learning better representations in service of various NLP tasks. MTL aims at improving the performance of a primary task, by jointly training on a secondary task. This paper introduces automated tasks, which exploit the sequential nature of the input data, as secondary tasks in an MTL model. We explore next word prediction, next character prediction, and missing word completion as potential automated tasks. Our results show that training on a primary task in parallel with a secondary automated task improves both the convergence speed and accuracy for the primary task. We suggest two methods for augmenting an existing network with automated tasks and establish better performance in topic prediction, sentiment analysis, and hashtag recommendation. Finally, we show that the MTL models can perform well on datasets that are small and colloquial by nature. |
| Tasks | Multi-Task Learning, Sentiment Analysis |
| Published | 2017-09-16 |
| URL | http://arxiv.org/abs/1709.05554v2 |
| http://arxiv.org/pdf/1709.05554v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-automated-multi-task-learning |
| Repo | |
| Framework | |
Beyond Forward Shortcuts: Fully Convolutional Master-Slave Networks (MSNets) with Backward Skip Connections for Semantic Segmentation
| Title | Beyond Forward Shortcuts: Fully Convolutional Master-Slave Networks (MSNets) with Backward Skip Connections for Semantic Segmentation |
| Authors | Abrar H. Abdulnabi, Stefan Winkler, Gang Wang |
| Abstract | Recent deep CNNs contain forward shortcut connections; i.e. skip connections from low to high layers. Reusing features from lower layers that have higher resolution (location information) benefit higher layers to recover lost details and mitigate information degradation. However, during inference the lower layers do not know about high layer features, although they contain contextual high semantics that benefit low layers to adaptively extract informative features for later layers. In this paper, we study the influence of backward skip connections which are in the opposite direction to forward shortcuts, i.e. paths from high layers to low layers. To achieve this – which indeed runs counter to the nature of feed-forward networks – we propose a new fully convolutional model that consists of a pair of networks. A Slave' network is dedicated to provide the backward connections from its top layers to the Master’ network’s bottom layers. The Master network is used to produce the final label predictions. In our experiments we validate the proposed FCN model on ADE20K (ImageNet scene parsing), PASCAL-Context, and PASCAL VOC 2011 datasets. |
| Tasks | Scene Parsing, Semantic Segmentation |
| Published | 2017-07-18 |
| URL | http://arxiv.org/abs/1707.05537v1 |
| http://arxiv.org/pdf/1707.05537v1.pdf | |
| PWC | https://paperswithcode.com/paper/beyond-forward-shortcuts-fully-convolutional |
| Repo | |
| Framework | |
Audio-replay attack detection countermeasures
| Title | Audio-replay attack detection countermeasures |
| Authors | Galina Lavrentyeva, Sergey Novoselov, Egor Malykh, Alexander Kozlov, Oleg Kudashev, Vadim Shchemelinin |
| Abstract | This paper presents the Speech Technology Center (STC) replay attack detection systems proposed for Automatic Speaker Verification Spoofing and Countermeasures Challenge 2017. In this study we focused on comparison of different spoofing detection approaches. These were GMM based methods, high level features extraction with simple classifier and deep learning frameworks. Experiments performed on the development and evaluation parts of the challenge dataset demonstrated stable efficiency of deep learning approaches in case of changing acoustic conditions. At the same time SVM classifier with high level features provided a substantial input in the efficiency of the resulting STC systems according to the fusion systems results. |
| Tasks | Speaker Verification |
| Published | 2017-05-24 |
| URL | http://arxiv.org/abs/1705.08858v1 |
| http://arxiv.org/pdf/1705.08858v1.pdf | |
| PWC | https://paperswithcode.com/paper/audio-replay-attack-detection-countermeasures |
| Repo | |
| Framework | |
Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search
| Title | Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search |
| Authors | Leonard Dahlmann, Evgeny Matusov, Pavel Petrushkov, Shahram Khadivi |
| Abstract | In this paper, we introduce a hybrid search for attention-based neural machine translation (NMT). A target phrase learned with statistical MT models extends a hypothesis in the NMT beam search when the attention of the NMT model focuses on the source words translated by this phrase. Phrases added in this way are scored with the NMT model, but also with SMT features including phrase-level translation probabilities and a target language model. Experimental results on German->English news domain and English->Russian e-commerce domain translation tasks show that using phrase-based models in NMT search improves MT quality by up to 2.3% BLEU absolute as compared to a strong NMT baseline. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2017-08-10 |
| URL | http://arxiv.org/abs/1708.03271v1 |
| http://arxiv.org/pdf/1708.03271v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-machine-translation-leveraging-phrase |
| Repo | |
| Framework | |
