Paper Group NAWR 1
Learning a model of facial shape and expression from 4D scans. AutoLearn - Automated Feature Generation and Selection. DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis. Grammatical Error Detection Using Error- and Grammaticality-Specific Word Embeddings. How Many Stemmata with Root De …
Learning a model of facial shape and expression from 4D scans
| Title | Learning a model of facial shape and expression from 4D scans |
| Authors | Tianye Li, Timo Bolkart, Michael J. Black, Hao Li, Javier Romero |
| Abstract | he field of 3D face modeling has a large gap between high-end and low-end methods. At the high end, the best facial animation is indistinguishablefrom real humans, but this comes at the cost of extensive manual labor. At the low end, face capture from consumer depth sensors relies on 3D face models that are not expressive enough to capture the variability in natural facial shape and expression. We seek a middle ground by learning a facial model from thousands of accurately aligned 3D scans. Our FLAME model (Faces Learned with an Articulated Model and Expressions) is designed to work with existing graphics software and be easy to fit to data. FLAME uses a linear shape space trained from 3800 scans of human heads. FLAME combines this linear shape space with an articulated jaw, neck, and eyeballs, pose-dependent corrective blendshapes, and additional global expression blendshapes. The pose and expression dependent articulations are learned from 4D face sequences in the D3DFACS dataset along with additional 4D sequences. We accurately register a template mesh to the scan sequences and make the D3DFACS registrations available for research purposes. In total the model is trained from over 33, 000 scans. FLAME is low-dimensional but more expressive than the FaceWarehouse model and the Basel Face Model. We compare FLAME to these models by fitting them to static 3D scans and 4D sequences using the same optimization method. FLAME is significantly more accurate and is available for research purposes. |
| Tasks | 3D Face Animation, 3D Face Reconstruction, Face Generation |
| Published | 2017-11-01 |
| URL | http://flame.is.tue.mpg.de/ |
| https://ps.is.tuebingen.mpg.de/uploads_file/attachment/attachment/400/paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-model-of-facial-shape-and |
| Repo | https://github.com/TimoBolkart/TF_FLAME |
| Framework | tf |
AutoLearn - Automated Feature Generation and Selection
| Title | AutoLearn - Automated Feature Generation and Selection |
| Authors | Ambika Kaul, Saket Maheshwary, Vikram Pudi |
| Abstract | In recent years, the importance of feature engineering has been confirmed by the exceptional performance of deep learning techniques, that automate this task for some applications. For others, feature engineering requires substantial manual effort in designing and selecting features and is often tedious and non-scalable. We present AutoLearn, a regression-based feature learning algorithm. Being data-driven, it requires no domain knowledge and is hence generic. Such a representation is learnt by mining pairwise feature associations, identifying the linear or non-linear relationship between each pair, applying regression and selecting those relationships that are stable and improve the prediction performance. Our experimental evaluation on 18 UC Irvine and 7 Gene expression datasets, across different domains, provides evidence that the features learnt through our model can improve the overall prediction accuracy by 13.28%, compared to original feature space and 5.87% over other top performing models, across 8 different classifiers without using any domain knowledge. |
| Tasks | Automated Feature Engineering, Feature Engineering, Feature Importance |
| Published | 2017-11-17 |
| URL | https://ieeexplore.ieee.org/abstract/document/8215494 |
| http://web2py.iiit.ac.in/research_centres/publications/download/inproceedings.pdf.88535e0ea3a74e72.4943444d2d20323031372e706466.pdf | |
| PWC | https://paperswithcode.com/paper/autolearn-automated-feature-generation-and |
| Repo | https://github.com/saket-maheshwary/AutoLearn |
| Framework | none |
DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis
| Title | DataStories at SemEval-2017 Task 4: Deep LSTM with Attention for Message-level and Topic-based Sentiment Analysis |
| Authors | Christos Baziotis, Nikos Pelekis, Christos Doulkeridis |
| Abstract | In this paper we present two deep-learning systems that competed at SemEval-2017 Task 4 {``}Sentiment Analysis in Twitter{''}. We participated in all subtasks for English tweets, involving message-level and topic-based sentiment polarity classification and quantification. We use Long Short-Term Memory (LSTM) networks augmented with two kinds of attention mechanisms, on top of word embeddings pre-trained on a big collection of Twitter messages. Also, we present a text processing tool suitable for social network messages, which performs tokenization, word normalization, segmentation and spell correction. Moreover, our approach uses no hand-crafted features or sentiment lexicons. We ranked 1st (tie) in Subtask A, and achieved very competitive results in the rest of the Subtasks. Both the word embeddings and our text processing tool are available to the research community. | |
| Tasks | Feature Engineering, Sentiment Analysis, Tokenization, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2126/ |
| https://www.aclweb.org/anthology/S17-2126 | |
| PWC | https://paperswithcode.com/paper/datastories-at-semeval-2017-task-4-deep-lstm |
| Repo | https://github.com/cbaziotis/ekphrasis |
| Framework | none |
Grammatical Error Detection Using Error- and Grammaticality-Specific Word Embeddings
| Title | Grammatical Error Detection Using Error- and Grammaticality-Specific Word Embeddings |
| Authors | Masahiro Kaneko, Yuya Sakaizawa, Mamoru Komachi |
| Abstract | In this study, we improve grammatical error detection by learning word embeddings that consider grammaticality and error patterns. Most existing algorithms for learning word embeddings usually model only the syntactic context of words so that classifiers treat erroneous and correct words as similar inputs. We address the problem of contextual information by considering learner errors. Specifically, we propose two models: one model that employs grammatical error patterns and another model that considers grammaticality of the target word. We determine grammaticality of n-gram sequence from the annotated error tags and extract grammatical error patterns for word embeddings from large-scale learner corpora. Experimental results show that a bidirectional long-short term memory model initialized by our word embeddings achieved the state-of-the-art accuracy by a large margin in an English grammatical error detection task on the First Certificate in English dataset. |
| Tasks | Grammatical Error Detection, Learning Word Embeddings, Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1005/ |
| https://www.aclweb.org/anthology/I17-1005 | |
| PWC | https://paperswithcode.com/paper/grammatical-error-detection-using-error-and |
| Repo | https://github.com/kanekomasahiro/grammatical-error-detection |
| Framework | none |
How Many Stemmata with Root Degree k?
| Title | How Many Stemmata with Root Degree k? |
| Authors | Armin Hoenen, Steffen Eger, Ralf Gehrke |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/W17-3402/ |
| https://www.aclweb.org/anthology/W17-3402 | |
| PWC | https://paperswithcode.com/paper/how-many-stemmata-with-root-degree-k |
| Repo | https://github.com/ArminHoenen/KFurcatingRootedGregTrees |
| Framework | none |
WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation
| Title | WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation |
| Authors | Thibaut Durand, Taylor Mordan, Nicolas Thome, Matthieu Cord |
| Abstract | This paper introduces WILDCAT, a deep learning method which jointly aims at aligning image regions for gaining spatial invariance and learning strongly localized features. Our model is trained using only global image labels and is devoted to three main visual recognition tasks: image classification, weakly supervised object localization and semantic segmentation. WILDCAT extends state-of-the-art Convolutional Neural Networks at three main levels: the use of Fully Convolutional Networks for maintaining spatial resolution, the explicit design in the network of local features related to different class modalities, and a new way to pool these features to provide a global image prediction required for weakly supervised training. Extensive experiments show that our model significantly outperforms state-of-the-art methods. |
| Tasks | Image Classification, Object Localization, Semantic Segmentation, Weakly-Supervised Object Localization |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Durand_WILDCAT_Weakly_Supervised_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Durand_WILDCAT_Weakly_Supervised_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/wildcat-weakly-supervised-learning-of-deep |
| Repo | https://github.com/durandtibo/wildcat.pytorch |
| Framework | pytorch |
Integrating Semantic Knowledge into Lexical Embeddings Based on Information Content Measurement
| Title | Integrating Semantic Knowledge into Lexical Embeddings Based on Information Content Measurement |
| Authors | Hsin-Yang Wang, Wei-Yun Ma |
| Abstract | Distributional word representations are widely used in NLP tasks. These representations are based on an assumption that words with a similar context tend to have a similar meaning. To improve the quality of the context-based embeddings, many researches have explored how to make full use of existing lexical resources. In this paper, we argue that while we incorporate the prior knowledge with context-based embeddings, words with different occurrences should be treated differently. Therefore, we propose to rely on the measurement of information content to control the degree of applying prior knowledge into context-based embeddings - different words would have different learning rates when adjusting their embeddings. In the result, we demonstrate that our embeddings get significant improvements on two different tasks: Word Similarity and Analogical Reasoning. |
| Tasks | Document Classification, Information Retrieval, Question Answering, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2082/ |
| https://www.aclweb.org/anthology/E17-2082 | |
| PWC | https://paperswithcode.com/paper/integrating-semantic-knowledge-into-lexical |
| Repo | https://github.com/hywangntut/KBE |
| Framework | none |
A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework
| Title | A Revisit of Sparse Coding Based Anomaly Detection in Stacked RNN Framework |
| Authors | Weixin Luo, Wen Liu, Shenghua Gao |
| Abstract | Motivated by the capability of sparse coding based anomaly detection, we propose a Temporally-coherent Sparse Coding (TSC) where we enforce similar neighbouring frames be encoded with similar reconstruction coefficients. Then we map the TSC with a special type of stacked Recurrent Neural Network (sRNN). By taking advantage sRNN in learning all parameters simultaneously, the nontrivial hyper-parameter selection to TSC can be avoided, meanwhile with a shallow sRNN, the reconstruction coefficients can be inferred within a forward pass, which reduces the computational cost for learning sparse coefficients. The contributions of this paper are two-fold: i) We propose a TSC, which can be mapped to a sRNN which facilitates the parameter optimization and accelerates the anomaly prediction. ii) We build a very large dataset which is even larger than the summation of all existing dataset for anomaly detection in terms of both the volume of data and the diversity of scenes. Extensive experiments on both a toy dataset and real datasets demonstrate that our TSC based and sRNN based method consistently outperform existing methods, which validates the effectiveness of our method. |
| Tasks | Anomaly Detection |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Luo_A_Revisit_of_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Luo_A_Revisit_of_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-revisit-of-sparse-coding-based-anomaly |
| Repo | https://github.com/StevenLiuWen/sRNN_TSC_Anomaly_Detection |
| Framework | tf |
Neural system identification for large populations separating “what” and “where”
| Title | Neural system identification for large populations separating “what” and “where” |
| Authors | David Klindt, Alexander S. Ecker, Thomas Euler, Matthias Bethge |
| Abstract | Neuroscientists classify neurons into different types that perform similar computations at different locations in the visual field. Traditional methods for neural system identification do not capitalize on this separation of “what” and “where”. Learning deep convolutional feature spaces that are shared among many neurons provides an exciting path forward, but the architectural design needs to account for data limitations: While new experimental techniques enable recordings from thousands of neurons, experimental time is limited so that one can sample only a small fraction of each neuron’s response space. Here, we show that a major bottleneck for fitting convolutional neural networks (CNNs) to neural data is the estimation of the individual receptive field locations – a problem that has been scratched only at the surface thus far. We propose a CNN architecture with a sparse readout layer factorizing the spatial (where) and feature (what) dimensions. Our network scales well to thousands of neurons and short recordings and can be trained end-to-end. We evaluate this architecture on ground-truth data to explore the challenges and limitations of CNN-based system identification. Moreover, we show that our network model outperforms current state-of-the art system identification models of mouse primary visual cortex. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6942-neural-system-identification-for-large-populations-separating-what-and-where |
| http://papers.nips.cc/paper/6942-neural-system-identification-for-large-populations-separating-what-and-where.pdf | |
| PWC | https://paperswithcode.com/paper/neural-system-identification-for-large-1 |
| Repo | https://github.com/david-klindt/NIPS2017 |
| Framework | tf |
Saliency Pattern Detection by Ranking Structured Trees
| Title | Saliency Pattern Detection by Ranking Structured Trees |
| Authors | Lei Zhu, Haibin Ling, Jin Wu, Huiping Deng, Jin Liu |
| Abstract | In this paper we propose a new salient object detection method via structured label prediction. By learning appearance features in rectangular regions, our structural region representation encodes the local saliency distribution with a matrix of binary labels. We show that the linear combination of structured labels can well model the saliency distribution in local regions. Representing region saliency with structured labels has two advantages: 1) it connects the label assignment of all enclosed pixels, which produces a smooth saliency prediction; and 2) regular-shaped nature of structured labels enables well definition of traditional cues such as regional properties and center surround contrast, and these cues help to build meaningful and informative saliency measures. To measure the consistency between a structured label and the corresponding saliency distribution, we further propose an adaptive label ranking algorithm using proposals that are generated by a CNN model. Finally, we introduce a K-NN enhanced graph representation for saliency propagation, which is more favorable for our task than the widely-used adjacent-graph-based ones. Experimental results demonstrate the effectiveness of our proposed method on six popular benchmarks compared with state-of-the-art approaches. |
| Tasks | Object Detection, Saliency Prediction, Salient Object Detection |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Zhu_Saliency_Pattern_Detection_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Zhu_Saliency_Pattern_Detection_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/saliency-pattern-detection-by-ranking |
| Repo | https://github.com/zhulei2016/RST-saliency |
| Framework | none |
An open-source tool for negation detection: a maximum-margin approach
| Title | An open-source tool for negation detection: a maximum-margin approach |
| Authors | Martine Enger, Erik Velldal, Lilja {\O}vrelid |
| Abstract | This paper presents an open-source toolkit for negation detection. It identifies negation cues and their corresponding scope in either raw or parsed text using maximum-margin classification. The system design draws on best practice from the existing literature on negation detection, aiming for a simple and portable system that still achieves competitive performance. Pre-trained models and experimental results are provided for English. |
| Tasks | Negation Detection, Structured Prediction |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1810/ |
| https://www.aclweb.org/anthology/W17-1810 | |
| PWC | https://paperswithcode.com/paper/an-open-source-tool-for-negation-detection-a |
| Repo | https://github.com/marenger/negtool |
| Framework | tf |
Scattertext: a Browser-Based Tool for Visualizing how Corpora Differ
| Title | Scattertext: a Browser-Based Tool for Visualizing how Corpora Differ |
| Authors | Jason Kessler |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4015/ |
| https://www.aclweb.org/anthology/P17-4015 | |
| PWC | https://paperswithcode.com/paper/scattertext-a-browser-based-tool-for |
| Repo | https://github.com/JasonKessler/scattertext |
| Framework | tf |
Hunt For The Unique, Stable, Sparse And Fast Feature Learning On Graphs
| Title | Hunt For The Unique, Stable, Sparse And Fast Feature Learning On Graphs |
| Authors | Saurabh Verma, Zhi-Li Zhang |
| Abstract | For the purpose of learning on graphs, we hunt for a graph feature representation that exhibit certain uniqueness, stability and sparsity properties while also being amenable to fast computation. This leads to the discovery of family of graph spectral distances (denoted as FGSD) and their based graph feature representations, which we prove to possess most of these desired properties. To both evaluate the quality of graph features produced by FGSD and demonstrate their utility, we apply them to the graph classification problem. Through extensive experiments, we show that a simple SVM based classification algorithm, driven with our powerful FGSD based graph features, significantly outperforms all the more sophisticated state-of-art algorithms on the unlabeled node datasets in terms of both accuracy and speed; it also yields very competitive results on the labeled datasets - despite the fact it does not utilize any node label information. |
| Tasks | Graph Classification |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6614-hunt-for-the-unique-stable-sparse-and-fast-feature-learning-on-graphs |
| http://papers.nips.cc/paper/6614-hunt-for-the-unique-stable-sparse-and-fast-feature-learning-on-graphs.pdf | |
| PWC | https://paperswithcode.com/paper/hunt-for-the-unique-stable-sparse-and-fast |
| Repo | https://github.com/benedekrozemberczki/karateclub |
| Framework | none |
Font Size: Community Preserving Network Embedding
| Title | Font Size: Community Preserving Network Embedding |
| Authors | Xiao Wang, Peng Cui, Jing Wang, Jian Pei, Wenwu Zhu, Shiqiang Yang |
| Abstract | Network embedding, aiming to learn the low-dimensional representations of nodes in networks, is of paramount importance in many real applications. One basic requirement of network embedding is to preserve the structure and inherent properties of the networks. While previous network embedding methods primarily preserve the microscopic structure, such as the first- and second-order proximities of nodes, the mesoscopic community structure, which is one of the most prominent feature of networks, is largely ignored. In this paper, we propose a novel Modularized Nonnegative Matrix Factorization (M-NMF) model to incorporate the community structure into network embedding. We exploit the consensus relationship between the representations of nodes and community structure, and then jointly optimize NMF based representation learning model and modularity based community detection model in a unified framework, which enables the learned representations of nodes to preserve both of the microscopic and community structures. We also provide efficient updating rules to infer the parameters of our model, together with the correctness and convergence guarantees. Extensive experimental results on a variety of real-world networks show the superior performance of the proposed method over the state-of-the-arts. |
| Tasks | Community Detection, Network Embedding, Representation Learning |
| Published | 2017-02-10 |
| URL | https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14589 |
| https://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14589/13763.pdf | |
| PWC | https://paperswithcode.com/paper/font-size-community-preserving-network |
| Repo | https://github.com/benedekrozemberczki/karateclub |
| Framework | none |
Automated WordNet Construction Using Word Embeddings
| Title | Automated WordNet Construction Using Word Embeddings |
| Authors | Mikhail Khodak, Andrej Risteski, Christiane Fellbaum, Sanjeev Arora |
| Abstract | We present a fully unsupervised method for automated construction of WordNets based upon recent advances in distributional representations of sentences and word-senses combined with readily available machine translation tools. The approach requires very few linguistic resources and is thus extensible to multiple target languages. To evaluate our method we construct two 600-word testsets for word-to-synset matching in French and Russian using native speakers and evaluate the performance of our method along with several other recent approaches. Our method exceeds the best language-specific and multi-lingual automated WordNets in F-score for both languages. The databases we construct for French and Russian, both languages without large publicly available manually constructed WordNets, will be publicly released along with the testsets. |
| Tasks | Information Retrieval, Machine Translation, Word Embeddings, Word Sense Induction |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1902/ |
| https://www.aclweb.org/anthology/W17-1902 | |
| PWC | https://paperswithcode.com/paper/automated-wordnet-construction-using-word |
| Repo | https://github.com/mkhodak/pawn |
| Framework | none |
