Paper Group ANR 30
Deep Architectures for Face Attributes. The Great Time Series Classification Bake Off: An Experimental Evaluation of Recently Proposed Algorithms. Extended Version. Co-Occurrence Patterns in the Voynich Manuscript. Divide and Conquer Local Average Regression. Using inspiration from synaptic plasticity rules to optimize traffic flow in distributed e …
Deep Architectures for Face Attributes
| Title | Deep Architectures for Face Attributes |
| Authors | Tobi Baumgartner, Jack Culpepper |
| Abstract | We train a deep convolutional neural network to perform identity classification using a new dataset of public figures annotated with age, gender, ethnicity and emotion labels, and then fine-tune it for attribute classification. An optimal sharing pattern of computational resources within this network is determined by experiment, requiring only 1 G flops to produce all predictions. Rather than fine-tune by relearning weights in one additional layer after the penultimate layer of the identity network, we try several different depths for each attribute. We find that prediction of age and emotion is improved by fine-tuning from earlier layers onward, presumably because deeper layers are progressively invariant to non-identity related changes in the input. |
| Tasks | |
| Published | 2016-09-28 |
| URL | http://arxiv.org/abs/1609.09018v1 |
| http://arxiv.org/pdf/1609.09018v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-architectures-for-face-attributes |
| Repo | |
| Framework | |
The Great Time Series Classification Bake Off: An Experimental Evaluation of Recently Proposed Algorithms. Extended Version
| Title | The Great Time Series Classification Bake Off: An Experimental Evaluation of Recently Proposed Algorithms. Extended Version |
| Authors | Anthony Bagnall, Aaron Bostrom, James Large, Jason Lines |
| Abstract | In the last five years there have been a large number of new time series classification algorithms proposed in the literature. These algorithms have been evaluated on subsets of the 47 data sets in the University of California, Riverside time series classification archive. The archive has recently been expanded to 85 data sets, over half of which have been donated by researchers at the University of East Anglia. Aspects of previous evaluations have made comparisons between algorithms difficult. For example, several different programming languages have been used, experiments involved a single train/test split and some used normalised data whilst others did not. The relaunch of the archive provides a timely opportunity to thoroughly evaluate algorithms on a larger number of datasets. We have implemented 18 recently proposed algorithms in a common Java framework and compared them against two standard benchmark classifiers (and each other) by performing 100 resampling experiments on each of the 85 datasets. We use these results to test several hypotheses relating to whether the algorithms are significantly more accurate than the benchmarks and each other. Our results indicate that only 9 of these algorithms are significantly more accurate than both benchmarks and that one classifier, the Collective of Transformation Ensembles, is significantly more accurate than all of the others. All of our experiments and results are reproducible: we release all of our code, results and experimental details and we hope these experiments form the basis for more rigorous testing of new algorithms in the future. |
| Tasks | Time Series, Time Series Classification |
| Published | 2016-02-04 |
| URL | http://arxiv.org/abs/1602.01711v1 |
| http://arxiv.org/pdf/1602.01711v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-great-time-series-classification-bake-off |
| Repo | |
| Framework | |
Co-Occurrence Patterns in the Voynich Manuscript
| Title | Co-Occurrence Patterns in the Voynich Manuscript |
| Authors | Torsten Timm |
| Abstract | The Voynich Manuscript is a medieval book written in an unknown script. This paper studies the distribution of similarly spelled words in the Voynich Manuscript. It shows that the distribution of words within the manuscript is not compatible with natural languages. |
| Tasks | |
| Published | 2016-01-27 |
| URL | http://arxiv.org/abs/1601.07435v2 |
| http://arxiv.org/pdf/1601.07435v2.pdf | |
| PWC | https://paperswithcode.com/paper/co-occurrence-patterns-in-the-voynich |
| Repo | |
| Framework | |
Divide and Conquer Local Average Regression
| Title | Divide and Conquer Local Average Regression |
| Authors | Xiangyu Chang, Shaobo Lin, Yao Wang |
| Abstract | The divide and conquer strategy, which breaks a massive data set into a se- ries of manageable data blocks, and then combines the independent results of data blocks to obtain a final decision, has been recognized as a state-of-the-art method to overcome challenges of massive data analysis. In this paper, we merge the divide and conquer strategy with local average regression methods to infer the regressive relationship of input-output pairs from a massive data set. After theoretically analyzing the pros and cons, we find that although the divide and conquer local average regression can reach the optimal learning rate, the restric- tion to the number of data blocks is a bit strong, which makes it only feasible for small number of data blocks. We then propose two variants to lessen (or remove) this restriction. Our results show that these variants can achieve the optimal learning rate with much milder restriction (or without such restriction). Extensive experimental studies are carried out to verify our theoretical assertions. |
| Tasks | |
| Published | 2016-01-23 |
| URL | http://arxiv.org/abs/1601.06239v2 |
| http://arxiv.org/pdf/1601.06239v2.pdf | |
| PWC | https://paperswithcode.com/paper/divide-and-conquer-local-average-regression |
| Repo | |
| Framework | |
Using inspiration from synaptic plasticity rules to optimize traffic flow in distributed engineered networks
| Title | Using inspiration from synaptic plasticity rules to optimize traffic flow in distributed engineered networks |
| Authors | Jonathan Y. Suen, Saket Navlakha |
| Abstract | Controlling the flow and routing of data is a fundamental problem in many distributed networks, including transportation systems, integrated circuits, and the Internet. In the brain, synaptic plasticity rules have been discovered that regulate network activity in response to environmental inputs, which enable circuits to be stable yet flexible. Here, we develop a new neuro-inspired model for network flow control that only depends on modifying edge weights in an activity-dependent manner. We show how two fundamental plasticity rules (long-term potentiation and long-term depression) can be cast as a distributed gradient descent algorithm for regulating traffic flow in engineered networks. We then characterize, both via simulation and analytically, how different forms of edge-weight update rules affect network routing efficiency and robustness. We find a close correspondence between certain classes of synaptic weight update rules derived experimentally in the brain and rules commonly used in engineering, suggesting common principles to both. |
| Tasks | |
| Published | 2016-11-21 |
| URL | http://arxiv.org/abs/1611.06937v1 |
| http://arxiv.org/pdf/1611.06937v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-inspiration-from-synaptic-plasticity |
| Repo | |
| Framework | |
A Robust Frame-based Nonlinear Prediction System for Automatic Speech Coding
| Title | A Robust Frame-based Nonlinear Prediction System for Automatic Speech Coding |
| Authors | Mahmood Yousefi-Azar, Farbod Razzazi |
| Abstract | In this paper, we propose a neural-based coding scheme in which an artificial neural network is exploited to automatically compress and decompress speech signals by a trainable approach. Having a two-stage training phase, the system can be fully specified to each speech frame and have robust performance across different speakers and wide range of spoken utterances. Indeed, Frame-based nonlinear predictive coding (FNPC) would code a frame in the procedure of training to predict the frame samples. The motivating objective is to analyze the system behavior in regenerating not only the envelope of spectra, but also the spectra phase. This scheme has been evaluated in time and discrete cosine transform (DCT) domains and the output of predicted phonemes show the potentiality of the FNPC to reconstruct complicated signals. The experiments were conducted on three voiced plosive phonemes, b/d/g/ in time and DCT domains versus the number of neurons in the hidden layer. Experiments approve the FNPC capability as an automatic coding system by which /b/d/g/ phonemes have been reproduced with a good accuracy. Evaluations revealed that the performance of FNPC system, trained to predict DCT coefficients is more desirable, particularly for frames with the wider distribution of energy, compared to time samples. |
| Tasks | |
| Published | 2016-01-22 |
| URL | http://arxiv.org/abs/1601.06008v1 |
| http://arxiv.org/pdf/1601.06008v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-robust-frame-based-nonlinear-prediction |
| Repo | |
| Framework | |
Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation
| Title | Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation |
| Authors | Zhicheng Yan, Hao Zhang, Yangqing Jia, Thomas Breuel, Yizhou Yu |
| Abstract | State-of-the-art results of semantic segmentation are established by Fully Convolutional neural Networks (FCNs). FCNs rely on cascaded convolutional and pooling layers to gradually enlarge the receptive fields of neurons, resulting in an indirect way of modeling the distant contextual dependence. In this work, we advocate the use of spatially recurrent layers (i.e. ReNet layers) which directly capture global contexts and lead to improved feature representations. We demonstrate the effectiveness of ReNet layers by building a Naive deep ReNet (N-ReNet), which achieves competitive performance on Stanford Background dataset. Furthermore, we integrate ReNet layers with FCNs, and develop a novel Hybrid deep ReNet (H-ReNet). It enjoys a few remarkable properties, including full-image receptive fields, end-to-end training, and efficient network execution. On the PASCAL VOC 2012 benchmark, the H-ReNet improves the results of state-of-the-art approaches Piecewise, CRFasRNN and DeepParsing by 3.6%, 2.3% and 0.2%, respectively, and achieves the highest IoUs for 13 out of the 20 object classes. |
| Tasks | Semantic Segmentation |
| Published | 2016-03-15 |
| URL | http://arxiv.org/abs/1603.04871v1 |
| http://arxiv.org/pdf/1603.04871v1.pdf | |
| PWC | https://paperswithcode.com/paper/combining-the-best-of-convolutional-layers |
| Repo | |
| Framework | |
CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection
| Title | CMS-RCNN: Contextual Multi-Scale Region-based CNN for Unconstrained Face Detection |
| Authors | Chenchen Zhu, Yutong Zheng, Khoa Luu, Marios Savvides |
| Abstract | Robust face detection in the wild is one of the ultimate components to support various facial related problems, i.e. unconstrained face recognition, facial periocular recognition, facial landmarking and pose estimation, facial expression recognition, 3D facial model construction, etc. Although the face detection problem has been intensely studied for decades with various commercial applications, it still meets problems in some real-world scenarios due to numerous challenges, e.g. heavy facial occlusions, extremely low resolutions, strong illumination, exceptionally pose variations, image or video compression artifacts, etc. In this paper, we present a face detection approach named Contextual Multi-Scale Region-based Convolution Neural Network (CMS-RCNN) to robustly solve the problems mentioned above. Similar to the region-based CNNs, our proposed network consists of the region proposal component and the region-of-interest (RoI) detection component. However, far apart of that network, there are two main contributions in our proposed network that play a significant role to achieve the state-of-the-art performance in face detection. Firstly, the multi-scale information is grouped both in region proposal and RoI detection to deal with tiny face regions. Secondly, our proposed network allows explicit body contextual reasoning in the network inspired from the intuition of human vision system. The proposed approach is benchmarked on two recent challenging face detection databases, i.e. the WIDER FACE Dataset which contains high degree of variability, as well as the Face Detection Dataset and Benchmark (FDDB). The experimental results show that our proposed approach trained on WIDER FACE Dataset outperforms strong baselines on WIDER FACE Dataset by a large margin, and consistently achieves competitive results on FDDB against the recent state-of-the-art face detection methods. |
| Tasks | Face Detection, Face Recognition, Facial Expression Recognition, Pose Estimation, Robust Face Recognition, Video Compression |
| Published | 2016-06-17 |
| URL | http://arxiv.org/abs/1606.05413v1 |
| http://arxiv.org/pdf/1606.05413v1.pdf | |
| PWC | https://paperswithcode.com/paper/cms-rcnn-contextual-multi-scale-region-based |
| Repo | |
| Framework | |
Low-Cost Scene Modeling using a Density Function Improves Segmentation Performance
| Title | Low-Cost Scene Modeling using a Density Function Improves Segmentation Performance |
| Authors | Vivek Sharma, Sule Yildirim-Yayilgan, Luc Van Gool |
| Abstract | We propose a low cost and effective way to combine a free simulation software and free CAD models for modeling human-object interaction in order to improve human & object segmentation. It is intended for research scenarios related to safe human-robot collaboration (SHRC) and interaction (SHRI) in the industrial domain. The task of human and object modeling has been used for detecting activity, and for inferring and predicting actions, different from those works, we do human and object modeling in order to learn interactions in RGB-D data for improving segmentation. For this purpose, we define a novel density function to model a three dimensional (3D) scene in a virtual environment (VREP). This density function takes into account various possible configurations of human-object and object-object relationships and interactions governed by their affordances. Using this function, we synthesize a large, realistic and highly varied synthetic RGB-D dataset that we use for training. We train a random forest classifier, and the pixelwise predictions obtained is integrated as a unary term in a pairwise conditional random fields (CRF). Our evaluation shows that modeling these interactions improves segmentation performance by ~7% in mean average precision and recall over state-of-the-art methods that ignore these interactions in real-world data. Our approach is computationally efficient, robust and can run real-time on consumer hardware. |
| Tasks | Human-Object Interaction Detection, Semantic Segmentation |
| Published | 2016-05-26 |
| URL | http://arxiv.org/abs/1605.08464v1 |
| http://arxiv.org/pdf/1605.08464v1.pdf | |
| PWC | https://paperswithcode.com/paper/low-cost-scene-modeling-using-a-density |
| Repo | |
| Framework | |
Probabilistic map-matching using particle filters
| Title | Probabilistic map-matching using particle filters |
| Authors | Kira Kempinska, Toby Davies, John Shawe-Taylor |
| Abstract | Increasing availability of vehicle GPS data has created potentially transformative opportunities for traffic management, route planning and other location-based services. Critical to the utility of the data is their accuracy. Map-matching is the process of improving the accuracy by aligning GPS data with the road network. In this paper, we propose a purely probabilistic approach to map-matching based on a sequential Monte Carlo algorithm known as particle filters. The approach performs map-matching by producing a range of candidate solutions, each with an associated probability score. We outline implementation details and thoroughly validate the technique on GPS data of varied quality. |
| Tasks | |
| Published | 2016-11-29 |
| URL | http://arxiv.org/abs/1611.09706v1 |
| http://arxiv.org/pdf/1611.09706v1.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-map-matching-using-particle |
| Repo | |
| Framework | |
New wavelet-based superresolution algorithm for speckle reduction in SAR images
| Title | New wavelet-based superresolution algorithm for speckle reduction in SAR images |
| Authors | Mario Mastriani |
| Abstract | This paper describes a novel projection algorithm, the Projection Onto Span Algorithm (POSA) for wavelet-based superresolution and removing speckle (in wavelet domain) of unknown variance from Synthetic Aperture Radar (SAR) images. Although the POSA is good as a new superresolution algorithm for image enhancement, image metrology and biometric identification, here one will use it like a tool of despeckling, being the first time that an algorithm of super-resolution is used for despeckling of SAR images. Specifically, the speckled SAR image is decomposed into wavelet subbands, POSA is applied to the high subbands, and reconstruct a SAR image from the modified detail coefficients. Experimental results demonstrate that the new method compares favorably to several other despeckling methods on test SAR images. |
| Tasks | Image Enhancement, Super-Resolution |
| Published | 2016-07-31 |
| URL | http://arxiv.org/abs/1608.00270v1 |
| http://arxiv.org/pdf/1608.00270v1.pdf | |
| PWC | https://paperswithcode.com/paper/new-wavelet-based-superresolution-algorithm |
| Repo | |
| Framework | |
Using Natural Language Processing and Qualitative Analysis to Intervene in Gang Violence: A Collaboration Between Social Work Researchers and Data Scientists
| Title | Using Natural Language Processing and Qualitative Analysis to Intervene in Gang Violence: A Collaboration Between Social Work Researchers and Data Scientists |
| Authors | Desmond Upton Patton, Kathleen McKeown, Owen Rambow, Jamie Macbeth |
| Abstract | The U.S. has the highest rate of firearm-related deaths when compared to other industrialized countries. Violence particularly affects low-income, urban neighborhoods in cities like Chicago, which saw a 40% increase in firearm violence from 2014 to 2015 to more than 3,000 shooting victims. While recent studies have found that urban, gang-involved individuals curate a unique and complex communication style within and between social media platforms, organizations focused on reducing gang violence are struggling to keep up with the growing complexity of social media platforms and the sheer volume of data they present. In this paper, describe the Digital Urban Violence Analysis Approach (DUVVA), a collaborative qualitative analysis method used in a collaboration between data scientists and social work researchers to develop a suite of systems for decoding the high- stress language of urban, gang-involved youth. Our approach leverages principles of grounded theory when analyzing approximately 800 tweets posted by Chicago gang members and participation of youth from Chicago neighborhoods to create a language resource for natural language processing (NLP) methods. In uncovering the unique language and communication style, we developed automated tools with the potential to detect aggressive language on social media and aid individuals and groups in performing violence prevention and interruption. |
| Tasks | |
| Published | 2016-09-28 |
| URL | http://arxiv.org/abs/1609.08779v1 |
| http://arxiv.org/pdf/1609.08779v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-natural-language-processing-and |
| Repo | |
| Framework | |
Cross Device Matching for Online Advertising with Neural Feature Ensembles : First Place Solution at CIKM Cup 2016
| Title | Cross Device Matching for Online Advertising with Neural Feature Ensembles : First Place Solution at CIKM Cup 2016 |
| Authors | Minh C. Phan, Yi Tay, Tuan-Anh Nguyen Pham |
| Abstract | We describe the 1st place winning approach for the CIKM Cup 2016 Challenge. In this paper, we provide an approach to reasonably identify same users across multiple devices based on browsing logs. Our approach regards a candidate ranking problem as pairwise classification and utilizes an unsupervised neural feature ensemble approach to learn latent features of users. Combined with traditional hand crafted features, each user pair feature is fed into a supervised classifier in order to perform pairwise classification. Lastly, we propose supervised and unsupervised inference techniques. |
| Tasks | |
| Published | 2016-10-23 |
| URL | http://arxiv.org/abs/1610.07119v2 |
| http://arxiv.org/pdf/1610.07119v2.pdf | |
| PWC | https://paperswithcode.com/paper/cross-device-matching-for-online-advertising |
| Repo | |
| Framework | |
Character Sequence Models for ColorfulWords
| Title | Character Sequence Models for ColorfulWords |
| Authors | Kazuya Kawakami, Chris Dyer, Bryan R. Routledge, Noah A. Smith |
| Abstract | We present a neural network architecture to predict a point in color space from the sequence of characters in the color’s name. Using large scale color–name pairs obtained from an online color design forum, we evaluate our model on a “color Turing test” and find that, given a name, the colors predicted by our model are preferred by annotators to color names created by humans. Our datasets and demo system are available online at colorlab.us. |
| Tasks | |
| Published | 2016-09-28 |
| URL | http://arxiv.org/abs/1609.08777v2 |
| http://arxiv.org/pdf/1609.08777v2.pdf | |
| PWC | https://paperswithcode.com/paper/character-sequence-models-for-colorfulwords |
| Repo | |
| Framework | |
Temporal Topic Analysis with Endogenous and Exogenous Processes
| Title | Temporal Topic Analysis with Endogenous and Exogenous Processes |
| Authors | Baiyang Wang, Diego Klabjan |
| Abstract | We consider the problem of modeling temporal textual data taking endogenous and exogenous processes into account. Such text documents arise in real world applications, including job advertisements and economic news articles, which are influenced by the fluctuations of the general economy. We propose a hierarchical Bayesian topic model which imposes a “group-correlated” hierarchical structure on the evolution of topics over time incorporating both processes, and show that this model can be estimated from Markov chain Monte Carlo sampling methods. We further demonstrate that this model captures the intrinsic relationships between the topic distribution and the time-dependent factors, and compare its performance with latent Dirichlet allocation (LDA) and two other related models. The model is applied to two collections of documents to illustrate its empirical performance: online job advertisements from DirectEmployers Association and journalists’ postings on BusinessInsider.com. |
| Tasks | |
| Published | 2016-07-04 |
| URL | http://arxiv.org/abs/1607.01274v1 |
| http://arxiv.org/pdf/1607.01274v1.pdf | |
| PWC | https://paperswithcode.com/paper/temporal-topic-analysis-with-endogenous-and |
| Repo | |
| Framework | |
