Paper Group ANR 1045
Cross-lingual Semantic Parsing. Hierarchical Selective Recruitment in Linear-Threshold Brain Networks – Part I: Single-Layer Dynamics and Selective Inhibition. Supervised Machine Learning for Extractive Query Based Summarisation of Biomedical Data. Gender Bias in Neural Natural Language Processing. Predicting the Future with Transformational State …
Cross-lingual Semantic Parsing
Title | Cross-lingual Semantic Parsing |
Authors | Sheng Zhang, Kevin Duh, Benjamin Van Durme |
Abstract | We introduce the task of cross-lingual semantic parsing: mapping content provided in a source language into a meaning representation based on a target language. We present: (1) a meaning representation designed to allow systems to target varying levels of structural complexity (shallow to deep analysis), (2) an evaluation metric to measure the similarity between system output and reference meaning representations, (3) an end-to-end model with a novel copy mechanism that supports intrasentential coreference, and (4) an evaluation dataset where experiments show our model outperforms strong baselines by at least 1.18 F1 score. |
Tasks | Semantic Parsing |
Published | 2018-04-21 |
URL | http://arxiv.org/abs/1804.08037v1 |
http://arxiv.org/pdf/1804.08037v1.pdf | |
PWC | https://paperswithcode.com/paper/cross-lingual-semantic-parsing |
Repo | |
Framework | |
Hierarchical Selective Recruitment in Linear-Threshold Brain Networks – Part I: Single-Layer Dynamics and Selective Inhibition
Title | Hierarchical Selective Recruitment in Linear-Threshold Brain Networks – Part I: Single-Layer Dynamics and Selective Inhibition |
Authors | Erfan Nozari, Jorge Cortés |
Abstract | Goal-driven selective attention (GDSA) refers to the brain’s function of prioritizing, according to one’s internal goals and desires, the activity of a task-relevant subset of its overall network to efficiently process relevant information while inhibiting the effects of distractions. Despite decades of research in neuroscience, a comprehensive understanding of GDSA is still lacking. We propose a novel framework for GDSA using concepts and tools from control theory as well as insights and structures from neuroscience. Central to this framework is an information-processing hierarchy with two main components: selective inhibition of task-irrelevant activity and top-down recruitment of task-relevant activity. We analyze the internal dynamics of each layer of the hierarchy described as a network with linear-threshold dynamics and derive conditions on its structure to guarantee existence and uniqueness of equilibria, asymptotic stability, and boundedness of trajectories. We also provide mechanisms that enforce selective inhibition using the biologically-inspired schemes of feedforward and feedback inhibition. Despite their differences, both schemes lead to the same conclusion: the intrinsic dynamical properties of the (not-inhibited) task-relevant subnetworks are the sole determiner of the dynamical properties that are achievable under selective inhibition. |
Tasks | |
Published | 2018-09-05 |
URL | https://arxiv.org/abs/1809.01674v3 |
https://arxiv.org/pdf/1809.01674v3.pdf | |
PWC | https://paperswithcode.com/paper/hierarchical-selective-recruitment-in-linear |
Repo | |
Framework | |
Supervised Machine Learning for Extractive Query Based Summarisation of Biomedical Data
Title | Supervised Machine Learning for Extractive Query Based Summarisation of Biomedical Data |
Authors | Mandeep Kaur, Diego Mollá |
Abstract | The automation of text summarisation of biomedical publications is a pressing need due to the plethora of information available on-line. This paper explores the impact of several supervised machine learning approaches for extracting multi-document summaries for given queries. In particular, we compare classification and regression approaches for query-based extractive summarisation using data provided by the BioASQ Challenge. We tackled the problem of annotating sentences for training classification systems and show that a simple annotation approach outperforms regression-based summarisation. |
Tasks | |
Published | 2018-09-14 |
URL | http://arxiv.org/abs/1809.05268v2 |
http://arxiv.org/pdf/1809.05268v2.pdf | |
PWC | https://paperswithcode.com/paper/supervised-machine-learning-for-extractive |
Repo | |
Framework | |
Gender Bias in Neural Natural Language Processing
Title | Gender Bias in Neural Natural Language Processing |
Authors | Kaiji Lu, Piotr Mardziel, Fangjing Wu, Preetam Amancharla, Anupam Datta |
Abstract | We examine whether neural natural language processing (NLP) systems reflect historical biases in training data. We define a general benchmark to quantify gender bias in a variety of neural NLP tasks. Our empirical evaluation with state-of-the-art neural coreference resolution and textbook RNN-based language models trained on benchmark datasets finds significant gender bias in how models view occupations. We then mitigate bias with CDA: a generic methodology for corpus augmentation via causal interventions that breaks associations between gendered and gender-neutral words. We empirically show that CDA effectively decreases gender bias while preserving accuracy. We also explore the space of mitigation strategies with CDA, a prior approach to word embedding debiasing (WED), and their compositions. We show that CDA outperforms WED, drastically so when word embeddings are trained. For pre-trained embeddings, the two methods can be effectively composed. We also find that as training proceeds on the original data set with gradient descent the gender bias grows as the loss reduces, indicating that the optimization encourages bias; CDA mitigates this behavior. |
Tasks | Coreference Resolution, Word Embeddings |
Published | 2018-07-31 |
URL | https://arxiv.org/abs/1807.11714v2 |
https://arxiv.org/pdf/1807.11714v2.pdf | |
PWC | https://paperswithcode.com/paper/gender-bias-in-neural-natural-language |
Repo | |
Framework | |
Predicting the Future with Transformational States
Title | Predicting the Future with Transformational States |
Authors | Andrew Jaegle, Oleh Rybkin, Konstantinos G. Derpanis, Kostas Daniilidis |
Abstract | An intelligent observer looks at the world and sees not only what is, but what is moving and what can be moved. In other words, the observer sees how the present state of the world can transform in the future. We propose a model that predicts future images by learning to represent the present state and its transformation given only a sequence of images. To do so, we introduce an architecture with a latent state composed of two components designed to capture (i) the present image state and (ii) the transformation between present and future states, respectively. We couple this latent state with a recurrent neural network (RNN) core that predicts future frames by transforming past states into future states by applying the accumulated state transformation with a learned operator. We describe how this model can be integrated into an encoder-decoder convolutional neural network (CNN) architecture that uses weighted residual connections to integrate representations of the past with representations of the future. Qualitatively, our approach generates image sequences that are stable and capture realistic motion over multiple predicted frames, without requiring adversarial training. Quantitatively, our method achieves prediction results comparable to state-of-the-art results on standard image prediction benchmarks (Moving MNIST, KTH, and UCF101). |
Tasks | |
Published | 2018-03-26 |
URL | http://arxiv.org/abs/1803.09760v1 |
http://arxiv.org/pdf/1803.09760v1.pdf | |
PWC | https://paperswithcode.com/paper/predicting-the-future-with-transformational |
Repo | |
Framework | |
Survey on Vision-based Path Prediction
Title | Survey on Vision-based Path Prediction |
Authors | Tsubasa Hirakawa, Takayoshi Yamashita, Toru Tamaki, Hironobu Fujiyoshi |
Abstract | Path prediction is a fundamental task for estimating how pedestrians or vehicles are going to move in a scene. Because path prediction as a task of computer vision uses video as input, various information used for prediction, such as the environment surrounding the target and the internal state of the target, need to be estimated from the video in addition to predicting paths. Many prediction approaches that include understanding the environment and the internal state have been proposed. In this survey, we systematically summarize methods of path prediction that take video as input and and extract features from the video. Moreover, we introduce datasets used to evaluate path prediction methods quantitatively. |
Tasks | |
Published | 2018-11-01 |
URL | http://arxiv.org/abs/1811.00233v1 |
http://arxiv.org/pdf/1811.00233v1.pdf | |
PWC | https://paperswithcode.com/paper/survey-on-vision-based-path-prediction |
Repo | |
Framework | |
3D model silhouette-based tracking in depth images for puppet suit dynamic video-mapping
Title | 3D model silhouette-based tracking in depth images for puppet suit dynamic video-mapping |
Authors | Guillaume Caron, Mounya Belghiti, Anthony Dessaux |
Abstract | Video-mapping is the process of coherent video-projection of images, animations or movies on static objects or buildings for shows. This paper focuses on the dynamic video-mapping of the suit of a puppet being moved by its puppeteer on the theater stage. This may allow changing the costume dynamically and simulate light interaction and more. Contrary to common video-mapping, the image warping cannot be done once, offline, before the show. It must be done in real-time, and considering a non-flat projection surface, so that the video-projected suit always maps perfectly the puppet, automatically. Hence, we propose a new visual tracking method of articulated object, for the puppet tracking, exploiting the silhouette of a 3D model of it, in the depth images of a Kinect v2. Then, considering the precise calibration between the latter and the video-projector, that we propose, coherent dynamic video-mapping is made possible as the presented results show. |
Tasks | Calibration, Visual Tracking |
Published | 2018-10-09 |
URL | http://arxiv.org/abs/1810.03956v1 |
http://arxiv.org/pdf/1810.03956v1.pdf | |
PWC | https://paperswithcode.com/paper/3d-model-silhouette-based-tracking-in-depth |
Repo | |
Framework | |
IPOD: Intensive Point-based Object Detector for Point Cloud
Title | IPOD: Intensive Point-based Object Detector for Point Cloud |
Authors | Zetong Yang, Yanan Sun, Shu Liu, Xiaoyong Shen, Jiaya Jia |
Abstract | We present a novel 3D object detection framework, named IPOD, based on raw point cloud. It seeds object proposal for each point, which is the basic element. This paradigm provides us with high recall and high fidelity of information, leading to a suitable way to process point cloud data. We design an end-to-end trainable architecture, where features of all points within a proposal are extracted from the backbone network and achieve a proposal feature for final bounding inference. These features with both context information and precise point cloud coordinates yield improved performance. We conduct experiments on KITTI dataset, evaluating our performance in terms of 3D object detection, Bird’s Eye View (BEV) detection and 2D object detection. Our method accomplishes new state-of-the-art , showing great advantage on the hard set. |
Tasks | 3D Object Detection, Object Detection |
Published | 2018-12-13 |
URL | http://arxiv.org/abs/1812.05276v1 |
http://arxiv.org/pdf/1812.05276v1.pdf | |
PWC | https://paperswithcode.com/paper/ipod-intensive-point-based-object-detector |
Repo | |
Framework | |
Unsupervised Band Selection of Hyperspectral Images via Multi-dictionary Sparse Representation
Title | Unsupervised Band Selection of Hyperspectral Images via Multi-dictionary Sparse Representation |
Authors | Fei Li, Pingping Zhang, Huchuan Lu |
Abstract | Hyperspectral images have far more spectral bands than ordinary multispectral images. Rich band information provides more favorable conditions for the tremendous applications. However, significant increase in the dimensionality of spectral bands may lead to the curse of dimensionality, especially for classification applications. Furthermore, there are a large amount of redundant information among the raw image cubes due to water absorptions, sensor noises and other influence factors. Band selection is a direct and effective method to remove redundant information and reduce the spectral dimension for decreasing computational complexity and avoiding the curse of dimensionality. In this paper, we present a novel learning framework for band selection based on the idea of sparse representation. More specifically, first each band is approximately represented by the linear combination of other bands, then the original band image can be represented by a multi-dictionary learning mechanism. As a result, a group of weights can be obtained by sparse optimization for all bands. Finally, the specific bands will be selected, if they get higher weights than other bands in the representation of the original image. Experimental results on three widely used hyperspectral datasets show that our proposed algorithm achieves better performance in hyperspectral image classification, when compared with other state-of-art band selection methods. |
Tasks | Dictionary Learning, Hyperspectral Image Classification, Image Classification |
Published | 2018-02-20 |
URL | http://arxiv.org/abs/1802.06983v1 |
http://arxiv.org/pdf/1802.06983v1.pdf | |
PWC | https://paperswithcode.com/paper/unsupervised-band-selection-of-hyperspectral |
Repo | |
Framework | |
ProstateGAN: Mitigating Data Bias via Prostate Diffusion Imaging Synthesis with Generative Adversarial Networks
Title | ProstateGAN: Mitigating Data Bias via Prostate Diffusion Imaging Synthesis with Generative Adversarial Networks |
Authors | Xiaodan Hu, Audrey G. Chung, Paul Fieguth, Farzad Khalvati, Masoom A. Haider, Alexander Wong |
Abstract | Generative Adversarial Networks (GANs) have shown considerable promise for mitigating the challenge of data scarcity when building machine learning-driven analysis algorithms. Specifically, a number of studies have shown that GAN-based image synthesis for data augmentation can aid in improving classification accuracy in a number of medical image analysis tasks, such as brain and liver image analysis. However, the efficacy of leveraging GANs for tackling prostate cancer analysis has not been previously explored. Motivated by this, in this study we introduce ProstateGAN, a GAN-based model for synthesizing realistic prostate diffusion imaging data. More specifically, in order to generate new diffusion imaging data corresponding to a particular cancer grade (Gleason score), we propose a conditional deep convolutional GAN architecture that takes Gleason scores into consideration during the training process. Experimental results show that high-quality synthetic prostate diffusion imaging data can be generated using the proposed ProstateGAN for specified Gleason scores. |
Tasks | Data Augmentation, Image Generation |
Published | 2018-11-14 |
URL | http://arxiv.org/abs/1811.05817v2 |
http://arxiv.org/pdf/1811.05817v2.pdf | |
PWC | https://paperswithcode.com/paper/prostategan-mitigating-data-bias-via-prostate |
Repo | |
Framework | |
Large Scale Scene Text Verification with Guided Attention
Title | Large Scale Scene Text Verification with Guided Attention |
Authors | Dafang He, Yeqing Li, Alexander Gorban, Derrall Heath, Julian Ibarz, Qian Yu, Daniel Kifer, C. Lee Giles |
Abstract | Many tasks are related to determining if a particular text string exists in an image. In this work, we propose a new framework that learns this task in an end-to-end way. The framework takes an image and a text string as input and then outputs the probability of the text string being present in the image. This is the first end-to-end framework that learns such relationships between text and images in scene text area. The framework does not require explicit scene text detection or recognition and thus no bounding box annotations are needed for it. It is also the first work in scene text area that tackles suh a weakly labeled problem. Based on this framework, we developed a model called Guided Attention. Our designed model achieves much better results than several state-of-the-art scene text reading based solutions for a challenging Street View Business Matching task. The task tries to find correct business names for storefront images and the dataset we collected for it is substantially larger, and more challenging than existing scene text dataset. This new real-world task provides a new perspective for studying scene text related problems. We also demonstrate the uniqueness of our task via a comparison between our problem and a typical Visual Question Answering problem. |
Tasks | Question Answering, Scene Text Detection, Visual Question Answering |
Published | 2018-04-23 |
URL | http://arxiv.org/abs/1804.08588v2 |
http://arxiv.org/pdf/1804.08588v2.pdf | |
PWC | https://paperswithcode.com/paper/large-scale-scene-text-verification-with |
Repo | |
Framework | |
Generic Camera Attribute Control using Bayesian Optimization
Title | Generic Camera Attribute Control using Bayesian Optimization |
Authors | Joowan Kim, Younggun Cho, Ayoung Kim |
Abstract | Cameras are the most widely exploited sensor in both robotics and computer vision communities. Despite their popularity, two dominant attributes (i.e., gain and exposure time) have been determined empirically and images are captured in very passive manner. In this paper, we present an active and generic camera attribute control scheme using Bayesian optimization. We extend from our previous work [1] in two aspects. First, we propose a method that jointly controls camera gain and exposure time. Secondly, to speed up the Bayesian optimization process, we introduce image synthesis using the camera response function (CRF). These synthesized images allowed us to diminish the image acquisition time during the Bayesian optimization phase, substantially improving overall control performance. The proposed method is validated both in an indoor and an outdoor environment where light condition rapidly changes. Supplementary material is available at https://youtu.be/XTYR_Mih3OU . |
Tasks | Image Generation |
Published | 2018-07-21 |
URL | http://arxiv.org/abs/1807.10596v3 |
http://arxiv.org/pdf/1807.10596v3.pdf | |
PWC | https://paperswithcode.com/paper/generic-camera-attribute-control-using |
Repo | |
Framework | |
Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification
Title | Exploiting Cross-Lingual Subword Similarities in Low-Resource Document Classification |
Authors | Mozhi Zhang, Yoshinari Fujinuma, Jordan Boyd-Graber |
Abstract | Text classification must sometimes be applied in a low-resource language with no labeled training data. However, training data may be available in a related language. We investigate whether character-level knowledge transfer from a related language helps text classification. We present a cross-lingual document classification framework (CACO) that exploits cross-lingual subword similarity by jointly training a character-based embedder and a word-based classifier. The embedder derives vector representations for input words from their written forms, and the classifier makes predictions based on the word vectors. We use a joint character representation for both the source language and the target language, which allows the embedder to generalize knowledge about source language words to target language words with similar forms. We propose a multi-task objective that can further improve the model if additional cross-lingual or monolingual resources are available. Experiments confirm that character-level knowledge transfer is more data-efficient than word-level transfer between related languages. |
Tasks | Cross-Lingual Document Classification, Document Classification, Text Classification, Transfer Learning |
Published | 2018-12-22 |
URL | https://arxiv.org/abs/1812.09617v3 |
https://arxiv.org/pdf/1812.09617v3.pdf | |
PWC | https://paperswithcode.com/paper/exploiting-cross-lingual-subword-similarities |
Repo | |
Framework | |
Predicting Natural Hazards with Neuronal Networks
Title | Predicting Natural Hazards with Neuronal Networks |
Authors | Matthias Rauter, Daniel Winkler |
Abstract | Gravitational mass flows, such as avalanches, debris flows and rockfalls are common events in alpine regions with high impact on transport routes. Within the last few decades, hazard zone maps have been developed to systematically approach this threat. These maps mark vulnerable zones in habitable areas to allow effective planning of hazard mitigation measures and development of settlements. Hazard zone maps have shown to be an effective tool to reduce fatalities during extreme events. They are created in a complex process, based on experience, empirical models, physical simulations and historical data. The generation of such maps is therefore expensive and limited to crucially important regions, e.g. permanently inhabited areas. In this work we interpret the task of hazard zone mapping as a classification problem. Every point in a specific area has to be classified according to its vulnerability. On a regional scale this leads to a segmentation problem, where the total area has to be divided in the respective hazard zones. The recent developments in artificial intelligence, namely convolutional neuronal networks, have led to major improvement in a very similar task, image classification and semantic segmentation, i.e. computer vision. We use a convolutional neuronal network to identify terrain formations with the potential for catastrophic snow avalanches and label points in their reach as vulnerable. Repeating this procedure for all points allows us to generate an artificial hazard zone map. We demonstrate that the approach is feasible and promising based on the hazard zone map of the Tirolean Oberland. However, more training data and further improvement of the method is required before such techniques can be applied reliably. |
Tasks | Image Classification, Physical Simulations, Semantic Segmentation |
Published | 2018-02-21 |
URL | http://arxiv.org/abs/1802.07257v1 |
http://arxiv.org/pdf/1802.07257v1.pdf | |
PWC | https://paperswithcode.com/paper/predicting-natural-hazards-with-neuronal |
Repo | |
Framework | |
Impacts of transport development on residence choice of renter households: An agent-based evaluation
Title | Impacts of transport development on residence choice of renter households: An agent-based evaluation |
Authors | A. S. Babakan, M. Taleai |
Abstract | Because of improving accessibility, transport developments play an important role in residence choice of renter households. In this paper, an agent-based model is developed to investigate impacts of different transport developments on residence choice of renter households in Tehran, the capital of Iran. In the proposed model, renter households are considered as agents who make a multi-objective decision and compete with each other to rent a preferred residential zone. Then, three transport development scenarios including construction a new highway, subway and bus rapid transit (BRT) line are simulated and resulting changes in residence choice of agents are evaluated. Results show that transport development scenarios significantly affect residence choice behavior of different socio-economic categories of renter households and lead to considerable changes in the residential demand, composition of residents, mean income level and mean car ownership in their vicinities. |
Tasks | |
Published | 2018-03-13 |
URL | http://arxiv.org/abs/1803.04932v1 |
http://arxiv.org/pdf/1803.04932v1.pdf | |
PWC | https://paperswithcode.com/paper/impacts-of-transport-development-on-residence |
Repo | |
Framework | |