Paper Group ANR 609
You Write Like You Eat: Stylistic variation as a predictor of social stratification. Robust Real-time RGB-D Visual Odometry in Dynamic Environments via Rigid Motion Model. Motion Segmentation Using Locally Affine Atom Voting. AI Meets Austen: Towards Human-Robot Discussions of Literary Metaphor. Voice Search and Typed Search Performance Comparison …
You Write Like You Eat: Stylistic variation as a predictor of social stratification
| Title | You Write Like You Eat: Stylistic variation as a predictor of social stratification |
| Authors | Angelo Basile, Albert Gatt, Malvina Nissim |
| Abstract | Inspired by Labov’s seminal work on stylistic variation as a function of social stratification, we develop and compare neural models that predict a person’s presumed socio-economic status, obtained through distant supervision,from their writing style on social media. The focus of our work is on identifying the most important stylistic parameters to predict socio-economic group. In particular, we show the effectiveness of morpho-syntactic features as stylistic predictors of socio-economic group,in contrast to lexical features, which are good predictors of topic. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.07265v1 |
| https://arxiv.org/pdf/1907.07265v1.pdf | |
| PWC | https://paperswithcode.com/paper/you-write-like-you-eat-stylistic-variation-as |
| Repo | |
| Framework | |
Robust Real-time RGB-D Visual Odometry in Dynamic Environments via Rigid Motion Model
| Title | Robust Real-time RGB-D Visual Odometry in Dynamic Environments via Rigid Motion Model |
| Authors | Sangil Lee, Clark Youngdong Son, H. Jin Kim |
| Abstract | In the paper, we propose a robust real-time visual odometry in dynamic environments via rigid-motion model updated by scene flow. The proposed algorithm consists of spatial motion segmentation and temporal motion tracking. The spatial segmentation first generates several motion hypotheses by using a grid-based scene flow and clusters the extracted motion hypotheses, separating objects that move independently of one another. Further, we use a dual-mode motion model to consistently distinguish between the static and dynamic parts in the temporal motion tracking stage. Finally, the proposed algorithm estimates the pose of a camera by taking advantage of the region classified as static parts. In order to evaluate the performance of visual odometry under the existence of dynamic rigid objects, we use self-collected dataset containing RGB-D images and motion capture data for ground-truth. We compare our algorithm with state-of-the-art visual odometry algorithms. The validation results suggest that the proposed algorithm can estimate the pose of a camera robustly and accurately in dynamic environments. |
| Tasks | Motion Capture, Motion Segmentation, Visual Odometry |
| Published | 2019-07-19 |
| URL | https://arxiv.org/abs/1907.08388v1 |
| https://arxiv.org/pdf/1907.08388v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-real-time-rgb-d-visual-odometry-in |
| Repo | |
| Framework | |
Motion Segmentation Using Locally Affine Atom Voting
| Title | Motion Segmentation Using Locally Affine Atom Voting |
| Authors | Erez Posner, Rami Hagege |
| Abstract | We present a novel method for motion segmentation called LAAV (Locally Affine Atom Voting). Our model’s main novelty is using sets of features to segment motion for all features in the scene. LAAV acts as a pre-processing pipeline stage for features in the image, followed by a fine-tuned version of the state-of-the-art Random Voting (RV) method. Unlike standard approaches, LAAV segments motion using feature-set affinities instead of pair-wise affinities between all features; therefore, it significantly simplifies complex scenarios and reduces the computational cost without a loss of accuracy. We describe how the challenges encountered by using previously suggested approaches are addressed using our model. We then compare our algorithm with several state-of-the-art methods. Experiments shows that our approach achieves the most accurate motion segmentation results and, in the presence of measurement noise, achieves comparable results to the other algorithms. |
| Tasks | Motion Segmentation |
| Published | 2019-07-13 |
| URL | https://arxiv.org/abs/1907.06091v1 |
| https://arxiv.org/pdf/1907.06091v1.pdf | |
| PWC | https://paperswithcode.com/paper/motion-segmentation-using-locally-affine-atom |
| Repo | |
| Framework | |
AI Meets Austen: Towards Human-Robot Discussions of Literary Metaphor
| Title | AI Meets Austen: Towards Human-Robot Discussions of Literary Metaphor |
| Authors | Natalie Parde, Rodney D. Nielsen |
| Abstract | Artificial intelligence is revolutionizing formal education, fueled by innovations in learning assessment, content generation, and instructional delivery. Informal, lifelong learning settings have been the subject of less attention. We provide a proof-of-concept for an embodied book discussion companion, designed to stimulate conversations with readers about particularly creative metaphors in fiction literature. We collect ratings from 26 participants, each of whom discuss Jane Austen’s “Pride and Prejudice” with the robot across one or more sessions, and find that participants rate their interactions highly. This suggests that companion robots could be an interesting entryway for the promotion of lifelong learning and cognitive exercise in future applications. |
| Tasks | |
| Published | 2019-04-07 |
| URL | http://arxiv.org/abs/1904.03713v1 |
| http://arxiv.org/pdf/1904.03713v1.pdf | |
| PWC | https://paperswithcode.com/paper/ai-meets-austen-towards-human-robot |
| Repo | |
| Framework | |
Voice Search and Typed Search Performance Comparison on Baidu Search System
| Title | Voice Search and Typed Search Performance Comparison on Baidu Search System |
| Authors | Hanqing Huang, Kezia Irene, Nahyun Ryu |
| Abstract | Although the voice search system is getting more and more developed, some people still have difficulties when searching for information with the voice search system. This paper is a pilot study to compare the search performance of people using voice search and typed search using Baidu search system. We surveyed and interviewed 40 Chinese students who have been using the Baidu search system. Afterward, we analyzed 8 people who had a middle to advanced searching ability by their behaviors, search results, and average query length. We found that there are a lot of variations among the participants’ time when searching for different queries, and there were some interesting behaviors that were displayed by a number of participants. We conclude that more participants are needed to make a firm conclusion on the performance comparison between the voice search and typed search. |
| Tasks | |
| Published | 2019-11-17 |
| URL | https://arxiv.org/abs/1911.11063v1 |
| https://arxiv.org/pdf/1911.11063v1.pdf | |
| PWC | https://paperswithcode.com/paper/voice-search-and-typed-search-performance |
| Repo | |
| Framework | |
An Efficient Solution to Non-Minimal Case Essential Matrix Estimation
| Title | An Efficient Solution to Non-Minimal Case Essential Matrix Estimation |
| Authors | Ji Zhao |
| Abstract | Finding relative pose between two calibrated images is a fundamental task in computer vision. Given five point correspondences, the classical five-point method can be used to calculate the essential matrix efficiently. For the non-minimal $N$ ($N > 5$) inlier point correspondences, which is called $N$-point problem, existing methods are either inefficient or prone to local minima. In this paper, we propose a globally optimal and efficient solver for the $N$-point problem. First we formulate the problem as a quadratically constrained quadratic program (QCQP). Then a globally optimal solution to this problem is obtained by semidefinite relaxation. This allows us to obtain certifiably globally optimal solutions to the original non-convex QCQP in polynomial time. The theoretical guarantees of the semidefinite relaxation are also provided, including the tightness and local stability. To deal with outliers, we also propose a robust $N$-point method using M-estimator. Extensive experiments on synthetic and real-world datasets demonstrated that our $N$-point method is $2\sim3$ orders of magnitude faster than state-of-the-art non-minimal solvers. Besides, our robust $N$-point method outperforms state-of-the-art methods in terms of robustness and accuracy. |
| Tasks | |
| Published | 2019-03-21 |
| URL | https://arxiv.org/abs/1903.09067v2 |
| https://arxiv.org/pdf/1903.09067v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-solution-to-non-minimal-case |
| Repo | |
| Framework | |
MRI Brain Tumor Segmentation using Random Forests and Fully Convolutional Networks
| Title | MRI Brain Tumor Segmentation using Random Forests and Fully Convolutional Networks |
| Authors | Mohammadreza Soltaninejad, Lei Zhang, Tryphon Lambrou, Guang Yang, Nigel Allinson, Xujiong Ye |
| Abstract | In this paper, we propose a novel learning based method for automated segmentation of brain tumor in multimodal MRI images, which incorporates two sets of machine -learned and hand crafted features. Fully convolutional networks (FCN) forms the machine learned features and texton based features are considered as hand-crafted features. Random forest (RF) is used to classify the MRI image voxels into normal brain tissues and different parts of tumors, i.e. edema, necrosis and enhancing tumor. The method was evaluated on BRATS 2017 challenge dataset. The results show that the proposed method provides promising segmentations. The mean Dice overlap measure for automatic brain tumor segmentation against ground truth is 0.86, 0.78 and 0.66 for whole tumor, core and enhancing tumor, respectively. |
| Tasks | Brain Tumor Segmentation |
| Published | 2019-09-13 |
| URL | https://arxiv.org/abs/1909.06337v1 |
| https://arxiv.org/pdf/1909.06337v1.pdf | |
| PWC | https://paperswithcode.com/paper/mri-brain-tumor-segmentation-using-random |
| Repo | |
| Framework | |
Creation of digital elevation models for river floodplains
| Title | Creation of digital elevation models for river floodplains |
| Authors | Anna Klikunova, Alexander Khoperskov |
| Abstract | A procedure for constructing a digital elevation model (DEM) of the northern part of the Volga-Akhtuba interfluve is described. The basis of our DEM is the elevation matrix of Shuttle Radar Topography Mission (SRTM) for which we carried out the refinement and updating of spatial data using satellite imagery, GPS data, depth measurements of the River Volga and River Akhtuba stream beds. The most important source of high-altitude data for the Volga-Akhtuba floodplain (VAF) can be the results of observations of the coastlines dynamics of small reservoirs (lakes, eriks, small channels) arising in the process of spring flooding and disappearing during low-flow periods. A set of digitized coastlines at different times of flooding can significantly improve the quality of the DEM. The method of constructing a digital elevation model includes an iterative procedure that uses the results of morphostructural analysis of the DEM and the numerical hydrodynamic simulations of the VAF flooding based on the shallow water model. |
| Tasks | |
| Published | 2019-08-18 |
| URL | https://arxiv.org/abs/1908.09005v1 |
| https://arxiv.org/pdf/1908.09005v1.pdf | |
| PWC | https://paperswithcode.com/paper/creation-of-digital-elevation-models-for |
| Repo | |
| Framework | |
Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text
| Title | Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text |
| Authors | Bhavana Dalvi Mishra, Niket Tandon, Antoine Bosselut, Wen-tau Yih, Peter Clark |
| Abstract | Our goal is to better comprehend procedural text, e.g., a paragraph about photosynthesis, by not only predicting what happens, but why some actions need to happen before others. Our approach builds on a prior process comprehension framework for predicting actions’ effects, to also identify subsequent steps that those effects enable. We present our new model (XPAD) that biases effect predictions towards those that (1) explain more of the actions in the paragraph and (2) are more plausible with respect to background knowledge. We also extend an existing benchmark dataset for procedural text comprehension, ProPara, by adding the new task of explaining actions by predicting their dependencies. We find that XPAD significantly outperforms prior systems on this task, while maintaining the performance on the original task in ProPara. The dataset is available at http://data.allenai.org/propara |
| Tasks | Reading Comprehension |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04745v2 |
| https://arxiv.org/pdf/1909.04745v2.pdf | |
| PWC | https://paperswithcode.com/paper/everything-happens-for-a-reason-discovering |
| Repo | |
| Framework | |
Label Prediction Framework for Semi-Supervised Cross-Modal Retrieval
| Title | Label Prediction Framework for Semi-Supervised Cross-Modal Retrieval |
| Authors | Devraj Mandal, Pramod Rao, Soma Biswas |
| Abstract | Cross-modal data matching refers to retrieval of data from one modality, when given a query from another modality. In general, supervised algorithms achieve better retrieval performance compared to their unsupervised counterpart, as they can learn better representative features by leveraging the available label information. However, this comes at the cost of requiring huge amount of labeled examples, which may not always be available. In this work, we propose a novel framework in a semi-supervised setting, which can predict the labels of the unlabeled data using complementary information from different modalities. The proposed framework can be used as an add-on with any baseline crossmodal algorithm to give significant performance improvement, even in case of limited labeled data. Finally, we analyze the challenging scenario where the unlabeled examples can even come from classes not in the training data and evaluate the performance of our algorithm under such setting. Extensive evaluation using several baseline algorithms across three different datasets shows the effectiveness of our label prediction framework. |
| Tasks | Cross-Modal Retrieval |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.11139v1 |
| https://arxiv.org/pdf/1905.11139v1.pdf | |
| PWC | https://paperswithcode.com/paper/label-prediction-framework-for-semi |
| Repo | |
| Framework | |
Tile Pattern KL-Divergence for Analysing and Evolving Game Levels
| Title | Tile Pattern KL-Divergence for Analysing and Evolving Game Levels |
| Authors | Simon M. Lucas, Vanessa Volz |
| Abstract | This paper provides a detailed investigation of using the Kullback-Leibler (KL) Divergence as a way to compare and analyse game-levels, and hence to use the measure as the objective function of an evolutionary algorithm to evolve new levels. We describe the benefits of its asymmetry for level analysis and demonstrate how (not surprisingly) the quality of the results depends on the features used. Here we use tile-patterns of various sizes as features. When using the measure for evolution-based level generation, we demonstrate that the choice of variation operator is critical in order to provide an efficient search process, and introduce a novel convolutional mutation operator to facilitate this. We compare the results with alternative generators, including evolving in the latent space of generative adversarial networks, and Wave Function Collapse. The results clearly show the proposed method to provide competitive performance, providing reasonable quality results with very fast training and reasonably fast generation. |
| Tasks | |
| Published | 2019-04-24 |
| URL | http://arxiv.org/abs/1905.05077v1 |
| http://arxiv.org/pdf/1905.05077v1.pdf | |
| PWC | https://paperswithcode.com/paper/190505077 |
| Repo | |
| Framework | |
Picture What you Read
| Title | Picture What you Read |
| Authors | Ignazio Gallo, Shah Nawaz, Alessandro Calefati, Riccardo La Grassa, Nicola Landro |
| Abstract | Visualization refers to our ability to create an image in our head based on the text we read or the words we hear. It is one of the many skills that makes reading comprehension possible. Convolutional Neural Networks (CNN) are an excellent tool for recognizing and classifying text documents. In addition, it can generate images conditioned on natural language. In this work, we utilize CNNs capabilities to generate realistic images representative of the text illustrating the semantic concept. We conducted various experiments to highlight the capacity of the proposed model to generate representative images of the text descriptions used as input to the proposed model. |
| Tasks | Reading Comprehension |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.05663v1 |
| https://arxiv.org/pdf/1909.05663v1.pdf | |
| PWC | https://paperswithcode.com/paper/picture-what-you-read |
| Repo | |
| Framework | |
ADDMC: Exact Weighted Model Counting with Algebraic Decision Diagrams
| Title | ADDMC: Exact Weighted Model Counting with Algebraic Decision Diagrams |
| Authors | Jeffrey M. Dudek, Vu H. N. Phan, Moshe Y. Vardi |
| Abstract | We compute exact literal-weighted model counts of CNF formulas. Our algorithm employs dynamic programming, with Algebraic Decision Diagrams as the primary data structure. This technique is implemented in ADDMC, a new model counter. We empirically evaluate various heuristics that can be used with ADDMC. We also compare ADDMC to state-of-the-art exact model counters (Cachet, c2d, d4, miniC2D, and sharpSAT) on the two largest CNF model counting benchmark families (BayesNet and Planning). ADDMC solves the most benchmarks in total within the given timeout. |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05000v1 |
| https://arxiv.org/pdf/1907.05000v1.pdf | |
| PWC | https://paperswithcode.com/paper/addmc-exact-weighted-model-counting-with |
| Repo | |
| Framework | |
A comprehensive, application-oriented study of catastrophic forgetting in DNNs
| Title | A comprehensive, application-oriented study of catastrophic forgetting in DNNs |
| Authors | B. Pfülb, A. Gepperth |
| Abstract | We present a large-scale empirical study of catastrophic forgetting (CF) in modern Deep Neural Network (DNN) models that perform sequential (or: incremental) learning. A new experimental protocol is proposed that enforces typical constraints encountered in application scenarios. As the investigation is empirical, we evaluate CF behavior on the hitherto largest number of visual classification datasets, from each of which we construct a representative number of Sequential Learning Tasks (SLTs) in close alignment to previous works on CF. Our results clearly indicate that there is no model that avoids CF for all investigated datasets and SLTs under application conditions. We conclude with a discussion of potential solutions and workarounds to CF, notably for the EWC and IMM models. |
| Tasks | |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.08101v1 |
| https://arxiv.org/pdf/1905.08101v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-comprehensive-application-oriented-study-of-1 |
| Repo | |
| Framework | |
Before we can find a model, we must forget about perfection
| Title | Before we can find a model, we must forget about perfection |
| Authors | Dimiter Dobrev |
| Abstract | With Reinforcement Learning we assume that a model of the world does exist. We assume furthermore that the model in question is perfect (i.e. it describes the world completely and unambiguously). This article will demonstrate that it does not make sense to search for the perfect model because this model is too complicated and practically impossible to find. We will show that we should abandon the pursuit of perfection and pursue Event-Driven (ED) models instead. These models are generalization of Markov Decision Process (MDP) models. This generalization is essential because nothing can be found without it. Rather than a single MDP, we will aim to find a raft of neat simple ED models each one describing a simple dependency or property. In other words, we will replace the search for a singular and complex perfect model with a search for a large number of simple models. |
| Tasks | |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.04964v1 |
| https://arxiv.org/pdf/1912.04964v1.pdf | |
| PWC | https://paperswithcode.com/paper/before-we-can-find-a-model-we-must-forget |
| Repo | |
| Framework | |
