Paper Group ANR 987
Empirical Evaluation of Character-Based Model on Neural Named-Entity Recognition in Indonesian Conversational Texts. Visual SLAM-based Localization and Navigation for Service Robots: The Pepper Case. Precise Box Score: Extract More Information from Datasets to Improve the Performance of Face Detection. Pushing the Limits of Unconstrained Face Detec …
Empirical Evaluation of Character-Based Model on Neural Named-Entity Recognition in Indonesian Conversational Texts
| Title | Empirical Evaluation of Character-Based Model on Neural Named-Entity Recognition in Indonesian Conversational Texts |
| Authors | Kemal Kurniawan, Samuel Louvan |
| Abstract | Despite the long history of named-entity recognition (NER) task in the natural language processing community, previous work rarely studied the task on conversational texts. Such texts are challenging because they contain a lot of word variations which increase the number of out-of-vocabulary (OOV) words. The high number of OOV words poses a difficulty for word-based neural models. Meanwhile, there is plenty of evidence to the effectiveness of character-based neural models in mitigating this OOV problem. We report an empirical evaluation of neural sequence labeling models with character embedding to tackle NER task in Indonesian conversational texts. Our experiments show that (1) character models outperform word embedding-only models by up to 4 $F_1$ points, (2) character models perform better in OOV cases with an improvement of as high as 15 $F_1$ points, and (3) character models are robust against a very high OOV rate. |
| Tasks | Named Entity Recognition |
| Published | 2018-05-31 |
| URL | http://arxiv.org/abs/1805.12291v3 |
| http://arxiv.org/pdf/1805.12291v3.pdf | |
| PWC | https://paperswithcode.com/paper/empirical-evaluation-of-character-based-model |
| Repo | |
| Framework | |
Visual SLAM-based Localization and Navigation for Service Robots: The Pepper Case
| Title | Visual SLAM-based Localization and Navigation for Service Robots: The Pepper Case |
| Authors | Cristopher Gómez, Matías Mattamala, Tim Resink, Javier Ruiz-del-Solar |
| Abstract | We propose a Visual-SLAM based localization and navigation system for service robots. Our system is built on top of the ORB-SLAM monocular system but extended by the inclusion of wheel odometry in the estimation procedures. As a case study, the proposed system is validated using the Pepper robot, whose short-range LIDARs and RGB-D camera do not allow the robot to self-localize in large environments. The localization system is tested in navigation tasks using Pepper in two different environments: a medium-size laboratory, and a large-size hall. |
| Tasks | |
| Published | 2018-11-20 |
| URL | http://arxiv.org/abs/1811.08414v1 |
| http://arxiv.org/pdf/1811.08414v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-slam-based-localization-and-navigation |
| Repo | |
| Framework | |
Precise Box Score: Extract More Information from Datasets to Improve the Performance of Face Detection
| Title | Precise Box Score: Extract More Information from Datasets to Improve the Performance of Face Detection |
| Authors | Ce Qi, Xiaoping Chen, Pingyu Wang, Fei Su |
| Abstract | For the training of face detection network based on R-CNN framework, anchors are assigned to be positive samples if intersection-over-unions (IoUs) with ground-truth are higher than the first threshold(such as 0.7); and to be negative samples if their IoUs are lower than the second threshold(such as 0.3). And the face detection model is trained by the above labels. However, anchors with IoU between first threshold and second threshold are not used. We propose a novel training strategy, Precise Box Score(PBS), to train object detection models. The proposed training strategy uses the anchors with IoUs between the first and second threshold, which can consistently improve the performance of face detection. Our proposed training strategy extracts more information from datasets, making better utilization of existing datasets. What’s more, we also introduce a simple but effective model compression method(SEMCM), which can boost the performance of face detectors further. Experimental results show that the performance of face detection network can consistently be improved based on our proposed scheme. |
| Tasks | Face Detection, Model Compression, Object Detection |
| Published | 2018-04-28 |
| URL | http://arxiv.org/abs/1804.10743v1 |
| http://arxiv.org/pdf/1804.10743v1.pdf | |
| PWC | https://paperswithcode.com/paper/precise-box-score-extract-more-information |
| Repo | |
| Framework | |
Pushing the Limits of Unconstrained Face Detection: a Challenge Dataset and Baseline Results
| Title | Pushing the Limits of Unconstrained Face Detection: a Challenge Dataset and Baseline Results |
| Authors | Hajime Nada, Vishwanath A. Sindagi, He Zhang, Vishal M. Patel |
| Abstract | Face detection has witnessed immense progress in the last few years, with new milestones being surpassed every year. While many challenges such as large variations in scale, pose, appearance are successfully addressed, there still exist several issues which are not specifically captured by existing methods or datasets. In this work, we identify the next set of challenges that requires attention from the research community and collect a new dataset of face images that involve these issues such as weather-based degradations, motion blur, focus blur and several others. We demonstrate that there is a considerable gap in the performance of state-of-the-art detectors and real-world requirements. Hence, in an attempt to fuel further research in unconstrained face detection, we present a new annotated Unconstrained Face Detection Dataset (UFDD) with several challenges and benchmark recent methods. Additionally, we provide an in-depth analysis of the results and failure cases of these methods. The dataset as well as baseline results will be made publicly available in due time. The UFDD dataset as well as baseline results are available at: www.ufdd.info/ |
| Tasks | Face Detection, Robust Face Recognition |
| Published | 2018-04-26 |
| URL | http://arxiv.org/abs/1804.10275v3 |
| http://arxiv.org/pdf/1804.10275v3.pdf | |
| PWC | https://paperswithcode.com/paper/pushing-the-limits-of-unconstrained-face |
| Repo | |
| Framework | |
Real-time Burst Photo Selection Using a Light-Head Adversarial Network
| Title | Real-time Burst Photo Selection Using a Light-Head Adversarial Network |
| Authors | Baoyuan Wang, Noranart Vesdapunt, Utkarsh Sinha, Lei Zhang |
| Abstract | We present an automatic moment capture system that runs in real-time on mobile cameras. The system is designed to run in the viewfinder mode and capture a burst sequence of frames before and after the shutter is pressed. For each frame, the system predicts in real-time a “goodness” score, based on which the best moment in the burst can be selected immediately after the shutter is released, without any user interference. To solve the problem, we develop a highly efficient deep neural network ranking model, which implicitly learns a “latent relative attribute” space to capture subtle visual differences within a sequence of burst images. Then the overall goodness is computed as a linear aggregation of the goodnesses of all the latent attributes. The latent relative attributes and the aggregation function can be seamlessly integrated in one fully convolutional network and trained in an end-to-end fashion. To obtain a compact model which can run on mobile devices in real-time, we have explored and evaluated a wide range of network design choices, taking into account the constraints of model size, computational cost, and accuracy. Extensive studies show that the best frame predicted by our model hit users’ top-1 (out of 11 on average) choice for $64.1%$ cases and top-3 choices for $86.2%$ cases. Moreover, the model(only 0.47M Bytes) can run in real time on mobile devices, e.g. only 13ms on iPhone 7 for one frame prediction. |
| Tasks | |
| Published | 2018-03-20 |
| URL | http://arxiv.org/abs/1803.07212v1 |
| http://arxiv.org/pdf/1803.07212v1.pdf | |
| PWC | https://paperswithcode.com/paper/real-time-burst-photo-selection-using-a-light |
| Repo | |
| Framework | |
Skin Tone Emoji and Sentiment on Twitter
| Title | Skin Tone Emoji and Sentiment on Twitter |
| Authors | Steven Coats |
| Abstract | In 2015, the Unicode Consortium introduced five skin tone emoji that can be used in combination with emoji representing human figures and body parts. In this study, use of the skin tone emoji is analyzed geographically in a large sample of data from Twitter. It can be shown that values for the skin tone emoji by country correspond approximately to the skin tone of the resident populations, and that a negative correlation exists between tweet sentiment and darker skin tone at the global level. In an era of large-scale migrations and continued sensitivity to questions of skin color and race, understanding how new language elements such as skin tone emoji are used can help frame our understanding of how people represent themselves and others in terms of a salient personal appearance attribute. |
| Tasks | |
| Published | 2018-04-20 |
| URL | http://arxiv.org/abs/1805.00444v1 |
| http://arxiv.org/pdf/1805.00444v1.pdf | |
| PWC | https://paperswithcode.com/paper/skin-tone-emoji-and-sentiment-on-twitter |
| Repo | |
| Framework | |
Unsupervised Learning of Sentence Representations Using Sequence Consistency
| Title | Unsupervised Learning of Sentence Representations Using Sequence Consistency |
| Authors | Siddhartha Brahma |
| Abstract | Computing universal distributed representations of sentences is a fundamental task in natural language processing. We propose ConsSent, a simple yet surprisingly powerful unsupervised method to learn such representations by enforcing consistency constraints on sequences of tokens. We consider two classes of such constraints – sequences that form a sentence and between two sequences that form a sentence when merged. We learn sentence encoders by training them to distinguish between consistent and inconsistent examples, the latter being generated by randomly perturbing consistent examples in six different ways. Extensive evaluation on several transfer learning and linguistic probing tasks shows improved performance over strong unsupervised and supervised baselines, substantially surpassing them in several cases. Our best results are achieved by training sentence encoders in a multitask setting and by an ensemble of encoders trained on the individual tasks. |
| Tasks | Transfer Learning |
| Published | 2018-08-10 |
| URL | http://arxiv.org/abs/1808.04217v4 |
| http://arxiv.org/pdf/1808.04217v4.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-of-sentence |
| Repo | |
| Framework | |
News Article Teaser Tweets and How to Generate Them
| Title | News Article Teaser Tweets and How to Generate Them |
| Authors | Sanjeev Kumar Karn, Mark Buckley, Ulli Waltinger, Hinrich Schütze |
| Abstract | In this work, we define the task of teaser generation and provide an evaluation benchmark and baseline systems for the process of generating teasers. A teaser is a short reading suggestion for an article that is illustrative and includes curiosity-arousing elements to entice potential readers to read particular news items. Teasers are one of the main vehicles for transmitting news to social media users. We compile a novel dataset of teasers by systematically accumulating tweets and selecting those that conform to the teaser definition. We have compared a number of neural abstractive architectures on the task of teaser generation and the overall best performing system is See et al.(2017)‘s seq2seq with pointer network. |
| Tasks | |
| Published | 2018-07-30 |
| URL | http://arxiv.org/abs/1807.11535v2 |
| http://arxiv.org/pdf/1807.11535v2.pdf | |
| PWC | https://paperswithcode.com/paper/news-article-teaser-tweets-and-how-to |
| Repo | |
| Framework | |
Benchmarking projective simulation in navigation problems
| Title | Benchmarking projective simulation in navigation problems |
| Authors | Alexey A. Melnikov, Adi Makmal, Hans J. Briegel |
| Abstract | Projective simulation (PS) is a model for intelligent agents with a deliberation capacity that is based on episodic memory. The model has been shown to provide a flexible framework for constructing reinforcement-learning agents, and it allows for quantum mechanical generalization, which leads to a speed-up in deliberation time. PS agents have been applied successfully in the context of complex skill learning in robotics, and in the design of state-of-the-art quantum experiments. In this paper, we study the performance of projective simulation in two benchmarking problems in navigation, namely the grid world and the mountain car problem. The performance of PS is compared to standard tabular reinforcement learning approaches, Q-learning and SARSA. Our comparison demonstrates that the performance of PS and standard learning approaches are qualitatively and quantitatively similar, while it is much easier to choose optimal model parameters in case of projective simulation, with a reduced computational effort of one to two orders of magnitude. Our results show that the projective simulation model stands out for its simplicity in terms of the number of model parameters, which makes it simple to set up the learning agent in unknown task environments. |
| Tasks | Q-Learning |
| Published | 2018-04-23 |
| URL | http://arxiv.org/abs/1804.08607v1 |
| http://arxiv.org/pdf/1804.08607v1.pdf | |
| PWC | https://paperswithcode.com/paper/benchmarking-projective-simulation-in |
| Repo | |
| Framework | |
Who did What at Where and When: Simultaneous Multi-Person Tracking and Activity Recognition
| Title | Who did What at Where and When: Simultaneous Multi-Person Tracking and Activity Recognition |
| Authors | Wenbo Li, Ming-Ching Chang, Siwei Lyu |
| Abstract | We present a bootstrapping framework to simultaneously improve multi-person tracking and activity recognition at individual, interaction and social group activity levels. The inference consists of identifying trajectories of all pedestrian actors, individual activities, pairwise interactions, and collective activities, given the observed pedestrian detections. Our method uses a graphical model to represent and solve the joint tracking and recognition problems via multi-stages: (1) activity-aware tracking, (2) joint interaction recognition and occlusion recovery, and (3) collective activity recognition. We solve the where and when problem with visual tracking, as well as the who and what problem with recognition. High-order correlations among the visible and occluded individuals, pairwise interactions, groups, and activities are then solved using a hypergraph formulation within the Bayesian framework. Experiments on several benchmarks show the advantages of our approach over state-of-art methods. |
| Tasks | Activity Recognition, Visual Tracking |
| Published | 2018-07-03 |
| URL | http://arxiv.org/abs/1807.01253v1 |
| http://arxiv.org/pdf/1807.01253v1.pdf | |
| PWC | https://paperswithcode.com/paper/who-did-what-at-where-and-when-simultaneous |
| Repo | |
| Framework | |
Understanding and Measuring Psychological Stress using Social Media
| Title | Understanding and Measuring Psychological Stress using Social Media |
| Authors | Sharath Chandra Guntuku, Anneke Buffone, Kokil Jaidka, Johannes Eichstaedt, Lyle Ungar |
| Abstract | A body of literature has demonstrated that users’ mental health conditions, such as depression and anxiety, can be predicted from their social media language. There is still a gap in the scientific understanding of how psychological stress is expressed on social media. Stress is one of the primary underlying causes and correlates of chronic physical illnesses and mental health conditions. In this paper, we explore the language of psychological stress with a dataset of 601 social media users, who answered the Perceived Stress Scale questionnaire and also consented to share their Facebook and Twitter data. Firstly, we find that stressed users post about exhaustion, losing control, increased self-focus and physical pain as compared to posts about breakfast, family-time, and travel by users who are not stressed. Secondly, we find that Facebook language is more predictive of stress than Twitter language. Thirdly, we demonstrate how the language based models thus developed can be adapted and be scaled to measure county-level trends. Since county-level language is easily available on Twitter using the Streaming API, we explore multiple domain adaptation algorithms to adapt user-level Facebook models to Twitter language. We find that domain-adapted and scaled social media-based measurements of stress outperform sociodemographic variables (age, gender, race, education, and income), against ground-truth survey-based stress measurements, both at the user- and the county-level in the U.S. Twitter language that scores higher in stress is also predictive of poorer health, less access to facilities and lower socioeconomic status in counties. We conclude with a discussion of the implications of using social media as a new tool for monitoring stress levels of both individuals and counties. |
| Tasks | Domain Adaptation |
| Published | 2018-11-19 |
| URL | http://arxiv.org/abs/1811.07430v2 |
| http://arxiv.org/pdf/1811.07430v2.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-and-measuring-psychological |
| Repo | |
| Framework | |
Neural network approach to classifying alarming student responses to online assessment
| Title | Neural network approach to classifying alarming student responses to online assessment |
| Authors | Christopher M. Ormerod, Amy E. Harris |
| Abstract | Automated scoring engines are increasingly being used to score the free-form text responses that students give to questions. Such engines are not designed to appropriately deal with responses that a human reader would find alarming such as those that indicate an intention to self-harm or harm others, responses that allude to drug abuse or sexual abuse or any response that would elicit concern for the student writing the response. Our neural network models have been designed to help identify these anomalous responses from a large collection of typical responses that students give. The responses identified by the neural network can be assessed for urgency, severity, and validity more quickly by a team of reviewers than otherwise possible. Given the anomalous nature of these types of responses, our goal is to maximize the chance of flagging these responses for review given the constraint that only a fixed percentage of responses can viably be assessed by a team of reviewers. |
| Tasks | |
| Published | 2018-09-20 |
| URL | http://arxiv.org/abs/1809.08899v1 |
| http://arxiv.org/pdf/1809.08899v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-approach-to-classifying |
| Repo | |
| Framework | |
A Classification Refinement Strategy for Semantic Segmentation
| Title | A Classification Refinement Strategy for Semantic Segmentation |
| Authors | James W. Davis, Christopher Menart, Muhammad Akbar, Roman Ilin |
| Abstract | Based on the observation that semantic segmentation errors are partially predictable, we propose a compact formulation using confusion statistics of the trained classifier to refine (re-estimate) the initial pixel label hypotheses. The proposed strategy is contingent upon computing the classifier confusion probabilities for a given dataset and estimating a relevant prior on the object classes present in the image to be classified. We provide a procedure to robustly estimate the confusion probabilities and explore multiple prior definitions. Experiments are shown comparing performances on multiple challenging datasets using different priors to improve a state-of-the-art semantic segmentation classifier. This study demonstrates the potential to significantly improve semantic labeling and motivates future work for reliable label prior estimation from images. |
| Tasks | Semantic Segmentation |
| Published | 2018-01-23 |
| URL | http://arxiv.org/abs/1801.07674v1 |
| http://arxiv.org/pdf/1801.07674v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-classification-refinement-strategy-for |
| Repo | |
| Framework | |
Deep Belief Networks Based Feature Generation and Regression for Predicting Wind Power
| Title | Deep Belief Networks Based Feature Generation and Regression for Predicting Wind Power |
| Authors | Asifullah Khan, Aneela Zameer, Tauseef Jamal, Ahmad Raza |
| Abstract | Wind energy forecasting helps to manage power production, and hence, reduces energy cost. Deep Neural Networks (DNN) mimics hierarchical learning in the human brain and thus possesses hierarchical, distributed, and multi-task learning capabilities. Based on aforementioned characteristics, we report Deep Belief Network (DBN) based forecast engine for wind power prediction because of its good generalization and unsupervised pre-training attributes. The proposed DBN-WP forecast engine, which exhibits stochastic feature generation capabilities and is composed of multiple Restricted Boltzmann Machines, generates suitable features for wind power prediction using atmospheric properties as input. DBN-WP, due to its unsupervised pre-training of RBM layers and generalization capabilities, is able to learn the fluctuations in the meteorological properties and thus is able to perform effective mapping of the wind power. In the deep network, a regression layer is appended at the end to predict sort-term wind power. It is experimentally shown that the deep learning and unsupervised pre-training capabilities of DBN based model has comparable and in some cases better results than hybrid and complex learning techniques proposed for wind power prediction. The proposed prediction system based on DBN, achieves mean values of RMSE, MAE and SDE as 0.124, 0.083 and 0.122, respectively. Statistical analysis of several independent executions of the proposed DBN-WP wind power prediction system demonstrates the stability of the system. The proposed DBN-WP architecture is easy to implement and offers generalization as regards the change in location of the wind farm is concerned. |
| Tasks | Multi-Task Learning |
| Published | 2018-07-31 |
| URL | http://arxiv.org/abs/1807.11682v1 |
| http://arxiv.org/pdf/1807.11682v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-belief-networks-based-feature-generation |
| Repo | |
| Framework | |
Federated Learning in Distributed Medical Databases: Meta-Analysis of Large-Scale Subcortical Brain Data
| Title | Federated Learning in Distributed Medical Databases: Meta-Analysis of Large-Scale Subcortical Brain Data |
| Authors | Santiago Silva, Boris Gutman, Eduardo Romero, Paul M Thompson, Andre Altmann, Marco Lorenzi |
| Abstract | At this moment, databanks worldwide contain brain images of previously unimaginable numbers. Combined with developments in data science, these massive data provide the potential to better understand the genetic underpinnings of brain diseases. However, different datasets, which are stored at different institutions, cannot always be shared directly due to privacy and legal concerns, thus limiting the full exploitation of big data in the study of brain disorders. Here we propose a federated learning framework for securely accessing and meta-analyzing any biomedical data without sharing individual information. We illustrate our framework by investigating brain structural relationships across diseases and clinical cohorts. The framework is first tested on synthetic data and then applied to multi-centric, multi-database studies including ADNI, PPMI, MIRIAD and UK Biobank, showing the potential of the approach for further applications in distributed analysis of multi-centric cohorts |
| Tasks | |
| Published | 2018-10-19 |
| URL | http://arxiv.org/abs/1810.08553v3 |
| http://arxiv.org/pdf/1810.08553v3.pdf | |
| PWC | https://paperswithcode.com/paper/federated-learning-in-distributed-medical |
| Repo | |
| Framework | |
