Paper Group ANR 618
How Curiosity can be modeled for a Clickbait Detector. Towards quantitative methods to assess network generative models. Multiple Lane Detection Algorithm Based on Optimised Dense Disparity Map Estimation. Active Learning using Deep Bayesian Networks for Surgical Workflow Analysis. Block-optimized Variable Bit Rate Neural Image Compression. What Ha …
How Curiosity can be modeled for a Clickbait Detector
| Title | How Curiosity can be modeled for a Clickbait Detector |
| Authors | Lasya Venneti, Aniket Alam |
| Abstract | The impact of continually evolving digital technologies and the proliferation of communications and content has now been widely acknowledged to be central to understanding our world. What is less acknowledged is that this is based on the successful arousing of curiosity both at the collective and individual levels. Advertisers, communication professionals and news editors are in constant competition to capture attention of the digital population perennially shifty and distracted. This paper, tries to understand how curiosity works in the digital world by attempting the first ever work done on quantifying human curiosity, basing itself on various theories drawn from humanities and social sciences. Curious communication pushes people to spot, read and click the message from their social feed or any other form of online presentation. Our approach focuses on measuring the strength of the stimulus to generate reader curiosity by using unsupervised and supervised machine learning algorithms, but is also informed by philosophical, psychological, neural and cognitive studies on this topic. Manually annotated news headlines - clickbaits - have been selected for the study, which are known to have drawn huge reader response. A binary classifier was developed based on human curiosity (unlike the work done so far using words and other linguistic features). Our classifier shows an accuracy of 97% . This work is part of the research in computational humanities on digital politics quantifying the emotions of curiosity and outrage on digital media. |
| Tasks | |
| Published | 2018-06-11 |
| URL | http://arxiv.org/abs/1806.04212v1 |
| http://arxiv.org/pdf/1806.04212v1.pdf | |
| PWC | https://paperswithcode.com/paper/how-curiosity-can-be-modeled-for-a-clickbait |
| Repo | |
| Framework | |
Towards quantitative methods to assess network generative models
| Title | Towards quantitative methods to assess network generative models |
| Authors | Vahid Mostofi, Sadegh Aliakbary |
| Abstract | Assessing generative models is not an easy task. Generative models should synthesize graphs which are not replicates of real networks but show topological features similar to real graphs. We introduce an approach for assessing graph generative models using graph classifiers. The inability of an established graph classifier for distinguishing real and synthesized graphs could be considered as a performance measurement for graph generators. |
| Tasks | |
| Published | 2018-09-05 |
| URL | http://arxiv.org/abs/1809.01369v1 |
| http://arxiv.org/pdf/1809.01369v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-quantitative-methods-to-assess |
| Repo | |
| Framework | |
Multiple Lane Detection Algorithm Based on Optimised Dense Disparity Map Estimation
| Title | Multiple Lane Detection Algorithm Based on Optimised Dense Disparity Map Estimation |
| Authors | Han Ma, Yixin Ma, Jianhao Jiao, M Usman Maqbool Bhutta, Mohammud Junaid Bocus, Lujia Wang, Ming Liu, Rui Fan |
| Abstract | Lane detection is very important for self-driving vehicles. In recent years, computer stereo vision has been prevalently used to enhance the accuracy of the lane detection systems. This paper mainly presents a multiple lane detection algorithm developed based on optimised dense disparity map estimation, where the disparity information obtained at time t_{n} is utilised to optimise the process of disparity estimation at time t_{n+1}. This is achieved by estimating the road model at time t_{n} and then controlling the search range for the disparity estimation at time t_{n+1}. The lanes are then detected using our previously published algorithm, where the vanishing point information is used to model the lanes. The experimental results illustrate that the runtime of the disparity estimation is reduced by around 37% and the accuracy of the lane detection is about 99%. |
| Tasks | Disparity Estimation, Lane Detection |
| Published | 2018-08-28 |
| URL | http://arxiv.org/abs/1808.09128v1 |
| http://arxiv.org/pdf/1808.09128v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiple-lane-detection-algorithm-based-on |
| Repo | |
| Framework | |
Active Learning using Deep Bayesian Networks for Surgical Workflow Analysis
| Title | Active Learning using Deep Bayesian Networks for Surgical Workflow Analysis |
| Authors | Sebastian Bodenstedt, Dominik Rivoir, Alexander Jenke, Martin Wagner, Michael Breucha, Beat Müller-Stich, Sören Torge Mees, Jürgen Weitz, Stefanie Speidel |
| Abstract | For many applications in the field of computer assisted surgery, such as providing the position of a tumor, specifying the most probable tool required next by the surgeon or determining the remaining duration of surgery, methods for surgical workflow analysis are a prerequisite. Often machine learning based approaches serve as basis for surgical workflow analysis. In general machine learning algorithms, such as convolutional neural networks (CNN), require large amounts of labeled data. While data is often available in abundance, many tasks in surgical workflow analysis need data annotated by domain experts, making it difficult to obtain a sufficient amount of annotations. The aim of using active learning to train a machine learning model is to reduce the annotation effort. Active learning methods determine which unlabeled data points would provide the most information according to some metric, such as prediction uncertainty. Experts will then be asked to only annotate these data points. The model is then retrained with the new data and used to select further data for annotation. Recently, active learning has been applied to CNN by means of Deep Bayesian Networks (DBN). These networks make it possible to assign uncertainties to predictions. In this paper, we present a DBN-based active learning approach adapted for image-based surgical workflow analysis task. Furthermore, by using a recurrent architecture, we extend this network to video-based surgical workflow analysis. We evaluate these approaches on the Cholec80 dataset by performing instrument presence detection and surgical phase segmentation. Here we are able to show that using a DBN-based active learning approach for selecting what data points to annotate next outperforms a baseline based on randomly selecting data points. |
| Tasks | Active Learning |
| Published | 2018-11-08 |
| URL | http://arxiv.org/abs/1811.03382v2 |
| http://arxiv.org/pdf/1811.03382v2.pdf | |
| PWC | https://paperswithcode.com/paper/active-learning-using-deep-bayesian-networks |
| Repo | |
| Framework | |
Block-optimized Variable Bit Rate Neural Image Compression
| Title | Block-optimized Variable Bit Rate Neural Image Compression |
| Authors | Caglar Aytekin, Xingyang Ni, Francesco Cricri, Jani Lainema, Emre Aksu, Miska Hannuksela |
| Abstract | In this work, we propose an end-to-end block-based auto-encoder system for image compression. We introduce novel contributions to neural-network based image compression, mainly in achieving binarization simulation, variable bit rates with multiple networks, entropy-friendly representations, inference-stage code optimization and performance-improving normalization layers in the auto-encoder. We evaluate and show the incremental performance increase of each of our contributions. |
| Tasks | Image Compression |
| Published | 2018-05-28 |
| URL | http://arxiv.org/abs/1805.10887v1 |
| http://arxiv.org/pdf/1805.10887v1.pdf | |
| PWC | https://paperswithcode.com/paper/block-optimized-variable-bit-rate-neural |
| Repo | |
| Framework | |
What Happened? Leveraging VerbNet to Predict the Effects of Actions in Procedural Text
| Title | What Happened? Leveraging VerbNet to Predict the Effects of Actions in Procedural Text |
| Authors | Peter Clark, Bhavana Dalvi, Niket Tandon |
| Abstract | Our goal is to answer questions about paragraphs describing processes (e.g., photosynthesis). Texts of this genre are challenging because the effects of actions are often implicit (unstated), requiring background knowledge and inference to reason about the changing world states. To supply this knowledge, we leverage VerbNet to build a rulebase (called the Semantic Lexicon) of the preconditions and effects of actions, and use it along with commonsense knowledge of persistence to answer questions about change. Our evaluation shows that our system, ProComp, significantly outperforms two strong reading comprehension (RC) baselines. Our contributions are two-fold: the Semantic Lexicon rulebase itself, and a demonstration of how a simulation-based approach to machine reading can outperform RC methods that rely on surface cues alone. Since this work was performed, we have developed neural systems that outperform ProComp, described elsewhere (Dalvi et al., NAACL’18). However, the Semantic Lexicon remains a novel and potentially useful resource, and its integration with neural systems remains a currently unexplored opportunity for further improvements in machine reading about processes. |
| Tasks | Reading Comprehension |
| Published | 2018-04-15 |
| URL | http://arxiv.org/abs/1804.05435v1 |
| http://arxiv.org/pdf/1804.05435v1.pdf | |
| PWC | https://paperswithcode.com/paper/what-happened-leveraging-verbnet-to-predict |
| Repo | |
| Framework | |
EmotiW 2018: Audio-Video, Student Engagement and Group-Level Affect Prediction
| Title | EmotiW 2018: Audio-Video, Student Engagement and Group-Level Affect Prediction |
| Authors | Abhinav Dhall, Amanjot Kaur, Roland Goecke, Tom Gedeon |
| Abstract | This paper details the sixth Emotion Recognition in the Wild (EmotiW) challenge. EmotiW 2018 is a grand challenge in the ACM International Conference on Multimodal Interaction 2018, Colorado, USA. The challenge aims at providing a common platform to researchers working in the affective computing community to benchmark their algorithms on `in the wild’ data. This year EmotiW contains three sub-challenges: a) Audio-video based emotion recognition; b) Student engagement prediction; and c) Group-level emotion recognition. The databases, protocols and baselines are discussed in detail. | |
| Tasks | Emotion Recognition |
| Published | 2018-08-23 |
| URL | http://arxiv.org/abs/1808.07773v1 |
| http://arxiv.org/pdf/1808.07773v1.pdf | |
| PWC | https://paperswithcode.com/paper/emotiw-2018-audio-video-student-engagement |
| Repo | |
| Framework | |
A Minesweeper Solver Using Logic Inference, CSP and Sampling
| Title | A Minesweeper Solver Using Logic Inference, CSP and Sampling |
| Authors | Yimin Tang, Tian Jiang, Yanpeng Hu |
| Abstract | Minesweeper as a puzzle video game and is proved that it is an NPC problem. We use CSP, Logic Inference and Sampling to make a minesweeper solver and we limit us each select in 5 seconds. |
| Tasks | |
| Published | 2018-10-07 |
| URL | http://arxiv.org/abs/1810.03151v1 |
| http://arxiv.org/pdf/1810.03151v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-minesweeper-solver-using-logic-inference |
| Repo | |
| Framework | |
Finding Good Representations of Emotions for Text Classification
| Title | Finding Good Representations of Emotions for Text Classification |
| Authors | Ji Ho Park |
| Abstract | It is important for machines to interpret human emotions properly for better human-machine communications, as emotion is an essential part of human-to-human communications. One aspect of emotion is reflected in the language we use. How to represent emotions in texts is a challenge in natural language processing (NLP). Although continuous vector representations like word2vec have become the new norm for NLP problems, their limitations are that they do not take emotions into consideration and can unintentionally contain bias toward certain identities like different genders. This thesis focuses on improving existing representations in both word and sentence levels by explicitly taking emotions inside text and model bias into account in their training process. Our improved representations can help to build more robust machine learning models for affect-related text classification like sentiment/emotion analysis and abusive language detection. We first propose representations called emotional word vectors (EVEC), which is learned from a convolutional neural network model with an emotion-labeled corpus, which is constructed using hashtags. Secondly, we extend to learning sentence-level representations with a huge corpus of texts with the pseudo task of recognizing emojis. Our results show that, with the representations trained from millions of tweets with weakly supervised labels such as hashtags and emojis, we can solve sentiment/emotion analysis tasks more effectively. Lastly, as examples of model bias in representations of existing approaches, we explore a specific problem of automatic detection of abusive language. We address the issue of gender bias in various neural network models by conducting experiments to measure and reduce those biases in the representations in order to build more robust classification models. |
| Tasks | Emotion Recognition, Text Classification |
| Published | 2018-08-22 |
| URL | http://arxiv.org/abs/1808.07235v1 |
| http://arxiv.org/pdf/1808.07235v1.pdf | |
| PWC | https://paperswithcode.com/paper/finding-good-representations-of-emotions-for |
| Repo | |
| Framework | |
A Machine-Learning Item Recommendation System for Video Games
| Title | A Machine-Learning Item Recommendation System for Video Games |
| Authors | Paul Bertens, Anna Guitart, Pei Pei Chen, África Periáñez |
| Abstract | Video-game players generate huge amounts of data, as everything they do within a game is recorded. In particular, among all the stored actions and behaviors, there is information on the in-game purchases of virtual products. Such information is of critical importance in modern free-to-play titles, where gamers can select or buy a profusion of items during the game in order to progress and fully enjoy their experience. To try to maximize these kind of purchases, one can use a recommendation system so as to present players with items that might be interesting for them. Such systems can better achieve their goal by employing machine learning algorithms that are able to predict the rating of an item or product by a particular user. In this paper we evaluate and compare two of these algorithms, an ensemble-based model (extremely randomized trees) and a deep neural network, both of which are promising candidates for operational video-game recommender engines. Item recommenders can help developers improve the game. But, more importantly, it should be possible to integrate them into the game, so that users automatically get personalized recommendations while playing. The presented models are not only able to meet this challenge, providing accurate predictions of the items that a particular player will find attractive, but also sufficiently fast and robust to be used in operational settings. |
| Tasks | |
| Published | 2018-06-13 |
| URL | http://arxiv.org/abs/1806.04900v2 |
| http://arxiv.org/pdf/1806.04900v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-machine-learning-item-recommendation-system |
| Repo | |
| Framework | |
Preference-Based Monte Carlo Tree Search
| Title | Preference-Based Monte Carlo Tree Search |
| Authors | Tobias Joppen, Christian Wirth, Johannes Fürnkranz |
| Abstract | Monte Carlo tree search (MCTS) is a popular choice for solving sequential anytime problems. However, it depends on a numeric feedback signal, which can be difficult to define. Real-time MCTS is a variant which may only rarely encounter states with an explicit, extrinsic reward. To deal with such cases, the experimenter has to supply an additional numeric feedback signal in the form of a heuristic, which intrinsically guides the agent. Recent work has shown evidence that in different areas the underlying structure is ordinal and not numerical. Hence erroneous and biased heuristics are inevitable, especially in such domains. In this paper, we propose a MCTS variant which only depends on qualitative feedback, and therefore opens up new applications for MCTS. We also find indications that translating absolute into ordinal feedback may be beneficial. Using a puzzle domain, we show that our preference-based MCTS variant, wich only receives qualitative feedback, is able to reach a performance level comparable to a regular MCTS baseline, which obtains quantitative feedback. |
| Tasks | |
| Published | 2018-07-17 |
| URL | http://arxiv.org/abs/1807.06286v1 |
| http://arxiv.org/pdf/1807.06286v1.pdf | |
| PWC | https://paperswithcode.com/paper/preference-based-monte-carlo-tree-search |
| Repo | |
| Framework | |
Context-Aware Pedestrian Motion Prediction In Urban Intersections
| Title | Context-Aware Pedestrian Motion Prediction In Urban Intersections |
| Authors | Golnaz Habibi, Nikita Jaipuria, Jonathan P. How |
| Abstract | This paper presents a novel context-based approach for pedestrian motion prediction in crowded, urban intersections, with the additional flexibility of prediction in similar, but new, environments. Previously, Chen et. al. combined Markovian-based and clustering-based approaches to learn motion primitives in a grid-based world and subsequently predict pedestrian trajectories by modeling the transition between learned primitives as a Gaussian Process (GP). This work extends that prior approach by incorporating semantic features from the environment (relative distance to curbside and status of pedestrian traffic lights) in the GP formulation for more accurate predictions of pedestrian trajectories over the same timescale. We evaluate the new approach on real-world data collected using one of the vehicles in the MIT Mobility On Demand fleet. The results show 12.5% improvement in prediction accuracy and a 2.65 times reduction in Area Under the Curve (AUC), which is used as a metric to quantify the span of predicted set of trajectories, such that a lower AUC corresponds to a higher level of confidence in the future direction of pedestrian motion. |
| Tasks | motion prediction |
| Published | 2018-06-25 |
| URL | http://arxiv.org/abs/1806.09453v1 |
| http://arxiv.org/pdf/1806.09453v1.pdf | |
| PWC | https://paperswithcode.com/paper/context-aware-pedestrian-motion-prediction-in |
| Repo | |
| Framework | |
Geometric Multi-Model Fitting by Deep Reinforcement Learning
| Title | Geometric Multi-Model Fitting by Deep Reinforcement Learning |
| Authors | Zongliang Zhang, Hongbin Zeng, Jonathan Li, Yiping Chen, Chenhui Yang, Cheng Wang |
| Abstract | This paper deals with the geometric multi-model fitting from noisy, unstructured point set data (e.g., laser scanned point clouds). We formulate multi-model fitting problem as a sequential decision making process. We then use a deep reinforcement learning algorithm to learn the optimal decisions towards the best fitting result. In this paper, we have compared our method against the state-of-the-art on simulated data. The results demonstrated that our approach significantly reduced the number of fitting iterations. |
| Tasks | Decision Making |
| Published | 2018-09-22 |
| URL | http://arxiv.org/abs/1809.08397v2 |
| http://arxiv.org/pdf/1809.08397v2.pdf | |
| PWC | https://paperswithcode.com/paper/geometric-multi-model-fitting-by-deep |
| Repo | |
| Framework | |
Meta-path Augmented Response Generation
| Title | Meta-path Augmented Response Generation |
| Authors | Yanran Li, Wenjie Li |
| Abstract | We propose a chatbot, namely Mocha to make good use of relevant entities when generating responses. Augmented with meta-path information, Mocha is able to mention proper entities following the conversation flow. |
| Tasks | Chatbot |
| Published | 2018-11-02 |
| URL | http://arxiv.org/abs/1811.00693v1 |
| http://arxiv.org/pdf/1811.00693v1.pdf | |
| PWC | https://paperswithcode.com/paper/meta-path-augmented-response-generation |
| Repo | |
| Framework | |
Extreme Value Theory for Open Set Classification – GPD and GEV Classifiers
| Title | Extreme Value Theory for Open Set Classification – GPD and GEV Classifiers |
| Authors | Edoardo Vignotto, Sebastian Engelke |
| Abstract | Classification tasks usually assume that all possible classes are present during the training phase. This is restrictive if the algorithm is used over a long time and possibly encounters samples from unknown classes. The recently introduced extreme value machine, a classifier motivated by extreme value theory, addresses this problem and achieves competitive performance in specific cases. We show that this algorithm can fail when the geometries of known and unknown classes differ. To overcome this problem, we propose two new algorithms relying on approximations from extreme value theory. We show the effectiveness of our classifiers in simulations and on the LETTER and MNIST data sets. |
| Tasks | |
| Published | 2018-08-29 |
| URL | https://arxiv.org/abs/1808.09902v4 |
| https://arxiv.org/pdf/1808.09902v4.pdf | |
| PWC | https://paperswithcode.com/paper/extreme-value-theory-for-open-set |
| Repo | |
| Framework | |
