Paper Group ANR 1146
Modeling human intuitions about liquid flow with particle-based simulation. A Semi-Markov Chain Approach to Modeling Respiratory Patterns Prior to Extubation in Preterm Infants. A Survey of Mobile Computing for the Visually Impaired. Towards Understanding and Answering Multi-Sentence Recommendation Questions on Tourism. Deja Vu: Motion Prediction i …
Modeling human intuitions about liquid flow with particle-based simulation
| Title | Modeling human intuitions about liquid flow with particle-based simulation |
| Authors | Christopher J. Bates, Ilker Yildirim, Joshua B. Tenenbaum, Peter Battaglia |
| Abstract | Humans can easily describe, imagine, and, crucially, predict a wide variety of behaviors of liquids–splashing, squirting, gushing, sloshing, soaking, dripping, draining, trickling, pooling, and pouring–despite tremendous variability in their material and dynamical properties. Here we propose and test a computational model of how people perceive and predict these liquid dynamics, based on coarse approximate simulations of fluids as collections of interacting particles. Our model is analogous to a “game engine in the head”, drawing on techniques for interactive simulations (as in video games) that optimize for efficiency and natural appearance rather than physical accuracy. In two behavioral experiments, we found that the model accurately captured people’s predictions about how liquids flow among complex solid obstacles, and was significantly better than two alternatives based on simple heuristics and deep neural networks. Our model was also able to explain how people’s predictions varied as a function of the liquids’ properties (e.g., viscosity and stickiness). Together, the model and empirical results extend the recent proposal that human physical scene understanding for the dynamics of rigid, solid objects can be supported by approximate probabilistic simulation, to the more complex and unexplored domain of fluid dynamics. |
| Tasks | Scene Understanding |
| Published | 2018-09-05 |
| URL | http://arxiv.org/abs/1809.01524v1 |
| http://arxiv.org/pdf/1809.01524v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-human-intuitions-about-liquid-flow |
| Repo | |
| Framework | |
A Semi-Markov Chain Approach to Modeling Respiratory Patterns Prior to Extubation in Preterm Infants
| Title | A Semi-Markov Chain Approach to Modeling Respiratory Patterns Prior to Extubation in Preterm Infants |
| Authors | Charles C. Onu, Lara J. Kanbar, Wissam Shalish, Karen A. Brown, Guilherme M. Sant’Anna, Robert E. Kearney, Doina Precup |
| Abstract | After birth, extremely preterm infants often require specialized respiratory management in the form of invasive mechanical ventilation (IMV). Protracted IMV is associated with detrimental outcomes and morbidities. Premature extubation, on the other hand, would necessitate reintubation which is risky, technically challenging and could further lead to lung injury or disease. We present an approach to modeling respiratory patterns of infants who succeeded extubation and those who required reintubation which relies on Markov models. We compare the use of traditional Markov chains to semi-Markov models which emphasize cross-pattern transitions and timing information, and to multi-chain Markov models which can concisely represent non-stationarity in respiratory behavior over time. The models we developed expose specific, unique similarities as well as vital differences between the two populations. |
| Tasks | |
| Published | 2018-08-24 |
| URL | http://arxiv.org/abs/1808.07989v1 |
| http://arxiv.org/pdf/1808.07989v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-semi-markov-chain-approach-to-modeling |
| Repo | |
| Framework | |
A Survey of Mobile Computing for the Visually Impaired
| Title | A Survey of Mobile Computing for the Visually Impaired |
| Authors | Martin Weiss, Margaux Luck, Roger Girgis, Chris Pal, Joseph Paul Cohen |
| Abstract | The number of visually impaired or blind (VIB) people in the world is estimated at several hundred million. Based on a series of interviews with the VIB and developers of assistive technology, this paper provides a survey of machine-learning based mobile applications and identifies the most relevant applications. We discuss the functionality of these apps, how they align with the needs and requirements of the VIB users, and how they can be improved with techniques such as federated learning and model compression. As a result of this study we identify promising future directions of research in mobile perception, micro-navigation, and content-summarization. |
| Tasks | Model Compression |
| Published | 2018-11-25 |
| URL | http://arxiv.org/abs/1811.10120v2 |
| http://arxiv.org/pdf/1811.10120v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-survey-of-mobile-computing-for-the-visually |
| Repo | |
| Framework | |
Towards Understanding and Answering Multi-Sentence Recommendation Questions on Tourism
| Title | Towards Understanding and Answering Multi-Sentence Recommendation Questions on Tourism |
| Authors | Danish Contractor, Barun Patra, Mausam Singla, Parag Singla |
| Abstract | We introduce the first system towards the novel task of answering complex multisentence recommendation questions in the tourism domain. Our solution uses a pipeline of two modules: question understanding and answering. For question understanding, we define an SQL-like query language that captures the semantic intent of a question; it supports operators like subset, negation, preference and similarity, which are often found in recommendation questions. We train and compare traditional CRFs as well as bidirectional LSTM-based models for converting a question to its semantic representation. We extend these models to a semisupervised setting with partially labeled sequences gathered through crowdsourcing. We find that our best model performs semi-supervised training of BiDiLSTM+CRF with hand-designed features and CCM(Chang et al., 2007) constraints. Finally, in an end to end QA system, our answering component converts our question representation into queries fired on underlying knowledge sources. Our experiments on two different answer corpora demonstrate that our system can significantly outperform baselines with up to 20 pt higher accuracy and 17 pt higher recall. |
| Tasks | |
| Published | 2018-01-05 |
| URL | http://arxiv.org/abs/1801.01825v1 |
| http://arxiv.org/pdf/1801.01825v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-understanding-and-answering-multi |
| Repo | |
| Framework | |
Deja Vu: Motion Prediction in Static Images
| Title | Deja Vu: Motion Prediction in Static Images |
| Authors | Silvia L. Pintea, Jan C. van Gemert, Arnold W. M. Smeulders |
| Abstract | This paper proposes motion prediction in single still images by learning it from a set of videos. The building assumption is that similar motion is characterized by similar appearance. The proposed method learns local motion patterns given a specific appearance and adds the predicted motion in a number of applications. This work (i) introduces a novel method to predict motion from appearance in a single static image, (ii) to that end, extends of the Structured Random Forest with regression derived from first principles, and (iii) shows the value of adding motion predictions in different tasks such as: weak frame-proposals containing unexpected events, action recognition, motion saliency. Illustrative results indicate that motion prediction is not only feasible, but also provides valuable information for a number of applications. |
| Tasks | motion prediction, Temporal Action Localization |
| Published | 2018-03-19 |
| URL | http://arxiv.org/abs/1803.06951v2 |
| http://arxiv.org/pdf/1803.06951v2.pdf | |
| PWC | https://paperswithcode.com/paper/deja-vu-motion-prediction-in-static-images |
| Repo | |
| Framework | |
Visual Affordance and Function Understanding: A Survey
| Title | Visual Affordance and Function Understanding: A Survey |
| Authors | Mohammed Hassanin, Salman Khan, Murat Tahtali |
| Abstract | Nowadays, robots are dominating the manufacturing, entertainment and healthcare industries. Robot vision aims to equip robots with the ability to discover information, understand it and interact with the environment. These capabilities require an agent to effectively understand object affordances and functionalities in complex visual domains. In this literature survey, we first focus on Visual affordances and summarize the state of the art as well as open problems and research gaps. Specifically, we discuss sub-problems such as affordance detection, categorization, segmentation and high-level reasoning. Furthermore, we cover functional scene understanding and the prevalent functional descriptors used in the literature. The survey also provides necessary background to the problem, sheds light on its significance and highlights the existing challenges for affordance and functionality learning. |
| Tasks | Scene Understanding |
| Published | 2018-07-18 |
| URL | http://arxiv.org/abs/1807.06775v1 |
| http://arxiv.org/pdf/1807.06775v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-affordance-and-function-understanding |
| Repo | |
| Framework | |
Unsupervised shape transformer for image translation and cross-domain retrieval
| Title | Unsupervised shape transformer for image translation and cross-domain retrieval |
| Authors | Kaili Wang, Liqian Ma, Jose Oramas, Luc Van Gool, Tinne Tuytelaars |
| Abstract | We address the problem of unsupervised geometric image-to-image translation. Rather than transferring the style of an image as a whole, our goal is to translate the geometry of an object as depicted in different domains while preserving its appearance characteristics. Our model is trained in an unsupervised fashion, i.e. without the need of paired images during training. It performs all steps of the shape transfer within a single model and without additional post-processing stages. Extensive experiments on the VITON, CMU-Multi-PIE and our own FashionStyle datasets show the effectiveness of the method. In addition, we show that despite their low-dimensionality, the features learned by our model are useful to the item retrieval task. |
| Tasks | Image-to-Image Translation |
| Published | 2018-12-05 |
| URL | http://arxiv.org/abs/1812.02134v2 |
| http://arxiv.org/pdf/1812.02134v2.pdf | |
| PWC | https://paperswithcode.com/paper/integrated-unpaired-appearance-preserving |
| Repo | |
| Framework | |
Differentiable Dynamic Programming for Structured Prediction and Attention
| Title | Differentiable Dynamic Programming for Structured Prediction and Attention |
| Authors | Arthur Mensch, Mathieu Blondel |
| Abstract | Dynamic programming (DP) solves a variety of structured combinatorial problems by iteratively breaking them down into smaller subproblems. In spite of their versatility, DP algorithms are usually non-differentiable, which hampers their use as a layer in neural networks trained by backpropagation. To address this issue, we propose to smooth the max operator in the dynamic programming recursion, using a strongly convex regularizer. This allows to relax both the optimal value and solution of the original combinatorial problem, and turns a broad class of DP algorithms into differentiable operators. Theoretically, we provide a new probabilistic perspective on backpropagating through these DP operators, and relate them to inference in graphical models. We derive two particular instantiations of our framework, a smoothed Viterbi algorithm for sequence prediction and a smoothed DTW algorithm for time-series alignment. We showcase these instantiations on two structured prediction tasks and on structured and sparse attention for neural machine translation. |
| Tasks | Machine Translation, Structured Prediction, Time Series, Time Series Alignment |
| Published | 2018-02-11 |
| URL | http://arxiv.org/abs/1802.03676v2 |
| http://arxiv.org/pdf/1802.03676v2.pdf | |
| PWC | https://paperswithcode.com/paper/differentiable-dynamic-programming-for |
| Repo | |
| Framework | |
Grounding the Semantics of Part-of-Day Nouns Worldwide using Twitter
| Title | Grounding the Semantics of Part-of-Day Nouns Worldwide using Twitter |
| Authors | David Vilares, Carlos Gómez-Rodríguez |
| Abstract | The usage of part-of-day nouns, such as ‘night’, and their time-specific greetings (‘good night’), varies across languages and cultures. We show the possibilities that Twitter offers for studying the semantics of these terms and its variability between countries. We mine a worldwide sample of multilingual tweets with temporal greetings, and study how their frequencies vary in relation with local time. The results provide insights into the semantics of these temporal expressions and the cultural and sociological factors influencing their usage. |
| Tasks | |
| Published | 2018-05-23 |
| URL | http://arxiv.org/abs/1805.09055v1 |
| http://arxiv.org/pdf/1805.09055v1.pdf | |
| PWC | https://paperswithcode.com/paper/grounding-the-semantics-of-part-of-day-nouns |
| Repo | |
| Framework | |
Multivariate Time-series Similarity Assessment via Unsupervised Representation Learning and Stratified Locality Sensitive Hashing: Application to Early Acute Hypotensive Episode Detection
| Title | Multivariate Time-series Similarity Assessment via Unsupervised Representation Learning and Stratified Locality Sensitive Hashing: Application to Early Acute Hypotensive Episode Detection |
| Authors | Jwala Dhamala, Emmanuel Azuh, Abdullah Al-Dujaili, Jonathan Rubin, Una-May O’Reilly |
| Abstract | Timely prediction of clinically critical events in Intensive Care Unit (ICU) is important for improving care and survival rate. Most of the existing approaches are based on the application of various classification methods on explicitly extracted statistical features from vital signals. In this work, we propose to eliminate the high cost of engineering hand-crafted features from multivariate time-series of physiologic signals by learning their representation with a sequence-to-sequence auto-encoder. We then propose to hash the learned representations to enable signal similarity assessment for the prediction of critical events. We apply this methodological framework to predict Acute Hypotensive Episodes (AHE) on a large and diverse dataset of vital signal recordings. Experiments demonstrate the ability of the presented framework in accurately predicting an upcoming AHE. |
| Tasks | Representation Learning, Time Series, Unsupervised Representation Learning |
| Published | 2018-11-14 |
| URL | http://arxiv.org/abs/1811.06106v3 |
| http://arxiv.org/pdf/1811.06106v3.pdf | |
| PWC | https://paperswithcode.com/paper/multivariate-time-series-similarity |
| Repo | |
| Framework | |
Adversarial Unsupervised Representation Learning for Activity Time-Series
| Title | Adversarial Unsupervised Representation Learning for Activity Time-Series |
| Authors | Karan Aggarwal, Shafiq Joty, Luis Fernandez-Luque, Jaideep Srivastava |
| Abstract | Sufficient physical activity and restful sleep play a major role in the prevention and cure of many chronic conditions. Being able to proactively screen and monitor such chronic conditions would be a big step forward for overall health. The rapid increase in the popularity of wearable devices provides a significant new source, making it possible to track the user’s lifestyle real-time. In this paper, we propose a novel unsupervised representation learning technique called activity2vec that learns and “summarizes” the discrete-valued activity time-series. It learns the representations with three components: (i) the co-occurrence and magnitude of the activity levels in a time-segment, (ii) neighboring context of the time-segment, and (iii) promoting subject-invariance with adversarial training. We evaluate our method on four disorder prediction tasks using linear classifiers. Empirical evaluation demonstrates that our proposed method scales and performs better than many strong baselines. The adversarial regime helps improve the generalizability of our representations by promoting subject invariant features. We also show that using the representations at the level of a day works the best since human activity is structured in terms of daily routines |
| Tasks | Representation Learning, Time Series, Unsupervised Representation Learning |
| Published | 2018-11-14 |
| URL | http://arxiv.org/abs/1811.06847v1 |
| http://arxiv.org/pdf/1811.06847v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-unsupervised-representation |
| Repo | |
| Framework | |
Instance Search via Instance Level Segmentation and Feature Representation
| Title | Instance Search via Instance Level Segmentation and Feature Representation |
| Authors | Yu Zhan, Wan-Lei Zhao |
| Abstract | Instance search is an interesting task as well as a challenging issue due to the lack of effective feature representation. In this paper, an instance level feature representation built upon fully convolutional instance-aware segmentation is proposed. The feature is ROI-pooled from the segmented instance region. So that instances in various sizes and layouts are represented by deep features in uniform length. This representation is further enhanced by the use of deformable ResNeXt blocks. Superior performance is observed in terms of its distinctiveness and scalability on a challenging evaluation dataset built by ourselves. In addition, the proposed enhancement on the network structure also shows superior performance on the instance segmentation task. |
| Tasks | Instance Search, Instance Segmentation, Semantic Segmentation |
| Published | 2018-06-10 |
| URL | https://arxiv.org/abs/1806.03576v2 |
| https://arxiv.org/pdf/1806.03576v2.pdf | |
| PWC | https://paperswithcode.com/paper/instance-search-via-instance-level |
| Repo | |
| Framework | |
A Report on the Complex Word Identification Shared Task 2018
| Title | A Report on the Complex Word Identification Shared Task 2018 |
| Authors | Seid Muhie Yimam, Chris Biemann, Shervin Malmasi, Gustavo H. Paetzold, Lucia Specia, Sanja Štajner, Anaïs Tack, Marcos Zampieri |
| Abstract | We report the findings of the second Complex Word Identification (CWI) shared task organized as part of the BEA workshop co-located with NAACL-HLT’2018. The second CWI shared task featured multilingual and multi-genre datasets divided into four tracks: English monolingual, German monolingual, Spanish monolingual, and a multilingual track with a French test set, and two tasks: binary classification and probabilistic classification. A total of 12 teams submitted their results in different task/track combinations and 11 of them wrote system description papers that are referred to in this report and appear in the BEA workshop proceedings. |
| Tasks | Complex Word Identification |
| Published | 2018-04-24 |
| URL | http://arxiv.org/abs/1804.09132v1 |
| http://arxiv.org/pdf/1804.09132v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-report-on-the-complex-word-identification |
| Repo | |
| Framework | |
Modeling outcomes of soccer matches
| Title | Modeling outcomes of soccer matches |
| Authors | Alkeos Tsokos, Santhosh Narayanan, Ioannis Kosmidis, Gianluca Baio, Mihai Cucuringu, Gavin Whitaker, Franz J. Király |
| Abstract | We compare various extensions of the Bradley-Terry model and a hierarchical Poisson log-linear model in terms of their performance in predicting the outcome of soccer matches (win, draw, or loss). The parameters of the Bradley-Terry extensions are estimated by maximizing the log-likelihood, or an appropriately penalized version of it, while the posterior densities of the parameters of the hierarchical Poisson log-linear model are approximated using integrated nested Laplace approximations. The prediction performance of the various modeling approaches is assessed using a novel, context-specific framework for temporal validation that is found to deliver accurate estimates of the test error. The direct modeling of outcomes via the various Bradley-Terry extensions and the modeling of match scores using the hierarchical Poisson log-linear model demonstrate similar behavior in terms of predictive performance. |
| Tasks | |
| Published | 2018-07-04 |
| URL | http://arxiv.org/abs/1807.01623v2 |
| http://arxiv.org/pdf/1807.01623v2.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-outcomes-of-soccer-matches |
| Repo | |
| Framework | |
Attentive Semantic Alignment with Offset-Aware Correlation Kernels
| Title | Attentive Semantic Alignment with Offset-Aware Correlation Kernels |
| Authors | Paul Hongsuck Seo, Jongmin Lee, Deunsol Jung, Bohyung Han, Minsu Cho |
| Abstract | Semantic correspondence is the problem of establishing correspondences across images depicting different instances of the same object or scene class. One of recent approaches to this problem is to estimate parameters of a global transformation model that densely aligns one image to the other. Since an entire correlation map between all feature pairs across images is typically used to predict such a global transformation, noisy features from different backgrounds, clutter, and occlusion distract the predictor from correct estimation of the alignment. This is a challenging issue, in particular, in the problem of semantic correspondence where a large degree of image variations is often involved. In this paper, we introduce an attentive semantic alignment method that focuses on reliable correlations, filtering out distractors. For effective attention, we also propose an offset-aware correlation kernel that learns to capture translation-invariant local transformations in computing correlation values over spatial locations. Experiments demonstrate the effectiveness of the attentive model and offset-aware kernel, and the proposed model combining both techniques achieves the state-of-the-art performance. |
| Tasks | |
| Published | 2018-08-06 |
| URL | http://arxiv.org/abs/1808.02128v2 |
| http://arxiv.org/pdf/1808.02128v2.pdf | |
| PWC | https://paperswithcode.com/paper/attentive-semantic-alignment-with-offset |
| Repo | |
| Framework | |
