Paper Group ANR 348
Inverse Reinforcement Learning Under Noisy Observations. (k,q)-Compressed Sensing for dMRI with Joint Spatial-Angular Sparsity Prior. TAMU at KBP 2017: Event Nugget Detection and Coreference Resolution. Recognition of Documents in Braille. Exploring Directional Path-Consistency for Solving Constraint Networks. Digitising Cultural Complexity: Repres …
Inverse Reinforcement Learning Under Noisy Observations
| Title | Inverse Reinforcement Learning Under Noisy Observations |
| Authors | Shervin Shahryari, Prashant Doshi |
| Abstract | We consider the problem of performing inverse reinforcement learning when the trajectory of the expert is not perfectly observed by the learner. Instead, a noisy continuous-time observation of the trajectory is provided to the learner. This problem exhibits wide-ranging applications and the specific application we consider here is the scenario in which the learner seeks to penetrate a perimeter patrolled by a robot. The learner’s field of view is limited due to which it cannot observe the patroller’s complete trajectory. Instead, we allow the learner to listen to the expert’s movement sound, which it can also use to estimate the expert’s state and action using an observation model. We treat the expert’s state and action as hidden data and present an algorithm based on expectation maximization and maximum entropy principle to solve the non-linear, non-convex problem. Related work considers discrete-time observations and an observation model that does not include actions. In contrast, our technique takes expectations over both state and action of the expert, enabling learning even in the presence of extreme noise and broader applications. |
| Tasks | |
| Published | 2017-10-27 |
| URL | http://arxiv.org/abs/1710.10116v1 |
| http://arxiv.org/pdf/1710.10116v1.pdf | |
| PWC | https://paperswithcode.com/paper/inverse-reinforcement-learning-under-noisy |
| Repo | |
| Framework | |
(k,q)-Compressed Sensing for dMRI with Joint Spatial-Angular Sparsity Prior
| Title | (k,q)-Compressed Sensing for dMRI with Joint Spatial-Angular Sparsity Prior |
| Authors | Evan Schwab, René Vidal, Nicolas Charon |
| Abstract | Advanced diffusion magnetic resonance imaging (dMRI) techniques, like diffusion spectrum imaging (DSI) and high angular resolution diffusion imaging (HARDI), remain underutilized compared to diffusion tensor imaging because the scan times needed to produce accurate estimations of fiber orientation are significantly longer. To accelerate DSI and HARDI, recent methods from compressed sensing (CS) exploit a sparse underlying representation of the data in the spatial and angular domains to undersample in the respective k- and q-spaces. State-of-the-art frameworks, however, impose sparsity in the spatial and angular domains separately and involve the sum of the corresponding sparse regularizers. In contrast, we propose a unified (k,q)-CS formulation which imposes sparsity jointly in the spatial-angular domain to further increase sparsity of dMRI signals and reduce the required subsampling rate. To efficiently solve this large-scale global reconstruction problem, we introduce a novel adaptation of the FISTA algorithm that exploits dictionary separability. We show on phantom and real HARDI data that our approach achieves significantly more accurate signal reconstructions than the state of the art while sampling only 2-4% of the (k,q)-space, allowing for the potential of new levels of dMRI acceleration. |
| Tasks | |
| Published | 2017-07-21 |
| URL | http://arxiv.org/abs/1707.09958v2 |
| http://arxiv.org/pdf/1707.09958v2.pdf | |
| PWC | https://paperswithcode.com/paper/kq-compressed-sensing-for-dmri-with-joint |
| Repo | |
| Framework | |
TAMU at KBP 2017: Event Nugget Detection and Coreference Resolution
| Title | TAMU at KBP 2017: Event Nugget Detection and Coreference Resolution |
| Authors | Prafulla Kumar Choubey, Ruihong Huang |
| Abstract | In this paper, we describe TAMU’s system submitted to the TAC KBP 2017 event nugget detection and coreference resolution task. Our system builds on the statistical and empirical observations made on training and development data. We found that modifiers of event nuggets tend to have unique syntactic distribution. Their parts-of-speech tags and dependency relations provides them essential characteristics that are useful in identifying their span and also defining their types and realis status. We further found that the joint modeling of event span detection and realis status identification performs better than the individual models for both tasks. Our simple system designed using minimal features achieved the micro-average F1 scores of 57.72, 44.27 and 42.47 for event span detection, type identification and realis status classification tasks respectively. Also, our system achieved the CoNLL F1 score of 27.20 in event coreference resolution task. |
| Tasks | Coreference Resolution |
| Published | 2017-11-06 |
| URL | http://arxiv.org/abs/1711.02162v2 |
| http://arxiv.org/pdf/1711.02162v2.pdf | |
| PWC | https://paperswithcode.com/paper/tamu-at-kbp-2017-event-nugget-detection-and |
| Repo | |
| Framework | |
Recognition of Documents in Braille
| Title | Recognition of Documents in Braille |
| Authors | Jomy John |
| Abstract | Visually impaired people are integral part of the society and it has been a must to provide them with means and system through which they may communicate with the world. In this work, I would like to address how computers can be made useful to read the scripts in Braille. The importance of this work is to reduce communication gap between visually impaired people and the society. Braille remains the most popular tactile reading code even in this century. There are numerous amount of literature locked up in Braille. Braille recognition not only reduces time in reading or extracting information from Braille document but also helps people engaged in special education for correcting papers and other school related works. The availability of such a system will enhance communication and collaboration possibilities with visually impaired people. Existing works supports only documents in white either bright or dull in colour. Hardly any work could be traced on hand printed ordinary documents in Braille. |
| Tasks | |
| Published | 2017-09-28 |
| URL | http://arxiv.org/abs/1709.09875v1 |
| http://arxiv.org/pdf/1709.09875v1.pdf | |
| PWC | https://paperswithcode.com/paper/recognition-of-documents-in-braille |
| Repo | |
| Framework | |
Exploring Directional Path-Consistency for Solving Constraint Networks
| Title | Exploring Directional Path-Consistency for Solving Constraint Networks |
| Authors | Shufeng Kong, Sanjiang Li, Michael Sioutis |
| Abstract | Among the local consistency techniques used for solving constraint networks, path-consistency (PC) has received a great deal of attention. However, enforcing PC is computationally expensive and sometimes even unnecessary. Directional path-consistency (DPC) is a weaker notion of PC that considers a given variable ordering and can thus be enforced more efficiently than PC. This paper shows that DPC (the DPC enforcing algorithm of Dechter and Pearl) decides the constraint satisfaction problem (CSP) of a constraint language if it is complete and has the variable elimination property (VEP). However, we also show that no complete VEP constraint language can have a domain with more than 2 values. We then present a simple variant of the DPC algorithm, called DPC*, and show that the CSP of a constraint language can be decided by DPC* if it is closed under a majority operation. In fact, DPC* is sufficient for guaranteeing backtrack-free search for such constraint networks. Examples of majority-closed constraint classes include the classes of connected row-convex (CRC) constraints and tree-preserving constraints, which have found applications in various domains, such as scene labeling, temporal reasoning, geometric reasoning, and logical filtering. Our experimental evaluations show that DPC* significantly outperforms the state-of-the-art algorithms for solving majority-closed constraints. |
| Tasks | Scene Labeling |
| Published | 2017-08-18 |
| URL | http://arxiv.org/abs/1708.05522v1 |
| http://arxiv.org/pdf/1708.05522v1.pdf | |
| PWC | https://paperswithcode.com/paper/exploring-directional-path-consistency-for |
| Repo | |
| Framework | |
Digitising Cultural Complexity: Representing Rich Cultural Data in a Big Data environment
| Title | Digitising Cultural Complexity: Representing Rich Cultural Data in a Big Data environment |
| Authors | Jennifer Edmond, Georgina Nugent Folan |
| Abstract | One of the major terminological forces driving ICT integration in research today is that of “big data.” While the phrase sounds inclusive and integrative, “big data” approaches are highly selective, excluding input that cannot be effectively structured, represented, or digitised. Data of this complex sort is precisely the kind that human activity produces, but the technological imperative to enhance signal through the reduction of noise does not accommodate this richness. Data and the computational approaches that facilitate “big data” have acquired a perceived objectivity that belies their curated, malleable, reactive, and performative nature. In an input environment where anything can “be data” once it is entered into the system as “data,” data cleaning and processing, together with the metadata and information architectures that structure and facilitate our cultural archives acquire a capacity to delimit what data are. This engenders a process of simplification that has major implications for the potential for future innovation within research environments that depend on rich material yet are increasingly mediated by digital technologies. This paper presents the preliminary findings of the European-funded KPLEX (Knowledge Complexity) project which investigates the delimiting effect digital mediation and datafication has on rich, complex cultural data. The paper presents a systematic review of existing implicit definitions of data, elaborating on the implications of these definitions and highlighting the ways in which metadata and computational technologies can restrict the interpretative potential of data. It sheds light on the gap between analogue or augmented digital practices and fully computational ones, and the strategies researchers have developed to deal with this gap. The paper proposes a reconceptualisation of data as it is functionally employed within digitally-mediated research so as to incorporate and acknowledge the richness and complexity of our source materials. |
| Tasks | |
| Published | 2017-11-13 |
| URL | http://arxiv.org/abs/1711.04452v1 |
| http://arxiv.org/pdf/1711.04452v1.pdf | |
| PWC | https://paperswithcode.com/paper/digitising-cultural-complexity-representing |
| Repo | |
| Framework | |
Automated Identification of Drug-Drug Interactions in Pediatric Congestive Heart Failure Patients
| Title | Automated Identification of Drug-Drug Interactions in Pediatric Congestive Heart Failure Patients |
| Authors | Daniel Miller |
| Abstract | Congestive Heart Failure, or CHF, is a serious medical condition that can result in fluid buildup in the body as a result of a weak heart. When the heart can’t pump enough blood to efficiently deliver nutrients and oxygen to the body, kidney function may be impaired, resulting in fluid retention. CHF patients require a broad drug regimen to maintain the delicate system balance, particularly between their heart and kidneys. These drugs include ACE inhibitors and Beta Blockers to control blood pressure, anticoagulants to prevent blood clots, and diuretics to reduce fluid overload. Many of these drugs may interact, and potential effects of these interactions must be weighed against their benefits. For this project, we consider a set of 44 drugs identified as specifically relevant for treating CHF by pediatric cardiologists at Lucile Packard Children’s Hospital. This list was generated as part of our current work at the LPCH Heart Center. The goal of this project is to identify and evaluate potentially harmful drug-drug interactions (DDIs) within pediatric patients with Congestive Heart Failure. This identification will be done autonomously, so that it may continuously update by evaluating newly published literature. |
| Tasks | |
| Published | 2017-02-11 |
| URL | http://arxiv.org/abs/1702.04615v1 |
| http://arxiv.org/pdf/1702.04615v1.pdf | |
| PWC | https://paperswithcode.com/paper/automated-identification-of-drug-drug |
| Repo | |
| Framework | |
Deep Regionlets for Object Detection
| Title | Deep Regionlets for Object Detection |
| Authors | Hongyu Xu, Xutao Lv, Xiaoyu Wang, Zhou Ren, Navaneeth Bodla, Rama Chellappa |
| Abstract | In this paper, we propose a novel object detection framework named “Deep Regionlets” by establishing a bridge between deep neural networks and conventional detection schema for accurate generic object detection. Motivated by the abilities of regionlets for modeling object deformation and multiple aspect ratios, we incorporate regionlets into an end-to-end trainable deep learning framework. The deep regionlets framework consists of a region selection network and a deep regionlet learning module. Specifically, given a detection bounding box proposal, the region selection network provides guidance on where to select regions to learn the features from. The regionlet learning module focuses on local feature selection and transformation to alleviate local variations. To this end, we first realize non-rectangular region selection within the detection framework to accommodate variations in object appearance. Moreover, we design a “gating network” within the regionlet leaning module to enable soft regionlet selection and pooling. The Deep Regionlets framework is trained end-to-end without additional efforts. We perform ablation studies and conduct extensive experiments on the PASCAL VOC and Microsoft COCO datasets. The proposed framework outperforms state-of-the-art algorithms, such as RetinaNet and Mask R-CNN, even without additional segmentation labels. |
| Tasks | Feature Selection, Object Detection |
| Published | 2017-12-06 |
| URL | http://arxiv.org/abs/1712.02408v3 |
| http://arxiv.org/pdf/1712.02408v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-regionlets-for-object-detection |
| Repo | |
| Framework | |
Random Subspace Two-dimensional LDA for Face Recognition
| Title | Random Subspace Two-dimensional LDA for Face Recognition |
| Authors | Garrett Bingham |
| Abstract | In this paper, a novel technique named random subspace two-dimensional LDA (RS-2DLDA) is developed for face recognition. This approach offers a number of improvements over the random subspace two-dimensional PCA (RS2DPCA) framework introduced by Nguyen et al. [5]. Firstly, the eigenvectors from 2DLDA have more discriminative power than those from 2DPCA, resulting in higher accuracy for the RS-2DLDA method over RS-2DPCA. Various distance metrics are evaluated, and a weighting scheme is developed to further boost accuracy. A series of experiments on the MORPH-II and ORL datasets are conducted to demonstrate the effectiveness of this approach. |
| Tasks | Face Recognition |
| Published | 2017-11-02 |
| URL | http://arxiv.org/abs/1711.00575v1 |
| http://arxiv.org/pdf/1711.00575v1.pdf | |
| PWC | https://paperswithcode.com/paper/random-subspace-two-dimensional-lda-for-face |
| Repo | |
| Framework | |
ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans
| Title | ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans |
| Authors | Angela Dai, Daniel Ritchie, Martin Bokeloh, Scott Reed, Jürgen Sturm, Matthias Nießner |
| Abstract | We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels. The key contribution of our method is its ability to handle large scenes with varying spatial extent, managing the cubic growth in data size as scene size increases. To this end, we devise a fully-convolutional generative 3D CNN model whose filter kernels are invariant to the overall scene size. The model can be trained on scene subvolumes but deployed on arbitrarily large scenes at test time. In addition, we propose a coarse-to-fine inference strategy in order to produce high-resolution output while also leveraging large input context sizes. In an extensive series of experiments, we carefully evaluate different model design choices, considering both deterministic and probabilistic models for completion and semantic inference. Our results show that we outperform other methods not only in the size of the environments handled and processing efficiency, but also with regard to completion quality and semantic segmentation performance by a significant margin. |
| Tasks | Semantic Segmentation |
| Published | 2017-12-29 |
| URL | http://arxiv.org/abs/1712.10215v2 |
| http://arxiv.org/pdf/1712.10215v2.pdf | |
| PWC | https://paperswithcode.com/paper/scancomplete-large-scale-scene-completion-and |
| Repo | |
| Framework | |
Power Plant Performance Modeling with Concept Drift
| Title | Power Plant Performance Modeling with Concept Drift |
| Authors | Rui Xu, Yunwen Xu, Weizhong Yan |
| Abstract | Power plant is a complex and nonstationary system for which the traditional machine learning modeling approaches fall short of expectations. The ensemble-based online learning methods provide an effective way to continuously learn from the dynamic environment and autonomously update models to respond to environmental changes. This paper proposes such an online ensemble regression approach to model power plant performance, which is critically important for operation optimization. The experimental results on both simulated and real data show that the proposed method can achieve performance with less than 1% mean average percentage error, which meets the general expectations in field operations. |
| Tasks | |
| Published | 2017-10-19 |
| URL | http://arxiv.org/abs/1710.07314v1 |
| http://arxiv.org/pdf/1710.07314v1.pdf | |
| PWC | https://paperswithcode.com/paper/power-plant-performance-modeling-with-concept |
| Repo | |
| Framework | |
Assessing the Stylistic Properties of Neurally Generated Text in Authorship Attribution
| Title | Assessing the Stylistic Properties of Neurally Generated Text in Authorship Attribution |
| Authors | E. Manjavacas, J. de Gussem, W. Daelemans, M. Kestemont |
| Abstract | Recent applications of neural language models have led to an increased interest in the automatic generation of natural language. However impressive, the evaluation of neurally generated text has so far remained rather informal and anecdotal. Here, we present an attempt at the systematic assessment of one aspect of the quality of neurally generated text. We focus on a specific aspect of neural language generation: its ability to reproduce authorial writing styles. Using established models for authorship attribution, we empirically assess the stylistic qualities of neurally generated text. In comparison to conventional language models, neural models generate fuzzier text that is relatively harder to attribute correctly. Nevertheless, our results also suggest that neurally generated text offers more valuable perspectives for the augmentation of training data. |
| Tasks | Text Generation |
| Published | 2017-08-18 |
| URL | http://arxiv.org/abs/1708.05536v1 |
| http://arxiv.org/pdf/1708.05536v1.pdf | |
| PWC | https://paperswithcode.com/paper/assessing-the-stylistic-properties-of |
| Repo | |
| Framework | |
End-to-End Audiovisual Fusion with LSTMs
| Title | End-to-End Audiovisual Fusion with LSTMs |
| Authors | Stavros Petridis, Yujiang Wang, Zuwei Li, Maja Pantic |
| Abstract | Several end-to-end deep learning approaches have been recently presented which simultaneously extract visual features from the input images and perform visual speech classification. However, research on jointly extracting audio and visual features and performing classification is very limited. In this work, we present an end-to-end audiovisual model based on Bidirectional Long Short-Term Memory (BLSTM) networks. To the best of our knowledge, this is the first audiovisual fusion model which simultaneously learns to extract features directly from the pixels and spectrograms and perform classification of speech and nonlinguistic vocalisations. The model consists of multiple identical streams, one for each modality, which extract features directly from mouth regions and spectrograms. The temporal dynamics in each stream/modality are modeled by a BLSTM and the fusion of multiple streams/modalities takes place via another BLSTM. An absolute improvement of 1.9% in the mean F1 of 4 nonlingusitic vocalisations over audio-only classification is reported on the AVIC database. At the same time, the proposed end-to-end audiovisual fusion system improves the state-of-the-art performance on the AVIC database leading to a 9.7% absolute increase in the mean F1 measure. We also perform audiovisual speech recognition experiments on the OuluVS2 database using different views of the mouth, frontal to profile. The proposed audiovisual system significantly outperforms the audio-only model for all views when the acoustic noise is high. |
| Tasks | Speech Recognition |
| Published | 2017-09-12 |
| URL | http://arxiv.org/abs/1709.04343v1 |
| http://arxiv.org/pdf/1709.04343v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-audiovisual-fusion-with-lstms |
| Repo | |
| Framework | |
Duluth at SemEval–2016 Task 14 : Extending Gloss Overlaps to Enrich Semantic Taxonomies
| Title | Duluth at SemEval–2016 Task 14 : Extending Gloss Overlaps to Enrich Semantic Taxonomies |
| Authors | Ted Pedersen |
| Abstract | This paper describes the Duluth systems that participated in Task 14 of SemEval 2016, Semantic Taxonomy Enrichment. There were three related systems in the formal evaluation which are discussed here, along with numerous post–evaluation runs. All of these systems identified synonyms between WordNet and other dictionaries by measuring the gloss overlaps between them. These systems perform better than the random baseline and one post–evaluation variation was within a respectable margin of the median result attained by all participating systems. |
| Tasks | |
| Published | 2017-05-01 |
| URL | http://arxiv.org/abs/1705.00390v1 |
| http://arxiv.org/pdf/1705.00390v1.pdf | |
| PWC | https://paperswithcode.com/paper/duluth-at-semeval-2016-task-14-extending-1 |
| Repo | |
| Framework | |
Spotting Separator Points at Line Terminals in Compressed Document Images for Text-line Segmentation
| Title | Spotting Separator Points at Line Terminals in Compressed Document Images for Text-line Segmentation |
| Authors | Amarnath R, P. Nagabhushan |
| Abstract | Line separators are used to segregate text-lines from one another in document image analysis. Finding the separator points at every line terminal in a document image would enable text-line segmentation. In particular, identifying the separators in handwritten text could be a thrilling exercise. Obviously it would be challenging to perform this in the compressed version of a document image and that is the proposed objective in this research. Such an effort would prevent the computational burden of decompressing a document for text-line segmentation. Since document images are generally compressed using run length encoding (RLE) technique as per the CCITT standards, the first column in the RLE will be a white column. The value (depth) in the white column is very low when a particular line is a text line and the depth could be larger at the point of text line separation. A longer consecutive sequence of such larger depth should indicate the gap between the text lines, which provides the separator region. In case of over separation and under separation issues, corrective actions such as deletion and insertion are suggested respectively. An extensive experimentation is conducted on the compressed images of the benchmark datasets of ICDAR13 and Alireza et al [17] to demonstrate the efficacy. |
| Tasks | |
| Published | 2017-08-18 |
| URL | http://arxiv.org/abs/1708.05545v1 |
| http://arxiv.org/pdf/1708.05545v1.pdf | |
| PWC | https://paperswithcode.com/paper/spotting-separator-points-at-line-terminals |
| Repo | |
| Framework | |
