Paper Group ANR 149
Goal-Driven Query Answering for Existential Rules with Equality. Concurrence-Aware Long Short-Term Sub-Memories for Person-Person Action Recognition. Scaling Active Search using Linear Similarity Functions. Simple Methods for Scanner Drift Normalization Validated for Automatic Segmentation of Knee Magnetic Resonance Imaging - with data from the Ost …
Goal-Driven Query Answering for Existential Rules with Equality
| Title | Goal-Driven Query Answering for Existential Rules with Equality |
| Authors | Michael Benedikt, Boris Motik, Efthymia Tsamoura |
| Abstract | Inspired by the magic sets for Datalog, we present a novel goal-driven approach for answering queries over terminating existential rules with equality (aka TGDs and EGDs). Our technique improves the performance of query answering by pruning the consequences that are not relevant for the query. This is challenging in our setting because equalities can potentially affect all predicates in a dataset. We address this problem by combining the existing singularization technique with two new ingredients: an algorithm for identifying the rules relevant to a query and a new magic sets algorithm. We show empirically that our technique can significantly improve the performance of query answering, and that it can mean the difference between answering a query in a few seconds or not being able to process the query at all. |
| Tasks | |
| Published | 2017-11-14 |
| URL | http://arxiv.org/abs/1711.05227v2 |
| http://arxiv.org/pdf/1711.05227v2.pdf | |
| PWC | https://paperswithcode.com/paper/goal-driven-query-answering-for-existential |
| Repo | |
| Framework | |
Concurrence-Aware Long Short-Term Sub-Memories for Person-Person Action Recognition
| Title | Concurrence-Aware Long Short-Term Sub-Memories for Person-Person Action Recognition |
| Authors | Xiangbo Shu, Jinhui Tang, Guo-Jun Qi, Yan Song, Zechao Li, Liyan Zhang |
| Abstract | Recently, Long Short-Term Memory (LSTM) has become a popular choice to model individual dynamics for single-person action recognition due to its ability of modeling the temporal information in various ranges of dynamic contexts. However, existing RNN models only focus on capturing the temporal dynamics of the person-person interactions by naively combining the activity dynamics of individuals or modeling them as a whole. This neglects the inter-related dynamics of how person-person interactions change over time. To this end, we propose a novel Concurrence-Aware Long Short-Term Sub-Memories (Co-LSTSM) to model the long-term inter-related dynamics between two interacting people on the bounding boxes covering people. Specifically, for each frame, two sub-memory units store individual motion information, while a concurrent LSTM unit selectively integrates and stores inter-related motion information between interacting people from these two sub-memory units via a new co-memory cell. Experimental results on the BIT and UT datasets show the superiority of Co-LSTSM compared with the state-of-the-art methods. |
| Tasks | Temporal Action Localization |
| Published | 2017-06-03 |
| URL | http://arxiv.org/abs/1706.00931v1 |
| http://arxiv.org/pdf/1706.00931v1.pdf | |
| PWC | https://paperswithcode.com/paper/concurrence-aware-long-short-term-sub |
| Repo | |
| Framework | |
Scaling Active Search using Linear Similarity Functions
| Title | Scaling Active Search using Linear Similarity Functions |
| Authors | Sibi Venkatesan, James K. Miller, Jeff Schneider, Artur Dubrawski |
| Abstract | Active Search has become an increasingly useful tool in information retrieval problems where the goal is to discover as many target elements as possible using only limited label queries. With the advent of big data, there is a growing emphasis on the scalability of such techniques to handle very large and very complex datasets. In this paper, we consider the problem of Active Search where we are given a similarity function between data points. We look at an algorithm introduced by Wang et al. [2013] for Active Search over graphs and propose crucial modifications which allow it to scale significantly. Their approach selects points by minimizing an energy function over the graph induced by the similarity function on the data. Our modifications require the similarity function to be a dot-product between feature vectors of data points, equivalent to having a linear kernel for the adjacency matrix. With this, we are able to scale tremendously: for $n$ data points, the original algorithm runs in $O(n^2)$ time per iteration while ours runs in only $O(nr + r^2)$ given $r$-dimensional features. We also describe a simple alternate approach using a weighted-neighbor predictor which also scales well. In our experiments, we show that our method is competitive with existing semi-supervised approaches. We also briefly discuss conditions under which our algorithm performs well. |
| Tasks | Information Retrieval |
| Published | 2017-04-30 |
| URL | http://arxiv.org/abs/1705.00334v2 |
| http://arxiv.org/pdf/1705.00334v2.pdf | |
| PWC | https://paperswithcode.com/paper/scaling-active-search-using-linear-similarity |
| Repo | |
| Framework | |
Simple Methods for Scanner Drift Normalization Validated for Automatic Segmentation of Knee Magnetic Resonance Imaging - with data from the Osteoarthritis Initiative
| Title | Simple Methods for Scanner Drift Normalization Validated for Automatic Segmentation of Knee Magnetic Resonance Imaging - with data from the Osteoarthritis Initiative |
| Authors | Erik B Dam |
| Abstract | Scanner drift is a well-known magnetic resonance imaging (MRI) artifact characterized by gradual signal degradation and scan intensity changes over time. In addition, hardware and software updates may imply abrupt changes in signal. The combined effects are particularly challenging for automatic image analysis methods used in longitudinal studies. The implication is increased measurement variation and a risk of bias in the estimations (e.g. in the volume change for a structure). We proposed two quite different approaches for scanner drift normalization and demonstrated the performance for segmentation of knee MRI using the fully automatic KneeIQ framework. The validation included a total of 1975 scans from both high-field and low-field MRI. The results demonstrated that the pre-processing method denoted Atlas Affine Normalization significantly removed scanner drift effects and ensured that the cartilage volume change quantifications became consistent with manual expert scores. |
| Tasks | |
| Published | 2017-12-22 |
| URL | http://arxiv.org/abs/1712.08425v1 |
| http://arxiv.org/pdf/1712.08425v1.pdf | |
| PWC | https://paperswithcode.com/paper/simple-methods-for-scanner-drift |
| Repo | |
| Framework | |
Enumeration of Extractive Oracle Summaries
| Title | Enumeration of Extractive Oracle Summaries |
| Authors | Tsutomu Hirao, Masaaki Nishino, Jun Suzuki, Masaaki Nagata |
| Abstract | To analyze the limitations and the future directions of the extractive summarization paradigm, this paper proposes an Integer Linear Programming (ILP) formulation to obtain extractive oracle summaries in terms of ROUGE-N. We also propose an algorithm that enumerates all of the oracle summaries for a set of reference summaries to exploit F-measures that evaluate which system summaries contain how many sentences that are extracted as an oracle summary. Our experimental results obtained from Document Understanding Conference (DUC) corpora demonstrated the following: (1) room still exists to improve the performance of extractive summarization; (2) the F-measures derived from the enumerated oracle summaries have significantly stronger correlations with human judgment than those derived from single oracle summaries. |
| Tasks | |
| Published | 2017-01-06 |
| URL | http://arxiv.org/abs/1701.01614v1 |
| http://arxiv.org/pdf/1701.01614v1.pdf | |
| PWC | https://paperswithcode.com/paper/enumeration-of-extractive-oracle-summaries |
| Repo | |
| Framework | |
A Resilient Image Matching Method with an Affine Invariant Feature Detector and Descriptor
| Title | A Resilient Image Matching Method with an Affine Invariant Feature Detector and Descriptor |
| Authors | Biao Zhao, Shigang Yue |
| Abstract | Image feature matching is to seek, localize and identify the similarities across the images. The matched local features between different images can indicate the similarities of their content. Resilience of image feature matching to large view point changes is challenging for a lot of applications such as 3D object reconstruction, object recognition and navigation, etc, which need accurate and robust feature matching from quite different view points. In this paper we propose a novel image feature matching algorithm, integrating our previous proposed Affine Invariant Feature Detector (AIFD) and new proposed Affine Invariant Feature Descriptor (AIFDd). Both stages of this new proposed algorithm can provide sufficient resilience to view point changes. With systematic experiments, we can prove that the proposed method of feature detector and descriptor outperforms other state-of-the-art feature matching algorithms especially on view points robustness. It also performs well under other conditions such as the change of illumination, rotation and compression, etc. |
| Tasks | 3D Object Reconstruction, Object Recognition, Object Reconstruction |
| Published | 2017-12-29 |
| URL | http://arxiv.org/abs/1802.09623v1 |
| http://arxiv.org/pdf/1802.09623v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-resilient-image-matching-method-with-an |
| Repo | |
| Framework | |
Computer-aided diagnosis of lung nodule using gradient tree boosting and Bayesian optimization
| Title | Computer-aided diagnosis of lung nodule using gradient tree boosting and Bayesian optimization |
| Authors | Mizuho Nishio, Mitsuo Nishizawa, Osamu Sugiyama, Ryosuke Kojima, Masahiro Yakami, Tomohiro Kuroda, Kaori Togashi |
| Abstract | We aimed to evaluate computer-aided diagnosis (CADx) system for lung nodule classification focusing on (i) usefulness of gradient tree boosting (XGBoost) and (ii) effectiveness of parameter optimization using Bayesian optimization (Tree Parzen Estimator, TPE) and random search. 99 lung nodules (62 lung cancers and 37 benign lung nodules) were included from public databases of CT images. A variant of local binary pattern was used for calculating feature vectors. Support vector machine (SVM) or XGBoost was trained using the feature vectors and their labels. TPE or random search was used for parameter optimization of SVM and XGBoost. Leave-one-out cross-validation was used for optimizing and evaluating the performance of our CADx system. Performance was evaluated using area under the curve (AUC) of receiver operating characteristic analysis. AUC was calculated 10 times, and its average was obtained. The best averaged AUC of SVM and XGBoost were 0.850 and 0.896, respectively; both were obtained using TPE. XGBoost was generally superior to SVM. Optimal parameters for achieving high AUC were obtained with fewer numbers of trials when using TPE, compared with random search. In conclusion, XGBoost was better than SVM for classifying lung nodules. TPE was more efficient than random search for parameter optimization. |
| Tasks | Lung Nodule Classification |
| Published | 2017-08-19 |
| URL | http://arxiv.org/abs/1708.05897v2 |
| http://arxiv.org/pdf/1708.05897v2.pdf | |
| PWC | https://paperswithcode.com/paper/computer-aided-diagnosis-of-lung-nodule-using |
| Repo | |
| Framework | |
Statistical Mechanics of Node-perturbation Learning with Noisy Baseline
| Title | Statistical Mechanics of Node-perturbation Learning with Noisy Baseline |
| Authors | Kazuyuki Hara, Kentaro Katahira, Masato Okada |
| Abstract | Node-perturbation learning is a type of statistical gradient descent algorithm that can be applied to problems where the objective function is not explicitly formulated, including reinforcement learning. It estimates the gradient of an objective function by using the change in the object function in response to the perturbation. The value of the objective function for an unperturbed output is called a baseline. Cho et al. proposed node-perturbation learning with a noisy baseline. In this paper, we report on building the statistical mechanics of Cho’s model and on deriving coupled differential equations of order parameters that depict learning dynamics. We also show how to derive the generalization error by solving the differential equations of order parameters. On the basis of the results, we show that Cho’s results are also apply in general cases and show some general performances of Cho’s model. |
| Tasks | |
| Published | 2017-06-20 |
| URL | http://arxiv.org/abs/1706.06953v1 |
| http://arxiv.org/pdf/1706.06953v1.pdf | |
| PWC | https://paperswithcode.com/paper/statistical-mechanics-of-node-perturbation |
| Repo | |
| Framework | |
Pomegranate: fast and flexible probabilistic modeling in python
| Title | Pomegranate: fast and flexible probabilistic modeling in python |
| Authors | Jacob Schreiber |
| Abstract | We present pomegranate, an open source machine learning package for probabilistic modeling in Python. Probabilistic modeling encompasses a wide range of methods that explicitly describe uncertainty using probability distributions. Three widely used probabilistic models implemented in pomegranate are general mixture models, hidden Markov models, and Bayesian networks. A primary focus of pomegranate is to abstract away the complexities of training models from their definition. This allows users to focus on specifying the correct model for their application instead of being limited by their understanding of the underlying algorithms. An aspect of this focus involves the collection of additive sufficient statistics from data sets as a strategy for training models. This approach trivially enables many useful learning strategies, such as out-of-core learning, minibatch learning, and semi-supervised learning, without requiring the user to consider how to partition data or modify the algorithms to handle these tasks themselves. pomegranate is written in Cython to speed up calculations and releases the global interpreter lock to allow for built-in multithreaded parallelism, making it competitive with—or outperform—other implementations of similar algorithms. This paper presents an overview of the design choices in pomegranate, and how they have enabled complex features to be supported by simple code. |
| Tasks | |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1711.00137v2 |
| http://arxiv.org/pdf/1711.00137v2.pdf | |
| PWC | https://paperswithcode.com/paper/pomegranate-fast-and-flexible-probabilistic |
| Repo | |
| Framework | |
3D Object Reconstruction from Hand-Object Interactions
| Title | 3D Object Reconstruction from Hand-Object Interactions |
| Authors | Dimitrios Tzionas, Juergen Gall |
| Abstract | Recent advances have enabled 3d object reconstruction approaches using a single off-the-shelf RGB-D camera. Although these approaches are successful for a wide range of object classes, they rely on stable and distinctive geometric or texture features. Many objects like mechanical parts, toys, household or decorative articles, however, are textureless and characterized by minimalistic shapes that are simple and symmetric. Existing in-hand scanning systems and 3d reconstruction techniques fail for such symmetric objects in the absence of highly distinctive features. In this work, we show that extracting 3d hand motion for in-hand scanning effectively facilitates the reconstruction of even featureless and highly symmetric objects and we present an approach that fuses the rich additional information of hands into a 3d reconstruction pipeline, significantly contributing to the state-of-the-art of in-hand scanning. |
| Tasks | 3D Object Reconstruction, 3D Reconstruction, Object Reconstruction |
| Published | 2017-04-03 |
| URL | http://arxiv.org/abs/1704.00529v1 |
| http://arxiv.org/pdf/1704.00529v1.pdf | |
| PWC | https://paperswithcode.com/paper/3d-object-reconstruction-from-hand-object |
| Repo | |
| Framework | |
Effects of Limiting Memory Capacity on the Behaviour of Exemplar Dynamics
| Title | Effects of Limiting Memory Capacity on the Behaviour of Exemplar Dynamics |
| Authors | B. Goodman, P. F. Tupper |
| Abstract | Exemplar models are a popular class of models used to describe language change. Here we study how limiting the memory capacity of an individual in these models affects the system’s behaviour. In particular we demonstrate the effect this change has on the extinction of categories. Previous work in exemplar dynamics has not addressed this question. In order to investigate this, we will inspect a simplified exemplar model. We will prove for the simplified model that all the sound categories but one will always become extinct, whether memory storage is limited or not. However, computer simulations show that changing the number of stored memories alters how fast categories become extinct. |
| Tasks | |
| Published | 2017-03-10 |
| URL | http://arxiv.org/abs/1703.03842v2 |
| http://arxiv.org/pdf/1703.03842v2.pdf | |
| PWC | https://paperswithcode.com/paper/effects-of-limiting-memory-capacity-on-the |
| Repo | |
| Framework | |
Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method
| Title | Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method |
| Authors | Xiao Han |
| Abstract | Liver lesion segmentation is an important step for liver cancer diagnosis, treatment planning and treatment evaluation. LiTS (Liver Tumor Segmentation Challenge) provides a common testbed for comparing different automatic liver lesion segmentation methods. We participate in this challenge by developing a deep convolutional neural network (DCNN) method. The particular DCNN model works in 2.5D in that it takes a stack of adjacent slices as input and produces the segmentation map corresponding to the center slice. The model has 32 layers in total and makes use of both long range concatenation connections of U-Net [1] and short-range residual connections from ResNet [2]. The model was trained using the 130 LiTS training datasets and achieved an average Dice score of 0.67 when evaluated on the 70 test CT scans, which ranked first for the LiTS challenge at the time of the ISBI 2017 conference. |
| Tasks | Lesion Segmentation |
| Published | 2017-04-24 |
| URL | http://arxiv.org/abs/1704.07239v1 |
| http://arxiv.org/pdf/1704.07239v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-liver-lesion-segmentation-using-a |
| Repo | |
| Framework | |
CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning
| Title | CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning |
| Authors | Yuxin Peng, Jinwei Qi, Yuxin Yuan |
| Abstract | It is known that the inconsistent distribution and representation of different modalities, such as image and text, cause the heterogeneity gap that makes it challenging to correlate such heterogeneous data. Generative adversarial networks (GANs) have shown its strong ability of modeling data distribution and learning discriminative representation, existing GANs-based works mainly focus on generative problem to generate new data. We have different goal, aim to correlate heterogeneous data, by utilizing the power of GANs to model cross-modal joint distribution. Thus, we propose Cross-modal GANs to learn discriminative common representation for bridging heterogeneity gap. The main contributions are: (1) Cross-modal GANs architecture is proposed to model joint distribution over data of different modalities. The inter-modality and intra-modality correlation can be explored simultaneously in generative and discriminative models. Both of them beat each other to promote cross-modal correlation learning. (2) Cross-modal convolutional autoencoders with weight-sharing constraint are proposed to form generative model. They can not only exploit cross-modal correlation for learning common representation, but also preserve reconstruction information for capturing semantic consistency within each modality. (3) Cross-modal adversarial mechanism is proposed, which utilizes two kinds of discriminative models to simultaneously conduct intra-modality and inter-modality discrimination. They can mutually boost to make common representation more discriminative by adversarial training process. To the best of our knowledge, our proposed CM-GANs approach is the first to utilize GANs to perform cross-modal common representation learning. Experiments are conducted to verify the performance of our proposed approach on cross-modal retrieval paradigm, compared with 10 methods on 3 cross-modal datasets. |
| Tasks | Cross-Modal Retrieval, Representation Learning |
| Published | 2017-10-14 |
| URL | http://arxiv.org/abs/1710.05106v2 |
| http://arxiv.org/pdf/1710.05106v2.pdf | |
| PWC | https://paperswithcode.com/paper/cm-gans-cross-modal-generative-adversarial |
| Repo | |
| Framework | |
Learning a Robust Society of Tracking Parts
| Title | Learning a Robust Society of Tracking Parts |
| Authors | Elena Burceanu, Marius Leordeanu |
| Abstract | Object tracking is an essential task in computer vision that has been studied since the early days of the field. Being able to follow objects that undergo different transformations in the video sequence, including changes in scale, illumination, shape and occlusions, makes the problem extremely difficult. One of the real challenges is to keep track of the changes in objects appearance and not drift towards the background clutter. Different from previous approaches, we obtain robustness against background with a tracker model that is composed of many different parts. They are classifiers that respond at different scales and locations. The tracker system functions as a society of parts, each having its own role and level of credibility. Reliable classifiers decide the tracker’s next move, while newcomers are first monitored before gaining the necessary level of reliability to participate in the decision process. Some parts that loose their consistency are rejected, while others that show consistency for a sufficiently long time are promoted to permanent roles. The tracker system, as a whole, could also go through different phases, from the usual, normal functioning to states of weak agreement and even crisis. The tracker system has different governing rules in each state. What truly distinguishes our work from others is not necessarily the strength of individual tracking parts, but the way in which they work together and build a strong and robust organization. We also propose an efficient way to learn simultaneously many tracking parts, with a single closed-form formulation. We obtain a fast and robust tracker with state of the art performance on the challenging OTB50 dataset. |
| Tasks | Object Tracking |
| Published | 2017-05-26 |
| URL | http://arxiv.org/abs/1705.09602v1 |
| http://arxiv.org/pdf/1705.09602v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-robust-society-of-tracking-parts-1 |
| Repo | |
| Framework | |
A Dataset for Developing and Benchmarking Active Vision
| Title | A Dataset for Developing and Benchmarking Active Vision |
| Authors | Phil Ammirato, Patrick Poirson, Eunbyung Park, Jana Kosecka, Alexander C. Berg |
| Abstract | We present a new public dataset with a focus on simulating robotic vision tasks in everyday indoor environments using real imagery. The dataset includes 20,000+ RGB-D images and 50,000+ 2D bounding boxes of object instances densely captured in 9 unique scenes. We train a fast object category detector for instance detection on our data. Using the dataset we show that, although increasingly accurate and fast, the state of the art for object detection is still severely impacted by object scale, occlusion, and viewing direction all of which matter for robotics applications. We next validate the dataset for simulating active vision, and use the dataset to develop and evaluate a deep-network-based system for next best move prediction for object classification using reinforcement learning. Our dataset is available for download at cs.unc.edu/~ammirato/active_vision_dataset_website/. |
| Tasks | Object Classification, Object Detection |
| Published | 2017-02-27 |
| URL | http://arxiv.org/abs/1702.08272v2 |
| http://arxiv.org/pdf/1702.08272v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-dataset-for-developing-and-benchmarking |
| Repo | |
| Framework | |
