Paper Group ANR 155
A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation. Method to Assess the Temporal Persistence of Potential Biometric Features: Application to Oculomotor, and Gait-Related Databases. Neither Quick Nor Proper – Evaluation of QuickProp for Learning Deep Neural Networks. Optical Flow with Semantic Segmentation and Localized Layers. …
A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation
| Title | A Robust 3D-2D Interactive Tool for Scene Segmentation and Annotation |
| Authors | Duc Thanh Nguyen, Binh-Son Hua, Lap-Fai Yu, Sai-Kit Yeung |
| Abstract | Recent advances of 3D acquisition devices have enabled large-scale acquisition of 3D scene data. Such data, if completely and well annotated, can serve as useful ingredients for a wide spectrum of computer vision and graphics works such as data-driven modeling and scene understanding, object detection and recognition. However, annotating a vast amount of 3D scene data remains challenging due to the lack of an effective tool and/or the complexity of 3D scenes (e.g. clutter, varying illumination conditions). This paper aims to build a robust annotation tool that effectively and conveniently enables the segmentation and annotation of massive 3D data. Our tool works by coupling 2D and 3D information via an interactive framework, through which users can provide high-level semantic annotation for objects. We have experimented our tool and found that a typical indoor scene could be well segmented and annotated in less than 30 minutes by using the tool, as opposed to a few hours if done manually. Along with the tool, we created a dataset of over a hundred 3D scenes associated with complete annotations using our tool. The tool and dataset are available at www.scenenn.net. |
| Tasks | Object Detection, Scene Segmentation, Scene Understanding |
| Published | 2016-10-19 |
| URL | http://arxiv.org/abs/1610.05883v1 |
| http://arxiv.org/pdf/1610.05883v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-robust-3d-2d-interactive-tool-for-scene |
| Repo | |
| Framework | |
Method to Assess the Temporal Persistence of Potential Biometric Features: Application to Oculomotor, and Gait-Related Databases
| Title | Method to Assess the Temporal Persistence of Potential Biometric Features: Application to Oculomotor, and Gait-Related Databases |
| Authors | Lee Friedman, Ioannis Rigas, Mark S. Nixon, Oleg V. Komogortsev |
| Abstract | Although temporal persistence, or permanence, is a well understood requirement for optimal biometric features, there is no general agreement on how to assess temporal persistence. We suggest that the best way to assess temporal persistence is to perform a test-retest study, and assess test-retest reliability. For ratio-scale features that are normally distributed, this is best done using the Intraclass Correlation Coefficient (ICC). For 10 distinct data sets (8 eye-movement related, and 2 gait related), we calculated the test-retest reliability (‘Temporal persistence’) of each feature, and compared biometric performance of high-ICC features to lower ICC features, and to the set of all features. We demonstrate that using a subset of only high-ICC features produced superior Rank-1-Identification Rate (Rank-1-IR) performance in 9 of 10 databases (p = 0.01, one-tailed). For Equal Error Rate (EER), using a subset of only high-ICC features produced superior performance in 8 of 10 databases (p = 0.055, one-tailed). In general, then, prescreening potential biometric features, and choosing only highly reliable features will yield better performance than lower ICC features or than the set of all features combined. We hypothesize that this would likely be the case for any biometric modality where the features can be expressed as quantitative values on an interval or ratio scale, assuming an adequate number of relatively independent features. |
| Tasks | |
| Published | 2016-09-13 |
| URL | http://arxiv.org/abs/1609.03948v1 |
| http://arxiv.org/pdf/1609.03948v1.pdf | |
| PWC | https://paperswithcode.com/paper/method-to-assess-the-temporal-persistence-of |
| Repo | |
| Framework | |
Neither Quick Nor Proper – Evaluation of QuickProp for Learning Deep Neural Networks
| Title | Neither Quick Nor Proper – Evaluation of QuickProp for Learning Deep Neural Networks |
| Authors | Clemens-Alexander Brust, Sven Sickert, Marcel Simon, Erik Rodner, Joachim Denzler |
| Abstract | Neural networks and especially convolutional neural networks are of great interest in current computer vision research. However, many techniques, extensions, and modifications have been published in the past, which are not yet used by current approaches. In this paper, we study the application of a method called QuickProp for training of deep neural networks. In particular, we apply QuickProp during learning and testing of fully convolutional networks for the task of semantic segmentation. We compare QuickProp empirically with gradient descent, which is the current standard method. Experiments suggest that QuickProp can not compete with standard gradient descent techniques for complex computer vision tasks like semantic segmentation. |
| Tasks | Semantic Segmentation |
| Published | 2016-06-14 |
| URL | http://arxiv.org/abs/1606.04333v2 |
| http://arxiv.org/pdf/1606.04333v2.pdf | |
| PWC | https://paperswithcode.com/paper/neither-quick-nor-proper-evaluation-of |
| Repo | |
| Framework | |
Optical Flow with Semantic Segmentation and Localized Layers
| Title | Optical Flow with Semantic Segmentation and Localized Layers |
| Authors | Laura Sevilla-Lara, Deqing Sun, Varun Jampani, Michael J. Black |
| Abstract | Existing optical flow methods make generic, spatially homogeneous, assumptions about the spatial structure of the flow. In reality, optical flow varies across an image depending on object class. Simply put, different objects move differently. Here we exploit recent advances in static semantic scene segmentation to segment the image into objects of different types. We define different models of image motion in these regions depending on the type of object. For example, we model the motion on roads with homographies, vegetation with spatially smooth flow, and independently moving objects like cars and planes with affine motion plus deviations. We then pose the flow estimation problem using a novel formulation of localized layers, which addresses limitations of traditional layered models for dealing with complex scene motion. Our semantic flow method achieves the lowest error of any published monocular method in the KITTI-2015 flow benchmark and produces qualitatively better flow and segmentation than recent top methods on a wide range of natural videos. |
| Tasks | Optical Flow Estimation, Scene Segmentation, Semantic Segmentation |
| Published | 2016-03-12 |
| URL | http://arxiv.org/abs/1603.03911v2 |
| http://arxiv.org/pdf/1603.03911v2.pdf | |
| PWC | https://paperswithcode.com/paper/optical-flow-with-semantic-segmentation-and |
| Repo | |
| Framework | |
Connecting the dots across time: Reconstruction of single cell signaling trajectories using time-stamped data
| Title | Connecting the dots across time: Reconstruction of single cell signaling trajectories using time-stamped data |
| Authors | Sayak Mukherjee, David Stewart, William Stewart, Lewis L. Lanier, Jayajit Das |
| Abstract | Single cell responses are shaped by the geometry of signaling kinetic trajectories carved in a multidimensional space spanned by signaling protein abundances. It is however challenging to assay large number (>3) of signaling species in live-cell imaging which makes it difficult to probe single cell signaling kinetic trajectories in large dimensions. Flow and mass cytometry techniques can measure a large number (4 - >40) of signaling species but are unable to track single cells. Thus cytometry experiments provide detailed time stamped snapshots of single cell signaling kinetics. Is it possible to use the time stamped cytometry data to reconstruct single cell signaling trajectories? Borrowing concepts of conserved and slow variables from non-equilibrium statistical physics we develop an approach to reconstruct signaling trajectories using snapshot data by creating new variables that remain invariant or vary slowly during the signaling kinetics. We apply this approach to reconstruct trajectories using snapshot data obtained from in silico simulations and live-cell imaging measurements. The use of invariants and slow variables to reconstruct trajectories provides a radically different way to track object using snapshot data. The approach is likely to have implications for solving matching problems in a wide range of disciplines. |
| Tasks | |
| Published | 2016-09-26 |
| URL | http://arxiv.org/abs/1609.08035v2 |
| http://arxiv.org/pdf/1609.08035v2.pdf | |
| PWC | https://paperswithcode.com/paper/connecting-the-dots-across-time |
| Repo | |
| Framework | |
Solution of linear ill-posed problems using random dictionaries
| Title | Solution of linear ill-posed problems using random dictionaries |
| Authors | Pawan Gupta, Marianna Pensky |
| Abstract | In the present paper we consider application of overcomplete dictionaries to solution of general ill-posed linear inverse problems. In the context of regression problems, there has been enormous amount of effort to recover an unknown function using such dictionaries. One of the most popular methods, lasso and its versions, is based on minimizing empirical likelihood and unfortunately, requires stringent assumptions on the dictionary, the, so called, compatibility conditions. Though compatibility conditions are hard to satisfy, it is well known that this can be accomplished by using random dictionaries. In the present paper, we show how one can apply random dictionaries to solution of ill-posed linear inverse problems. We put a theoretical foundation under the suggested methodology and study its performance via simulations. |
| Tasks | |
| Published | 2016-05-25 |
| URL | http://arxiv.org/abs/1605.07913v3 |
| http://arxiv.org/pdf/1605.07913v3.pdf | |
| PWC | https://paperswithcode.com/paper/solution-of-linear-ill-posed-problems-using |
| Repo | |
| Framework | |
Tangled Splines
| Title | Tangled Splines |
| Authors | Aditya Tatu |
| Abstract | Extracting shape information from object bound- aries is a well studied problem in vision, and has found tremen- dous use in applications like object recognition. Conversely, studying the space of shapes represented by curves satisfying certain constraints is also intriguing. In this paper, we model and analyze the space of shapes represented by a 3D curve (space curve) formed by connecting n pieces of quarter of a unit circle. Such a space curve is what we call a Tangle, the name coming from a toy built on the same principle. We provide two models for the shape space of n-link open and closed tangles, and we show that tangles are a subset of trigonometric splines of a certain order. We give algorithms for curve approximation using open/closed tangles, computing geodesics on these shape spaces, and to find the deformation that takes one given tangle to another given tangle, i.e., the Log map. The algorithms provided yield tangles upto a small and acceptable tolerance, as shown by the results given in the paper. |
| Tasks | Object Recognition |
| Published | 2016-10-10 |
| URL | http://arxiv.org/abs/1610.03129v1 |
| http://arxiv.org/pdf/1610.03129v1.pdf | |
| PWC | https://paperswithcode.com/paper/tangled-splines |
| Repo | |
| Framework | |
DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks
| Title | DeepCut: Object Segmentation from Bounding Box Annotations using Convolutional Neural Networks |
| Authors | Martin Rajchl, Matthew C. H. Lee, Ozan Oktay, Konstantinos Kamnitsas, Jonathan Passerat-Palmbach, Wenjia Bai, Mellisa Damodaram, Mary A. Rutherford, Joseph V. Hajnal, Bernhard Kainz, Daniel Rueckert |
| Abstract | In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled with bounding box annotations. It extends the approach of the well-known GrabCut method to include machine learning by training a neural network classifier from bounding box annotations. We formulate the problem as an energy minimisation problem over a densely-connected conditional random field and iteratively update the training targets to obtain pixelwise object segmentations. Additionally, we propose variants of the DeepCut method and compare those to a naive approach to CNN training under weak supervision. We test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset and obtain encouraging results in terms of accuracy. |
| Tasks | Semantic Segmentation |
| Published | 2016-05-25 |
| URL | http://arxiv.org/abs/1605.07866v2 |
| http://arxiv.org/pdf/1605.07866v2.pdf | |
| PWC | https://paperswithcode.com/paper/deepcut-object-segmentation-from-bounding-box |
| Repo | |
| Framework | |
Exploiting variable associations to configure efficient local search algorithms in large-scale binary integer programs
| Title | Exploiting variable associations to configure efficient local search algorithms in large-scale binary integer programs |
| Authors | Shunji Umetani |
| Abstract | We present a data mining approach for reducing the search space of local search algorithms in a class of binary integer programs including the set covering and partitioning problems. The quality of locally optimal solutions typically improves if a larger neighborhood is used, while the computation time of searching the neighborhood increases exponentially. To overcome this, we extract variable associations from the instance to be solved in order to identify promising pairs of flipping variables in the neighborhood search. Based on this, we develop a 4-flip neighborhood local search algorithm that incorporates an efficient incremental evaluation of solutions and an adaptive control of penalty weights. Computational results show that the proposed method improves the performance of the local search algorithm for large-scale set covering and partitioning problems. |
| Tasks | |
| Published | 2016-04-28 |
| URL | http://arxiv.org/abs/1604.08448v2 |
| http://arxiv.org/pdf/1604.08448v2.pdf | |
| PWC | https://paperswithcode.com/paper/exploiting-variable-associations-to-configure |
| Repo | |
| Framework | |
Truncated Variational Expectation Maximization
| Title | Truncated Variational Expectation Maximization |
| Authors | Jörg Lücke |
| Abstract | We derive a novel variational expectation maximization approach based on truncated posterior distributions. Truncated distributions are proportional to exact posteriors within subsets of a discrete state space and equal zero otherwise. The treatment of the distributions’ subsets as variational parameters distinguishes the approach from previous variational approaches. The specific structure of truncated distributions allows for deriving novel and mathematically grounded results, which in turn can be used to formulate novel efficient algorithms to optimize the parameters of probabilistic generative models. Most centrally, we find the variational lower bounds that correspond to truncated distributions to be given by very concise and efficiently computable expressions, while update equations for model parameters remain in their standard form. Based on these findings, we show how efficient and easily applicable meta-algorithms can be formulated that guarantee a monotonic increase of the variational bound. Example applications of the here derived framework provide novel theoretical results and learning procedures for latent variable models as well as mixture models. Furthermore, we show that truncated variation EM naturally interpolates between standard EM with full posteriors and EM based on the maximum a-posteriori state (MAP). The approach can, therefore, be regarded as a generalization of the popular `hard EM’ approach towards a similarly efficient method which can capture more of the true posterior structure. | |
| Tasks | Latent Variable Models |
| Published | 2016-10-10 |
| URL | https://arxiv.org/abs/1610.03113v3 |
| https://arxiv.org/pdf/1610.03113v3.pdf | |
| PWC | https://paperswithcode.com/paper/truncated-variational-expectation |
| Repo | |
| Framework | |
Toward Word Embedding for Personalized Information Retrieval
| Title | Toward Word Embedding for Personalized Information Retrieval |
| Authors | Nawal Ould-Amer, Philippe Mulhem, Mathias Gery |
| Abstract | This paper presents preliminary works on using Word Embedding (word2vec) for query expansion in the context of Personalized Information Retrieval. Traditionally, word embeddings are learned on a general corpus, like Wikipedia. In this work we try to personalize the word embeddings learning, by achieving the learning on the user’s profile. The word embeddings are then in the same context than the user interests. Our proposal is evaluated on the CLEF Social Book Search 2016 collection. The results obtained show that some efforts should be made in the way to apply Word Embedding in the context of Personalized Information Retrieval. |
| Tasks | Information Retrieval, Word Embeddings |
| Published | 2016-06-22 |
| URL | http://arxiv.org/abs/1606.06991v1 |
| http://arxiv.org/pdf/1606.06991v1.pdf | |
| PWC | https://paperswithcode.com/paper/toward-word-embedding-for-personalized |
| Repo | |
| Framework | |
Variational Inference with Hamiltonian Monte Carlo
| Title | Variational Inference with Hamiltonian Monte Carlo |
| Authors | Christopher Wolf, Maximilian Karl, Patrick van der Smagt |
| Abstract | Variational inference lies at the core of many state-of-the-art algorithms. To improve the approximation of the posterior beyond parametric families, it was proposed to include MCMC steps into the variational lower bound. In this work we explore this idea using steps of the Hamiltonian Monte Carlo (HMC) algorithm, an efficient MCMC method. In particular, we incorporate the acceptance step of the HMC algorithm, guaranteeing asymptotic convergence to the true posterior. Additionally, we introduce some extensions to the HMC algorithm geared towards faster convergence. The theoretical advantages of these modifications are reflected by performance improvements in our experimental results. |
| Tasks | |
| Published | 2016-09-26 |
| URL | http://arxiv.org/abs/1609.08203v1 |
| http://arxiv.org/pdf/1609.08203v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-inference-with-hamiltonian-monte |
| Repo | |
| Framework | |
Learning from Imbalanced Multiclass Sequential Data Streams Using Dynamically Weighted Conditional Random Fields
| Title | Learning from Imbalanced Multiclass Sequential Data Streams Using Dynamically Weighted Conditional Random Fields |
| Authors | Roberto L. Shinmoto Torres, Damith C. Ranasinghe, Qinfeng Shi, Anton van den Hengel |
| Abstract | The present study introduces a method for improving the classification performance of imbalanced multiclass data streams from wireless body worn sensors. Data imbalance is an inherent problem in activity recognition caused by the irregular time distribution of activities, which are sequential and dependent on previous movements. We use conditional random fields (CRF), a graphical model for structured classification, to take advantage of dependencies between activities in a sequence. However, CRFs do not consider the negative effects of class imbalance during training. We propose a class-wise dynamically weighted CRF (dWCRF) where weights are automatically determined during training by maximizing the expected overall F-score. Our results based on three case studies from a healthcare application using a batteryless body worn sensor, demonstrate that our method, in general, improves overall and minority class F-score when compared to other CRF based classifiers and achieves similar or better overall and class-wise performance when compared to SVM based classifiers under conditions of limited training data. We also confirm the performance of our approach using an additional battery powered body worn sensor dataset, achieving similar results in cases of high class imbalance. |
| Tasks | Activity Recognition |
| Published | 2016-03-11 |
| URL | http://arxiv.org/abs/1603.03627v1 |
| http://arxiv.org/pdf/1603.03627v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-imbalanced-multiclass |
| Repo | |
| Framework | |
Demand Prediction and Placement Optimization for Electric Vehicle Charging Stations
| Title | Demand Prediction and Placement Optimization for Electric Vehicle Charging Stations |
| Authors | Ragavendran Gopalakrishnan, Arpita Biswas, Alefiya Lightwala, Skanda Vasudevan, Partha Dutta, Abhishek Tripathi |
| Abstract | Effective placement of charging stations plays a key role in Electric Vehicle (EV) adoption. In the placement problem, given a set of candidate sites, an optimal subset needs to be selected with respect to the concerns of both (a) the charging station service provider, such as the demand at the candidate sites and the budget for deployment, and (b) the EV user, such as charging station reachability and short waiting times at the station. This work addresses these concerns, making the following three novel contributions: (i) a supervised multi-view learning framework using Canonical Correlation Analysis (CCA) for demand prediction at candidate sites, using multiple datasets such as points of interest information, traffic density, and the historical usage at existing charging stations; (ii) a mixed-packing-and- covering optimization framework that models competing concerns of the service provider and EV users; (iii) an iterative heuristic to solve these problems by alternately invoking knapsack and set cover algorithms. The performance of the demand prediction model and the placement optimization heuristic are evaluated using real world data. |
| Tasks | MULTI-VIEW LEARNING |
| Published | 2016-04-19 |
| URL | http://arxiv.org/abs/1604.05472v2 |
| http://arxiv.org/pdf/1604.05472v2.pdf | |
| PWC | https://paperswithcode.com/paper/demand-prediction-and-placement-optimization |
| Repo | |
| Framework | |
Semi-automatic Simultaneous Interpreting Quality Evaluation
| Title | Semi-automatic Simultaneous Interpreting Quality Evaluation |
| Authors | Xiaojun Zhang |
| Abstract | Increasing interpreting needs a more objective and automatic measurement. We hold a basic idea that ‘translating means translating meaning’ in that we can assessment interpretation quality by comparing the meaning of the interpreting output with the source input. That is, a translation unit of a ‘chunk’ named Frame which comes from frame semantics and its components named Frame Elements (FEs) which comes from Frame Net are proposed to explore their matching rate between target and source texts. A case study in this paper verifies the usability of semi-automatic graded semantic-scoring measurement for human simultaneous interpreting and shows how to use frame and FE matches to score. Experiments results show that the semantic-scoring metrics have a significantly correlation coefficient with human judgment. |
| Tasks | |
| Published | 2016-11-12 |
| URL | http://arxiv.org/abs/1611.04052v1 |
| http://arxiv.org/pdf/1611.04052v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-automatic-simultaneous-interpreting |
| Repo | |
| Framework | |
