Paper Group ANR 349
KS_JU@DPIL-FIRE2016:Detecting Paraphrases in Indian Languages Using Multinomial Logistic Regression Model. Learning to Perform Physics Experiments via Deep Reinforcement Learning. Gaze2Segment: A Pilot Study for Integrating Eye-Tracking Technology into Medical Image Segmentation. Variables effecting photomosaic reconstruction and ortho-rectificatio …
KS_JU@DPIL-FIRE2016:Detecting Paraphrases in Indian Languages Using Multinomial Logistic Regression Model
| Title | KS_JU@DPIL-FIRE2016:Detecting Paraphrases in Indian Languages Using Multinomial Logistic Regression Model |
| Authors | Kamal Sarkar |
| Abstract | In this work, we describe a system that detects paraphrases in Indian Languages as part of our participation in the shared Task on detecting paraphrases in Indian Languages (DPIL) organized by Forum for Information Retrieval Evaluation (FIRE) in 2016. Our paraphrase detection method uses a multinomial logistic regression model trained with a variety of features which are basically lexical and semantic level similarities between two sentences in a pair. The performance of the system has been evaluated against the test set released for the FIRE 2016 shared task on DPIL. Our system achieves the highest f-measure of 0.95 on task1 in Punjabi language.The performance of our system on task1 in Hindi language is f-measure of 0.90. Out of 11 teams participated in the shared task, only four teams participated in all four languages, Hindi, Punjabi, Malayalam and Tamil, but the remaining 7 teams participated in one of the four languages. We also participated in task1 and task2 both for all four Indian Languages. The overall average performance of our system including task1 and task2 overall four languages is F1-score of 0.81 which is the second highest score among the four systems that participated in all four languages. |
| Tasks | Information Retrieval |
| Published | 2016-12-24 |
| URL | http://arxiv.org/abs/1612.08171v1 |
| http://arxiv.org/pdf/1612.08171v1.pdf | |
| PWC | https://paperswithcode.com/paper/ks_judpil-fire2016detecting-paraphrases-in |
| Repo | |
| Framework | |
Learning to Perform Physics Experiments via Deep Reinforcement Learning
| Title | Learning to Perform Physics Experiments via Deep Reinforcement Learning |
| Authors | Misha Denil, Pulkit Agrawal, Tejas D Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas |
| Abstract | When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way. This process of active interaction is in the same spirit as a scientist performing experiments to discover hidden facts. Recent advances in artificial intelligence have yielded machines that can achieve superhuman performance in Go, Atari, natural language processing, and complex control problems; however, it is not clear that these systems can rival the scientific intuition of even a young child. In this work we introduce a basic set of tasks that require agents to estimate properties such as mass and cohesion of objects in an interactive simulated environment where they can manipulate the objects and observe the consequences. We found that state of art deep reinforcement learning methods can learn to perform the experiments necessary to discover such hidden properties. By systematically manipulating the problem difficulty and the cost incurred by the agent for performing experiments, we found that agents learn different strategies that balance the cost of gathering information against the cost of making mistakes in different situations. |
| Tasks | |
| Published | 2016-11-06 |
| URL | http://arxiv.org/abs/1611.01843v3 |
| http://arxiv.org/pdf/1611.01843v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-perform-physics-experiments-via |
| Repo | |
| Framework | |
Gaze2Segment: A Pilot Study for Integrating Eye-Tracking Technology into Medical Image Segmentation
| Title | Gaze2Segment: A Pilot Study for Integrating Eye-Tracking Technology into Medical Image Segmentation |
| Authors | Naji Khosravan, Haydar Celik, Baris Turkbey, Ruida Cheng, Evan McCreedy, Matthew McAuliffe, Sandra Bednarova, Elizabeth Jones, Xinjian Chen, Peter L. Choyke, Bradford J. Wood, Ulas Bagci |
| Abstract | This study introduced a novel system, called Gaze2Segment, integrating biological and computer vision techniques to support radiologists’ reading experience with an automatic image segmentation task. During diagnostic assessment of lung CT scans, the radiologists’ gaze information were used to create a visual attention map. This map was then combined with a computer-derived saliency map, extracted from the gray-scale CT images. The visual attention map was used as an input for indicating roughly the location of a object of interest. With computer-derived saliency information, on the other hand, we aimed at finding foreground and background cues for the object of interest. At the final step, these cues were used to initiate a seed-based delineation process. Segmentation accuracy of the proposed Gaze2Segment was found to be 86% with dice similarity coefficient and 1.45 mm with Hausdorff distance. To the best of our knowledge, Gaze2Segment is the first true integration of eye-tracking technology into a medical image segmentation task without the need for any further user-interaction. |
| Tasks | Eye Tracking, Medical Image Segmentation, Semantic Segmentation |
| Published | 2016-08-10 |
| URL | http://arxiv.org/abs/1608.03235v1 |
| http://arxiv.org/pdf/1608.03235v1.pdf | |
| PWC | https://paperswithcode.com/paper/gaze2segment-a-pilot-study-for-integrating |
| Repo | |
| Framework | |
Variables effecting photomosaic reconstruction and ortho-rectification from aerial survey datasets
| Title | Variables effecting photomosaic reconstruction and ortho-rectification from aerial survey datasets |
| Authors | Jonathan Byrne, Debra Laefer |
| Abstract | Unmanned aerial vehicles now make it possible to obtain high quality aerial imagery at a low cost, but processing those images into a single, useful entity is neither simple nor seamless. Specifically, there are factors that must be addressed when merging multiple images into a single coherent one. While ortho-rectification can be done, it tends to be expensive and time consuming. Image stitching offers a more economical, low-tech approach. However direct application tends to fail for low-elevation imagery due to one or more factors including insufficient keypoints, parallax issues, and homogeneity of the surveyed area. This paper discusses these problems and possible solutions when using techniques such as image stitching and structure from motion for generating ortho-rectified imagery. These are presented in terms of actual Irish projects including the Boland’s Mills building in Dublin’s city centre, the Kilmoon Cross Farm, and the Richview buildings on the University College Dublin campus. Implications for various Irish industries are explained in terms of both urban and rural projects. |
| Tasks | Image Stitching |
| Published | 2016-11-10 |
| URL | http://arxiv.org/abs/1611.03318v1 |
| http://arxiv.org/pdf/1611.03318v1.pdf | |
| PWC | https://paperswithcode.com/paper/variables-effecting-photomosaic |
| Repo | |
| Framework | |
Screen Content Image Segmentation Using Robust Regression and Sparse Decomposition
| Title | Screen Content Image Segmentation Using Robust Regression and Sparse Decomposition |
| Authors | Shervin Minaee, Yao Wang |
| Abstract | This paper considers how to separate text and/or graphics from smooth background in screen content and mixed document images and proposes two approaches to perform this segmentation task. The proposed methods make use of the fact that the background in each block is usually smoothly varying and can be modeled well by a linear combination of a few smoothly varying basis functions, while the foreground text and graphics create sharp discontinuity. The algorithms separate the background and foreground pixels by trying to fit background pixel values in the block into a smooth function using two different schemes. One is based on robust regression, where the inlier pixels will be considered as background, while remaining outlier pixels will be considered foreground. The second approach uses a sparse decomposition framework where the background and foreground layers are modeled with a smooth and sparse components respectively. These algorithms have been tested on images extracted from HEVC standard test sequences for screen content coding, and are shown to have superior performance over previous approaches. The proposed methods can be used in different applications such as text extraction, separate coding of background and foreground for compression of screen content, and medical image segmentation. |
| Tasks | Medical Image Segmentation, Semantic Segmentation |
| Published | 2016-07-08 |
| URL | http://arxiv.org/abs/1607.02547v1 |
| http://arxiv.org/pdf/1607.02547v1.pdf | |
| PWC | https://paperswithcode.com/paper/screen-content-image-segmentation-using |
| Repo | |
| Framework | |
Measuring and Predicting Tag Importance for Image Retrieval
| Title | Measuring and Predicting Tag Importance for Image Retrieval |
| Authors | Shangwen Li, Sanjay Purushotham, Chen Chen, Yuzhuo Ren, C. -C. Jay Kuo |
| Abstract | Textual data such as tags, sentence descriptions are combined with visual cues to reduce the semantic gap for image retrieval applications in today’s Multimodal Image Retrieval (MIR) systems. However, all tags are treated as equally important in these systems, which may result in misalignment between visual and textual modalities during MIR training. This will further lead to degenerated retrieval performance at query time. To address this issue, we investigate the problem of tag importance prediction, where the goal is to automatically predict the tag importance and use it in image retrieval. To achieve this, we first propose a method to measure the relative importance of object and scene tags from image sentence descriptions. Using this as the ground truth, we present a tag importance prediction model to jointly exploit visual, semantic and context cues. The Structural Support Vector Machine (SSVM) formulation is adopted to ensure efficient training of the prediction model. Then, the Canonical Correlation Analysis (CCA) is employed to learn the relation between the image visual feature and tag importance to obtain robust retrieval performance. Experimental results on three real-world datasets show a significant performance improvement of the proposed MIR with Tag Importance Prediction (MIR/TIP) system over other MIR systems. |
| Tasks | Image Retrieval |
| Published | 2016-02-28 |
| URL | http://arxiv.org/abs/1602.08680v3 |
| http://arxiv.org/pdf/1602.08680v3.pdf | |
| PWC | https://paperswithcode.com/paper/measuring-and-predicting-tag-importance-for |
| Repo | |
| Framework | |
Inferring object rankings based on noisy pairwise comparisons from multiple annotators
| Title | Inferring object rankings based on noisy pairwise comparisons from multiple annotators |
| Authors | Rahul Gupta, Shrikanth Narayanan |
| Abstract | Ranking a set of objects involves establishing an order allowing for comparisons between any pair of objects in the set. Oftentimes, due to the unavailability of a ground truth of ranked orders, researchers resort to obtaining judgments from multiple annotators followed by inferring the ground truth based on the collective knowledge of the crowd. However, the aggregation is often ad-hoc and involves imposing stringent assumptions in inferring the ground truth (e.g. majority vote). In this work, we propose Expectation-Maximization (EM) based algorithms that rely on the judgments from multiple annotators and the object attributes for inferring the latent ground truth. The algorithm learns the relation between the latent ground truth and object attributes as well as annotator specific probabilities of flipping, a metric to assess annotator quality. We further extend the EM algorithm to allow for a variable probability of flipping based on the pair of objects at hand. We test our algorithms on two data sets with synthetic annotations and investigate the impact of annotator quality and quantity on the inferred ground truth. We also obtain the results on two other data sets with annotations from machine/human annotators and interpret the output trends based on the data characteristics. |
| Tasks | |
| Published | 2016-12-13 |
| URL | http://arxiv.org/abs/1612.04413v1 |
| http://arxiv.org/pdf/1612.04413v1.pdf | |
| PWC | https://paperswithcode.com/paper/inferring-object-rankings-based-on-noisy |
| Repo | |
| Framework | |
Image stitching with perspective-preserving warping
| Title | Image stitching with perspective-preserving warping |
| Authors | Tianzhu Xiang, Gui-Song Xia, Liangpei Zhang |
| Abstract | Image stitching algorithms often adopt the global transformation, such as homography, and work well for planar scenes or parallax free camera motions. However, these conditions are easily violated in practice. With casual camera motions, variable taken views, large depth change, or complex structures, it is a challenging task for stitching these images. The global transformation model often provides dreadful stitching results, such as misalignments or projective distortions, especially perspective distortion. To this end, we suggest a perspective-preserving warping for image stitching, which spatially combines local projective transformations and similarity transformation. By weighted combination scheme, our approach gradually extrapolates the local projective transformations of the overlapping regions into the non-overlapping regions, and thus the final warping can smoothly change from projective to similarity. The proposed method can provide satisfactory alignment accuracy as well as reduce the projective distortions and maintain the multi-perspective view. Experiments on a variety of challenging images confirm the efficiency of the approach. |
| Tasks | Image Stitching |
| Published | 2016-05-17 |
| URL | http://arxiv.org/abs/1605.05019v1 |
| http://arxiv.org/pdf/1605.05019v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-stitching-with-perspective-preserving |
| Repo | |
| Framework | |
Sex, drugs, and violence
| Title | Sex, drugs, and violence |
| Authors | Stefania Raimondo, Frank Rudzicz |
| Abstract | Automatically detecting inappropriate content can be a difficult NLP task, requiring understanding context and innuendo, not just identifying specific keywords. Due to the large quantity of online user-generated content, automatic detection is becoming increasingly necessary. We take a largely unsupervised approach using a large corpus of narratives from a community-based self-publishing website and a small segment of crowd-sourced annotations. We explore topic modelling using latent Dirichlet allocation (and a variation), and use these to regress appropriateness ratings, effectively automating rating for suitability. The results suggest that certain topics inferred may be useful in detecting latent inappropriateness – yielding recall up to 96% and low regression errors. |
| Tasks | |
| Published | 2016-08-11 |
| URL | http://arxiv.org/abs/1608.03448v1 |
| http://arxiv.org/pdf/1608.03448v1.pdf | |
| PWC | https://paperswithcode.com/paper/sex-drugs-and-violence |
| Repo | |
| Framework | |
A Grassmannian Graph Approach to Affine Invariant Feature Matching
| Title | A Grassmannian Graph Approach to Affine Invariant Feature Matching |
| Authors | Mark Moyou, John Corring, Adrian Peter, Anand Rangarajan |
| Abstract | In this work, we present a novel and practical approach to address one of the longstanding problems in computer vision: 2D and 3D affine invariant feature matching. Our Grassmannian Graph (GrassGraph) framework employs a two stage procedure that is capable of robustly recovering correspondences between two unorganized, affinely related feature (point) sets. The first stage maps the feature sets to an affine invariant Grassmannian representation, where the features are mapped into the same subspace. It turns out that coordinate representations extracted from the Grassmannian differ by an arbitrary orthonormal matrix. In the second stage, by approximating the Laplace-Beltrami operator (LBO) on these coordinates, this extra orthonormal factor is nullified, providing true affine-invariant coordinates which we then utilize to recover correspondences via simple nearest neighbor relations. The resulting GrassGraph algorithm is empirically shown to work well in non-ideal scenarios with noise, outliers, and occlusions. Our validation benchmarks use an unprecedented 440,000+ experimental trials performed on 2D and 3D datasets, with a variety of parameter settings and competing methods. State-of-the-art performance in the majority of these extensive evaluations confirm the utility of our method. |
| Tasks | |
| Published | 2016-01-28 |
| URL | http://arxiv.org/abs/1601.07648v2 |
| http://arxiv.org/pdf/1601.07648v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-grassmannian-graph-approach-to-affine |
| Repo | |
| Framework | |
Combinatorial Topic Models using Small-Variance Asymptotics
| Title | Combinatorial Topic Models using Small-Variance Asymptotics |
| Authors | Ke Jiang, Suvrit Sra, Brian Kulis |
| Abstract | Topic models have emerged as fundamental tools in unsupervised machine learning. Most modern topic modeling algorithms take a probabilistic view and derive inference algorithms based on Latent Dirichlet Allocation (LDA) or its variants. In contrast, we study topic modeling as a combinatorial optimization problem, and propose a new objective function derived from LDA by passing to the small-variance limit. We minimize the derived objective by using ideas from combinatorial optimization, which results in a new, fast, and high-quality topic modeling algorithm. In particular, we show that our results are competitive with popular LDA-based topic modeling approaches, and also discuss the (dis)similarities between our approach and its probabilistic counterparts. |
| Tasks | Combinatorial Optimization, Topic Models |
| Published | 2016-04-07 |
| URL | http://arxiv.org/abs/1604.02027v2 |
| http://arxiv.org/pdf/1604.02027v2.pdf | |
| PWC | https://paperswithcode.com/paper/combinatorial-topic-models-using-small |
| Repo | |
| Framework | |
Incorporating prior knowledge in medical image segmentation: a survey
| Title | Incorporating prior knowledge in medical image segmentation: a survey |
| Authors | Masoud S. Nosrati, Ghassan Hamarneh |
| Abstract | Medical image segmentation, the task of partitioning an image into meaningful parts, is an important step toward automating medical image analysis and is at the crux of a variety of medical imaging applications, such as computer aided diagnosis, therapy planning and delivery, and computer aided interventions. However, the existence of noise, low contrast and objects’ complexity in medical images are critical obstacles that stand in the way of achieving an ideal segmentation system. Incorporating prior knowledge into image segmentation algorithms has proven useful for obtaining more accurate and plausible results. This paper surveys the different types of prior knowledge that have been utilized in different segmentation frameworks. We focus our survey on optimization-based methods that incorporate prior information into their frameworks. We review and compare these methods in terms of the types of prior employed, the domain of formulation (continuous vs. discrete), and the optimization techniques (global vs. local). We also created an interactive online database of existing works and categorized them based on the type of prior knowledge they use. Our website is interactive so that researchers can contribute to keep the database up to date. We conclude the survey by discussing different aspects of designing an energy functional for image segmentation, open problems, and future perspectives. |
| Tasks | Medical Image Segmentation, Semantic Segmentation |
| Published | 2016-07-05 |
| URL | http://arxiv.org/abs/1607.01092v1 |
| http://arxiv.org/pdf/1607.01092v1.pdf | |
| PWC | https://paperswithcode.com/paper/incorporating-prior-knowledge-in-medical |
| Repo | |
| Framework | |
Efficient iterative policy optimization
| Title | Efficient iterative policy optimization |
| Authors | Nicolas Le Roux |
| Abstract | We tackle the issue of finding a good policy when the number of policy updates is limited. This is done by approximating the expected policy reward as a sequence of concave lower bounds which can be efficiently maximized, drastically reducing the number of policy updates required to achieve good performance. We also extend existing methods to negative rewards, enabling the use of control variates. |
| Tasks | |
| Published | 2016-12-28 |
| URL | http://arxiv.org/abs/1612.08967v1 |
| http://arxiv.org/pdf/1612.08967v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-iterative-policy-optimization |
| Repo | |
| Framework | |
Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much
| Title | Scan Order in Gibbs Sampling: Models in Which it Matters and Bounds on How Much |
| Authors | Bryan He, Christopher De Sa, Ioannis Mitliagkas, Christopher Ré |
| Abstract | Gibbs sampling is a Markov Chain Monte Carlo sampling technique that iteratively samples variables from their conditional distributions. There are two common scan orders for the variables: random scan and systematic scan. Due to the benefits of locality in hardware, systematic scan is commonly used, even though most statistical guarantees are only for random scan. While it has been conjectured that the mixing times of random scan and systematic scan do not differ by more than a logarithmic factor, we show by counterexample that this is not the case, and we prove that that the mixing times do not differ by more than a polynomial factor under mild conditions. To prove these relative bounds, we introduce a method of augmenting the state space to study systematic scan using conductance. |
| Tasks | |
| Published | 2016-06-10 |
| URL | http://arxiv.org/abs/1606.03432v1 |
| http://arxiv.org/pdf/1606.03432v1.pdf | |
| PWC | https://paperswithcode.com/paper/scan-order-in-gibbs-sampling-models-in-which |
| Repo | |
| Framework | |
DimensionApp : android app to estimate object dimensions
| Title | DimensionApp : android app to estimate object dimensions |
| Authors | Suriya Singh, Vijay Kumar |
| Abstract | In this project, we develop an android app that uses on computer vision techniques to estimate an object dimension present in field of view. The app while having compact size, is accurate upto +/- 5 mm and robust towards touch inputs. We use single-view metrology to compute accurate measurement. Unlike previous approaches, our technique does not rely on line detection and can be generalize to any object shape easily. |
| Tasks | |
| Published | 2016-09-24 |
| URL | http://arxiv.org/abs/1609.07597v1 |
| http://arxiv.org/pdf/1609.07597v1.pdf | |
| PWC | https://paperswithcode.com/paper/dimensionapp-android-app-to-estimate-object |
| Repo | |
| Framework | |
