Paper Group ANR 533
Human Pose Estimation in Space and Time using 3D CNN. Efficient Calculation of Bigram Frequencies in a Corpus of Short Texts. Detection and Visualization of Endoleaks in CT Data for Monitoring of Thoracic and Abdominal Aortic Aneurysm Stents. Evaluating Urbanization from Satellite and Aerial Images by means of a statistical approach to the texture …
Human Pose Estimation in Space and Time using 3D CNN
| Title | Human Pose Estimation in Space and Time using 3D CNN |
| Authors | Agne Grinciunaite, Amogh Gudi, Emrah Tasli, Marten den Uyl |
| Abstract | This paper explores the capabilities of convolutional neural networks to deal with a task that is easily manageable for humans: perceiving 3D pose of a human body from varying angles. However, in our approach, we are restricted to using a monocular vision system. For this purpose, we apply a convolutional neural network approach on RGB videos and extend it to three dimensional convolutions. This is done via encoding the time dimension in videos as the 3\ts{rd} dimension in convolutional space, and directly regressing to human body joint positions in 3D coordinate space. This research shows the ability of such a network to achieve state-of-the-art performance on the selected Human3.6M dataset, thus demonstrating the possibility of successfully representing temporal data with an additional dimension in the convolutional operation. |
| Tasks | Pose Estimation |
| Published | 2016-08-31 |
| URL | http://arxiv.org/abs/1609.00036v3 |
| http://arxiv.org/pdf/1609.00036v3.pdf | |
| PWC | https://paperswithcode.com/paper/human-pose-estimation-in-space-and-time-using |
| Repo | |
| Framework | |
Efficient Calculation of Bigram Frequencies in a Corpus of Short Texts
| Title | Efficient Calculation of Bigram Frequencies in a Corpus of Short Texts |
| Authors | Melvyn Drag, Gauthaman Vasudevan |
| Abstract | We show that an efficient and popular method for calculating bigram frequencies is unsuitable for bodies of short texts and offer a simple alternative. Our method has the same computational complexity as the old method and offers an exact count instead of an approximation. |
| Tasks | |
| Published | 2016-04-18 |
| URL | http://arxiv.org/abs/1604.05559v1 |
| http://arxiv.org/pdf/1604.05559v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-calculation-of-bigram-frequencies |
| Repo | |
| Framework | |
Detection and Visualization of Endoleaks in CT Data for Monitoring of Thoracic and Abdominal Aortic Aneurysm Stents
| Title | Detection and Visualization of Endoleaks in CT Data for Monitoring of Thoracic and Abdominal Aortic Aneurysm Stents |
| Authors | Jing Lu, Jan Egger, Andreas Wimmer, Stefan Großkopf, Bernd Freisleben |
| Abstract | In this paper we present an efficient algorithm for the segmentation of the inner and outer boundary of thoratic and abdominal aortic aneurysms (TAA & AAA) in computed tomography angiography (CTA) acquisitions. The aneurysm segmentation includes two steps: first, the inner boundary is segmented based on a grey level model with two thresholds; then, an adapted active contour model approach is applied to the more complicated outer boundary segmentation, with its initialization based on the available inner boundary segmentation. An opacity image, which aims at enhancing important features while reducing spurious structures, is calculated from the CTA images and employed to guide the deformation of the model. In addition, the active contour model is extended by a constraint force that prevents intersections of the inner and outer boundary and keeps the outer boundary at a distance, given by the thrombus thickness, to the inner boundary. Based upon the segmentation results, we can measure the aneurysm size at each centerline point on the centerline orthogonal multiplanar reformatting (MPR) plane. Furthermore, a 3D TAA or AAA model is reconstructed from the set of segmented contours, and the presence of endoleaks is detected and highlighted. The implemented method has been evaluated on nine clinical CTA data sets with variations in anatomy and location of the pathology and has shown promising results. |
| Tasks | |
| Published | 2016-02-09 |
| URL | http://arxiv.org/abs/1602.02881v1 |
| http://arxiv.org/pdf/1602.02881v1.pdf | |
| PWC | https://paperswithcode.com/paper/detection-and-visualization-of-endoleaks-in |
| Repo | |
| Framework | |
Evaluating Urbanization from Satellite and Aerial Images by means of a statistical approach to the texture analysis
| Title | Evaluating Urbanization from Satellite and Aerial Images by means of a statistical approach to the texture analysis |
| Authors | Amelia Carolina Sparavigna |
| Abstract | Statistical methods are usually applied in the processing of digital images for the analysis of the textures displayed by them. Aiming to evaluate the urbanization of a given location from satellite or aerial images, here we consider a simple processing to distinguish in them the ‘urban’ from the ‘rural’ texture. The method is based on the mean values and the standard deviations of the colour tones of image pixels. The processing of the input images allows to obtain some maps from which a quantitative evaluation of the textures can be obtained. |
| Tasks | Texture Classification |
| Published | 2016-11-10 |
| URL | http://arxiv.org/abs/1611.03469v1 |
| http://arxiv.org/pdf/1611.03469v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluating-urbanization-from-satellite-and |
| Repo | |
| Framework | |
Online Learning to Rank with Top-k Feedback
| Title | Online Learning to Rank with Top-k Feedback |
| Authors | Sougata Chaudhuri, Ambuj Tewari |
| Abstract | We consider two settings of online learning to rank where feedback is restricted to top ranked items. The problem is cast as an online game between a learner and sequence of users, over $T$ rounds. In both settings, the learners objective is to present ranked list of items to the users. The learner’s performance is judged on the entire ranked list and true relevances of the items. However, the learner receives highly restricted feedback at end of each round, in form of relevances of only the top $k$ ranked items, where $k \ll m$. The first setting is \emph{non-contextual}, where the list of items to be ranked is fixed. The second setting is \emph{contextual}, where lists of items vary, in form of traditional query-document lists. No stochastic assumption is made on the generation process of relevances of items and contexts. We provide efficient ranking strategies for both the settings. The strategies achieve $O(T^{2/3})$ regret, where regret is based on popular ranking measures in first setting and ranking surrogates in second setting. We also provide impossibility results for certain ranking measures and a certain class of surrogates, when feedback is restricted to the top ranked item, i.e. $k=1$. We empirically demonstrate the performance of our algorithms on simulated and real world datasets. |
| Tasks | Learning-To-Rank |
| Published | 2016-08-23 |
| URL | http://arxiv.org/abs/1608.06408v1 |
| http://arxiv.org/pdf/1608.06408v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-learning-to-rank-with-top-k-feedback |
| Repo | |
| Framework | |
Active Learning Algorithms for Graphical Model Selection
| Title | Active Learning Algorithms for Graphical Model Selection |
| Authors | Gautam Dasarathy, Aarti Singh, Maria-Florina Balcan, Jong Hyuk Park |
| Abstract | The problem of learning the structure of a high dimensional graphical model from data has received considerable attention in recent years. In many applications such as sensor networks and proteomics it is often expensive to obtain samples from all the variables involved simultaneously. For instance, this might involve the synchronization of a large number of sensors or the tagging of a large number of proteins. To address this important issue, we initiate the study of a novel graphical model selection problem, where the goal is to optimize the total number of scalar samples obtained by allowing the collection of samples from only subsets of the variables. We propose a general paradigm for graphical model selection where feedback is used to guide the sampling to high degree vertices, while obtaining only few samples from the ones with the low degrees. We instantiate this framework with two specific active learning algorithms, one of which makes mild assumptions but is computationally expensive, while the other is more computationally efficient but requires stronger (nevertheless standard) assumptions. Whereas the sample complexity of passive algorithms is typically a function of the maximum degree of the graph, we show that the sample complexity of our algorithms is provable smaller and that it depends on a novel local complexity measure that is akin to the average degree of the graph. We finally demonstrate the efficacy of our framework via simulations. |
| Tasks | Active Learning, Model Selection |
| Published | 2016-02-01 |
| URL | http://arxiv.org/abs/1602.00354v2 |
| http://arxiv.org/pdf/1602.00354v2.pdf | |
| PWC | https://paperswithcode.com/paper/active-learning-algorithms-for-graphical |
| Repo | |
| Framework | |
Unbiased Learning-to-Rank with Biased Feedback
| Title | Unbiased Learning-to-Rank with Biased Feedback |
| Authors | Thorsten Joachims, Adith Swaminathan, Tobias Schnabel |
| Abstract | Implicit feedback (e.g., clicks, dwell times, etc.) is an abundant source of data in human-interactive systems. While implicit feedback has many advantages (e.g., it is inexpensive to collect, user centric, and timely), its inherent biases are a key obstacle to its effective use. For example, position bias in search rankings strongly influences how many clicks a result receives, so that directly using click data as a training signal in Learning-to-Rank (LTR) methods yields sub-optimal results. To overcome this bias problem, we present a counterfactual inference framework that provides the theoretical basis for unbiased LTR via Empirical Risk Minimization despite biased data. Using this framework, we derive a Propensity-Weighted Ranking SVM for discriminative learning from implicit feedback, where click models take the role of the propensity estimator. In contrast to most conventional approaches to de-bias the data using click models, this allows training of ranking functions even in settings where queries do not repeat. Beyond the theoretical support, we show empirically that the proposed learning method is highly effective in dealing with biases, that it is robust to noise and propensity model misspecification, and that it scales efficiently. We also demonstrate the real-world applicability of our approach on an operational search engine, where it substantially improves retrieval performance. |
| Tasks | Counterfactual Inference, Learning-To-Rank |
| Published | 2016-08-16 |
| URL | http://arxiv.org/abs/1608.04468v1 |
| http://arxiv.org/pdf/1608.04468v1.pdf | |
| PWC | https://paperswithcode.com/paper/unbiased-learning-to-rank-with-biased |
| Repo | |
| Framework | |
Bridging the Gap: Incorporating a Semantic Similarity Measure for Effectively Mapping PubMed Queries to Documents
| Title | Bridging the Gap: Incorporating a Semantic Similarity Measure for Effectively Mapping PubMed Queries to Documents |
| Authors | Sun Kim, Nicolas Fiorini, W. John Wilbur, Zhiyong Lu |
| Abstract | The main approach of traditional information retrieval (IR) is to examine how many words from a query appear in a document. A drawback of this approach, however, is that it may fail to detect relevant documents where no or only few words from a query are found. The semantic analysis methods such as LSA (latent semantic analysis) and LDA (latent Dirichlet allocation) have been proposed to address the issue, but their performance is not superior compared to common IR approaches. Here we present a query-document similarity measure motivated by the Word Mover’s Distance. Unlike other similarity measures, the proposed method relies on neural word embeddings to compute the distance between words. This process helps identify related words when no direct matches are found between a query and a document. Our method is efficient and straightforward to implement. The experimental results on TREC Genomics data show that our approach outperforms the BM25 ranking function by an average of 12% in mean average precision. Furthermore, for a real-world dataset collected from the PubMed search logs, we combine the semantic measure with BM25 using a learning to rank method, which leads to improved ranking scores by up to 25%. This experiment demonstrates that the proposed approach and BM25 nicely complement each other and together produce superior performance. |
| Tasks | Information Retrieval, Learning-To-Rank, Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2016-08-05 |
| URL | http://arxiv.org/abs/1608.01972v2 |
| http://arxiv.org/pdf/1608.01972v2.pdf | |
| PWC | https://paperswithcode.com/paper/bridging-the-gap-incorporating-a-semantic |
| Repo | |
| Framework | |
Learning to Rank for Synthesizing Planning Heuristics
| Title | Learning to Rank for Synthesizing Planning Heuristics |
| Authors | Caelan Reed Garrett, Leslie Pack Kaelbling, Tomas Lozano-Perez |
| Abstract | We investigate learning heuristics for domain-specific planning. Prior work framed learning a heuristic as an ordinary regression problem. However, in a greedy best-first search, the ordering of states induced by a heuristic is more indicative of the resulting planner’s performance than mean squared error. Thus, we instead frame learning a heuristic as a learning to rank problem which we solve using a RankSVM formulation. Additionally, we introduce new methods for computing features that capture temporal interactions in an approximate plan. Our experiments on recent International Planning Competition problems show that the RankSVM learned heuristics outperform both the original heuristics and heuristics learned through ordinary regression. |
| Tasks | Learning-To-Rank |
| Published | 2016-08-03 |
| URL | http://arxiv.org/abs/1608.01302v1 |
| http://arxiv.org/pdf/1608.01302v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-rank-for-synthesizing-planning |
| Repo | |
| Framework | |
Divide-and-Conquer based Ensemble to Spot Emotions in Speech using MFCC and Random Forest
| Title | Divide-and-Conquer based Ensemble to Spot Emotions in Speech using MFCC and Random Forest |
| Authors | Abdul Malik Badshah, Jamil Ahmad, Mi Young Lee, Sung Wook Baik |
| Abstract | Besides spoken words, speech signals also carry information about speaker gender, age, and emotional state which can be used in a variety of speech analysis applications. In this paper, a divide and conquer strategy for ensemble classification has been proposed to recognize emotions in speech. Intrinsic hierarchy in emotions has been utilized to construct an emotions tree, which assisted in breaking down the emotion recognition task into smaller sub tasks. The proposed framework generates predictions in three phases. Firstly, emotions are detected in the input speech signal by classifying it as neutral or emotional. If the speech is classified as emotional, then in the second phase, it is further classified into positive and negative classes. Finally, individual positive or negative emotions are identified based on the outcomes of the previous stages. Several experiments have been performed on a widely used benchmark dataset. The proposed method was able to achieve improved recognition rates as compared to several other approaches. |
| Tasks | Emotion Recognition |
| Published | 2016-10-05 |
| URL | http://arxiv.org/abs/1610.01382v1 |
| http://arxiv.org/pdf/1610.01382v1.pdf | |
| PWC | https://paperswithcode.com/paper/divide-and-conquer-based-ensemble-to-spot |
| Repo | |
| Framework | |
Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks
| Title | Joint Semantic Segmentation and Depth Estimation with Deep Convolutional Networks |
| Authors | Arsalan Mousavian, Hamed Pirsiavash, Jana Kosecka |
| Abstract | Multi-scale deep CNNs have been used successfully for problems mapping each pixel to a label, such as depth estimation and semantic segmentation. It has also been shown that such architectures are reusable and can be used for multiple tasks. These networks are typically trained independently for each task by varying the output layer(s) and training objective. In this work we present a new model for simultaneous depth estimation and semantic segmentation from a single RGB image. Our approach demonstrates the feasibility of training parts of the model for each task and then fine tuning the full, combined model on both tasks simultaneously using a single loss function. Furthermore we couple the deep CNN with fully connected CRF, which captures the contextual relationships and interactions between the semantic and depth cues improving the accuracy of the final results. The proposed model is trained and evaluated on NYUDepth V2 dataset outperforming the state of the art methods on semantic segmentation and achieving comparable results on the task of depth estimation. |
| Tasks | Depth Estimation, Semantic Segmentation |
| Published | 2016-04-25 |
| URL | http://arxiv.org/abs/1604.07480v3 |
| http://arxiv.org/pdf/1604.07480v3.pdf | |
| PWC | https://paperswithcode.com/paper/joint-semantic-segmentation-and-depth |
| Repo | |
| Framework | |
CrowdMI: Multiple Imputation via Crowdsourcing
| Title | CrowdMI: Multiple Imputation via Crowdsourcing |
| Authors | Lovedeep Gondara |
| Abstract | Can humans impute missing data with similar proficiency as machines? This is the question we aim to answer in this paper. We present a novel idea of converting observations with missing data in to a survey questionnaire, which is presented to crowdworkers for completion. We replicate a multiple imputation framework by having multiple unique crowdworkers complete our questionnaire. Experimental results demonstrate that using our method, it is possible to generate valid imputations for qualitative and quantitative missing data, with results comparable to imputations generated by complex statistical models. |
| Tasks | Imputation |
| Published | 2016-12-08 |
| URL | http://arxiv.org/abs/1612.02707v4 |
| http://arxiv.org/pdf/1612.02707v4.pdf | |
| PWC | https://paperswithcode.com/paper/crowdmi-multiple-imputation-via-crowdsourcing |
| Repo | |
| Framework | |
A Lower Bound Analysis of Population-based Evolutionary Algorithms for Pseudo-Boolean Functions
| Title | A Lower Bound Analysis of Population-based Evolutionary Algorithms for Pseudo-Boolean Functions |
| Authors | Chao Qian, Yang Yu, Zhi-Hua Zhou |
| Abstract | Evolutionary algorithms (EAs) are population-based general-purpose optimization algorithms, and have been successfully applied in various real-world optimization tasks. However, previous theoretical studies often employ EAs with only a parent or offspring population and focus on specific problems. Furthermore, they often only show upper bounds on the running time, while lower bounds are also necessary to get a complete understanding of an algorithm. In this paper, we analyze the running time of the ($\mu$+$\lambda$)-EA (a general population-based EA with mutation only) on the class of pseudo-Boolean functions with a unique global optimum. By applying the recently proposed switch analysis approach, we prove the lower bound $\Omega(n \ln n+ \mu + \lambda n\ln\ln n/ \ln n)$ for the first time. Particularly on the two widely-studied problems, OneMax and LeadingOnes, the derived lower bound discloses that the ($\mu$+$\lambda$)-EA will be strictly slower than the (1+1)-EA when the population size $\mu$ or $\lambda$ is above a moderate order. Our results imply that the increase of population size, while usually desired in practice, bears the risk of increasing the lower bound of the running time and thus should be carefully considered. |
| Tasks | |
| Published | 2016-06-10 |
| URL | http://arxiv.org/abs/1606.03326v1 |
| http://arxiv.org/pdf/1606.03326v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-lower-bound-analysis-of-population-based |
| Repo | |
| Framework | |
Weighted diffusion LMP algorithm for distributed estimation in non-uniform noise conditions
| Title | Weighted diffusion LMP algorithm for distributed estimation in non-uniform noise conditions |
| Authors | H. Zayyani, M. Korki |
| Abstract | This letter presents an improved version of diffusion least mean ppower (LMP) algorithm for distributed estimation. Instead of sum of mean square errors, a weighted sum of mean square error is defined as the cost function for global and local cost functions of a network of sensors. The weight coefficients are updated by a simple steepest-descent recursion to minimize the error signal of the global and local adaptive algorithm. Simulation results show the advantages of the proposed weighted diffusion LMP over the diffusion LMP algorithm specially in the non-uniform noise conditions in a sensor network. |
| Tasks | |
| Published | 2016-08-06 |
| URL | http://arxiv.org/abs/1608.02060v1 |
| http://arxiv.org/pdf/1608.02060v1.pdf | |
| PWC | https://paperswithcode.com/paper/weighted-diffusion-lmp-algorithm-for |
| Repo | |
| Framework | |
Learning Mixtures of Plackett-Luce Models
| Title | Learning Mixtures of Plackett-Luce Models |
| Authors | Zhibing Zhao, Peter Piech, Lirong Xia |
| Abstract | In this paper we address the identifiability and efficient learning problems of finite mixtures of Plackett-Luce models for rank data. We prove that for any $k\geq 2$, the mixture of $k$ Plackett-Luce models for no more than $2k-1$ alternatives is non-identifiable and this bound is tight for $k=2$. For generic identifiability, we prove that the mixture of $k$ Plackett-Luce models over $m$ alternatives is generically identifiable if $k\leq\lfloor\frac {m-2} 2\rfloor!$. We also propose an efficient generalized method of moments (GMM) algorithm to learn the mixture of two Plackett-Luce models and show that the algorithm is consistent. Our experiments show that our GMM algorithm is significantly faster than the EMM algorithm by Gormley and Murphy (2008), while achieving competitive statistical efficiency. |
| Tasks | |
| Published | 2016-03-23 |
| URL | https://arxiv.org/abs/1603.07323v4 |
| https://arxiv.org/pdf/1603.07323v4.pdf | |
| PWC | https://paperswithcode.com/paper/learning-mixtures-of-plackett-luce-models |
| Repo | |
| Framework | |
