Paper Group ANR 253
Token-based Function Computation with Memory. Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification. Finite-sample risk bounds for maximum likelihood estimation with arbitrary penalties. Hybrid Conditional Planning using Answer Set Programming. Scientific document summarization via citation contextualization and scientif …
Token-based Function Computation with Memory
| Title | Token-based Function Computation with Memory |
| Authors | Saber Salehkaleybar, S. Jamaloddin Golestani |
| Abstract | In distributed function computation, each node has an initial value and the goal is to compute a function of these values in a distributed manner. In this paper, we propose a novel token-based approach to compute a wide class of target functions to which we refer as “Token-based function Computation with Memory” (TCM) algorithm. In this approach, node values are attached to tokens and travel across the network. Each pair of travelling tokens would coalesce when they meet, forming a token with a new value as a function of the original token values. In contrast to the Coalescing Random Walk (CRW) algorithm, where token movement is governed by random walk, meeting of tokens in our scheme is accelerated by adopting a novel chasing mechanism. We proved that, compared to the CRW algorithm, the TCM algorithm results in a reduction of time complexity by a factor of at least $\sqrt{n/\log(n)}$ in Erd"os-Renyi and complete graphs, and by a factor of $\log(n)/\log(\log(n))$ in torus networks. Simulation results show that there is at least a constant factor improvement in the message complexity of TCM algorithm in all considered topologies. Robustness of the CRW and TCM algorithms in the presence of node failure is analyzed. We show that their robustness can be improved by running multiple instances of the algorithms in parallel. |
| Tasks | |
| Published | 2017-03-26 |
| URL | http://arxiv.org/abs/1703.08831v1 |
| http://arxiv.org/pdf/1703.08831v1.pdf | |
| PWC | https://paperswithcode.com/paper/token-based-function-computation-with-memory |
| Repo | |
| Framework | |
Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification
| Title | Deep Ranking Model by Large Adaptive Margin Learning for Person Re-identification |
| Authors | Jiayun Wang, Sanping Zhou, Jinjun Wang, Qiqi Hou |
| Abstract | Person re-identification aims to match images of the same person across disjoint camera views, which is a challenging problem in video surveillance. The major challenge of this task lies in how to preserve the similarity of the same person against large variations caused by complex backgrounds, mutual occlusions and different illuminations, while discriminating the different individuals. In this paper, we present a novel deep ranking model with feature learning and fusion by learning a large adaptive margin between the intra-class distance and inter-class distance to solve the person re-identification problem. Specifically, we organize the training images into a batch of pairwise samples. Treating these pairwise samples as inputs, we build a novel part-based deep convolutional neural network (CNN) to learn the layered feature representations by preserving a large adaptive margin. As a result, the final learned model can effectively find out the matched target to the anchor image among a number of candidates in the gallery image set by learning discriminative and stable feature representations. Overcoming the weaknesses of conventional fixed-margin loss functions, our adaptive margin loss function is more appropriate for the dynamic feature space. On four benchmark datasets, PRID2011, Market1501, CUHK01 and 3DPeS, we extensively conduct comparative evaluations to demonstrate the advantages of the proposed method over the state-of-the-art approaches in person re-identification. |
| Tasks | Person Re-Identification |
| Published | 2017-07-03 |
| URL | http://arxiv.org/abs/1707.00409v2 |
| http://arxiv.org/pdf/1707.00409v2.pdf | |
| PWC | https://paperswithcode.com/paper/deep-ranking-model-by-large-adaptive-margin |
| Repo | |
| Framework | |
Finite-sample risk bounds for maximum likelihood estimation with arbitrary penalties
| Title | Finite-sample risk bounds for maximum likelihood estimation with arbitrary penalties |
| Authors | W. D. Brinda, Jason M. Klusowski |
| Abstract | The MDL two-part coding $ \textit{index of resolvability} $ provides a finite-sample upper bound on the statistical risk of penalized likelihood estimators over countable models. However, the bound does not apply to unpenalized maximum likelihood estimation or procedures with exceedingly small penalties. In this paper, we point out a more general inequality that holds for arbitrary penalties. In addition, this approach makes it possible to derive exact risk bounds of order $1/n$ for iid parametric models, which improves on the order $(\log n)/n$ resolvability bounds. We conclude by discussing implications for adaptive estimation. |
| Tasks | |
| Published | 2017-12-29 |
| URL | http://arxiv.org/abs/1712.10087v1 |
| http://arxiv.org/pdf/1712.10087v1.pdf | |
| PWC | https://paperswithcode.com/paper/finite-sample-risk-bounds-for-maximum |
| Repo | |
| Framework | |
Hybrid Conditional Planning using Answer Set Programming
| Title | Hybrid Conditional Planning using Answer Set Programming |
| Authors | Ibrahim Faruk Yalciner, Ahmed Nouman, Volkan Patoglu, Esra Erdem |
| Abstract | We introduce a parallel offline algorithm for computing hybrid conditional plans, called HCP-ASP, oriented towards robotics applications. HCP-ASP relies on modeling actuation actions and sensing actions in an expressive nonmonotonic language of answer set programming (ASP), and computation of the branches of a conditional plan in parallel using an ASP solver. In particular, thanks to external atoms, continuous feasibility checks (like collision checks) are embedded into formal representations of actuation actions and sensing actions in ASP; and thus each branch of a hybrid conditional plan describes a feasible execution of actions to reach their goals. Utilizing nonmonotonic constructs and nondeterministic choices, partial knowledge about states and nondeterministic effects of sensing actions can be explicitly formalized in ASP; and thus each branch of a conditional plan can be computed by an ASP solver without necessitating a conformant planner and an ordering of sensing actions in advance. We apply our method in a service robotics domain and report experimental evaluations. Furthermore, we present performance comparisons with other compilation based conditional planners on standardized benchmark domains. This paper is under consideration for acceptance in TPLP. |
| Tasks | |
| Published | 2017-07-19 |
| URL | http://arxiv.org/abs/1707.05904v1 |
| http://arxiv.org/pdf/1707.05904v1.pdf | |
| PWC | https://paperswithcode.com/paper/hybrid-conditional-planning-using-answer-set |
| Repo | |
| Framework | |
Scientific document summarization via citation contextualization and scientific discourse
| Title | Scientific document summarization via citation contextualization and scientific discourse |
| Authors | Arman Cohan, Nazli Goharian |
| Abstract | The rapid growth of scientific literature has made it difficult for the researchers to quickly learn about the developments in their respective fields. Scientific document summarization addresses this challenge by providing summaries of the important contributions of scientific papers. We present a framework for scientific summarization which takes advantage of the citations and the scientific discourse structure. Citation texts often lack the evidence and context to support the content of the cited paper and are even sometimes inaccurate. We first address the problem of inaccuracy of the citation texts by finding the relevant context from the cited paper. We propose three approaches for contextualizing citations which are based on query reformulation, word embeddings, and supervised learning. We then train a model to identify the discourse facets for each citation. We finally propose a method for summarizing scientific papers by leveraging the faceted citations and their corresponding contexts. We evaluate our proposed method on two scientific summarization datasets in the biomedical and computational linguistics domains. Extensive evaluation results show that our methods can improve over the state of the art by large margins. |
| Tasks | Document Summarization, Word Embeddings |
| Published | 2017-06-12 |
| URL | http://arxiv.org/abs/1706.03449v1 |
| http://arxiv.org/pdf/1706.03449v1.pdf | |
| PWC | https://paperswithcode.com/paper/scientific-document-summarization-via |
| Repo | |
| Framework | |
Predicting Demographics, Moral Foundations, and Human Values from Digital Behaviors
| Title | Predicting Demographics, Moral Foundations, and Human Values from Digital Behaviors |
| Authors | Kyriaki Kalimeri, Mariano G. Beiro, Matteo Delfino, Robert Raleigh, Ciro Cattuto |
| Abstract | Personal electronic devices including smartphones give access to behavioural signals that can be used to learn about the characteristics and preferences of individuals. In this study, we explore the connection between demographic and psychological attributes and the digital behavioural records, for a cohort of 7,633 people, closely representative of the US population with respect to gender, age, geographical distribution, education, and income. Along with the demographic data, we collected self-reported assessments on validated psychometric questionnaires for moral traits and basic human values and combined this information with passively collected multi-modal digital data from web browsing behaviour and smartphone usage. A machine learning framework was then designed to infer both the demographic and psychological attributes from the behavioural data. In a cross-validated setting, our models predicted demographic attributes with good accuracy as measured by the weighted AUROC score (Area Under the Receiver Operating Characteristic), but were less performant for the moral traits and human values. These results call for further investigation since they are still far from unveiling individuals’ psychological fabric. This connection, along with the most predictive features that we provide for each attribute, might prove useful for designing personalised services, communication strategies, and interventions, and can be used to sketch a portrait of people with a similar worldview. |
| Tasks | |
| Published | 2017-12-05 |
| URL | http://arxiv.org/abs/1712.01930v4 |
| http://arxiv.org/pdf/1712.01930v4.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-demographics-moral-foundations-and |
| Repo | |
| Framework | |
Shortcut Sequence Tagging
| Title | Shortcut Sequence Tagging |
| Authors | Huijia Wu, Jiajun Zhang, Chengqing Zong |
| Abstract | Deep stacked RNNs are usually hard to train. Adding shortcut connections across different layers is a common way to ease the training of stacked networks. However, extra shortcuts make the recurrent step more complicated. To simply the stacked architecture, we propose a framework called shortcut block, which is a marriage of the gating mechanism and shortcuts, while discarding the self-connected part in LSTM cell. We present extensive empirical experiments showing that this design makes training easy and improves generalization. We propose various shortcut block topologies and compositions to explore its effectiveness. Based on this architecture, we obtain a 6% relatively improvement over the state-of-the-art on CCGbank supertagging dataset. We also get comparable results on POS tagging task. |
| Tasks | |
| Published | 2017-01-03 |
| URL | http://arxiv.org/abs/1701.00576v1 |
| http://arxiv.org/pdf/1701.00576v1.pdf | |
| PWC | https://paperswithcode.com/paper/shortcut-sequence-tagging |
| Repo | |
| Framework | |
Multi-camera Multi-Object Tracking
| Title | Multi-camera Multi-Object Tracking |
| Authors | Wenqian Liu, Octavia Camps, Mario Sznaier |
| Abstract | In this paper, we propose a pipeline for multi-target visual tracking under multi-camera system. For multi-camera system tracking problem, efficient data association across cameras, and at the same time, across frames becomes more important than single-camera system tracking. However, most of the multi-camera tracking algorithms emphasis on single camera across frame data association. Thus in our work, we model our tracking problem as a global graph, and adopt Generalized Maximum Multi Clique optimization problem as our core algorithm to take both across frame and across camera data correlation into account all together. Furthermore, in order to compute good similarity scores as the input of our graph model, we extract both appearance and dynamic motion similarities. For appearance feature, Local Maximal Occurrence Representation(LOMO) feature extraction algorithm for ReID is conducted. When it comes to capturing the dynamic information, we build Hankel matrix for each tracklet of target and apply rank estimation with Iterative Hankel Total Least Squares(IHTLS) algorithm to it. We evaluate our tracker on the challenging Terrace Sequences from EPFL CVLAB as well as recently published Duke MTMC dataset. |
| Tasks | Multi-Object Tracking, Object Tracking, Visual Tracking |
| Published | 2017-09-20 |
| URL | http://arxiv.org/abs/1709.07065v1 |
| http://arxiv.org/pdf/1709.07065v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-camera-multi-object-tracking |
| Repo | |
| Framework | |
Driver Drowsiness Estimation from EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR)
| Title | Driver Drowsiness Estimation from EEG Signals Using Online Weighted Adaptation Regularization for Regression (OwARR) |
| Authors | Dongrui Wu, Vernon J. Lawhern, Stephen Gordon, Brent J. Lance, Chin-Teng Lin |
| Abstract | One big challenge that hinders the transition of brain-computer interfaces (BCIs) from laboratory settings to real-life applications is the availability of high-performance and robust learning algorithms that can effectively handle individual differences, i.e., algorithms that can be applied to a new subject with zero or very little subject-specific calibration data. Transfer learning and domain adaptation have been extensively used for this purpose. However, most previous works focused on classification problems. This paper considers an important regression problem in BCI, namely, online driver drowsiness estimation from EEG signals. By integrating fuzzy sets with domain adaptation, we propose a novel online weighted adaptation regularization for regression (OwARR) algorithm to reduce the amount of subject-specific calibration data, and also a source domain selection (SDS) approach to save about half of the computational cost of OwARR. Using a simulated driving dataset with 15 subjects, we show that OwARR and OwARR-SDS can achieve significantly smaller estimation errors than several other approaches. We also provide comprehensive analyses on the robustness of OwARR and OwARR-SDS. |
| Tasks | Calibration, Domain Adaptation, EEG, Transfer Learning |
| Published | 2017-02-09 |
| URL | http://arxiv.org/abs/1702.02901v1 |
| http://arxiv.org/pdf/1702.02901v1.pdf | |
| PWC | https://paperswithcode.com/paper/driver-drowsiness-estimation-from-eeg-signals |
| Repo | |
| Framework | |
Accelerated Dual Learning by Homotopic Initialization
| Title | Accelerated Dual Learning by Homotopic Initialization |
| Authors | Hadi Daneshmand, Hamed Hassani, Thomas Hofmann |
| Abstract | Gradient descent and coordinate descent are well understood in terms of their asymptotic behavior, but less so in a transient regime often used for approximations in machine learning. We investigate how proper initialization can have a profound effect on finding near-optimal solutions quickly. We show that a certain property of a data set, namely the boundedness of the correlations between eigenfeatures and the response variable, can lead to faster initial progress than expected by commonplace analysis. Convex optimization problems can tacitly benefit from that, but this automatism does not apply to their dual formulation. We analyze this phenomenon and devise provably good initialization strategies for dual optimization as well as heuristics for the non-convex case, relevant for deep learning. We find our predictions and methods to be experimentally well-supported. |
| Tasks | |
| Published | 2017-06-13 |
| URL | http://arxiv.org/abs/1706.03958v1 |
| http://arxiv.org/pdf/1706.03958v1.pdf | |
| PWC | https://paperswithcode.com/paper/accelerated-dual-learning-by-homotopic |
| Repo | |
| Framework | |
Learning Convolutional Networks for Content-weighted Image Compression
| Title | Learning Convolutional Networks for Content-weighted Image Compression |
| Authors | Mu Li, Wangmeng Zuo, Shuhang Gu, Debin Zhao, David Zhang |
| Abstract | Lossy image compression is generally formulated as a joint rate-distortion optimization to learn encoder, quantizer, and decoder. However, the quantizer is non-differentiable, and discrete entropy estimation usually is required for rate control. These make it very challenging to develop a convolutional network (CNN)-based image compression system. In this paper, motivated by that the local information content is spatially variant in an image, we suggest that the bit rate of the different parts of the image should be adapted to local content. And the content aware bit rate is allocated under the guidance of a content-weighted importance map. Thus, the sum of the importance map can serve as a continuous alternative of discrete entropy estimation to control compression rate. And binarizer is adopted to quantize the output of encoder due to the binarization scheme is also directly defined by the importance map. Furthermore, a proxy function is introduced for binary operation in backward propagation to make it differentiable. Therefore, the encoder, decoder, binarizer and importance map can be jointly optimized in an end-to-end manner by using a subset of the ImageNet database. In low bit rate image compression, experiments show that our system significantly outperforms JPEG and JPEG 2000 by structural similarity (SSIM) index, and can produce the much better visual result with sharp edges, rich textures, and fewer artifacts. |
| Tasks | Image Compression |
| Published | 2017-03-30 |
| URL | http://arxiv.org/abs/1703.10553v2 |
| http://arxiv.org/pdf/1703.10553v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-convolutional-networks-for-content |
| Repo | |
| Framework | |
Efficiently Tracking Homogeneous Regions in Multichannel Images
| Title | Efficiently Tracking Homogeneous Regions in Multichannel Images |
| Authors | Tobias Böttger, Christina Eisenhofer |
| Abstract | We present a method for tracking Maximally Stable Homogeneous Regions (MSHR) in images with an arbitrary number of channels. MSHR are conceptionally very similar to Maximally Stable Extremal Regions (MSER) and Maximally Stable Color Regions (MSCR), but can also be applied to hyperspectral and color images while remaining extremely efficient. The presented approach makes use of the edge-based component-tree which can be calculated in linear time. In the tracking step, the MSHR are localized by matching them to the nodes in the component-tree. We use rotationally invariant region and gray-value features that can be calculated through first and second order moments at low computational complexity. Furthermore, we use a weighted feature vector to improve the data association in the tracking step. The algorithm is evaluated on a collection of different tracking scenes from the literature. Furthermore, we present two different applications: 2D object tracking and the 3D segmentation of organs. |
| Tasks | Object Tracking |
| Published | 2017-08-16 |
| URL | http://arxiv.org/abs/1708.04804v1 |
| http://arxiv.org/pdf/1708.04804v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficiently-tracking-homogeneous-regions-in |
| Repo | |
| Framework | |
First-Person Perceptual Guidance Behavior Decomposition using Active Constraint Classification
| Title | First-Person Perceptual Guidance Behavior Decomposition using Active Constraint Classification |
| Authors | Andrew Feit, Berenice Mettler |
| Abstract | Humans exhibit a wide range of adaptive and robust dynamic motion behavior that is yet unmatched by autonomous control systems. These capabilities are essential for real-time behavior generation in cluttered environments. Recent work suggests that human capabilities rely on task structure learning and embedded or ecological cognition in the form of perceptual guidance. This paper describes the experimental investigation of the functional elements of human motion guidance, focusing on the control and perceptual mechanisms. The motion, control, and perceptual data from first-person guidance experiments is decomposed into elemental segments based on invariants. These elements are then analyzed to determine their functional characteristics. The resulting model explains the structure of the agent-environment interaction and provides lawful descriptions of specific perceptual guidance and control mechanisms. |
| Tasks | |
| Published | 2017-10-18 |
| URL | http://arxiv.org/abs/1710.06943v1 |
| http://arxiv.org/pdf/1710.06943v1.pdf | |
| PWC | https://paperswithcode.com/paper/first-person-perceptual-guidance-behavior |
| Repo | |
| Framework | |
Named Entity Evolution Recognition on the Blogosphere
| Title | Named Entity Evolution Recognition on the Blogosphere |
| Authors | Helge Holzmann, Nina Tahmasebi, Thomas Risse |
| Abstract | Advancements in technology and culture lead to changes in our language. These changes create a gap between the language known by users and the language stored in digital archives. It affects user’s possibility to firstly find content and secondly interpret that content. In previous work we introduced our approach for Named Entity Evolution Recognition~(NEER) in newspaper collections. Lately, increasing efforts in Web preservation lead to increased availability of Web archives covering longer time spans. However, language on the Web is more dynamic than in traditional media and many of the basic assumptions from the newspaper domain do not hold for Web data. In this paper we discuss the limitations of existing methodology for NEER. We approach these by adapting an existing NEER method to work on noisy data like the Web and the Blogosphere in particular. We develop novel filters that reduce the noise and make use of Semantic Web resources to obtain more information about terms. Our evaluation shows the potentials of the proposed approach. |
| Tasks | |
| Published | 2017-02-03 |
| URL | http://arxiv.org/abs/1702.01187v1 |
| http://arxiv.org/pdf/1702.01187v1.pdf | |
| PWC | https://paperswithcode.com/paper/named-entity-evolution-recognition-on-the |
| Repo | |
| Framework | |
Insights into Entity Name Evolution on Wikipedia
| Title | Insights into Entity Name Evolution on Wikipedia |
| Authors | Helge Holzmann, Thomas Risse |
| Abstract | Working with Web archives raises a number of issues caused by their temporal characteristics. Depending on the age of the content, additional knowledge might be needed to find and understand older texts. Especially facts about entities are subject to change. Most severe in terms of information retrieval are name changes. In order to find entities that have changed their name over time, search engines need to be aware of this evolution. We tackle this problem by analyzing Wikipedia in terms of entity evolutions mentioned in articles regardless the structural elements. We gathered statistics and automatically extracted minimum excerpts covering name changes by incorporating lists dedicated to that subject. In future work, these excerpts are going to be used to discover patterns and detect changes in other sources. In this work we investigate whether or not Wikipedia is a suitable source for extracting the required knowledge. |
| Tasks | Information Retrieval |
| Published | 2017-02-03 |
| URL | http://arxiv.org/abs/1702.01172v1 |
| http://arxiv.org/pdf/1702.01172v1.pdf | |
| PWC | https://paperswithcode.com/paper/insights-into-entity-name-evolution-on |
| Repo | |
| Framework | |
