May 7, 2019

2838 words 14 mins read

Paper Group ANR 112

Multivariate Dependence Beyond Shannon Information. Learning Adaptive Parameter Tuning for Image Processing. UTCNN: a Deep Learning Model of Stance Classificationon on Social Media Text. Better Image Segmentation by Exploiting Dense Semantic Predictions. HNP3: A Hierarchical Nonparametric Point Process for Modeling Content Diffusion over Social Med …

Multivariate Dependence Beyond Shannon Information


Title	Multivariate Dependence Beyond Shannon Information
Authors	Ryan G. James, James P. Crutchfield
Abstract	Accurately determining dependency structure is critical to discovering a system’s causal organization. We recently showed that the transfer entropy fails in a key aspect of this—measuring information flow—due to its conflation of dyadic and polyadic relationships. We extend this observation to demonstrate that this is true of all such Shannon information measures when used to analyze multivariate dependencies. This has broad implications, particularly when employing information to express the organization and mechanisms embedded in complex systems, including the burgeoning efforts to combine complex network theory with information theory. Here, we do not suggest that any aspect of information theory is wrong. Rather, the vast majority of its informational measures are simply inadequate for determining the meaningful dependency structure within joint probability distributions. Therefore, such information measures are inadequate for discovering intrinsic causal relations. We close by demonstrating that such distributions exist across an arbitrary set of variables.
Tasks
Published	2016-09-05
URL	http://arxiv.org/abs/1609.01233v2
PDF	http://arxiv.org/pdf/1609.01233v2.pdf
PWC	https://paperswithcode.com/paper/multivariate-dependence-beyond-shannon
Repo
Framework

Learning Adaptive Parameter Tuning for Image Processing


Title	Learning Adaptive Parameter Tuning for Image Processing
Authors	Jingming Dong, Iuri Frosio, Jan Kautz
Abstract	The non-stationary nature of image characteristics calls for adaptive processing, based on the local image content. We propose a simple and flexible method to learn local tuning of parameters in adaptive image processing: we extract simple local features from an image and learn the relation between these features and the optimal filtering parameters. Learning is performed by optimizing a user defined cost function (any image quality metric) on a training set. We apply our method to three classical problems (denoising, demosaicing and deblurring) and we show the effectiveness of the learned parameter modulation strategies. We also show that these strategies are consistent with theoretical results from the literature.
Tasks	Deblurring, Demosaicking, Denoising
Published	2016-10-28
URL	http://arxiv.org/abs/1610.09414v2
PDF	http://arxiv.org/pdf/1610.09414v2.pdf
PWC	https://paperswithcode.com/paper/learning-adaptive-parameter-tuning-for-image
Repo
Framework


Title	UTCNN: a Deep Learning Model of Stance Classificationon on Social Media Text
Authors	Wei-Fan Chen, Lun-Wei Ku
Abstract	Most neural network models for document classification on social media focus on text infor-mation to the neglect of other information on these platforms. In this paper, we classify post stance on social media channels and develop UTCNN, a neural network model that incorporates user tastes, topic tastes, and user comments on posts. UTCNN not only works on social media texts, but also analyzes texts in forums and message boards. Experiments performed on Chinese Facebook data and English online debate forum data show that UTCNN achieves a 0.755 macro-average f-score for supportive, neutral, and unsupportive stance classes on Facebook data, which is significantly better than models in which either user, topic, or comment information is withheld. This model design greatly mitigates the lack of data for the minor class without the use of oversampling. In addition, UTCNN yields a 0.842 accuracy on English online debate forum data, which also significantly outperforms results from previous work as well as other deep learning models, showing that UTCNN performs well regardless of language or platform.
Tasks	Document Classification
Published	2016-11-11
URL	http://arxiv.org/abs/1611.03599v1
PDF	http://arxiv.org/pdf/1611.03599v1.pdf
PWC	https://paperswithcode.com/paper/utcnn-a-deep-learning-model-of-stance
Repo
Framework

Better Image Segmentation by Exploiting Dense Semantic Predictions


Title	Better Image Segmentation by Exploiting Dense Semantic Predictions
Authors	Qiyang Zhao, Lewis D Griffin
Abstract	It is well accepted that image segmentation can benefit from utilizing multilevel cues. The paper focuses on utilizing the FCNN-based dense semantic predictions in the bottom-up image segmentation, arguing to take semantic cues into account from the very beginning. By this we can avoid merging regions of similar appearance but distinct semantic categories as possible. The semantic inefficiency problem is handled. We also propose a straightforward way to use the contour cues to suppress the noise in multilevel cues, thus to improve the segmentation robustness. The evaluation on the BSDS500 shows that we obtain the competitive region and boundary performance. Furthermore, since all individual regions can be assigned with appropriate semantic labels during the computation, we are capable of extracting the adjusted semantic segmentations. The experiment on Pascal VOC 2012 shows our improvement to the original semantic segmentations which derives directly from the dense predictions.
Tasks	Semantic Segmentation
Published	2016-06-05
URL	http://arxiv.org/abs/1606.01481v1
PDF	http://arxiv.org/pdf/1606.01481v1.pdf
PWC	https://paperswithcode.com/paper/better-image-segmentation-by-exploiting-dense
Repo
Framework


Title	HNP3: A Hierarchical Nonparametric Point Process for Modeling Content Diffusion over Social Media
Authors	Seyed Abbas Hosseini, Ali Khodadadi, Soheil Arabzade, Hamid R. Rabiee
Abstract	This paper introduces a novel framework for modeling temporal events with complex longitudinal dependency that are generated by dependent sources. This framework takes advantage of multidimensional point processes for modeling time of events. The intensity function of the proposed process is a mixture of intensities, and its complexity grows with the complexity of temporal patterns of data. Moreover, it utilizes a hierarchical dependent nonparametric approach to model marks of events. These capabilities allow the proposed model to adapt its temporal and topical complexity according to the complexity of data, which makes it a suitable candidate for real world scenarios. An online inference algorithm is also proposed that makes the framework applicable to a vast range of applications. The framework is applied to a real world application, modeling the diffusion of contents over networks. Extensive experiments reveal the effectiveness of the proposed framework in comparison with state-of-the-art methods.
Tasks	Point Processes
Published	2016-10-02
URL	http://arxiv.org/abs/1610.00246v1
PDF	http://arxiv.org/pdf/1610.00246v1.pdf
PWC	https://paperswithcode.com/paper/hnp3-a-hierarchical-nonparametric-point
Repo
Framework

Exact Sampling from Determinantal Point Processes


Title	Exact Sampling from Determinantal Point Processes
Authors	Philipp Hennig, Roman Garnett
Abstract	Determinantal point processes (DPPs) are an important concept in random matrix theory and combinatorics. They have also recently attracted interest in the study of numerical methods for machine learning, as they offer an elegant “missing link” between independent Monte Carlo sampling and deterministic evaluation on regular grids, applicable to a general set of spaces. This is helpful whenever an algorithm explores to reduce uncertainty, such as in active learning, Bayesian optimization, reinforcement learning, and marginalization in graphical models. To draw samples from a DPP in practice, existing literature focuses on approximate schemes of low cost, or comparably inefficient exact algorithms like rejection sampling. We point out that, for many settings of relevance to machine learning, it is also possible to draw exact samples from DPPs on continuous domains. We start from an intuitive example on the real line, which is then generalized to multivariate real vector spaces. We also compare to previously studied approximations, showing that exact sampling, despite higher cost, can be preferable where precision is needed.
Tasks	Active Learning, Point Processes
Published	2016-09-22
URL	http://arxiv.org/abs/1609.06840v2
PDF	http://arxiv.org/pdf/1609.06840v2.pdf
PWC	https://paperswithcode.com/paper/exact-sampling-from-determinantal-point
Repo
Framework

Deep Fruit Detection in Orchards


Title	Deep Fruit Detection in Orchards
Authors	Suchet Bargoti, James Underwood
Abstract	An accurate and reliable image based fruit detection system is critical for supporting higher level agriculture tasks such as yield mapping and robotic harvesting. This paper presents the use of a state-of-the-art object detection framework, Faster R-CNN, in the context of fruit detection in orchards, including mangoes, almonds and apples. Ablation studies are presented to better understand the practical deployment of the detection network, including how much training data is required to capture variability in the dataset. Data augmentation techniques are shown to yield significant performance gains, resulting in a greater than two-fold reduction in the number of training images required. In contrast, transferring knowledge between orchards contributed to negligible performance gain over initialising the Deep Convolutional Neural Network directly from ImageNet features. Finally, to operate over orchard data containing between 100-1000 fruit per image, a tiling approach is introduced for the Faster R-CNN framework. The study has resulted in the best yet detection performance for these orchards relative to previous works, with an F1-score of >0.9 achieved for apples and mangoes.
Tasks	Data Augmentation, Object Detection
Published	2016-10-12
URL	http://arxiv.org/abs/1610.03677v2
PDF	http://arxiv.org/pdf/1610.03677v2.pdf
PWC	https://paperswithcode.com/paper/deep-fruit-detection-in-orchards
Repo
Framework

The Chow Form of the Essential Variety in Computer Vision


Title	The Chow Form of the Essential Variety in Computer Vision
Authors	Gunnar Fløystad, Joe Kileel, Giorgio Ottaviani
Abstract	The Chow form of the essential variety in computer vision is calculated. Our derivation uses secant varieties, Ulrich sheaves and representation theory. Numerical experiments show that our formula can detect noisy point correspondences between two images.
Tasks
Published	2016-04-15
URL	http://arxiv.org/abs/1604.04372v2
PDF	http://arxiv.org/pdf/1604.04372v2.pdf
PWC	https://paperswithcode.com/paper/the-chow-form-of-the-essential-variety-in
Repo
Framework

Cascading Bandits for Large-Scale Recommendation Problems


Title	Cascading Bandits for Large-Scale Recommendation Problems
Authors	Shi Zong, Hao Ni, Kenny Sung, Nan Rosemary Ke, Zheng Wen, Branislav Kveton
Abstract	Most recommender systems recommend a list of items. The user examines the list, from the first item to the last, and often chooses the first attractive item and does not examine the rest. This type of user behavior can be modeled by the cascade model. In this work, we study cascading bandits, an online learning variant of the cascade model where the goal is to recommend $K$ most attractive items from a large set of $L$ candidate items. We propose two algorithms for solving this problem, which are based on the idea of linear generalization. The key idea in our solutions is that we learn a predictor of the attraction probabilities of items from their features, as opposing to learning the attraction probability of each item independently as in the existing work. This results in practical learning algorithms whose regret does not depend on the number of items $L$. We bound the regret of one algorithm and comprehensively evaluate the other on a range of recommendation problems. The algorithm performs well and outperforms all baselines.
Tasks	Recommendation Systems
Published	2016-03-17
URL	http://arxiv.org/abs/1603.05359v2
PDF	http://arxiv.org/pdf/1603.05359v2.pdf
PWC	https://paperswithcode.com/paper/cascading-bandits-for-large-scale
Repo
Framework

Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource


Title	Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource
Authors	Stéphan Tulkens, Chris Emmery, Walter Daelemans
Abstract	Word embeddings have recently seen a strong increase in interest as a result of strong performance gains on a variety of tasks. However, most of this research also underlined the importance of benchmark datasets, and the difficulty of constructing these for a variety of language-specific tasks. Still, many of the datasets used in these tasks could prove to be fruitful linguistic resources, allowing for unique observations into language use and variability. In this paper we demonstrate the performance of multiple types of embeddings, created with both count and prediction-based architectures on a variety of corpora, in two language-specific tasks: relation evaluation, and dialect identification. For the latter, we compare unsupervised methods with a traditional, hand-crafted dictionary. With this research, we provide the embeddings themselves, the relation evaluation task benchmark for use in further research, and demonstrate how the benchmarked embeddings prove a useful unsupervised linguistic resource, effectively used in a downstream task.
Tasks	Word Embeddings
Published	2016-07-01
URL	http://arxiv.org/abs/1607.00225v1
PDF	http://arxiv.org/pdf/1607.00225v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-unsupervised-dutch-word-embeddings
Repo
Framework

Human Action Recognition without Human


Title	Human Action Recognition without Human
Authors	Yun He, Soma Shirakabe, Yutaka Satoh, Hirokatsu Kataoka
Abstract	The objective of this paper is to evaluate “human action recognition without human”. Motion representation is frequently discussed in human action recognition. We have examined several sophisticated options, such as dense trajectories (DT) and the two-stream convolutional neural network (CNN). However, some features from the background could be too strong, as shown in some recent studies on human action recognition. Therefore, we considered whether a background sequence alone can classify human actions in current large-scale action datasets (e.g., UCF101). In this paper, we propose a novel concept for human action analysis that is named “human action recognition without human”. An experiment clearly shows the effect of a background sequence for understanding an action label.
Tasks	Temporal Action Localization
Published	2016-08-29
URL	http://arxiv.org/abs/1608.07876v1
PDF	http://arxiv.org/pdf/1608.07876v1.pdf
PWC	https://paperswithcode.com/paper/human-action-recognition-without-human
Repo
Framework

Local communities obstruct global consensus: Naming game on multi-local-world networks


Title	Local communities obstruct global consensus: Naming game on multi-local-world networks
Authors	Yang Lou, Guanrong Chen, Zhengping Fan, Luna Xiang
Abstract	Community structure is essential for social communications, where individuals belonging to the same community are much more actively interacting and communicating with each other than those in different communities within the human society. Naming game, on the other hand, is a social communication model that simulates the process of learning a name of an object within a community of humans, where the individuals can generally reach global consensus asymptotically through iterative pair-wise conversations. The underlying network indicates the relationships among the individuals. In this paper, three typical topologies, namely random-graph, small-world and scale-free networks, are employed, which are embedded with the multi-local-world community structure, to study the naming game. Simulations show that 1) the convergence process to global consensus is getting slower as the community structure becomes more prominent, and eventually might fail; 2) if the inter-community connections are sufficiently dense, neither the number nor the size of the communities affects the convergence process; and 3) for different topologies with the same average node-degree, local clustering of individuals obstruct or prohibit global consensus to take place. The results reveal the role of local communities in a global naming game in social network studies.
Tasks
Published	2016-05-20
URL	http://arxiv.org/abs/1605.06304v2
PDF	http://arxiv.org/pdf/1605.06304v2.pdf
PWC	https://paperswithcode.com/paper/local-communities-obstruct-global-consensus
Repo
Framework

Sequence Classification with Neural Conditional Random Fields


Title	Sequence Classification with Neural Conditional Random Fields
Authors	Myriam Abramson
Abstract	The proliferation of sensor devices monitoring human activity generates voluminous amount of temporal sequences needing to be interpreted and categorized. Moreover, complex behavior detection requires the personalization of multi-sensor fusion algorithms. Conditional random fields (CRFs) are commonly used in structured prediction tasks such as part-of-speech tagging in natural language processing. Conditional probabilities guide the choice of each tag/label in the sequence conflating the structured prediction task with the sequence classification task where different models provide different categorization of the same sequence. The claim of this paper is that CRF models also provide discriminative models to distinguish between types of sequence regardless of the accuracy of the labels obtained if we calibrate the class membership estimate of the sequence. We introduce and compare different neural network based linear-chain CRFs and we present experiments on two complex sequence classification and structured prediction tasks to support this claim.
Tasks	Part-Of-Speech Tagging, Sensor Fusion, Structured Prediction
Published	2016-02-05
URL	http://arxiv.org/abs/1602.02123v1
PDF	http://arxiv.org/pdf/1602.02123v1.pdf
PWC	https://paperswithcode.com/paper/sequence-classification-with-neural
Repo
Framework

Deep Quality: A Deep No-reference Quality Assessment System


Title	Deep Quality: A Deep No-reference Quality Assessment System
Authors	Prajna Paramita Dash, Akshaya Mishra, Alexander Wong
Abstract	Image quality assessment (IQA) continues to garner great interest in the research community, particularly given the tremendous rise in consumer video capture and streaming. Despite significant research effort in IQA in the past few decades, the area of no-reference image quality assessment remains a great challenge and is largely unsolved. In this paper, we propose a novel no-reference image quality assessment system called Deep Quality, which leverages the power of deep learning to model the complex relationship between visual content and the perceived quality. Deep Quality consists of a novel multi-scale deep convolutional neural network, trained to learn to assess image quality based on training samples consisting of different distortions and degradations such as blur, Gaussian noise, and compression artifacts. Preliminary results using the CSIQ benchmark image quality dataset showed that Deep Quality was able to achieve strong quality prediction performance (89% patch-level and 98% image-level prediction accuracy), being able to achieve similar performance as full-reference IQA methods.
Tasks	Image Quality Assessment, No-Reference Image Quality Assessment
Published	2016-09-22
URL	http://arxiv.org/abs/1609.07170v1
PDF	http://arxiv.org/pdf/1609.07170v1.pdf
PWC	https://paperswithcode.com/paper/deep-quality-a-deep-no-reference-quality
Repo
Framework

Talk it up or play it down? (Un)expected correlations between (de-)emphasis and recurrence of discussion points in consequential U.S. economic policy meetings


Title	Talk it up or play it down? (Un)expected correlations between (de-)emphasis and recurrence of discussion points in consequential U.S. economic policy meetings
Authors	Chenhao Tan, Lillian Lee
Abstract	In meetings where important decisions get made, what items receive more attention may influence the outcome. We examine how different types of rhetorical (de-)emphasis – including hedges, superlatives, and contrastive conjunctions – correlate with what gets revisited later, controlling for item frequency and speaker. Our data consists of transcripts of recurring meetings of the Federal Reserve’s Open Market Committee (FOMC), where important aspects of U.S. monetary policy are decided on. Surprisingly, we find that words appearing in the context of hedging, which is usually considered a way to express uncertainty, are more likely to be repeated in subsequent meetings, while strong emphasis indicated by superlatives has a slightly negative effect on word recurrence in subsequent meetings. We also observe interesting patterns in how these effects vary depending on social factors such as status and gender of the speaker. For instance, the positive effects of hedging are more pronounced for female speakers than for male speakers.
Tasks
Published	2016-12-19
URL	http://arxiv.org/abs/1612.06391v1
PDF	http://arxiv.org/pdf/1612.06391v1.pdf
PWC	https://paperswithcode.com/paper/talk-it-up-or-play-it-down-unexpected
Repo
Framework