May 7, 2019

3278 words 16 mins read

Paper Group AWR 61

Sentiment Analysis of Twitter Data for Predicting Stock Market Movements. Watch What You Just Said: Image Captioning with Text-Conditional Attention. Disentangling factors of variation in deep representations using adversarial training. Large-Scale Kernel Methods for Independence Testing. One-Shot Video Object Segmentation. Deep Label Distribution …

Sentiment Analysis of Twitter Data for Predicting Stock Market Movements


Title	Sentiment Analysis of Twitter Data for Predicting Stock Market Movements
Authors	Venkata Sasank Pagolu, Kamal Nayan Reddy Challa, Ganapati Panda, Babita Majhi
Abstract	Predicting stock market movements is a well-known problem of interest. Now-a-days social media is perfectly representing the public sentiment and opinion about current events. Especially, twitter has attracted a lot of attention from researchers for studying the public sentiments. Stock market prediction on the basis of public sentiments expressed on twitter has been an intriguing field of research. Previous studies have concluded that the aggregate public mood collected from twitter may well be correlated with Dow Jones Industrial Average Index (DJIA). The thesis of this work is to observe how well the changes in stock prices of a company, the rises and falls, are correlated with the public opinions being expressed in tweets about that company. Understanding author’s opinion from a piece of text is the objective of sentiment analysis. The present paper have employed two different textual representations, Word2vec and N-gram, for analyzing the public sentiments in tweets. In this paper, we have applied sentiment analysis and supervised machine learning principles to the tweets extracted from twitter and analyze the correlation between stock market movements of a company and sentiments in tweets. In an elaborate way, positive news and tweets in social media about a company would definitely encourage people to invest in the stocks of that company and as a result the stock price of that company would increase. At the end of the paper, it is shown that a strong correlation exists between the rise and falls in stock prices with the public sentiments in tweets.
Tasks	Sentiment Analysis, Stock Market Prediction
Published	2016-10-28
URL	http://arxiv.org/abs/1610.09225v1
PDF	http://arxiv.org/pdf/1610.09225v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-analysis-of-twitter-data-for
Repo	https://github.com/ap0996/TweetAnalyser
Framework	none

Watch What You Just Said: Image Captioning with Text-Conditional Attention


Title	Watch What You Just Said: Image Captioning with Text-Conditional Attention
Authors	Luowei Zhou, Chenliang Xu, Parker Koch, Jason J. Corso
Abstract	Attention mechanisms have attracted considerable interest in image captioning due to its powerful performance. However, existing methods use only visual content as attention and whether textual context can improve attention in image captioning remains unsolved. To explore this problem, we propose a novel attention mechanism, called \textit{text-conditional attention}, which allows the caption generator to focus on certain image features given previously generated text. To obtain text-related image features for our attention model, we adopt the guiding Long Short-Term Memory (gLSTM) captioning architecture with CNN fine-tuning. Our proposed method allows joint learning of the image embedding, text embedding, text-conditional attention and language model with one network architecture in an end-to-end manner. We perform extensive experiments on the MS-COCO dataset. The experimental results show that our method outperforms state-of-the-art captioning methods on various quantitative metrics as well as in human evaluation, which supports the use of our text-conditional attention in image captioning.
Tasks	Image Captioning, Language Modelling
Published	2016-06-15
URL	http://arxiv.org/abs/1606.04621v3
PDF	http://arxiv.org/pdf/1606.04621v3.pdf
PWC	https://paperswithcode.com/paper/watch-what-you-just-said-image-captioning
Repo	https://github.com/LuoweiZhou/e2e-gLSTM-sc
Framework	none

Disentangling factors of variation in deep representations using adversarial training


Title	Disentangling factors of variation in deep representations using adversarial training
Authors	Michael Mathieu, Junbo Zhao, Pablo Sprechmann, Aditya Ramesh, Yann LeCun
Abstract	We introduce a conditional generative model for learning to disentangle the hidden factors of variation within a set of labeled observations, and separate them into complementary codes. One code summarizes the specified factors of variation associated with the labels. The other summarizes the remaining unspecified variability. During training, the only available source of supervision comes from our ability to distinguish among different observations belonging to the same class. Examples of such observations include images of a set of labeled objects captured at different viewpoints, or recordings of set of speakers dictating multiple phrases. In both instances, the intra-class diversity is the source of the unspecified factors of variation: each object is observed at multiple viewpoints, and each speaker dictates multiple phrases. Learning to disentangle the specified factors from the unspecified ones becomes easier when strong supervision is possible. Suppose that during training, we have access to pairs of images, where each pair shows two different objects captured from the same viewpoint. This source of alignment allows us to solve our task using existing methods. However, labels for the unspecified factors are usually unavailable in realistic scenarios where data acquisition is not strictly controlled. We address the problem of disentanglement in this more general setting by combining deep convolutional autoencoders with a form of adversarial training. Both factors of variation are implicitly captured in the organization of the learned embedding space, and can be used for solving single-image analogies. Experimental results on synthetic and real datasets show that the proposed method is capable of generalizing to unseen classes and intra-class variabilities.
Tasks
Published	2016-11-10
URL	http://arxiv.org/abs/1611.03383v1
PDF	http://arxiv.org/pdf/1611.03383v1.pdf
PWC	https://paperswithcode.com/paper/disentangling-factors-of-variation-in-deep
Repo	https://github.com/ananyahjha93/disentangling-factors-of-variation-using-adversarial-training
Framework	pytorch

Large-Scale Kernel Methods for Independence Testing


Title	Large-Scale Kernel Methods for Independence Testing
Authors	Qinyi Zhang, Sarah Filippi, Arthur Gretton, Dino Sejdinovic
Abstract	Representations of probability measures in reproducing kernel Hilbert spaces provide a flexible framework for fully nonparametric hypothesis tests of independence, which can capture any type of departure from independence, including nonlinear associations and multivariate interactions. However, these approaches come with an at least quadratic computational cost in the number of observations, which can be prohibitive in many applications. Arguably, it is exactly in such large-scale datasets that capturing any type of dependence is of interest, so striking a favourable tradeoff between computational efficiency and test performance for kernel independence tests would have a direct impact on their applicability in practice. In this contribution, we provide an extensive study of the use of large-scale kernel approximations in the context of independence testing, contrasting block-based, Nystrom and random Fourier feature approaches. Through a variety of synthetic data experiments, it is demonstrated that our novel large scale methods give comparable performance with existing methods whilst using significantly less computation time and memory.
Tasks
Published	2016-06-25
URL	http://arxiv.org/abs/1606.07892v1
PDF	http://arxiv.org/pdf/1606.07892v1.pdf
PWC	https://paperswithcode.com/paper/large-scale-kernel-methods-for-independence
Repo	https://github.com/IBM/SIC
Framework	pytorch

One-Shot Video Object Segmentation


Title	One-Shot Video Object Segmentation
Authors	Sergi Caelles, Kevis-Kokitsi Maninis, Jordi Pont-Tuset, Laura Leal-Taixé, Daniel Cremers, Luc Van Gool
Abstract	This paper tackles the task of semi-supervised video object segmentation, i.e., the separation of an object from the background in a video, given the mask of the first frame. We present One-Shot Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Although all frames are processed independently, the results are temporally coherent and stable. We perform experiments on two annotated video segmentation databases, which show that OSVOS is fast and improves the state of the art by a significant margin (79.8% vs 68.0%).
Tasks	Semi-supervised Video Object Segmentation, Video Object Segmentation, Visual Object Tracking
Published	2016-11-16
URL	http://arxiv.org/abs/1611.05198v4
PDF	http://arxiv.org/pdf/1611.05198v4.pdf
PWC	https://paperswithcode.com/paper/one-shot-video-object-segmentation
Repo	https://github.com/scaelles/OSVOS-TensorFlow
Framework	tf

Deep Label Distribution Learning with Label Ambiguity


Title	Deep Label Distribution Learning with Label Ambiguity
Authors	Bin-Bin Gao, Chao Xing, Chen-Wei Xie, Jianxin Wu, Xin Geng
Abstract	Convolutional Neural Networks (ConvNets) have achieved excellent recognition performance in various visual recognition tasks. A large labeled training set is one of the most important factors for its success. However, it is difficult to collect sufficient training images with precise labels in some domains such as apparent age estimation, head pose estimation, multi-label classification and semantic segmentation. Fortunately, there is ambiguous information among labels, which makes these tasks different from traditional classification. Based on this observation, we convert the label of each image into a discrete label distribution, and learn the label distribution by minimizing a Kullback-Leibler divergence between the predicted and ground-truth label distributions using deep ConvNets. The proposed DLDL (Deep Label Distribution Learning) method effectively utilizes the label ambiguity in both feature learning and classifier learning, which help prevent the network from over-fitting even when the training set is small. Experimental results show that the proposed approach produces significantly better results than state-of-the-art methods for age estimation and head pose estimation. At the same time, it also improves recognition performance for multi-label classification and semantic segmentation tasks.
Tasks	Age Estimation, Head Pose Estimation, Multi-Label Classification, Pose Estimation, Semantic Segmentation
Published	2016-11-06
URL	http://arxiv.org/abs/1611.01731v2
PDF	http://arxiv.org/pdf/1611.01731v2.pdf
PWC	https://paperswithcode.com/paper/deep-label-distribution-learning-with-label
Repo	https://github.com/gaobb/DLDL
Framework	none

Alternating Direction Graph Matching


Title	Alternating Direction Graph Matching
Authors	D. Khuê Lê-Huu, Nikos Paragios
Abstract	In this paper, we introduce a graph matching method that can account for constraints of arbitrary order, with arbitrary potential functions. Unlike previous decomposition approaches that rely on the graph structures, we introduce a decomposition of the matching constraints. Graph matching is then reformulated as a non-convex non-separable optimization problem that can be split into smaller and much-easier-to-solve subproblems, by means of the alternating direction method of multipliers. The proposed framework is modular, scalable, and can be instantiated into different variants. Two instantiations are studied exploring pairwise and higher-order constraints. Experimental results on widely adopted benchmarks involving synthetic and real examples demonstrate that the proposed solutions outperform existing pairwise graph matching methods, and competitive with the state of the art in higher-order settings.
Tasks	Graph Matching
Published	2016-11-22
URL	http://arxiv.org/abs/1611.07583v4
PDF	http://arxiv.org/pdf/1611.07583v4.pdf
PWC	https://paperswithcode.com/paper/alternating-direction-graph-matching
Repo	https://github.com/netw0rkf10w/adgm
Framework	none

Double/Debiased Machine Learning for Treatment and Causal Parameters


Title	Double/Debiased Machine Learning for Treatment and Causal Parameters
Authors	Victor Chernozhukov, Denis Chetverikov, Mert Demirer, Esther Duflo, Christian Hansen, Whitney Newey, James Robins
Abstract	Most modern supervised statistical/machine learning (ML) methods are explicitly designed to solve prediction problems very well. Achieving this goal does not imply that these methods automatically deliver good estimators of causal parameters. Examples of such parameters include individual regression coefficients, average treatment effects, average lifts, and demand or supply elasticities. In fact, estimates of such causal parameters obtained via naively plugging ML estimators into estimating equations for such parameters can behave very poorly due to the regularization bias. Fortunately, this regularization bias can be removed by solving auxiliary prediction problems via ML tools. Specifically, we can form an orthogonal score for the target low-dimensional parameter by combining auxiliary and main ML predictions. The score is then used to build a de-biased estimator of the target parameter which typically will converge at the fastest possible 1/root(n) rate and be approximately unbiased and normal, and from which valid confidence intervals for these parameters of interest may be constructed. The resulting method thus could be called a “double ML” method because it relies on estimating primary and auxiliary predictive models. In order to avoid overfitting, our construction also makes use of the K-fold sample splitting, which we call cross-fitting. This allows us to use a very broad set of ML predictive methods in solving the auxiliary and main prediction problems, such as random forest, lasso, ridge, deep neural nets, boosted trees, as well as various hybrids and aggregators of these methods.
Tasks	Causal Inference
Published	2016-07-30
URL	http://arxiv.org/abs/1608.00060v6
PDF	http://arxiv.org/pdf/1608.00060v6.pdf
PWC	https://paperswithcode.com/paper/doubledebiased-machine-learning-for-treatment
Repo	https://github.com/Microsoft/EconML
Framework	none

Learning a metric for class-conditional KNN


Title	Learning a metric for class-conditional KNN
Authors	Daniel Jiwoong Im, Graham W. Taylor
Abstract	Naive Bayes Nearest Neighbour (NBNN) is a simple and effective framework which addresses many of the pitfalls of K-Nearest Neighbour (KNN) classification. It has yielded competitive results on several computer vision benchmarks. Its central tenet is that during NN search, a query is not compared to every example in a database, ignoring class information. Instead, NN searches are performed within each class, generating a score per class. A key problem with NN techniques, including NBNN, is that they fail when the data representation does not capture perceptual (e.g.~class-based) similarity. NBNN circumvents this by using independent engineered descriptors (e.g.~SIFT). To extend its applicability outside of image-based domains, we propose to learn a metric which captures perceptual similarity. Similar to how Neighbourhood Components Analysis optimizes a differentiable form of KNN classification, we propose “Class Conditional” metric learning (CCML), which optimizes a soft form of the NBNN selection rule. Typical metric learning algorithms learn either a global or local metric. However, our proposed method can be adjusted to a particular level of locality by tuning a single parameter. An empirical evaluation on classification and retrieval tasks demonstrates that our proposed method clearly outperforms existing learned distance metrics across a variety of image and non-image datasets.
Tasks	Metric Learning
Published	2016-07-11
URL	http://arxiv.org/abs/1607.03050v1
PDF	http://arxiv.org/pdf/1607.03050v1.pdf
PWC	https://paperswithcode.com/paper/learning-a-metric-for-class-conditional-knn
Repo	https://github.com/jiwoongim/CCML
Framework	none

Feature Pyramid Networks for Object Detection


Title	Feature Pyramid Networks for Object Detection
Authors	Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie
Abstract	Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But recent deep learning object detectors have avoided pyramid representations, in part because they are compute and memory intensive. In this paper, we exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost. A top-down architecture with lateral connections is developed for building high-level semantic feature maps at all scales. This architecture, called a Feature Pyramid Network (FPN), shows significant improvement as a generic feature extractor in several applications. Using FPN in a basic Faster R-CNN system, our method achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles, surpassing all existing single-model entries including those from the COCO 2016 challenge winners. In addition, our method can run at 5 FPS on a GPU and thus is a practical and accurate solution to multi-scale object detection. Code will be made publicly available.
Tasks	Object Detection
Published	2016-12-09
URL	http://arxiv.org/abs/1612.03144v2
PDF	http://arxiv.org/pdf/1612.03144v2.pdf
PWC	https://paperswithcode.com/paper/feature-pyramid-networks-for-object-detection
Repo	https://github.com/soeaver/py-RFCN-priv
Framework	none

Visual Storytelling


Title	Visual Storytelling
Authors	Ting-Hao, Huang, Francis Ferraro, Nasrin Mostafazadeh, Ishan Misra, Aishwarya Agrawal, Jacob Devlin, Ross Girshick, Xiaodong He, Pushmeet Kohli, Dhruv Batra, C. Lawrence Zitnick, Devi Parikh, Lucy Vanderwende, Michel Galley, Margaret Mitchell
Abstract	We introduce the first dataset for sequential vision-to-language, and explore how this data may be used for the task of visual storytelling. The first release of this dataset, SIND v.1, includes 81,743 unique photos in 20,211 sequences, aligned to both descriptive (caption) and story language. We establish several strong baselines for the storytelling task, and motivate an automatic metric to benchmark progress. Modelling concrete description as well as figurative and social language, as provided in this dataset and the storytelling task, has the potential to move artificial intelligence from basic understandings of typical visual scenes towards more and more human-like understanding of grounded event structure and subjective expression.
Tasks	Visual Storytelling
Published	2016-04-13
URL	http://arxiv.org/abs/1604.03968v1
PDF	http://arxiv.org/pdf/1604.03968v1.pdf
PWC	https://paperswithcode.com/paper/visual-storytelling
Repo	https://github.com/Pendulibrium/ai-visual-storytelling-seq2seq
Framework	tf

Inverse Compositional Spatial Transformer Networks


Title	Inverse Compositional Spatial Transformer Networks
Authors	Chen-Hsuan Lin, Simon Lucey
Abstract	In this paper, we establish a theoretical connection between the classical Lucas & Kanade (LK) algorithm and the emerging topic of Spatial Transformer Networks (STNs). STNs are of interest to the vision and learning communities due to their natural ability to combine alignment and classification within the same theoretical framework. Inspired by the Inverse Compositional (IC) variant of the LK algorithm, we present Inverse Compositional Spatial Transformer Networks (IC-STNs). We demonstrate that IC-STNs can achieve better performance than conventional STNs with less model capacity; in particular, we show superior performance in pure image alignment tasks as well as joint alignment/classification problems on real-world problems.
Tasks
Published	2016-12-12
URL	http://arxiv.org/abs/1612.03897v1
PDF	http://arxiv.org/pdf/1612.03897v1.pdf
PWC	https://paperswithcode.com/paper/inverse-compositional-spatial-transformer
Repo	https://github.com/chenhsuanlin/inverse-compositional-STN
Framework	tf

Photo Aesthetics Ranking Network with Attributes and Content Adaptation


Title	Photo Aesthetics Ranking Network with Attributes and Content Adaptation
Authors	Shu Kong, Xiaohui Shen, Zhe Lin, Radomir Mech, Charless Fowlkes
Abstract	Real-world applications could benefit from the ability to automatically generate a fine-grained ranking of photo aesthetics. However, previous methods for image aesthetics analysis have primarily focused on the coarse, binary categorization of images into high- or low-aesthetic categories. In this work, we propose to learn a deep convolutional neural network to rank photo aesthetics in which the relative ranking of photo aesthetics are directly modeled in the loss function. Our model incorporates joint learning of meaningful photographic attributes and image content information which can help regularize the complicated photo aesthetics rating problem. To train and analyze this model, we have assembled a new aesthetics and attributes database (AADB) which contains aesthetic scores and meaningful attributes assigned to each image by multiple human raters. Anonymized rater identities are recorded across images allowing us to exploit intra-rater consistency using a novel sampling strategy when computing the ranking loss of training image pairs. We show the proposed sampling strategy is very effective and robust in face of subjective judgement of image aesthetics by individuals with different aesthetic tastes. Experiments demonstrate that our unified model can generate aesthetic rankings that are more consistent with human ratings. To further validate our model, we show that by simply thresholding the estimated aesthetic scores, we are able to achieve state-or-the-art classification performance on the existing AVA dataset benchmark.
Tasks	Aesthetics Quality Assessment
Published	2016-06-06
URL	http://arxiv.org/abs/1606.01621v2
PDF	http://arxiv.org/pdf/1606.01621v2.pdf
PWC	https://paperswithcode.com/paper/photo-aesthetics-ranking-network-with
Repo	https://github.com/aimerykong/deepImageAestheticsAnalysis
Framework	none

Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies


Title	Sublabel-Accurate Convex Relaxation of Vectorial Multilabel Energies
Authors	Emanuel Laude, Thomas Möllenhoff, Michael Moeller, Jan Lellmann, Daniel Cremers
Abstract	Convex relaxations of nonconvex multilabel problems have been demonstrated to produce superior (provably optimal or near-optimal) solutions to a variety of classical computer vision problems. Yet, they are of limited practical use as they require a fine discretization of the label space, entailing a huge demand in memory and runtime. In this work, we propose the first sublabel accurate convex relaxation for vectorial multilabel problems. The key idea is that we approximate the dataterm of the vectorial labeling problem in a piecewise convex (rather than piecewise linear) manner. As a result we have a more faithful approximation of the original cost function that provides a meaningful interpretation for the fractional solutions of the relaxed convex problem. In numerous experiments on large-displacement optical flow estimation and on color image denoising we demonstrate that the computed solutions have superior quality while requiring much lower memory and runtime.
Tasks	Denoising, Image Denoising, Optical Flow Estimation
Published	2016-04-07
URL	http://arxiv.org/abs/1604.01980v2
PDF	http://arxiv.org/pdf/1604.01980v2.pdf
PWC	https://paperswithcode.com/paper/sublabel-accurate-convex-relaxation-of
Repo	https://github.com/tum-vision/sublabel_relax
Framework	none

Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access


Title	Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access
Authors	Bhuwan Dhingra, Lihong Li, Xiujun Li, Jianfeng Gao, Yun-Nung Chen, Faisal Ahmed, Li Deng
Abstract	This paper proposes KB-InfoBot – a multi-turn dialogue agent which helps users search Knowledge Bases (KBs) without composing complicated queries. Such goal-oriented dialogue agents typically need to interact with an external database to access real-world knowledge. Previous systems achieved this by issuing a symbolic query to the KB to retrieve entries based on their attributes. However, such symbolic operations break the differentiability of the system and prevent end-to-end training of neural dialogue agents. In this paper, we address this limitation by replacing symbolic queries with an induced “soft” posterior distribution over the KB that indicates which entities the user is interested in. Integrating the soft retrieval process with a reinforcement learner leads to higher task success rate and reward in both simulations and against real users. We also present a fully neural end-to-end agent, trained entirely from user feedback, and discuss its application towards personalized dialogue agents. The source code is available at https://github.com/MiuLab/KB-InfoBot.
Tasks
Published	2016-09-03
URL	http://arxiv.org/abs/1609.00777v3
PDF	http://arxiv.org/pdf/1609.00777v3.pdf
PWC	https://paperswithcode.com/paper/towards-end-to-end-reinforcement-learning-of
Repo	https://github.com/MiuLab/KB-InfoBot
Framework	none