Paper Group ANR 354
Investigating Human Factors in Image Forgery Detection. Label Refinement Network for Coarse-to-Fine Semantic Segmentation. Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes. Efficient Social Network Multilingual Classification using Character, POS n-grams and Dynamic Normalization. Dynamics of core of langua …
Investigating Human Factors in Image Forgery Detection
| Title | Investigating Human Factors in Image Forgery Detection |
| Authors | Parag S. Chandakkar, Baoxin Li |
| Abstract | In today’s age of internet and social media, one can find an enormous volume of forged images on-line. These images have been used in the past to convey falsified information and achieve harmful intentions. The spread and the effect of the social media only makes this problem more severe. While creating forged images has become easier due to software advancements, there is no automated algorithm which can reliably detect forgery. Image forgery detection can be seen as a subset of image understanding problem. Human performance is still the gold-standard for these type of problems when compared to existing state-of-art automated algorithms. We conduct a subjective evaluation test with the aid of eye-tracker to investigate into human factors associated with this problem. We compare the performance of an automated algorithm and humans for forgery detection problem. We also develop an algorithm which uses the data from the evaluation test to predict the difficulty-level of an image (the difficulty-level of an image here denotes how difficult it is for humans to detect forgery in an image. Terms such as “Easy/difficult image” will be used in the same context). The experimental results presented in this paper should facilitate development of better algorithms in the future. |
| Tasks | |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01262v1 |
| http://arxiv.org/pdf/1704.01262v1.pdf | |
| PWC | https://paperswithcode.com/paper/investigating-human-factors-in-image-forgery |
| Repo | |
| Framework | |
Label Refinement Network for Coarse-to-Fine Semantic Segmentation
| Title | Label Refinement Network for Coarse-to-Fine Semantic Segmentation |
| Authors | Md Amirul Islam, Shujon Naha, Mrigank Rochan, Neil Bruce, Yang Wang |
| Abstract | We consider the problem of semantic image segmentation using deep convolutional neural networks. We propose a novel network architecture called the label refinement network that predicts segmentation labels in a coarse-to-fine fashion at several resolutions. The segmentation labels at a coarse resolution are used together with convolutional features to obtain finer resolution segmentation labels. We define loss functions at several stages in the network to provide supervisions at different stages. Our experimental results on several standard datasets demonstrate that the proposed model provides an effective way of producing pixel-wise dense image labeling. |
| Tasks | Semantic Segmentation |
| Published | 2017-03-01 |
| URL | http://arxiv.org/abs/1703.00551v1 |
| http://arxiv.org/pdf/1703.00551v1.pdf | |
| PWC | https://paperswithcode.com/paper/label-refinement-network-for-coarse-to-fine |
| Repo | |
| Framework | |
Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes
| Title | Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes |
| Authors | Ahmed M. Alaa, Mihaela van der Schaar |
| Abstract | Predicated on the increasing abundance of electronic health records, we investi- gate the problem of inferring individualized treatment effects using observational data. Stemming from the potential outcomes model, we propose a novel multi- task learning framework in which factual and counterfactual outcomes are mod- eled as the outputs of a function in a vector-valued reproducing kernel Hilbert space (vvRKHS). We develop a nonparametric Bayesian method for learning the treatment effects using a multi-task Gaussian process (GP) with a linear coregion- alization kernel as a prior over the vvRKHS. The Bayesian approach allows us to compute individualized measures of confidence in our estimates via pointwise credible intervals, which are crucial for realizing the full potential of precision medicine. The impact of selection bias is alleviated via a risk-based empirical Bayes method for adapting the multi-task GP prior, which jointly minimizes the empirical error in factual outcomes and the uncertainty in (unobserved) counter- factual outcomes. We conduct experiments on observational datasets for an inter- ventional social program applied to premature infants, and a left ventricular assist device applied to cardiac patients wait-listed for a heart transplant. In both experi- ments, we show that our method significantly outperforms the state-of-the-art. |
| Tasks | Bayesian Inference, Gaussian Processes, Multi-Task Learning |
| Published | 2017-04-10 |
| URL | http://arxiv.org/abs/1704.02801v2 |
| http://arxiv.org/pdf/1704.02801v2.pdf | |
| PWC | https://paperswithcode.com/paper/bayesian-inference-of-individualized |
| Repo | |
| Framework | |
Efficient Social Network Multilingual Classification using Character, POS n-grams and Dynamic Normalization
| Title | Efficient Social Network Multilingual Classification using Character, POS n-grams and Dynamic Normalization |
| Authors | Carlos-Emiliano González-Gallardo, Juan-Manuel Torres-Moreno, Azucena Montes Rendón, Gerardo Sierra |
| Abstract | In this paper we describe a dynamic normalization process applied to social network multilingual documents (Facebook and Twitter) to improve the performance of the Author profiling task for short texts. After the normalization process, $n$-grams of characters and n-grams of POS tags are obtained to extract all the possible stylistic information encoded in the documents (emoticons, character flooding, capital letters, references to other users, hyperlinks, hashtags, etc.). Experiments with SVM showed up to 90% of performance. |
| Tasks | |
| Published | 2017-02-21 |
| URL | http://arxiv.org/abs/1702.06467v1 |
| http://arxiv.org/pdf/1702.06467v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-social-network-multilingual |
| Repo | |
| Framework | |
Dynamics of core of language vocabulary
| Title | Dynamics of core of language vocabulary |
| Authors | Valery D. Solovyev, Vladimir V. Bochkarev, Anna V. Shevlyakova |
| Abstract | Studies of the overall structure of vocabulary and its dynamics became possible due to creation of diachronic text corpora, especially Google Books Ngram. This article discusses the question of core change rate and the degree to which the core words cover the texts. Different periods of the last three centuries and six main European languages presented in Google Books Ngram are compared. The main result is high stability of core change rate, which is analogous to stability of the Swadesh list. |
| Tasks | |
| Published | 2017-05-29 |
| URL | http://arxiv.org/abs/1705.10112v1 |
| http://arxiv.org/pdf/1705.10112v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamics-of-core-of-language-vocabulary |
| Repo | |
| Framework | |
On Hölder projective divergences
| Title | On Hölder projective divergences |
| Authors | Frank Nielsen, Ke Sun, Stéphane Marchand-Maillet |
| Abstract | We describe a framework to build distances by measuring the tightness of inequalities, and introduce the notion of proper statistical divergences and improper pseudo-divergences. We then consider the H"older ordinary and reverse inequalities, and present two novel classes of H"older divergences and pseudo-divergences that both encapsulate the special case of the Cauchy-Schwarz divergence. We report closed-form formulas for those statistical dissimilarities when considering distributions belonging to the same exponential family provided that the natural parameter space is a cone (e.g., multivariate Gaussians), or affine (e.g., categorical distributions). Those new classes of H"older distances are invariant to rescaling, and thus do not require distributions to be normalized. Finally, we show how to compute statistical H"older centroids with respect to those divergences, and carry out center-based clustering toy experiments on a set of Gaussian distributions that demonstrate empirically that symmetrized H"older divergences outperform the symmetric Cauchy-Schwarz divergence. |
| Tasks | |
| Published | 2017-01-14 |
| URL | http://arxiv.org/abs/1701.03916v1 |
| http://arxiv.org/pdf/1701.03916v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-holder-projective-divergences |
| Repo | |
| Framework | |
A Non-Rigid Map Fusion-Based RGB-Depth SLAM Method for Endoscopic Capsule Robots
| Title | A Non-Rigid Map Fusion-Based RGB-Depth SLAM Method for Endoscopic Capsule Robots |
| Authors | Mehmet Turan, Yasin Almalioglu, Helder Araujo, Ender Konukoglu, Metin Sitti |
| Abstract | In the gastrointestinal (GI) tract endoscopy field, ingestible wireless capsule endoscopy is considered as a minimally invasive novel diagnostic technology to inspect the entire GI tract and to diagnose various diseases and pathologies. Since the development of this technology, medical device companies and many groups have made significant progress to turn such passive capsule endoscopes into robotic active capsule endoscopes to achieve almost all functions of current active flexible endoscopes. However, the use of robotic capsule endoscopy still has some challenges. One such challenge is the precise localization of such active devices in 3D world, which is essential for a precise three-dimensional (3D) mapping of the inner organ. A reliable 3D map of the explored inner organ could assist the doctors to make more intuitive and correct diagnosis. In this paper, we propose to our knowledge for the first time in literature a visual simultaneous localization and mapping (SLAM) method specifically developed for endoscopic capsule robots. The proposed RGB-Depth SLAM method is capable of capturing comprehensive dense globally consistent surfel-based maps of the inner organs explored by an endoscopic capsule robot in real time. This is achieved by using dense frame-to-model camera tracking and windowed surfelbased fusion coupled with frequent model refinement through non-rigid surface deformations. |
| Tasks | Simultaneous Localization and Mapping |
| Published | 2017-05-15 |
| URL | http://arxiv.org/abs/1705.05444v1 |
| http://arxiv.org/pdf/1705.05444v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-non-rigid-map-fusion-based-rgb-depth-slam |
| Repo | |
| Framework | |
Heterogeneous Information Network Embedding for Meta Path based Proximity
| Title | Heterogeneous Information Network Embedding for Meta Path based Proximity |
| Authors | Zhipeng Huang, Nikos Mamoulis |
| Abstract | A network embedding is a representation of a large graph in a low-dimensional space, where vertices are modeled as vectors. The objective of a good embedding is to preserve the proximity between vertices in the original graph. This way, typical search and mining methods can be applied in the embedded space with the help of off-the-shelf multidimensional indexing approaches. Existing network embedding techniques focus on homogeneous networks, where all vertices are considered to belong to a single class. |
| Tasks | Network Embedding |
| Published | 2017-01-19 |
| URL | http://arxiv.org/abs/1701.05291v1 |
| http://arxiv.org/pdf/1701.05291v1.pdf | |
| PWC | https://paperswithcode.com/paper/heterogeneous-information-network-embedding |
| Repo | |
| Framework | |
Evolving Game Skill-Depth using General Video Game AI Agents
| Title | Evolving Game Skill-Depth using General Video Game AI Agents |
| Authors | Jialin Liu, Julian Togelius, Diego Perez-Liebana, Simon M. Lucas |
| Abstract | Most games have, or can be generalised to have, a number of parameters that may be varied in order to provide instances of games that lead to very different player experiences. The space of possible parameter settings can be seen as a search space, and we can therefore use a Random Mutation Hill Climbing algorithm or other search methods to find the parameter settings that induce the best games. One of the hardest parts of this approach is defining a suitable fitness function. In this paper we explore the possibility of using one of a growing set of General Video Game AI agents to perform automatic play-testing. This enables a very general approach to game evaluation based on estimating the skill-depth of a game. Agent-based play-testing is computationally expensive, so we compare two simple but efficient optimisation algorithms: the Random Mutation Hill-Climber and the Multi-Armed Bandit Random Mutation Hill-Climber. For the test game we use a space-battle game in order to provide a suitable balance between simulation speed and potential skill-depth. Results show that both algorithms are able to rapidly evolve game versions with significant skill-depth, but that choosing a suitable resampling number is essential in order to combat the effects of noise. |
| Tasks | |
| Published | 2017-03-18 |
| URL | http://arxiv.org/abs/1703.06275v1 |
| http://arxiv.org/pdf/1703.06275v1.pdf | |
| PWC | https://paperswithcode.com/paper/evolving-game-skill-depth-using-general-video |
| Repo | |
| Framework | |
Siamese LSTM based Fiber Structural Similarity Network (FS2Net) for Rotation Invariant Brain Tractography Segmentation
| Title | Siamese LSTM based Fiber Structural Similarity Network (FS2Net) for Rotation Invariant Brain Tractography Segmentation |
| Authors | Shreyas Malakarjun Patil, Aditya Nigam, Arnav Bhavsar, Chiranjoy Chattopadhyay |
| Abstract | In this paper, we propose a novel deep learning architecture combining stacked Bi-directional LSTM and LSTMs with the Siamese network architecture for segmentation of brain fibers, obtained from tractography data, into anatomically meaningful clusters. The proposed network learns the structural difference between fibers of different classes, which enables it to classify fibers with high accuracy. Importantly, capturing such deep inter and intra class structural relationship also ensures that the segmentation is robust to relative rotation among test and training data, hence can be used with unregistered data. Our extensive experimentation over order of hundred-thousands of fibers show that the proposed model achieves state-of-the-art results, even in cases of large relative rotations between test and training data. |
| Tasks | |
| Published | 2017-12-28 |
| URL | http://arxiv.org/abs/1712.09792v1 |
| http://arxiv.org/pdf/1712.09792v1.pdf | |
| PWC | https://paperswithcode.com/paper/siamese-lstm-based-fiber-structural |
| Repo | |
| Framework | |
Volumetric Super-Resolution of Multispectral Data
| Title | Volumetric Super-Resolution of Multispectral Data |
| Authors | Vildan Atalay Aydin, Hassan Foroosh |
| Abstract | Most multispectral remote sensors (e.g. QuickBird, IKONOS, and Landsat 7 ETM+) provide low-spatial high-spectral resolution multispectral (MS) or high-spatial low-spectral resolution panchromatic (PAN) images, separately. In order to reconstruct a high-spatial/high-spectral resolution multispectral image volume, either the information in MS and PAN images are fused (i.e. pansharpening) or super-resolution reconstruction (SRR) is used with only MS images captured on different dates. Existing methods do not utilize temporal information of MS and high spatial resolution of PAN images together to improve the resolution. In this paper, we propose a multiframe SRR algorithm using pansharpened MS images, taking advantage of both temporal and spatial information available in multispectral imagery, in order to exceed spatial resolution of given PAN images. We first apply pansharpening to a set of multispectral images and their corresponding PAN images captured on different dates. Then, we use the pansharpened multispectral images as input to the proposed wavelet-based multiframe SRR method to yield full volumetric SRR. The proposed SRR method is obtained by deriving the subband relations between multitemporal MS volumes. We demonstrate the results on Landsat 7 ETM+ images comparing our method to conventional techniques. |
| Tasks | Super-Resolution |
| Published | 2017-05-14 |
| URL | http://arxiv.org/abs/1705.05745v1 |
| http://arxiv.org/pdf/1705.05745v1.pdf | |
| PWC | https://paperswithcode.com/paper/volumetric-super-resolution-of-multispectral |
| Repo | |
| Framework | |
Gaussian Process bandits with adaptive discretization
| Title | Gaussian Process bandits with adaptive discretization |
| Authors | Shubhanshu Shekhar, Tara Javidi |
| Abstract | In this paper, the problem of maximizing a black-box function $f:\mathcal{X} \to \mathbb{R}$ is studied in the Bayesian framework with a Gaussian Process (GP) prior. In particular, a new algorithm for this problem is proposed, and high probability bounds on its simple and cumulative regret are established. The query point selection rule in most existing methods involves an exhaustive search over an increasingly fine sequence of uniform discretizations of $\mathcal{X}$. The proposed algorithm, in contrast, adaptively refines $\mathcal{X}$ which leads to a lower computational complexity, particularly when $\mathcal{X}$ is a subset of a high dimensional Euclidean space. In addition to the computational gains, sufficient conditions are identified under which the regret bounds of the new algorithm improve upon the known results. Finally an extension of the algorithm to the case of contextual bandits is proposed, and high probability bounds on the contextual regret are presented. |
| Tasks | Multi-Armed Bandits |
| Published | 2017-12-05 |
| URL | http://arxiv.org/abs/1712.01447v2 |
| http://arxiv.org/pdf/1712.01447v2.pdf | |
| PWC | https://paperswithcode.com/paper/gaussian-process-bandits-with-adaptive |
| Repo | |
| Framework | |
Video Salient Object Detection via Fully Convolutional Networks
| Title | Video Salient Object Detection via Fully Convolutional Networks |
| Authors | Wenguan Wang, Jianbing Shen, Ling Shao |
| Abstract | This paper proposes a deep learning model to efficiently detect salient regions in videos. It addresses two important issues: (1) deep video saliency model training with the absence of sufficiently large and pixel-wise annotated video data, and (2) fast video saliency training and detection. The proposed deep video saliency network consists of two modules, for capturing the spatial and temporal saliency information, respectively. The dynamic saliency model, explicitly incorporating saliency estimates from the static saliency model, directly produces spatiotemporal saliency inference without time-consuming optical flow computation. We further propose a novel data augmentation technique that simulates video training data from existing annotated image datasets, which enables our network to learn diverse saliency information and prevents overfitting with the limited number of training videos. Leveraging our synthetic video data (150K video sequences) and real videos, our deep video saliency model successfully learns both spatial and temporal saliency cues, thus producing accurate spatiotemporal saliency estimate. We advance the state-of-the-art on the DAVIS dataset (MAE of .06) and the FBMS dataset (MAE of .07), and do so with much improved speed (2fps with all steps). |
| Tasks | Data Augmentation, Object Detection, Optical Flow Estimation, Salient Object Detection, Video Salient Object Detection |
| Published | 2017-02-02 |
| URL | http://arxiv.org/abs/1702.00871v3 |
| http://arxiv.org/pdf/1702.00871v3.pdf | |
| PWC | https://paperswithcode.com/paper/video-salient-object-detection-via-fully |
| Repo | |
| Framework | |
Fuzzy Ontology-Based Sentiment Analysis of Transportation and City Feature Reviews for Safe Traveling
| Title | Fuzzy Ontology-Based Sentiment Analysis of Transportation and City Feature Reviews for Safe Traveling |
| Authors | Farman Ali, D. Kwak, Pervez Khan, S. M. Riazul Islam, K. H. Kim, K. S. Kwak |
| Abstract | Traffic congestion is rapidly increasing in urban areas, particularly in mega cities. To date, there exist a few sensor network based systems to address this problem. However, these techniques are not suitable enough in terms of monitoring an entire transportation system and delivering emergency services when needed. These techniques require real-time data and intelligent ways to quickly determine traffic activity from useful information. In addition, these existing systems and websites on city transportation and travel rely on rating scores for different factors (e.g., safety, low crime rate, cleanliness, etc.). These rating scores are not efficient enough to deliver precise information, whereas reviews or tweets are significant, because they help travelers and transportation administrators to know about each aspect of the city. However, it is difficult for travelers to read, and for transportation systems to process, all reviews and tweets to obtain expressive sentiments regarding the needs of the city. The optimum solution for this kind of problem is analyzing the information available on social network platforms and performing sentiment analysis. On the other hand, crisp ontology-based frameworks cannot extract blurred information from tweets and reviews; therefore, they produce inadequate results. In this regard, this paper proposes fuzzy ontology-based sentiment analysis and SWRL rule-based decision-making to monitor transportation activities and to make a city- feature polarity map for travelers. This system retrieves reviews and tweets related to city features and transportation activities. The feature opinions are extracted from these retrieved data, and then fuzzy ontology is used to determine the transportation and city-feature polarity. A fuzzy ontology and an intelligent system prototype are developed by using Prot'eg'e OWL and Java, respectively. |
| Tasks | Decision Making, Sentiment Analysis |
| Published | 2017-01-19 |
| URL | http://arxiv.org/abs/1701.05334v1 |
| http://arxiv.org/pdf/1701.05334v1.pdf | |
| PWC | https://paperswithcode.com/paper/fuzzy-ontology-based-sentiment-analysis-of |
| Repo | |
| Framework | |
L1-regularized Reconstruction Error as Alpha Matte
| Title | L1-regularized Reconstruction Error as Alpha Matte |
| Authors | Jubin Johnson, Hisham Cholakkal, Deepu Rajan |
| Abstract | Sampling-based alpha matting methods have traditionally followed the compositing equation to estimate the alpha value at a pixel from a pair of foreground (F) and background (B) samples. The (F,B) pair that produces the least reconstruction error is selected, followed by alpha estimation. The significance of that residual error has been left unexamined. In this letter, we propose a video matting algorithm that uses L1-regularized reconstruction error of F and B samples as a measure of the alpha matte. A multi-frame non-local means framework using coherency sensitive hashing is utilized to ensure temporal coherency in the video mattes. Qualitative and quantitative evaluations on a dataset exclusively for video matting demonstrate the effectiveness of the proposed matting algorithm. |
| Tasks | |
| Published | 2017-02-09 |
| URL | http://arxiv.org/abs/1702.02744v1 |
| http://arxiv.org/pdf/1702.02744v1.pdf | |
| PWC | https://paperswithcode.com/paper/l1-regularized-reconstruction-error-as-alpha |
| Repo | |
| Framework | |
