Paper Group ANR 550
Proceedings of the First International Workshop on Deep Learning and Music. A Trolling Hierarchy in Social Media and A Conditional Random Field For Trolling Detection. The Candidate Multi-Cut for Cell Segmentation. Who wins the Miss Contest for Imputation Methods? Our Vote for Miss BooPF. Multi-Path Region-Based Convolutional Neural Network for Acc …
Proceedings of the First International Workshop on Deep Learning and Music
| Title | Proceedings of the First International Workshop on Deep Learning and Music |
| Authors | Dorien Herremans, Ching-Hua Chuan |
| Abstract | Proceedings of the First International Workshop on Deep Learning and Music, joint with IJCNN, Anchorage, US, May 17-18, 2017 |
| Tasks | |
| Published | 2017-06-27 |
| URL | http://arxiv.org/abs/1706.08675v1 |
| http://arxiv.org/pdf/1706.08675v1.pdf | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-international-3 |
| Repo | |
| Framework | |
A Trolling Hierarchy in Social Media and A Conditional Random Field For Trolling Detection
| Title | A Trolling Hierarchy in Social Media and A Conditional Random Field For Trolling Detection |
| Authors | Luis Gerardo Mojica |
| Abstract | An-ever increasing number of social media websites, electronic newspapers and Internet forums allow visitors to leave comments for others to read and interact. This exchange is not free from participants with malicious intentions, which do not contribute with the written conversation. Among different communities users adopt strategies to handle such users. In this paper we present a comprehensive categorization of the trolling phenomena resource, inspired by politeness research and propose a model that jointly predicts four crucial aspects of trolling: intention, interpretation, intention disclosure and response strategy. Finally, we present a new annotated dataset containing excerpts of conversations involving trolls and the interactions with other users that we hope will be a useful resource for the research community. |
| Tasks | |
| Published | 2017-04-07 |
| URL | http://arxiv.org/abs/1704.02385v1 |
| http://arxiv.org/pdf/1704.02385v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-trolling-hierarchy-in-social-media-and-a |
| Repo | |
| Framework | |
The Candidate Multi-Cut for Cell Segmentation
| Title | The Candidate Multi-Cut for Cell Segmentation |
| Authors | Jan Funke, Chong Zhang, Tobias Pietzsch, Stephan Saalfeld |
| Abstract | Two successful approaches for the segmentation of biomedical images are (1) the selection of segment candidates from a merge-tree, and (2) the clustering of small superpixels by solving a Multi-Cut problem. In this paper, we introduce a model that unifies both approaches. Our model, the Candidate Multi-Cut (CMC), allows joint selection and clustering of segment candidates from a merge-tree. This way, we overcome the respective limitations of the individual methods: (1) the space of possible segmentations is not constrained to candidates of a merge-tree, and (2) the decision for clustering can be made on candidates larger than superpixels, using features over larger contexts. We solve the optimization problem of selecting and clustering of candidates using an integer linear program. On datasets of 2D light microscopy of cell populations and 3D electron microscopy of neurons, we show that our method generalizes well and generates more accurate segmentations than merge-tree or Multi-Cut methods alone. |
| Tasks | Cell Segmentation |
| Published | 2017-07-04 |
| URL | http://arxiv.org/abs/1707.00907v1 |
| http://arxiv.org/pdf/1707.00907v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-candidate-multi-cut-for-cell-segmentation |
| Repo | |
| Framework | |
Who wins the Miss Contest for Imputation Methods? Our Vote for Miss BooPF
| Title | Who wins the Miss Contest for Imputation Methods? Our Vote for Miss BooPF |
| Authors | Burim Ramosaj, Markus Pauly |
| Abstract | Missing data is an expected issue when large amounts of data is collected, and several imputation techniques have been proposed to tackle this problem. Beneath classical approaches such as MICE, the application of Machine Learning techniques is tempting. Here, the recently proposed missForest imputation method has shown high imputation accuracy under the Missing (Completely) at Random scheme with various missing rates. In its core, it is based on a random forest for classification and regression, respectively. In this paper we study whether this approach can even be enhanced by other methods such as the stochastic gradient tree boosting method, the C5.0 algorithm or modified random forest procedures. In particular, other resampling strategies within the random forest protocol are suggested. In an extensive simulation study, we analyze their performances for continuous, categorical as well as mixed-type data. Therein, MissBooPF, a combination of the stochastic gradient tree boosting method together with the parametrically bootstrapped random forest method, appeared to be promising. Finally, an empirical analysis focusing on credit information and Facebook data is conducted. |
| Tasks | Imputation |
| Published | 2017-11-30 |
| URL | http://arxiv.org/abs/1711.11394v1 |
| http://arxiv.org/pdf/1711.11394v1.pdf | |
| PWC | https://paperswithcode.com/paper/who-wins-the-miss-contest-for-imputation |
| Repo | |
| Framework | |
Multi-Path Region-Based Convolutional Neural Network for Accurate Detection of Unconstrained “Hard Faces”
| Title | Multi-Path Region-Based Convolutional Neural Network for Accurate Detection of Unconstrained “Hard Faces” |
| Authors | Yuguang Liu, Martin D. Levine |
| Abstract | Large-scale variations still pose a challenge in unconstrained face detection. To the best of our knowledge, no current face detection algorithm can detect a face as large as 800 x 800 pixels while simultaneously detecting another one as small as 8 x 8 pixels within a single image with equally high accuracy. We propose a two-stage cascaded face detection framework, Multi-Path Region-based Convolutional Neural Network (MP-RCNN), that seamlessly combines a deep neural network with a classic learning strategy, to tackle this challenge. The first stage is a Multi-Path Region Proposal Network (MP-RPN) that proposes faces at three different scales. It simultaneously utilizes three parallel outputs of the convolutional feature maps to predict multi-scale candidate face regions. The “atrous” convolution trick (convolution with up-sampled filters) and a newly proposed sampling layer for “hard” examples are embedded in MP-RPN to further boost its performance. The second stage is a Boosted Forests classifier, which utilizes deep facial features pooled from inside the candidate face regions as well as deep contextual features pooled from a larger region surrounding the candidate face regions. This step is included to further remove hard negative samples. Experiments show that this approach achieves state-of-the-art face detection performance on the WIDER FACE dataset “hard” partition, outperforming the former best result by 9.6% for the Average Precision. |
| Tasks | Face Detection, Robust Face Recognition |
| Published | 2017-03-27 |
| URL | http://arxiv.org/abs/1703.09145v1 |
| http://arxiv.org/pdf/1703.09145v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-path-region-based-convolutional-neural |
| Repo | |
| Framework | |
On Preemption and Overdetermination in Formal Theories of Causality
| Title | On Preemption and Overdetermination in Formal Theories of Causality |
| Authors | Sjur K Dyrkolbotn |
| Abstract | One of the key challenges when looking for the causes of a complex event is to determine the causal status of factors that are neither individually necessary nor individually sufficient to produce that event. In order to reason about how such factors should be taken into account, we need a vocabulary to distinguish different cases. In philosophy, the concept of overdetermination and the concept of preemption serve an important purpose in this regard, although their exact meaning tends to remain elusive. In this paper, I provide theory-neutral definitions of these concepts using structural equations in the Halpern-Pearl tradition. While my definitions do not presuppose any particular causal theory, they take such a theory as a variable parameter. This enables us to specify formal constraints on theories of causality, in terms of a pre-theoretic understanding of what preemption and overdetermination actually mean. I demonstrate the usefulness of this by presenting and arguing for what I call the principle of presumption. Roughly speaking, this principle states that a possible cause can only be regarded as having been preempted if there is independent evidence to support such an inference. I conclude by showing that the principle of presumption is violated by the two main theories of causality formulated in the Halpern-Pearl tradition. The paper concludes by defining the class of empirical causal theories, characterised in terms of a fixed-point of counterfactual reasoning about difference-making. It is argued that theories of actual causality ought to be empirical. |
| Tasks | |
| Published | 2017-10-10 |
| URL | http://arxiv.org/abs/1710.03390v1 |
| http://arxiv.org/pdf/1710.03390v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-preemption-and-overdetermination-in-formal |
| Repo | |
| Framework | |
Holistic Planimetric prediction to Local Volumetric prediction for 3D Human Pose Estimation
| Title | Holistic Planimetric prediction to Local Volumetric prediction for 3D Human Pose Estimation |
| Authors | Gyeongsik Moon, Ju Yong Chang, Yumin Suh, Kyoung Mu Lee |
| Abstract | We propose a novel approach to 3D human pose estimation from a single depth map. Recently, convolutional neural network (CNN) has become a powerful paradigm in computer vision. Many of computer vision tasks have benefited from CNNs, however, the conventional approach to directly regress 3D body joint locations from an image does not yield a noticeably improved performance. In contrast, we formulate the problem as estimating per-voxel likelihood of key body joints from a 3D occupancy grid. We argue that learning a mapping from volumetric input to volumetric output with 3D convolution consistently improves the accuracy when compared to learning a regression from depth map to 3D joint coordinates. We propose a two-stage approach to reduce the computational overhead caused by volumetric representation and 3D convolution: Holistic 2D prediction and Local 3D prediction. In the first stage, Planimetric Network (P-Net) estimates per-pixel likelihood for each body joint in the holistic 2D space. In the second stage, Volumetric Network (V-Net) estimates the per-voxel likelihood of each body joints in the local 3D space around the 2D estimations of the first stage, effectively reducing the computational cost. Our model outperforms existing methods by a large margin in publicly available datasets. |
| Tasks | 3D Human Pose Estimation, Pose Estimation |
| Published | 2017-06-15 |
| URL | http://arxiv.org/abs/1706.04758v2 |
| http://arxiv.org/pdf/1706.04758v2.pdf | |
| PWC | https://paperswithcode.com/paper/holistic-planimetric-prediction-to-local |
| Repo | |
| Framework | |
Fast online low-rank tensor subspace tracking by CP decomposition using recursive least squares from incomplete observations
| Title | Fast online low-rank tensor subspace tracking by CP decomposition using recursive least squares from incomplete observations |
| Authors | Hiroyuki Kasai |
| Abstract | We consider the problem of online subspace tracking of a partially observed high-dimensional data stream corrupted by noise, where we assume that the data lie in a low-dimensional linear subspace. This problem is cast as an online low-rank tensor completion problem. We propose a novel online tensor subspace tracking algorithm based on the CANDECOMP/PARAFAC (CP) decomposition, dubbed OnLine Low-rank Subspace tracking by TEnsor CP Decomposition (OLSTEC). The proposed algorithm especially addresses the case in which the subspace of interest is dynamically time-varying. To this end, we build up our proposed algorithm exploiting the recursive least squares (RLS), which is the second-order gradient algorithm. Numerical evaluations on synthetic datasets and real-world datasets such as communication network traffic, environmental data, and surveillance videos, show that the proposed OLSTEC algorithm outperforms state-of-the-art online algorithms in terms of the convergence rate per iteration. |
| Tasks | |
| Published | 2017-09-29 |
| URL | http://arxiv.org/abs/1709.10276v1 |
| http://arxiv.org/pdf/1709.10276v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-online-low-rank-tensor-subspace-tracking |
| Repo | |
| Framework | |
Item Recommendation with Continuous Experience Evolution of Users using Brownian Motion
| Title | Item Recommendation with Continuous Experience Evolution of Users using Brownian Motion |
| Authors | Subhabrata Mukherjee, Stephan Guennemann, Gerhard Weikum |
| Abstract | Online review communities are dynamic as users join and leave, adopt new vocabulary, and adapt to evolving trends. Recent work has shown that recommender systems benefit from explicit consideration of user experience. However, prior work assumes a fixed number of discrete experience levels, whereas in reality users gain experience and mature continuously over time. This paper presents a new model that captures the continuous evolution of user experience, and the resulting language model in reviews and other posts. Our model is unsupervised and combines principles of Geometric Brownian Motion, Brownian Motion, and Latent Dirichlet Allocation to trace a smooth temporal progression of user experience and language model respectively. We develop practical algorithms for estimating the model parameters from data and for inference with our model (e.g., to recommend items). Extensive experiments with five real-world datasets show that our model not only fits data better than discrete-model baselines, but also outperforms state-of-the-art methods for predicting item ratings. |
| Tasks | Language Modelling, Recommendation Systems |
| Published | 2017-05-07 |
| URL | http://arxiv.org/abs/1705.02669v3 |
| http://arxiv.org/pdf/1705.02669v3.pdf | |
| PWC | https://paperswithcode.com/paper/item-recommendation-with-continuous |
| Repo | |
| Framework | |
A Simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex Regularizer
| Title | A Simple Analysis for Exp-concave Empirical Minimization with Arbitrary Convex Regularizer |
| Authors | Tianbao Yang, Zhe Li, Lijun Zhang |
| Abstract | In this paper, we present a simple analysis of {\bf fast rates} with {\it high probability} of {\bf empirical minimization} for {\it stochastic composite optimization} over a finite-dimensional bounded convex set with exponential concave loss functions and an arbitrary convex regularization. To the best of our knowledge, this result is the first of its kind. As a byproduct, we can directly obtain the fast rate with {\it high probability} for exponential concave empirical risk minimization with and without any convex regularization, which not only extends existing results of empirical risk minimization but also provides a unified framework for analyzing exponential concave empirical risk minimization with and without {\it any} convex regularization. Our proof is very simple only exploiting the covering number of a finite-dimensional bounded set and a concentration inequality of random vectors. |
| Tasks | |
| Published | 2017-09-09 |
| URL | http://arxiv.org/abs/1709.02909v1 |
| http://arxiv.org/pdf/1709.02909v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-simple-analysis-for-exp-concave-empirical |
| Repo | |
| Framework | |
Story Generation from Sequence of Independent Short Descriptions
| Title | Story Generation from Sequence of Independent Short Descriptions |
| Authors | Parag Jain, Priyanka Agrawal, Abhijit Mishra, Mohak Sukhwani, Anirban Laha, Karthik Sankaranarayanan |
| Abstract | Existing Natural Language Generation (NLG) systems are weak AI systems and exhibit limited capabilities when language generation tasks demand higher levels of creativity, originality and brevity. Effective solutions or, at least evaluations of modern NLG paradigms for such creative tasks have been elusive, unfortunately. This paper introduces and addresses the task of coherent story generation from independent descriptions, describing a scene or an event. Towards this, we explore along two popular text-generation paradigms – (1) Statistical Machine Translation (SMT), posing story generation as a translation problem and (2) Deep Learning, posing story generation as a sequence to sequence learning problem. In SMT, we chose two popular methods such as phrase based SMT (PB-SMT) and syntax based SMT (SYNTAX-SMT) to `translate’ the incoherent input text into stories. We then implement a deep recurrent neural network (RNN) architecture that encodes sequence of variable length input descriptions to corresponding latent representations and decodes them to produce well formed comprehensive story like summaries. The efficacy of the suggested approaches is demonstrated on a publicly available dataset with the help of popular machine translation and summarization evaluation metrics. | |
| Tasks | Machine Translation, Text Generation |
| Published | 2017-07-18 |
| URL | http://arxiv.org/abs/1707.05501v2 |
| http://arxiv.org/pdf/1707.05501v2.pdf | |
| PWC | https://paperswithcode.com/paper/story-generation-from-sequence-of-independent |
| Repo | |
| Framework | |
Faceness-Net: Face Detection through Deep Facial Part Responses
| Title | Faceness-Net: Face Detection through Deep Facial Part Responses |
| Authors | Shuo Yang, Ping Luo, Chen Change Loy, Xiaoou Tang |
| Abstract | We propose a deep convolutional neural network (CNN) for face detection leveraging on facial attributes based supervision. We observe a phenomenon that part detectors emerge within CNN trained to classify attributes from uncropped face images, without any explicit part supervision. The observation motivates a new method for finding faces through scoring facial parts responses by their spatial structure and arrangement. The scoring mechanism is data-driven, and carefully formulated considering challenging cases where faces are only partially visible. This consideration allows our network to detect faces under severe occlusion and unconstrained pose variations. Our method achieves promising performance on popular benchmarks including FDDB, PASCAL Faces, AFW, and WIDER FACE. |
| Tasks | Face Detection |
| Published | 2017-01-29 |
| URL | http://arxiv.org/abs/1701.08393v3 |
| http://arxiv.org/pdf/1701.08393v3.pdf | |
| PWC | https://paperswithcode.com/paper/faceness-net-face-detection-through-deep |
| Repo | |
| Framework | |
Revisiting the problem of audio-based hit song prediction using convolutional neural networks
| Title | Revisiting the problem of audio-based hit song prediction using convolutional neural networks |
| Authors | Li-Chia Yang, Szu-Yu Chou, Jen-Yu Liu, Yi-Hsuan Yang, Yi-An Chen |
| Abstract | Being able to predict whether a song can be a hit has impor- tant applications in the music industry. Although it is true that the popularity of a song can be greatly affected by exter- nal factors such as social and commercial influences, to which degree audio features computed from musical signals (whom we regard as internal factors) can predict song popularity is an interesting research question on its own. Motivated by the recent success of deep learning techniques, we attempt to ex- tend previous work on hit song prediction by jointly learning the audio features and prediction models using deep learning. Specifically, we experiment with a convolutional neural net- work model that takes the primitive mel-spectrogram as the input for feature learning, a more advanced JYnet model that uses an external song dataset for supervised pre-training and auto-tagging, and the combination of these two models. We also consider the inception model to characterize audio infor- mation in different scales. Our experiments suggest that deep structures are indeed more accurate than shallow structures in predicting the popularity of either Chinese or Western Pop songs in Taiwan. We also use the tags predicted by JYnet to gain insights into the result of different models. |
| Tasks | |
| Published | 2017-04-05 |
| URL | http://arxiv.org/abs/1704.01280v1 |
| http://arxiv.org/pdf/1704.01280v1.pdf | |
| PWC | https://paperswithcode.com/paper/revisiting-the-problem-of-audio-based-hit |
| Repo | |
| Framework | |
On the Reliable Detection of Concept Drift from Streaming Unlabeled Data
| Title | On the Reliable Detection of Concept Drift from Streaming Unlabeled Data |
| Authors | Tegjyot Singh Sethi, Mehmed Kantardzic |
| Abstract | Classifiers deployed in the real world operate in a dynamic environment, where the data distribution can change over time. These changes, referred to as concept drift, can cause the predictive performance of the classifier to drop over time, thereby making it obsolete. To be of any real use, these classifiers need to detect drifts and be able to adapt to them, over time. Detecting drifts has traditionally been approached as a supervised task, with labeled data constantly being used for validating the learned model. Although effective in detecting drifts, these techniques are impractical, as labeling is a difficult, costly and time consuming activity. On the other hand, unsupervised change detection techniques are unreliable, as they produce a large number of false alarms. The inefficacy of the unsupervised techniques stems from the exclusion of the characteristics of the learned classifier, from the detection process. In this paper, we propose the Margin Density Drift Detection (MD3) algorithm, which tracks the number of samples in the uncertainty region of a classifier, as a metric to detect drift. The MD3 algorithm is a distribution independent, application independent, model independent, unsupervised and incremental algorithm for reliably detecting drifts from data streams. Experimental evaluation on 6 drift induced datasets and 4 additional datasets from the cybersecurity domain demonstrates that the MD3 approach can reliably detect drifts, with significantly fewer false alarms compared to unsupervised feature based drift detectors. The reduced false alarms enables the signaling of drifts only when they are most likely to affect classification performance. As such, the MD3 approach leads to a detection scheme which is credible, label efficient and general in its applicability. |
| Tasks | |
| Published | 2017-03-31 |
| URL | http://arxiv.org/abs/1704.00023v1 |
| http://arxiv.org/pdf/1704.00023v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-reliable-detection-of-concept-drift |
| Repo | |
| Framework | |
Inner-Scene Similarities as a Contextual Cue for Object Detection
| Title | Inner-Scene Similarities as a Contextual Cue for Object Detection |
| Authors | Noa Arbel, Tamar Avraham, Michael Lindenbaum |
| Abstract | Using image context is an effective approach for improving object detection. Previously proposed methods used contextual cues that rely on semantic or spatial information. In this work, we explore a different kind of contextual information: inner-scene similarity. We present the CISS (Context by Inner Scene Similarity) algorithm, which is based on the observation that two visually similar sub-image patches are likely to share semantic identities, especially when both appear in the same image. CISS uses base-scores provided by a base detector and performs as a post-detection stage. For each candidate sub-image (denoted anchor), the CISS algorithm finds a few similar sub-images (denoted supporters), and, using them, calculates a new enhanced score for the anchor. This is done by utilizing the base-scores of the supporters and a pre-trained dependency model. The new scores are modeled as a linear function of the base scores of the anchor and the supporters and is estimated using a minimum mean square error optimization. This approach results in: (a) improved detection of partly occluded objects (when there are similar non-occluded objects in the scene), and (b) fewer false alarms (when the base detector mistakenly classifies a background patch as an object). This work relates to Duncan and Humphreys’ “similarity theory,” a psychophysical study. which suggested that the human visual system perceptually groups similar image regions and that the classification of one region is affected by the estimated identity of the other. Experimental results demonstrate the enhancement of a base detector’s scores on the PASCAL VOC dataset. |
| Tasks | Object Detection |
| Published | 2017-07-14 |
| URL | http://arxiv.org/abs/1707.04406v1 |
| http://arxiv.org/pdf/1707.04406v1.pdf | |
| PWC | https://paperswithcode.com/paper/inner-scene-similarities-as-a-contextual-cue |
| Repo | |
| Framework | |
