Paper Group ANR 1227
AraNet: A Deep Learning Toolkit for Arabic Social Media. XceptionTime: A Novel Deep Architecture based on Depthwise Separable Convolutions for Hand Gesture Classification. Personalized Re-ranking for Recommendation. Driving Reinforcement Learning with Models. Learning deep representations for video-based intake gesture detection. State Representati …
AraNet: A Deep Learning Toolkit for Arabic Social Media
| Title | AraNet: A Deep Learning Toolkit for Arabic Social Media |
| Authors | Muhammad Abdul-Mageed, Chiyu Zhang, Azadeh Hashemi, El Moatez Billah Nagoudi |
| Abstract | We describe AraNet, a collection of deep learning Arabic social media processing tools. Namely, we exploit an extensive host of publicly available and novel social media datasets to train bidirectional encoders from transformer models (BERT) to predict age, dialect, gender, emotion, irony, and sentiment. AraNet delivers state-of-the-art performance on a number of the cited tasks and competitively on others. In addition, AraNet has the advantage of being exclusively based on a deep learning framework and hence feature engineering free. To the best of our knowledge, AraNet is the first to performs predictions across such a wide range of tasks for Arabic NLP and thus meets a critical needs. We publicly release AraNet to accelerate research and facilitate comparisons across the different tasks. |
| Tasks | Feature Engineering |
| Published | 2019-12-30 |
| URL | https://arxiv.org/abs/1912.13072v1 |
| https://arxiv.org/pdf/1912.13072v1.pdf | |
| PWC | https://paperswithcode.com/paper/aranet-a-deep-learning-toolkit-for-arabic |
| Repo | |
| Framework | |
XceptionTime: A Novel Deep Architecture based on Depthwise Separable Convolutions for Hand Gesture Classification
| Title | XceptionTime: A Novel Deep Architecture based on Depthwise Separable Convolutions for Hand Gesture Classification |
| Authors | Elahe Rahimian, Soheil Zabihi, Seyed Farokh Atashzar, Amir Asif, Arash Mohammadi |
| Abstract | Capitalizing on the need for addressing the existing challenges associated with gesture recognition via sparse multichannel surface Electromyography (sEMG) signals, the paper proposes a novel deep learning model, referred to as the XceptionTime architecture. The proposed innovative XceptionTime is designed by integration of depthwise separable convolutions, adaptive average pooling, and a novel non-linear normalization technique. At the heart of the proposed architecture is several XceptionTime modules concatenated in series fashion designed to capture both temporal and spatial information-bearing contents of the sparse multichannel sEMG signals without the need for data augmentation and/or manual design of feature extraction. In addition, through integration of adaptive average pooling, Conv1D, and the non-linear normalization approach, XceptionTime is less prone to overfitting, more robust to temporal translation of the input, and more importantly is independent from the input window size. Finally, by utilizing the depthwise separable convolutions, the XceptionTime network has far fewer parameters resulting in a less complex network. The performance of XceptionTime is tested on a sub Ninapro dataset, DB1, and the results showed a superior performance in comparison to any existing counterparts. In this regard, 5:71% accuracy improvement, on a window size 200ms, is reported in this paper, for the first time. |
| Tasks | Data Augmentation, Gesture Recognition |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03803v1 |
| https://arxiv.org/pdf/1911.03803v1.pdf | |
| PWC | https://paperswithcode.com/paper/xceptiontime-a-novel-deep-architecture-based |
| Repo | |
| Framework | |
Personalized Re-ranking for Recommendation
| Title | Personalized Re-ranking for Recommendation |
| Authors | Changhua Pei, Yi Zhang, Yongfeng Zhang, Fei Sun, Xiao Lin, Hanxiao Sun, Jian Wu, Peng Jiang, Wenwu Ou |
| Abstract | Ranking is a core task in recommender systems, which aims at providing an ordered list of items to users. Typically, a ranking function is learned from the labeled dataset to optimize the global performance, which produces a ranking score for each individual item. However, it may be sub-optimal because the scoring function applies to each item individually and does not explicitly consider the mutual influence between items, as well as the differences of users’ preferences or intents. Therefore, we propose a personalized re-ranking model for recommender systems. The proposed re-ranking model can be easily deployed as a follow-up modular after any ranking algorithm, by directly using the existing ranking feature vectors. It directly optimizes the whole recommendation list by employing a transformer structure to efficiently encode the information of all items in the list. Specifically, the Transformer applies a self-attention mechanism that directly models the global relationships between any pair of items in the whole list. We confirm that the performance can be further improved by introducing pre-trained embedding to learn personalized encoding functions for different users. Experimental results on both offline benchmarks and real-world online e-commerce systems demonstrate the significant improvements of the proposed re-ranking model. |
| Tasks | Recommendation Systems |
| Published | 2019-04-15 |
| URL | https://arxiv.org/abs/1904.06813v3 |
| https://arxiv.org/pdf/1904.06813v3.pdf | |
| PWC | https://paperswithcode.com/paper/personalized-context-aware-re-ranking-for-e |
| Repo | |
| Framework | |
Driving Reinforcement Learning with Models
| Title | Driving Reinforcement Learning with Models |
| Authors | Meghana Rathi, Pietro Ferraro, Giovanni Russo |
| Abstract | In this paper we propose a new approach to complement reinforcement learning (RL) with model-based control (in particular, Model Predictive Control - MPC). We introduce an algorithm, the MPC augmented RL (MPRL) that combines RL and MPC in a novel way so that they can augment each other’s strengths. We demonstrate the effectiveness of the MPRL by letting it play against the Atari game Pong. For this task, the results highlight how MPRL is able to outperform both RL and MPC when these are used individually. |
| Tasks | |
| Published | 2019-11-11 |
| URL | https://arxiv.org/abs/1911.04400v2 |
| https://arxiv.org/pdf/1911.04400v2.pdf | |
| PWC | https://paperswithcode.com/paper/driving-reinforcement-learning-with-models |
| Repo | |
| Framework | |
Learning deep representations for video-based intake gesture detection
| Title | Learning deep representations for video-based intake gesture detection |
| Authors | Philipp V. Rouast, Marc T. P. Adam |
| Abstract | Automatic detection of individual intake gestures during eating occasions has the potential to improve dietary monitoring and support dietary recommendations. Existing studies typically make use of on-body solutions such as inertial and audio sensors, while video is used as ground truth. Intake gesture detection directly based on video has rarely been attempted. In this study, we address this gap and show that deep learning architectures can successfully be applied to the problem of video-based detection of intake gestures. For this purpose, we collect and label video data of eating occasions using 360-degree video of 102 participants. Applying state-of-the-art approaches from video action recognition, our results show that (1) the best model achieves an $F_1$ score of 0.858, (2) appearance features contribute more than motion features, and (3) temporal context in form of multiple video frames is essential for top model performance. |
| Tasks | Temporal Action Localization |
| Published | 2019-09-24 |
| URL | https://arxiv.org/abs/1909.10695v1 |
| https://arxiv.org/pdf/1909.10695v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-deep-representations-for-video-based |
| Repo | |
| Framework | |
State Representation Learning from Demonstration
| Title | State Representation Learning from Demonstration |
| Authors | Astrid Merckling, Alexandre Coninx, Loic Cressot, Stephane Doncieux, Nicolas Perrin |
| Abstract | In a context where several policies can be observed as black boxes on different instances of a control task, we propose a method to derive a state representation that can be relied on to reproduce any of the observed policies. We do so via imitation learning on a multi-head neural network consisting of a first part that outputs a common state representation and then one head per policy to imitate. If the demonstrations contain enough diversity, the state representation is general and can be transferred to learn new instances of the task. We present a proof of concept with experimental results on a simulated 2D robotic arm performing a reaching task, with noisy image inputs containing a distractor, and show that the state representations learned provide a greater speed up to end-to-end reinforcement learning on new instances of the task than with other classical representations. |
| Tasks | Imitation Learning, Representation Learning |
| Published | 2019-09-15 |
| URL | https://arxiv.org/abs/1910.01738v1 |
| https://arxiv.org/pdf/1910.01738v1.pdf | |
| PWC | https://paperswithcode.com/paper/state-representation-learning-from |
| Repo | |
| Framework | |
Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation
| Title | Fast and Furious Convergence: Stochastic Second Order Methods under Interpolation |
| Authors | Si Yi Meng, Sharan Vaswani, Issam Laradji, Mark Schmidt, Simon Lacoste-Julien |
| Abstract | We consider stochastic second-order methods for minimizing smooth and strongly-convex functions under an interpolation condition satisfied by over-parameterized models. Under this condition, we show that the regularized subsampled Newton method (R-SSN) achieves global linear convergence with an adaptive step-size and a constant batch-size. By growing the batch size for both the subsampled gradient and Hessian, we show that R-SSN can converge at a quadratic rate in a local neighbourhood of the solution. We also show that R-SSN attains local linear convergence for the family of self-concordant functions. Furthermore, we analyze stochastic BFGS algorithms in the interpolation setting and prove their global linear convergence. We empirically evaluate stochastic L-BFGS and a “Hessian-free” implementation of R-SSN for binary classification on synthetic, linearly-separable datasets and real datasets under a kernel mapping. Our experimental results demonstrate the fast convergence of these methods, both in terms of the number of iterations and wall-clock time. |
| Tasks | |
| Published | 2019-10-11 |
| URL | https://arxiv.org/abs/1910.04920v2 |
| https://arxiv.org/pdf/1910.04920v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-and-furious-convergence-stochastic |
| Repo | |
| Framework | |
Provable Computational and Statistical Guarantees for Efficient Learning of Continuous-Action Graphical Games
| Title | Provable Computational and Statistical Guarantees for Efficient Learning of Continuous-Action Graphical Games |
| Authors | Adarsh Barik, Jean Honorio |
| Abstract | In this paper, we study the problem of learning the set of pure strategy Nash equilibria and the exact structure of a continuous-action graphical game with quadratic payoffs by observing a small set of perturbed equilibria. A continuous-action graphical game can possibly have an uncountable set of Nash euqilibria. We propose a $\ell_{12}-$ block regularized method which recovers a graphical game, whose Nash equilibria are the $\epsilon$-Nash equilibria of the game from which the data was generated (true game). Under a slightly stringent condition on the parameters of the true game, our method recovers the exact structure of the graphical game. Our method has a logarithmic sample complexity with respect to the number of players. It also runs in polynomial time. |
| Tasks | |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.04225v1 |
| https://arxiv.org/pdf/1911.04225v1.pdf | |
| PWC | https://paperswithcode.com/paper/provable-computational-and-statistical |
| Repo | |
| Framework | |
Chatter Diagnosis in Milling Using Supervised Learning and Topological Features Vector
| Title | Chatter Diagnosis in Milling Using Supervised Learning and Topological Features Vector |
| Authors | Melih C. Yesilli, Sarah Tymochko, Firas A. Khasawneh, Elizabeth Munch |
| Abstract | Chatter detection has become a prominent subject of interest due to its effect on cutting tool life, surface finish and spindle of machine tool. Most of the existing methods in chatter detection literature are based on signal processing and signal decomposition. In this study, we use topological features of data simulating cutting tool vibrations, combined with four supervised machine learning algorithms to diagnose chatter in the milling process. Persistence diagrams, a method of representing topological features, are not easily used in the context of machine learning, so they must be transformed into a form that is more amenable. Specifically, we will focus on two different methods for featurizing persistence diagrams, Carlsson coordinates and template functions. In this paper, we provide classification results for simulated data from various cutting configurations, including upmilling and downmilling, in addition to the same data with some added noise. Our results show that Carlsson Coordinates and Template Functions yield accuracies as high as 96% and 95%, respectively. We also provide evidence that these topological methods are noise robust descriptors for chatter detection. |
| Tasks | |
| Published | 2019-10-27 |
| URL | https://arxiv.org/abs/1910.12359v1 |
| https://arxiv.org/pdf/1910.12359v1.pdf | |
| PWC | https://paperswithcode.com/paper/chatter-diagnosis-in-milling-using-supervised |
| Repo | |
| Framework | |
PolyGAN: High-Order Polynomial Generators
| Title | PolyGAN: High-Order Polynomial Generators |
| Authors | Grigorios Chrysos, Stylianos Moschoglou, Yannis Panagakis, Stefanos Zafeiriou |
| Abstract | Generative Adversarial Networks (GANs) have become the gold standard when it comes to learning generative models for high-dimensional distributions. Since their advent, numerous variations of GANs have been introduced in the literature, primarily focusing on utilization of novel loss functions, optimization/regularization strategies and network architectures. In this paper, we turn our attention to the generator and investigate the use of high-order polynomials as an alternative class of universal function approximators. Concretely, we propose PolyGAN, where we model the data generator by means of a high-order polynomial whose unknown parameters are naturally represented by high-order tensors. We introduce two tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks that only employ linear/convolutional blocks. We exhibit for the first time that by using our approach a GAN generator can approximate the data distribution without using any activation functions. Thorough experimental evaluation on both synthetic and real data (images and 3D point clouds) demonstrates the merits of PolyGAN against the state of the art. |
| Tasks | |
| Published | 2019-08-19 |
| URL | https://arxiv.org/abs/1908.06571v2 |
| https://arxiv.org/pdf/1908.06571v2.pdf | |
| PWC | https://paperswithcode.com/paper/polygan-high-order-polynomial-generators |
| Repo | |
| Framework | |
A Stock Selection Method Based on Earning Yield Forecast Using Sequence Prediction Models
| Title | A Stock Selection Method Based on Earning Yield Forecast Using Sequence Prediction Models |
| Authors | Jessie Sun |
| Abstract | Long-term investors, different from short-term traders, focus on examining the underlying forces that affect the well-being of a company. They rely on fundamental analysis which attempts to measure the intrinsic value an equity. Quantitative investment researchers have identified some value factors to determine the cost of investment for a stock and compare different stocks. This paper proposes using sequence prediction models to forecast a value factor-the earning yield (EBIT/EV) of a company for stock selection. Two advanced sequence prediction models-Long Short-term Memory (LSTM) and Gated Recurrent Unit (GRU) networks are studied. These two models can overcome the inherent problems of a standard Recurrent Neural Network, i.e., vanishing and exploding gradients. This paper firstly introduces the theories of the networks. And then elaborates the workflow of stock pool creation, feature selection, data structuring, model setup and model evaluation. The LSTM and GRU models demonstrate superior performance of forecast accuracy over a traditional Feedforward Neural Network model. The GRU model slightly outperformed the LSTM model. |
| Tasks | Feature Selection |
| Published | 2019-05-13 |
| URL | https://arxiv.org/abs/1905.04842v1 |
| https://arxiv.org/pdf/1905.04842v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-stock-selection-method-based-on-earning |
| Repo | |
| Framework | |
Unconstrained Foreground Object Search
| Title | Unconstrained Foreground Object Search |
| Authors | Yinan Zhao, Brian Price, Scott Cohen, Danna Gurari |
| Abstract | Many people search for foreground objects to use when editing images. While existing methods can retrieve candidates to aid in this, they are constrained to returning objects that belong to a pre-specified semantic class. We instead propose a novel problem of unconstrained foreground object (UFO) search and introduce a solution that supports efficient search by encoding the background image in the same latent space as the candidate foreground objects. A key contribution of our work is a cost-free, scalable approach for creating a large-scale training dataset with a variety of foreground objects of differing semantic categories per image location. Quantitative and human-perception experiments with two diverse datasets demonstrate the advantage of our UFO search solution over related baselines. |
| Tasks | |
| Published | 2019-08-10 |
| URL | https://arxiv.org/abs/1908.03675v1 |
| https://arxiv.org/pdf/1908.03675v1.pdf | |
| PWC | https://paperswithcode.com/paper/unconstrained-foreground-object-search |
| Repo | |
| Framework | |
Learning Resilient Behaviors for Navigation Under Uncertainty Environments
| Title | Learning Resilient Behaviors for Navigation Under Uncertainty Environments |
| Authors | Tingxiang Fan, Pinxin Long, Wenxi Liu, Jia Pan, Ruigang Yang, Dinesh Manocha |
| Abstract | Deep reinforcement learning has great potential to acquire complex, adaptive behaviors for autonomous agents automatically. However, the underlying neural network polices have not been widely deployed in real-world applications, especially in these safety-critical tasks (e.g., autonomous driving). One of the reasons is that the learned policy cannot perform flexible and resilient behaviors as traditional methods to adapt to diverse environments. In this paper, we consider the problem that a mobile robot learns adaptive and resilient behaviors for navigating in unseen uncertain environments while avoiding collisions. We present a novel approach for uncertainty-aware navigation by introducing an uncertainty-aware predictor to model the environmental uncertainty, and we propose a novel uncertainty-aware navigation network to learn resilient behaviors in the prior unknown environments. To train the proposed uncertainty-aware network more stably and efficiently, we present the temperature decay training paradigm, which balances exploration and exploitation during the training process. Our experimental evaluation demonstrates that our approach can learn resilient behaviors in diverse environments and generate adaptive trajectories according to environmental uncertainties. |
| Tasks | Autonomous Driving |
| Published | 2019-10-22 |
| URL | https://arxiv.org/abs/1910.09998v1 |
| https://arxiv.org/pdf/1910.09998v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-resilient-behaviors-for-navigation |
| Repo | |
| Framework | |
SynthCity: A large scale synthetic point cloud
| Title | SynthCity: A large scale synthetic point cloud |
| Authors | David Griffiths, Jan Boehm |
| Abstract | With deep learning becoming a more prominent approach for automatic classification of three-dimensional point cloud data, a key bottleneck is the amount of high quality training data, especially when compared to that available for two-dimensional images. One potential solution is the use of synthetic data for pre-training networks, however the ability for models to generalise from synthetic data to real world data has been poorly studied for point clouds. Despite this, a huge wealth of 3D virtual environments exist which, if proved effective can be exploited. We therefore argue that research in this domain would be of significant use. In this paper we present SynthCity an open dataset to help aid research. SynthCity is a 367.9M point synthetic full colour Mobile Laser Scanning point cloud. Every point is assigned a label from one of nine categories. We generate our point cloud in a typical Urban/Suburban environment using the Blensor plugin for Blender. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04758v1 |
| https://arxiv.org/pdf/1907.04758v1.pdf | |
| PWC | https://paperswithcode.com/paper/synthcity-a-large-scale-synthetic-point-cloud |
| Repo | |
| Framework | |
The iMet Collection 2019 Challenge Dataset
| Title | The iMet Collection 2019 Challenge Dataset |
| Authors | Chenyang Zhang, Christine Kaeser-Chen, Grace Vesom, Jennie Choi, Maria Kessler, Serge Belongie |
| Abstract | Existing computer vision technologies in artwork recognition focus mainly on instance retrieval or coarse-grained attribute classification. In this work, we present a novel dataset for fine-grained artwork attribute recognition. The images in the dataset are professional photographs of classic artworks from the Metropolitan Museum of Art, and annotations are curated and verified by world-class museum experts. In addition, we also present the iMet Collection 2019 Challenge as part of the FGVC6 workshop. Through the competition, we aim to spur the enthusiasm of the fine-grained visual recognition research community and advance the state-of-the-art in digital curation of museum collections. |
| Tasks | Fine-Grained Visual Recognition |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.00901v2 |
| https://arxiv.org/pdf/1906.00901v2.pdf | |
| PWC | https://paperswithcode.com/paper/190600901 |
| Repo | |
| Framework | |
