Paper Group ANR 531
An efficient high-probability algorithm for Linear Bandits. Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions. FAST: A Framework to Accelerate Super-Resolution Processing on Compressed Videos. A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech. VRPBench: A Vehicle Routing Benchmark T …
An efficient high-probability algorithm for Linear Bandits
| Title | An efficient high-probability algorithm for Linear Bandits |
| Authors | Gábor Braun, Sebastian Pokutta |
| Abstract | For the linear bandit problem, we extend the analysis of algorithm CombEXP from [R. Combes, M. S. Talebi Mazraeh Shahi, A. Proutiere, and M. Lelarge. Combinatorial bandits revisited. In C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett, editors, Advances in Neural Information Processing Systems 28, pages 2116–2124. Curran Associates, Inc., 2015. URL http://papers.nips.cc/paper/5831-combinatorial-bandits-revisited.pdf] to the high-probability case against adaptive adversaries, allowing actions to come from an arbitrary polytope. We prove a high-probability regret of (O(T^{2/3})) for time horizon (T). While this bound is weaker than the optimal (O(\sqrt{T})) bound achieved by GeometricHedge in [P. L. Bartlett, V. Dani, T. Hayes, S. Kakade, A. Rakhlin, and A. Tewari. High-probability regret bounds for bandit online linear optimization. In 21th Annual Conference on Learning Theory (COLT 2008), July 2008. http://eprints.qut.edu.au/45706/1/30-Bartlett.pdf], CombEXP is computationally efficient, requiring only an efficient linear optimization oracle over the convex hull of the actions. |
| Tasks | |
| Published | 2016-10-06 |
| URL | http://arxiv.org/abs/1610.02072v2 |
| http://arxiv.org/pdf/1610.02072v2.pdf | |
| PWC | https://paperswithcode.com/paper/an-efficient-high-probability-algorithm-for |
| Repo | |
| Framework | |
Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions
| Title | Semi-Coupled Two-Stream Fusion ConvNets for Action Recognition at Extremely Low Resolutions |
| Authors | Jiawei Chen, Jonathan Wu, Janusz Konrad, Prakash Ishwar |
| Abstract | Deep convolutional neural networks (ConvNets) have been recently shown to attain state-of-the-art performance for action recognition on standard-resolution videos. However, less attention has been paid to recognition performance at extremely low resolutions (eLR) (e.g., 16 x 12 pixels). Reliable action recognition using eLR cameras would address privacy concerns in various application environments such as private homes, hospitals, nursing/rehabilitation facilities, etc. In this paper, we propose a semi-coupled filter-sharing network that leverages high resolution (HR) videos during training in order to assist an eLR ConvNet. We also study methods for fusing spatial and temporal ConvNets customized for eLR videos in order to take advantage of appearance and motion information. Our method outperforms state-of-the-art methods at extremely low resolutions on IXMAS (93.7%) and HMDB (29.2%) datasets. |
| Tasks | Temporal Action Localization |
| Published | 2016-10-12 |
| URL | http://arxiv.org/abs/1610.03898v2 |
| http://arxiv.org/pdf/1610.03898v2.pdf | |
| PWC | https://paperswithcode.com/paper/semi-coupled-two-stream-fusion-convnets-for |
| Repo | |
| Framework | |
FAST: A Framework to Accelerate Super-Resolution Processing on Compressed Videos
| Title | FAST: A Framework to Accelerate Super-Resolution Processing on Compressed Videos |
| Authors | Zhengdong Zhang, Vivienne Sze |
| Abstract | State-of-the-art super-resolution (SR) algorithms require significant computational resources to achieve real-time throughput (e.g., 60Mpixels/s for HD video). This paper introduces FAST (Free Adaptive Super-resolution via Transfer), a framework to accelerate any SR algorithm applied to compressed videos. FAST exploits the temporal correlation between adjacent frames such that SR is only applied to a subset of frames; SR pixels are then transferred to the other frames. The transferring process has negligible computation cost as it uses information already embedded in the compressed video (e.g., motion vectors and residual). Adaptive processing is used to retain accuracy when the temporal correlation is not present (e.g., occlusions). FAST accelerates state-of-the-art SR algorithms by up to 15x with a visual quality loss of 0.2dB. FAST is an important step towards real-time SR algorithms for ultra-HD displays and energy constrained devices (e.g., phones and tablets). |
| Tasks | Super-Resolution |
| Published | 2016-03-29 |
| URL | http://arxiv.org/abs/1603.08968v2 |
| http://arxiv.org/pdf/1603.08968v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-a-framework-to-accelerate-super |
| Repo | |
| Framework | |
A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech
| Title | A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech |
| Authors | Mourad Mars, Mounir Zrigui, Mohamed Belgacem, Anis Zouaghi |
| Abstract | This work is part of a large research project entitled “Or'eodule” aimed at developing tools for automatic speech recognition, translation, and synthesis for Arabic language. Our attention has mainly been focused on an attempt to improve the probabilistic model on which our semantic decoder is based. To achieve this goal, we have decided to test the influence of the pertinent context use, and of the contextual data integration of different types, on the effectiveness of the semantic decoder. The findings are quite satisfactory. |
| Tasks | Speech Recognition |
| Published | 2016-10-08 |
| URL | http://arxiv.org/abs/1610.02493v1 |
| http://arxiv.org/pdf/1610.02493v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-semantic-analyzer-for-the-comprehension-of |
| Repo | |
| Framework | |
VRPBench: A Vehicle Routing Benchmark Tool
| Title | VRPBench: A Vehicle Routing Benchmark Tool |
| Authors | Guilherme A. Zeni, Mauro Menzori, P. S. Martins, Luis A. A. Meira |
| Abstract | The number of optimization techniques in the combinatorial domain is large and diversified. Nevertheless, there is still a lack of real benchmarks to validate optimization algorithms. In this work we introduce VRPBench, a tool to create instances and visualize solutions to the Vehicle Routing Problem (VRP) in a planar graph embedded in the Euclidean 2D space. We use VRPBench to model a real-world mail delivery case of the city of Artur Nogueira. Such scenarios were characterized as a multi-objective optimization of the VRP. We extracted a weighted graph from a digital map of the city to create a challenging benchmark for the VRP. Each instance models one generic day of mail delivery with hundreds to thousands of delivery points, thus allowing both the comparison and validation of optimization algorithms for routing problems. |
| Tasks | |
| Published | 2016-10-18 |
| URL | http://arxiv.org/abs/1610.05402v1 |
| http://arxiv.org/pdf/1610.05402v1.pdf | |
| PWC | https://paperswithcode.com/paper/vrpbench-a-vehicle-routing-benchmark-tool |
| Repo | |
| Framework | |
Homogeneity of Cluster Ensembles
| Title | Homogeneity of Cluster Ensembles |
| Authors | Brijnesh J. Jain |
| Abstract | The expectation and the mean of partitions generated by a cluster ensemble are not unique in general. This issue poses challenges in statistical inference and cluster stability. In this contribution, we state sufficient conditions for uniqueness of expectation and mean. The proposed conditions show that a unique mean is neither exceptional nor generic. To cope with this issue, we introduce homogeneity as a measure of how likely is a unique mean for a sample of partitions. We show that homogeneity is related to cluster stability. This result points to a possible conflict between cluster stability and diversity in consensus clustering. To assess homogeneity in a practical setting, we propose an efficient way to compute a lower bound of homogeneity. Empirical results using the k-means algorithm suggest that uniqueness of the mean partition is not exceptional for real-world data. Moreover, for samples of high homogeneity, uniqueness can be enforced by increasing the number of data points or by removing outlier partitions. In a broader context, this contribution can be placed as a further step towards a statistical theory of partitions. |
| Tasks | |
| Published | 2016-02-08 |
| URL | http://arxiv.org/abs/1602.02543v1 |
| http://arxiv.org/pdf/1602.02543v1.pdf | |
| PWC | https://paperswithcode.com/paper/homogeneity-of-cluster-ensembles |
| Repo | |
| Framework | |
A robust autoassociative memory with coupled networks of Kuramoto-type oscillators
| Title | A robust autoassociative memory with coupled networks of Kuramoto-type oscillators |
| Authors | Daniel Heger, Katharina Krischer |
| Abstract | Uncertain recognition success, unfavorable scaling of connection complexity or dependence on complex external input impair the usefulness of current oscillatory neural networks for pattern recognition or restrict technical realizations to small networks. We propose a new network architecture of coupled oscillators for pattern recognition which shows none of the mentioned aws. Furthermore we illustrate the recognition process with simulation results and analyze the new dynamics analytically: Possible output patterns are isolated attractors of the system. Additionally, simple criteria for recognition success are derived from a lower bound on the basins of attraction. |
| Tasks | |
| Published | 2016-04-07 |
| URL | http://arxiv.org/abs/1604.02085v2 |
| http://arxiv.org/pdf/1604.02085v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-robust-autoassociative-memory-with-coupled |
| Repo | |
| Framework | |
Online Event Recognition from Moving Vessel Trajectories
| Title | Online Event Recognition from Moving Vessel Trajectories |
| Authors | Kostas Patroumpas, Elias Alevizos, Alexander Artikis, Marios Vodas, Nikos Pelekis, Yannis Theodoridis |
| Abstract | We present a system for online monitoring of maritime activity over streaming positions from numerous vessels sailing at sea. It employs an online tracking module for detecting important changes in the evolving trajectory of each vessel across time, and thus can incrementally retain concise, yet reliable summaries of its recent movement. In addition, thanks to its complex event recognition module, this system can also offer instant notification to marine authorities regarding emergency situations, such as risk of collisions, suspicious moves in protected zones, or package picking at open sea. Not only did our extensive tests validate the performance, efficiency, and robustness of the system against scalable volumes of real-world and synthetically enlarged datasets, but its deployment against online feeds from vessels has also confirmed its capabilities for effective, real-time maritime surveillance. |
| Tasks | |
| Published | 2016-01-22 |
| URL | http://arxiv.org/abs/1601.06041v1 |
| http://arxiv.org/pdf/1601.06041v1.pdf | |
| PWC | https://paperswithcode.com/paper/online-event-recognition-from-moving-vessel |
| Repo | |
| Framework | |
Why and How to Pay Different Attention to Phrase Alignments of Different Intensities
| Title | Why and How to Pay Different Attention to Phrase Alignments of Different Intensities |
| Authors | Wenpeng Yin, Hinrich Schütze |
| Abstract | This work studies comparatively two typical sentence pair classification tasks: textual entailment (TE) and answer selection (AS), observing that phrase alignments of different intensities contribute differently in these tasks. We address the problems of identifying phrase alignments of flexible granularity and pooling alignments of different intensities for these tasks. Examples for flexible granularity are alignments between two single words, between a single word and a phrase and between a short phrase and a long phrase. By intensity we roughly mean the degree of match, it ranges from identity over surface-form co-occurrence, rephrasing and other semantic relatedness to unrelated words as in lots of parenthesis text. Prior work (i) has limitations in phrase generation and representation, or (ii) conducts alignment at word and phrase levels by handcrafted features or (iii) utilizes a single attention mechanism over alignment intensities without considering the characteristics of specific tasks, which limits the system’s effectiveness across tasks. We propose an architecture based on Gated Recurrent Unit that supports (i) representation learning of phrases of arbitrary granularity and (ii) task-specific focusing of phrase alignments between two sentences by attention pooling. Experimental results on TE and AS match our observation and are state-of-the-art. |
| Tasks | Answer Selection, Natural Language Inference, Representation Learning |
| Published | 2016-04-23 |
| URL | http://arxiv.org/abs/1604.06896v2 |
| http://arxiv.org/pdf/1604.06896v2.pdf | |
| PWC | https://paperswithcode.com/paper/why-and-how-to-pay-different-attention-to |
| Repo | |
| Framework | |
M$^2$S-Net: Multi-Modal Similarity Metric Learning based Deep Convolutional Network for Answer Selection
| Title | M$^2$S-Net: Multi-Modal Similarity Metric Learning based Deep Convolutional Network for Answer Selection |
| Authors | Lingxun Meng, Yan Li |
| Abstract | Recent works using artificial neural networks based on distributed word representation greatly boost performance on various natural language processing tasks, especially the answer selection problem. Nevertheless, most of the previous works used deep learning methods (like LSTM-RNN, CNN, etc.) only to capture semantic representation of each sentence separately, without considering the interdependence between each other. In this paper, we propose a novel end-to-end learning framework which constitutes deep convolutional neural network based on multi-modal similarity metric learning (M$^2$S-Net) on pairwise tokens. The proposed model demonstrates its performance by surpassing previous state-of-the-art systems on the answer selection benchmark, i.e., TREC-QA dataset, in both MAP and MRR metrics. |
| Tasks | Answer Selection, Metric Learning |
| Published | 2016-04-19 |
| URL | http://arxiv.org/abs/1604.05519v3 |
| http://arxiv.org/pdf/1604.05519v3.pdf | |
| PWC | https://paperswithcode.com/paper/m2s-net-multi-modal-similarity-metric |
| Repo | |
| Framework | |
Boosting Factor-Specific Functional Historical Models for the Detection of Synchronisation in Bioelectrical Signals
| Title | Boosting Factor-Specific Functional Historical Models for the Detection of Synchronisation in Bioelectrical Signals |
| Authors | David Rügamer, Sarah Brockhaus, Kornelia Gentsch, Klaus Scherer, Sonja Greven |
| Abstract | The link between different psychophysiological measures during emotion episodes is not well understood. To analyse the functional relationship between electroencephalography (EEG) and facial electromyography (EMG), we apply historical function-on-function regression models to EEG and EMG data that were simultaneously recorded from 24 participants while they were playing a computerised gambling task. Given the complexity of the data structure for this application, we extend simple functional historical models to models including random historical effects, factor-specific historical effects, and factor-specific random historical effects. Estimation is conducted by a component-wise gradient boosting algorithm, which scales well to large data sets and complex models. |
| Tasks | EEG, Electromyography (EMG) |
| Published | 2016-09-20 |
| URL | http://arxiv.org/abs/1609.06070v2 |
| http://arxiv.org/pdf/1609.06070v2.pdf | |
| PWC | https://paperswithcode.com/paper/boosting-factor-specific-functional |
| Repo | |
| Framework | |
RAISR: Rapid and Accurate Image Super Resolution
| Title | RAISR: Rapid and Accurate Image Super Resolution |
| Authors | Yaniv Romano, John Isidoro, Peyman Milanfar |
| Abstract | Given an image, we wish to produce an image of larger size with significantly more pixels and higher image quality. This is generally known as the Single Image Super-Resolution (SISR) problem. The idea is that with sufficient training data (corresponding pairs of low and high resolution images) we can learn set of filters (i.e. a mapping) that when applied to given image that is not in the training set, will produce a higher resolution version of it, where the learning is preferably low complexity. In our proposed approach, the run-time is more than one to two orders of magnitude faster than the best competing methods currently available, while producing results comparable or better than state-of-the-art. A closely related topic is image sharpening and contrast enhancement, i.e., improving the visual quality of a blurry image by amplifying the underlying details (a wide range of frequencies). Our approach additionally includes an extremely efficient way to produce an image that is significantly sharper than the input blurry one, without introducing artifacts such as halos and noise amplification. We illustrate how this effective sharpening algorithm, in addition to being of independent interest, can be used as a pre-processing step to induce the learning of more effective upscaling filters with built-in sharpening and contrast enhancement effect. |
| Tasks | Image Super-Resolution, Super-Resolution |
| Published | 2016-06-03 |
| URL | http://arxiv.org/abs/1606.01299v3 |
| http://arxiv.org/pdf/1606.01299v3.pdf | |
| PWC | https://paperswithcode.com/paper/raisr-rapid-and-accurate-image-super |
| Repo | |
| Framework | |
Semi-Dense 3D Semantic Mapping from Monocular SLAM
| Title | Semi-Dense 3D Semantic Mapping from Monocular SLAM |
| Authors | Xuanpeng Li, Rachid Belaroussi |
| Abstract | The bundle of geometry and appearance in computer vision has proven to be a promising solution for robots across a wide variety of applications. Stereo cameras and RGB-D sensors are widely used to realise fast 3D reconstruction and trajectory tracking in a dense way. However, they lack flexibility of seamless switch between different scaled environments, i.e., indoor and outdoor scenes. In addition, semantic information are still hard to acquire in a 3D mapping. We address this challenge by combining the state-of-art deep learning method and semi-dense Simultaneous Localisation and Mapping (SLAM) based on video stream from a monocular camera. In our approach, 2D semantic information are transferred to 3D mapping via correspondence between connective Keyframes with spatial consistency. There is no need to obtain a semantic segmentation for each frame in a sequence, so that it could achieve a reasonable computation time. We evaluate our method on indoor/outdoor datasets and lead to an improvement in the 2D semantic labelling over baseline single frame predictions. |
| Tasks | 3D Reconstruction, Semantic Segmentation |
| Published | 2016-11-13 |
| URL | http://arxiv.org/abs/1611.04144v1 |
| http://arxiv.org/pdf/1611.04144v1.pdf | |
| PWC | https://paperswithcode.com/paper/semi-dense-3d-semantic-mapping-from-monocular |
| Repo | |
| Framework | |
Selective Inference Approach for Statistically Sound Predictive Pattern Mining
| Title | Selective Inference Approach for Statistically Sound Predictive Pattern Mining |
| Authors | Shinya Suzumura, Kazuya Nakagawa, Mahito Sugiyama, Koji Tsuda, Ichiro Takeuchi |
| Abstract | Discovering statistically significant patterns from databases is an important challenging problem. The main obstacle of this problem is in the difficulty of taking into account the selection bias, i.e., the bias arising from the fact that patterns are selected from extremely large number of candidates in databases. In this paper, we introduce a new approach for predictive pattern mining problems that can address the selection bias issue. Our approach is built on a recently popularized statistical inference framework called selective inference. In selective inference, statistical inferences (such as statistical hypothesis testing) are conducted based on sampling distributions conditional on a selection event. If the selection event is characterized in a tractable way, statistical inferences can be made without minding selection bias issue. However, in pattern mining problems, it is difficult to characterize the entire selection process of mining algorithms. Our main contribution in this paper is to solve this challenging problem for a class of predictive pattern mining problems by introducing a novel algorithmic framework. We demonstrate that our approach is useful for finding statistically significant patterns from databases. |
| Tasks | |
| Published | 2016-02-15 |
| URL | http://arxiv.org/abs/1602.04601v2 |
| http://arxiv.org/pdf/1602.04601v2.pdf | |
| PWC | https://paperswithcode.com/paper/selective-inference-approach-for |
| Repo | |
| Framework | |
Face Image Analysis using AAM, Gabor, LBP and WD features for Gender, Age, Expression and Ethnicity Classification
| Title | Face Image Analysis using AAM, Gabor, LBP and WD features for Gender, Age, Expression and Ethnicity Classification |
| Authors | N. S. Lakshmiprabha |
| Abstract | The growth in electronic transactions and human machine interactions rely on the information such as gender, age, expression and ethnicity provided by the face image. In order to obtain these information, feature extraction plays a major role. In this paper, retrieval of age, gender, expression and race information from an individual face image is analysed using different feature extraction methods. The performance of four major feature extraction methods such as Active Appearance Model (AAM), Gabor wavelets, Local Binary Pattern (LBP) and Wavelet Decomposition (WD) are analyzed for gender recognition, age estimation, expression recognition and racial recognition in terms of accuracy (recognition rate), time for feature extraction, neural training and time to test an image. Each of this recognition system is compared with four feature extractors on same dataset (training and validation set) to get a better understanding in its performance. Experiments carried out on FG-NET, Cohn-Kanade, PAL face database shows that each method has its own merits and demerits. Hence it is practically impossible to define a method which is best at all circumstances with less computational complexity. Further, a detailed comparison of age estimation and age estimation using gender information is provided along with a solution to overcome aging effect in case of gender recognition. An attempt has been made in obtaining all (i.e. gender, age range, expression and ethnicity) information from a test image in a single go. |
| Tasks | Age Estimation |
| Published | 2016-03-29 |
| URL | http://arxiv.org/abs/1604.01684v1 |
| http://arxiv.org/pdf/1604.01684v1.pdf | |
| PWC | https://paperswithcode.com/paper/face-image-analysis-using-aam-gabor-lbp-and |
| Repo | |
| Framework | |
