【arxiv论文】 Computation and Language 2020-02-14

发表于 2020-02-15 更新于 2020-03-05 分类于 arxiv ， CL 18k 31 分钟

目录

1. Looking Enhances Listening: Recovering Missing Speech Using Images [PDF] 摘要

2. Pre-Training for Query Rewriting in A Spoken Language Understanding System [PDF] 摘要

3. Sentiment Analysis Using Averaged Weighted Word Vector Features [PDF] 摘要

4. Sparse and Structured Visual Attention [PDF] 摘要

5. Unsupervised Separation of Native and Loanwords for Malayalam and Telugu [PDF] 摘要

6. Comparison of Turkish Word Representations Trained on Different Morphological Forms [PDF] 摘要

7. Keyphrase Extraction with Span-based Feature Representations [PDF] 摘要

8. Exploiting the Matching Information in the Support Set for Few Shot Event Classification [PDF] 摘要

9. What Would You Ask the Machine Learning Model? Identification of User Needs for Model Explanations Based on Human-Model Conversations [PDF] 摘要

10. Image-to-Image Translation with Text Guidance [PDF] 摘要

11. Deep compositional robotic planners that follow natural language commands [PDF] 摘要

12. A Combined Stochastic and Physical Framework for Modeling Indoor 5G Millimeter Wave Propagation [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-02-14

发表于 2020-02-15 更新于 2020-03-05 分类于 arxiv ， CV 42k 1:10

目录

1. Automatically Discovering and Learning New Visual Categories with Ranking Statistics [PDF] 摘要

2. Classifying the classifier: dissecting the weight space of neural networks [PDF] 摘要

3. Summarizing the performances of a background subtraction algorithm measured on several videos [PDF] 摘要

4. GANILLA: Generative Adversarial Networks for Image to Illustration Translation [PDF] 摘要

5. Asynchronous Tracking-by-Detection on Adaptive Time Surfaces for Event-based Object Tracking [PDF] 摘要

6. SpotNet: Self-Attention Multi-Task Network for Object Detection [PDF] 摘要

7. Replacing Mobile Camera ISP with a Single Deep Learning Model [PDF] 摘要

8. Chaotic Phase Synchronization and Desynchronization in an Oscillator Network for Object Selection [PDF] 摘要

9. EndoL2H: Deep Super-Resolution for Capsule Endoscopy [PDF] 摘要

10. Emotion Recognition for In-the-wild Videos [PDF] 摘要

11. Recurrent Attention Model with Log-Polar Mapping is Robust against Adversarial Attacks [PDF] 摘要

12. Hypergraph Optimization for Multi-structural Geometric Model Fitting [PDF] 摘要

13. Object Detection on Single Monocular Images through Canonical Correlation Analysis [PDF] 摘要

14. Continual Universal Object Detection [PDF] 摘要

15. SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud [PDF] 摘要

16. Improving Efficiency in Neural Network Accelerator Using Operands Hamming Distance optimization [PDF] 摘要

17. Solving Missing-Annotation Object Detection with Background Recalibration Loss [PDF] 摘要

18. Leveraging Affect Transfer Learning for Behavior Prediction in an Intelligent Tutoring System [PDF] 摘要

19. Image-to-Image Translation with Text Guidance [PDF] 摘要

20. Cross-Iteration Batch Normalization [PDF] 摘要

21. A Simple Framework for Contrastive Learning of Visual Representations [PDF] 摘要

22. Generative-based Airway and Vessel Morphology Quantification on Chest CT Images [PDF] 摘要

23. Neuromorphologicaly-preserving Volumetric data encoding using VQ-VAE [PDF] 摘要

24. FRSign: A Large-Scale Traffic Light Dataset for Autonomous Trains [PDF] 摘要

25. Machines Learn Appearance Bias in Face Recognition [PDF] 摘要

26. Sparse and Structured Visual Attention [PDF] 摘要

27. Superpixel Image Classification with Graph Attention Networks [PDF] 摘要

28. Deep Learning-based End-to-end Diagnosis System for Avascular Necrosis of Femoral Head [PDF] 摘要

29. Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner [PDF] 摘要

30. Real or Not Real, that is the Question [PDF] 摘要

31. MLFcGAN: Multi-level Feature Fusion based Conditional GAN for Underwater Image Color Correction [PDF] 摘要

32. Physical Accuracy of Deep Neural Networks for 2D and 3D Multi-Mineral Segmentation of Rock micro-CT Images [PDF] 摘要

33. A Provably Robust Multiple Rotation Averaging Scheme for SO(2) [PDF] 摘要

34. Geom-GCN: Geometric Graph Convolutional Networks [PDF] 摘要

35. HypoML: Visual Analysis for Hypothesis-based Evaluation of Machine Learning Models [PDF] 摘要

36. Graph Similarity Using PageRank and Persistent Homology [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-02-13

发表于 2020-02-14 更新于 2020-03-05 分类于 arxiv ， CV 52k 1:27

目录

1. Rembrandts and Robots: Using Neural Networks to Explore Authorship in Painting [PDF] 摘要

2. Component Analysis for Visual Question Answering Architectures [PDF] 摘要

3. AlignNet: A Unifying Approach to Audio-Visual Alignment [PDF] 摘要

4. Detect and Correct Bias in Multi-Site Neuroimaging Datasets [PDF] 摘要

5. Intra-Camera Supervised Person Re-Identification [PDF] 摘要

6. Learning light field synthesis with Multi-Plane Images: scene encoding as a recurrent segmentation task [PDF] 摘要

7. Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis [PDF] 摘要

8. Real-Time Semantic Background Subtraction [PDF] 摘要

9. Hierarchical Auto-Regressive Model for Image Compression Incorporating Object Saliency and a Deep Perceptual Loss [PDF] 摘要

10. Towards Precise Intra-camera Supervised Person Re-identification [PDF] 摘要

11. A Zero-Shot based Fingerprint Presentation Attack Detection System [PDF] 摘要

12. Bi-Directional Generation for Unsupervised Domain Adaptation [PDF] 摘要

13. Analysis Of Multi Field Of View Cnn And Attention Cnn On H&E Stained Whole-slide Images On Hepatocellular Carcinoma [PDF] 摘要

14. End-to-End Face Parsing via Interlinked Convolutional Neural Networks [PDF] 摘要

15. Uniform Interpolation Constrained Geodesic Learning on Data Manifold [PDF] 摘要

16. Deep-HR: Fast Heart Rate Estimation from Face Video Under Realistic Conditions [PDF] 摘要

17. A Visual-inertial Navigation Method for High-Speed Unmanned Aerial Vehicles [PDF] 摘要

18. MFFW: A new dataset for multi-focus image fusion [PDF] 摘要

19. Efficient Training of Deep Convolutional Neural Networks by Augmentation in Embedding Space [PDF] 摘要

20. Progressive Object Transfer Detection [PDF] 摘要

21. Improving Place Recognition Using Dynamic Object Detection [PDF] 摘要

22. Learning spatio-temporal representations with temporal squeeze pooling [PDF] 摘要

23. Object Detection as a Positive-Unlabeled Problem [PDF] 摘要

24. Validating uncertainty in medical image translation [PDF] 摘要

25. Finding novelty with uncertainty [PDF] 摘要

26. Patternless Adversarial Attacks on Video Recognition Networks [PDF] 摘要

27. From IC Layout to Die Photo: A CNN-Based Data-Driven Approach [PDF] 摘要

28. Synaptic Integration of Spatiotemporal Features with a Dynamic Neuromorphic Processor [PDF] 摘要

29. Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes [PDF] 摘要

30. A Single RGB Camera Based Gait Analysis with a Mobile Tele-Robot for Healthcare [PDF] 摘要

31. fastai: A Layered API for Deep Learning [PDF] 摘要

32. A Non-Intrusive Correction Algorithm for Classification Problems with Corrupted Data [PDF] 摘要

33. Neuroevolution of Neural Network Architectures Using CoDeepNEAT and Keras [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-02-13

发表于 2020-02-14 更新于 2020-03-05 分类于 arxiv ， CL 17k 29 分钟

目录

1. Learning to Compare for Better Training and Evaluation of Open Domain Natural Language Generation Models [PDF] 摘要

2. Joint Embedding in Named Entity Linking on Sentence Level [PDF] 摘要

3. Utilizing BERT Intermediate Layers for Aspect Based Sentiment Analysis and Natural Language Inference [PDF] 摘要

4. ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems [PDF] 摘要

5. Two Huge Title and Keyword Generation Corpora of Research Articles [PDF] 摘要

6. Adjusting Image Attributes of Localized Regions with Low-level Dialogue [PDF] 摘要

7. Constructing a Highlight Classifier with an Attention Based LSTM Neural Network [PDF] 摘要

8. Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances [PDF] 摘要

9. DeepMutation: A Neural Mutation Tool [PDF] 摘要

10. On Layer Normalization in the Transformer Architecture [PDF] 摘要

11. Superbloom: Bloom filter meets Transformer [PDF] 摘要

12. A Non-Intrusive Correction Algorithm for Classification Problems with Corrupted Data [PDF] 摘要

阅读全文 »

【论文笔记】Unsupervised Domain Adaptation for Neural Machine Translation with Iterative Back Translation

发表于 2020-02-13 分类于 论文笔记 833 1 分钟

AAAI 迭代回翻 非监督 领域适应

Unsupervised Domain Adaptation for Neural Machine Translation with Iterative Back Translation. Di Jin, Zhijing Jin, Joey Tianyi Zhou, Peter Szolovits. AAAI 2020. [PDF]

阅读全文 »

【arxiv论文】 Computation and Language 2020-02-12

发表于 2020-02-12 更新于 2020-03-05 分类于 arxiv ， CL 16k 27 分钟

目录

1. The Rumour Mill: Making Misinformation Spread Visible and Tangible [PDF] 摘要

2. ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning [PDF] 摘要

3. Learning Coupled Policies for Simultaneous Machine Translation [PDF] 摘要

4. Non-Autoregressive Neural Dialogue Generation [PDF] 摘要

5. Performance Comparison of Crowdworkers and NLP Tools onNamed-Entity Recognition and Sentiment Analysis of Political Tweets [PDF] 摘要

6. Training with Streaming Annotation [PDF] 摘要

7. Automatic Discourse Segmentation: an evaluation in French [PDF] 摘要

8. An experiment exploring the theoretical and methodological challenges in developing a semi-automated approach to analysis of small-N qualitative data [PDF] 摘要

9. HGAT: Hierarchical Graph Attention Network for Fake News Detection [PDF] 摘要

10. Convolutional Neural Networks and a Transfer Learning Strategy to Classify Parkinson's Disease from Speech in Three Different Languages [PDF] 摘要

11. Adversarial Filters of Dataset Biases [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-02-11

发表于 2020-02-11 更新于 2020-03-05 分类于 arxiv ， CV 20k 34 分钟

目录

1. Upper, Middle and Lower Region Learning for Facial Action Unit Detection [PDF] 摘要

2. Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation [PDF] 摘要

3. Unconstrained Periocular Recognition: Using Generative Deep Learning Frameworks for Attribute Normalization [PDF] 摘要

4. StickyPillars: Robust feature matching on point clouds using Graph Neural Networks [PDF] 摘要

5. Joint Encoding of Appearance and Motion Features with Self-supervision for First Person Action Recognition [PDF] 摘要

6. RePose: Learning Deep Kinematic Priors for Fast Human Pose Estimation [PDF] 摘要

7. 6DoF Object Pose Estimation via Differentiable Proxy Voting Loss [PDF] 摘要

8. Hierarchical Multi-Process Fusion for Visual Place Recognition [PDF] 摘要

9. CIFAR-10 Image Classification Using Feature Ensembles [PDF] 摘要

10. Exploiting Temporal Coherence for Multi-modal Video Categorization [PDF] 摘要

11. Attentive Group Equivariant Convolutional Networks [PDF] 摘要

12. Level Three Synthetic Fingerprint Generation [PDF] 摘要

13. Automatic image-based identification and biomass estimation of invertebrates [PDF] 摘要

14. CONVINCE: Collaborative Cross-Camera Video Analytics at the Edge [PDF] 摘要

15. Deep Learning for Classifying Food Waste [PDF] 摘要

16. Multi-stream Faster RCNN for Mitosis Counting in Breast Cancer Images [PDF] 摘要

17. Towards Deep Machine Reasoning: a Prototype-based Deep Neural Network with Decision Tree Inference [PDF] 摘要

18. Deriving Emotions and Sentiments from Visual Content: A Disaster Analysis Use Case [PDF] 摘要

19. Improving the Evaluation of Generative Models with Fuzzy Logic [PDF] 摘要

20. Learning Numerical Observers using Unsupervised Domain Adaptation [PDF] 摘要

21. Music2Dance: Music-driven Dance Generation using WaveNet [PDF] 摘要

22. An Empirical Study of Person Re-Identification with Attributes [PDF] 摘要

23. Weighted Average Precision: Adversarial Example Detection in the Visual Perception of Autonomous Vehicles [PDF] 摘要

24. An Overview of Two Age Synthesis and Estimation Techniques [PDF] 摘要

25. DFKI Cabin Simulator: A Test Platform for Visual In-Cabin Monitoring Functions [PDF] 摘要

26. Black Box Explanation by Learning Image Exemplars in the Latent Feature Space [PDF] 摘要

27. Dynamic Error-bounded Lossy Compression (EBLC) to Reduce the Bandwidth Requirement for Real-time Vision-based Pedestrian Safety Applications [PDF] 摘要

28. Efficient Scene Text Detection with Textual Attention Tower [PDF] 摘要

29. Convolutional Hierarchical Attention Network for Query-Focused Video Summarization [PDF] 摘要

30. Localizing Multi-scale Semantic Patches for Image Classification [PDF] 摘要

31. Universal Semantic Segmentation for Fisheye Urban Driving Images [PDF] 摘要

32. Real-Time Object Detection and Recognition on Low-Compute Humanoid Robots using Deep Learning [PDF] 摘要

33. Iterative energy-based projection on a normal data manifold for anomaly localization [PDF] 摘要

34. Robust Multimodal Image Registration Using Deep Recurrent Reinforcement Learning [PDF] 摘要

35. Impact of Data Quality on Deep Neural Network Training [PDF] 摘要

36. RSnet: An improvement for Darknet [PDF] 摘要

37. Driver Drowsiness Detection Model Using Convolutional Neural Networks Techniques for Android Application [PDF] 摘要

38. Durocmien: A deep framework for duroc skeleton extraction in constraint environment [PDF] 摘要

39. Deep Frequent Spatial Temporal Learning for Face Anti-Spoofing [PDF] 摘要

40. Unsupervised deep clustering for predictive texture pattern discovery in medical images [PDF] 摘要

41. Fabricated Pictures Detection with Graph Matching [PDF] 摘要

42. Knowledge Distillation for Brain Tumor Segmentation [PDF] 摘要

43. Deep Multi-task Multi-label CNN for Effective Facial Attribute Classification [PDF] 摘要

44. Uncertainty Estimation for End-To-End Learned Dense Stereo Matching via Probabilistic Deep Learning [PDF] 摘要

45. Distribution Distillation Loss: Generic Approach for Improving Face Recognition from Hard Samples [PDF] 摘要

46. CRVOS: Clue Refining Network for Video Object Segmentation [PDF] 摘要

47. Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation [PDF] 摘要

48. End-to-End Facial Deep Learning Feature Compression with Teacher-Student Enhancement [PDF] 摘要

49. Post-Comparison Mitigation of Demographic Bias in Face Recognition Using Fair Score Normalization [PDF] 摘要

50. Prototype Refinement Network for Few-Shot Segmentation [PDF] 摘要

51. Automatic detection and counting of retina cell nuclei using deep learning [PDF] 摘要

52. FAU, Facial Expressions, Valence and Arousal: A Multi-task Solution [PDF] 摘要

53. Vehicle Driving Assistant [PDF] 摘要

54. From Anchor Generation to Distribution Alignment: Learning a Discriminative Embedding Space for Zero-Shot Recognition [PDF] 摘要

55. UGRWO-Sampling: A modified random walk under-sampling approach based on graphs to imbalanced data classification [PDF] 摘要

56. A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling [PDF] 摘要

57. Segmenting unseen industrial components in a heavy clutter using rgb-d fusion and synthetic data [PDF] 摘要

58. ABBA: Saliency-Regularized Motion-Based Adversarial Blur Attack [PDF] 摘要

59. Medical Image Registration Using Deep Neural Networks: A Comprehensive Review [PDF] 摘要

60. Two-Stream Aural-Visual Affect Analysis in the Wild [PDF] 摘要

61. MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data [PDF] 摘要

62. Weakly Supervised Attention Pyramid Convolutional Neural Network for Fine-Grained Visual Classification [PDF] 摘要

63. Dynamic Inference: A New Approach Toward Efficient Video Action Recognition [PDF] 摘要

64. VIFB: A Visible and Infrared Image Fusion Benchmark [PDF] 摘要

65. Unlabeled Data Deployment for Classification of Diabetic Retinopathy Images Using Knowledge Transfer [PDF] 摘要

66. FSD-10: A Dataset for Competitive Sports Content Analysis [PDF] 摘要

67. Face Hallucination with Finishing Touches [PDF] 摘要

68. Splitting Convolutional Neural Network Structures for Efficient Inference [PDF] 摘要

69. Convolutional Neural Network Pruning Using Filter Attenuation [PDF] 摘要

70. PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification [PDF] 摘要

71. Asymmetric Rejection Loss for Fairer Face Recognition [PDF] 摘要

72. Learning efficient structured dictionary for image classification [PDF] 摘要

73. Weakly-Supervised Multi-Person Action Recognition in 360$^{\circ}$ Videos [PDF] 摘要

74. GradMix: Multi-source Transfer across Domains and Tasks [PDF] 摘要

75. Ensemble of Deep Convolutional Neural Networks for Automatic Pavement Crack Detection and Measurement [PDF] 摘要

76. Multi-Label Class Balancing Algorithm for Action Unit Detection [PDF] 摘要

77. Intrinsic Dimension Estimation via Nearest Constrained Subspace Classifier [PDF] 摘要

78. Exocentric to Egocentric Image Generation via Parallel Generative Adversarial Network [PDF] 摘要

79. Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition [PDF] 摘要

80. Sparsity-Aware Deep Learning for Automatic 4D Facial Expression Recognition [PDF] 摘要

81. CTM: Collaborative Temporal Modeling for Action Recognition [PDF] 摘要

82. Multi-Modality Cascaded Fusion Technology for Autonomous Driving [PDF] 摘要

83. Symbiotic Attention with Privileged Information for Egocentric Action Recognition [PDF] 摘要

84. Variable-Viewpoint Representations for 3D Object Recognition [PDF] 摘要

85. Attacking Optical Character Recognition (OCR) Systems with Adversarial Watermarks [PDF] 摘要

86. Bone Suppression on Chest Radiographs With Adversarial Learning [PDF] 摘要

87. Local Facial Attribute Transfer through Inpainting [PDF] 摘要

88. Unsupervised Discovery of Interpretable Directions in the GAN Latent Space [PDF] 摘要

89. Learning End-to-End Lossy Image Compression: A Benchmark [PDF] 摘要

90. Distributed Bayesian Matrix Decomposition for Big Data Mining and Clustering [PDF] 摘要

91. Adversarial TCAV -- Robust and Effective Interpretation of Intermediate Layers in Neural Networks [PDF] 摘要

92. Multi-object Monocular SLAM for Dynamic Environments [PDF] 摘要

93. Ultra High Fidelity Image Compression with $\ell_\infty$-constrained Encoding and Deep Decoding [PDF] 摘要

94. Semi-Supervised Class Discovery [PDF] 摘要

95. A Deep Learning Approach to Automate High-Resolution Blood Vessel Reconstruction on Computerized Tomography Images With or Without the Use of Contrast Agent [PDF] 摘要

96. A Unified End-to-End Framework for Efficient Deep Image Compression [PDF] 摘要

97. Multi-Task Learning by a Top-Down Control Network [PDF] 摘要

98. Out-of-Distribution Detection with Distance Guarantee in Deep Generative Models [PDF] 摘要

99. Holographic Image Sensing [PDF] 摘要

100. Soft Threshold Weight Reparameterization for Learnable Sparsity [PDF] 摘要

101. Correction of Chromatic Aberration from a Single Image Using Keypoints [PDF] 摘要

102. Deep No-reference Tone Mapped Image Quality Assessment [PDF] 摘要

103. Ramifications and Diminution of Image Noise in Iris Recognition System [PDF] 摘要

104. An Empirical Evaluation of Perturbation-based Defenses [PDF] 摘要

105. Predictive online optimisation with applications to optical flow [PDF] 摘要

106. Cognitive Anthropomorphism of AI: How Humans and Computers Classify Images [PDF] 摘要

107. Improving the Adversarial Robustness of Transfer Learning via Noisy Feature Distillation [PDF] 摘要

108. DropCluster: A structured dropout for convolutional networks [PDF] 摘要

109. SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-02-11

发表于 2020-02-11 更新于 2020-03-05 分类于 arxiv ， CL 32k 53 分钟

目录

1. End-to-End Multi-speaker Speech Recognition with Transformer [PDF] 摘要

2. A Probabilistic Formulation of Unsupervised Text Style Transfer [PDF] 摘要

3. A Study of Human Summaries of Scientific Articles [PDF] 摘要

4. What Changed Your Mind: The Roles of Dynamic Topics and Discourse in Argumentation Process [PDF] 摘要

5. Multilingual Alignment of Contextual Word Representations [PDF] 摘要

6. Limits of Detecting Text Generated by Large-Scale Language Models [PDF] 摘要

7. Abstractive Summarization for Low Resource Data using Domain Transfer and Data Synthesis [PDF] 摘要

8. Attend to the beginning: A study on using bidirectional attention for extractive summarization [PDF] 摘要

9. Short Text Classification via Knowledge powered Attention with Similarity Matrix based CNN [PDF] 摘要

10. Rough Set based Aggregate Rank Measure & its Application to Supervised Multi Document Summarization [PDF] 摘要

11. Mining Commonsense Facts from the Physical World [PDF] 摘要

12. HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional Attention [PDF] 摘要

13. LAVA NAT: A Non-Autoregressive Translation Model with Look-Around Decoding and Vocabulary Attention [PDF] 摘要

14. Blank Language Models [PDF] 摘要

15. Description Based Text Classification with Reinforcement Learning [PDF] 摘要

16. autoNLP: NLP Feature Recommendations for Text Analytics Applications [PDF] 摘要

17. Snippext: Semi-supervised Opinion Mining with Augmented Data [PDF] 摘要

18. Pre-training Tasks for Embedding-based Large-scale Retrieval [PDF] 摘要

19. A Novel Kuhnian Ontology for Epistemic Classification of STM Scholarly Articles [PDF] 摘要

20. SPA: Verbal Interactions between Agents and Avatars in Shared Virtual Environments using Propositional Planning [PDF] 摘要

21. Time-aware Large Kernel Convolutions [PDF] 摘要

阅读全文 »