【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-06

发表于 2020-04-06 分类于 arxiv ， CV 82k 2:17

目录

1. Near-chip Dynamic Vision Filtering for Low-Bandwidth Pedestrian Detection [PDF] 摘要

2. S2DNet: Learning Accurate Correspondences for Sparse-to-Dense Feature Matching [PDF] 摘要

3. Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation [PDF] 摘要

4. PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation [PDF] 摘要

5. Deep Learning based detection of Acute Aortic Syndrome in contrast CT images [PDF] 摘要

6. Quantifying Data Augmentation for LiDAR based 3D Object Detection [PDF] 摘要

7. Deep Learning for Image Search and Retrieval in Large Remote Sensing Archives [PDF] 摘要

8. Interpreting Medical Image Classifiers by Optimization Based Counterfactual Impact Analysis [PDF] 摘要

9. HandVoxNet: Deep Voxel-Based Network for 3D Hand Shape and Pose Estimation from a Single Depth Map [PDF] 摘要

10. DFNet: Discriminative feature extraction and integration network for salient object detection [PDF] 摘要

11. Sparse Concept Coded Tetrolet Transform for Unconstrained Odia Character Recognition [PDF] 摘要

12. Context Prior for Scene Segmentation [PDF] 摘要

13. Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges [PDF] 摘要

14. RANSAC-Flow: generic two-stage image alignment [PDF] 摘要

15. Two-Stream AMTnet for Action Detection [PDF] 摘要

16. Cell Segmentation and Tracking using Distance Transform Predictions and Movement Estimation with Graph-Based Matching [PDF] 摘要

17. Gradient Centralization: A New Optimization Technique for Deep Neural Networks [PDF] 摘要

18. Self-Paced Deep Regression Forests with Consideration on Underrepresented Samples [PDF] 摘要

19. Disassembling Object Representations without Labels [PDF] 摘要

20. Demographic Bias: A Challenge for Fingervein Recognition Systems? [PDF] 摘要

21. TEA: Temporal Excitation and Aggregation for Action Recognition [PDF] 摘要

22. LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention [PDF] 摘要

23. Effective Fusion of Deep Multitasking Representations for Robust Visual Tracking [PDF] 摘要

24. Sequential Learning for Domain Generalization [PDF] 摘要

25. FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret [PDF] 摘要

26. Deep White-Balance Editing [PDF] 摘要

27. Context-Aware Multi-Task Learning for Traffic Scene Recognition in Autonomous Vehicles [PDF] 摘要

28. Learning Pose-invariant 3D Object Reconstruction from Single-view Images [PDF] 摘要

29. A Fast Fully Octave Convolutional Neural Network for Document Image Segmentation [PDF] 摘要

30. From Paris to Berlin: Discovering Fashion Style Influences Around the World [PDF] 摘要

31. Towards Better Generalization: Joint Depth-Pose Learning without PoseNet [PDF] 摘要

32. Generative PointNet: Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification [PDF] 摘要

33. Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths from a Monocular Camera [PDF] 摘要

34. BosphorusSign22k Sign Language Recognition Dataset [PDF] 摘要

35. Knowing What, Where and When to Look: Efficient Video Action Modeling with Attention [PDF] 摘要

36. Guided Variational Autoencoder for Disentanglement Learning [PDF] 摘要

37. Semantic Segmentation of Underwater Imagery: Dataset and Benchmark [PDF] 摘要

38. Deformation-Aware 3D Model Embedding and Retrieval [PDF] 摘要

39. Temporal Accumulative Features for Sign Language Recognition [PDF] 摘要

40. Deep Transfer Learning for Texture Classification in Colorectal Cancer Histology [PDF] 摘要

41. Cell Segmentation by Combining Marker-Controlled Watershed and Deep Learning [PDF] 摘要

42. Detection of Perineural Invasion in Prostate Needle Biopsies with Deep Neural Networks [PDF] 摘要

43. Retinopathy of Prematurity Stage Diagnosis Using Object Segmentation and Convolutional Neural Networks [PDF] 摘要

44. Crossover-Net: Leveraging the Vertical-Horizontal Crossover Relation for Robust Segmentation [PDF] 摘要

45. Characterization of Multiple 3D LiDARs for Localization and Mapping using Normal Distributions Transform [PDF] 摘要

46. STAN-CT: Standardizing CT Image using Generative Adversarial Network [PDF] 摘要

47. Extraction and Assessment of Naturalistic Human Driving Trajectories from Infrastructure Camera and Radar Sensors [PDF] 摘要

48. Quantification of Tomographic Patterns associated with COVID-19 from Chest CT [PDF] 摘要

49. Introducing Anisotropic Minkowski Functionals and Quantitative Anisotropy Measures for Local Structure Analysis in Biomedical Imaging [PDF] 摘要

50. Detection of Coronavirus (COVID-19) Associated Pneumonia based on Generative Adversarial Networks and a Fine-Tuned Deep Transfer Learning Model using Chest X-ray Dataset [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-04-06

发表于 2020-04-06 分类于 arxiv ， CL 14k 23 分钟

目录

1. A Set of Recommendations for Assessing Human-Machine Parity in Language Translation [PDF] 摘要

2. Directions in Abusive Language Training Data: Garbage In, Garbage Out [PDF] 摘要

3. Aligned Cross Entropy for Non-Autoregressive Machine Translation [PDF] 摘要

4. Analyzing autoencoder-based acoustic word embeddings [PDF] 摘要

5. Keyphrase Rubric Relationship Classification in Complex Assignments [PDF] 摘要

6. Learning synchronous context-free grammars with multiple specialised non-terminals for hierarchical phrase-based translation [PDF] 摘要

7. XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation [PDF] 摘要

8. MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing [PDF] 摘要

9. R3: A Reading Comprehension Benchmark Requiring Reasoning Processes [PDF] 摘要

10. Towards Relevance and Sequence Modeling in Language Recognition [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-03

发表于 2020-04-03 分类于 arxiv ， CV 76k 2:06

目录

1. Learning to See Through Obstructions [PDF] 摘要

2. Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training [PDF] 摘要

3. Tracking Objects as Points [PDF] 摘要

4. Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image [PDF] 摘要

5. DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes [PDF] 摘要

6. Bodies at Rest: 3D Human Pose and Shape Estimation from a Pressure Image using Synthetic Data [PDF] 摘要

7. BUDA: Boundless Unsupervised Domain Adaptation in Semantic Segmentation [PDF] 摘要

8. ProxyNCA++: Revisiting and Revitalizing Proxy Neighborhood Component Analysis [PDF] 摘要

9. An Attention-Based Deep Learning Model for Multiple Pedestrian Attributes Recognition [PDF] 摘要

10. Map-Enhanced Ego-Lane Detection in the Missing Feature Scenarios [PDF] 摘要

11. MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model [PDF] 摘要

12. Learning Longterm Representations for Person Re-Identification Using Radio Signals [PDF] 摘要

13. Model-based disentanglement of lens occlusions [PDF] 摘要

14. Effect of Annotation Errors on Drone Detection with YOLOv3 [PDF] 摘要

15. Objects of violence: synthetic data for practical ML in human rights investigations [PDF] 摘要

16. Face Quality Estimation and Its Correlation to Demographic and Non-Demographic Bias in Face Recognition [PDF] 摘要

17. DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes [PDF] 摘要

18. PaStaNet: Toward Human Activity Knowledge Engine [PDF] 摘要

19. Controllable Orthogonalization in Training DNNs [PDF] 摘要

20. Learning to Segment the Tail [PDF] 摘要

21. Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers [PDF] 摘要

22. Occlusion-Aware Depth Estimation with Adaptive Normal Constraints [PDF] 摘要

23. Robust Single-Image Super-Resolution via CNNs and TV-TV Minimization [PDF] 摘要

24. Improving 3D Object Detection through Progressive Population Based Augmentation [PDF] 摘要

25. Tracking by Instance Detection: A Meta-Learning Approach [PDF] 摘要

26. SSHFD: Single Shot Human Fall Detection with Occluded Joints Resilience [PDF] 摘要

27. Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation [PDF] 摘要

28. Graph-based fusion for change detection in multi-spectral images [PDF] 摘要

29. Scene-Adaptive Video Frame Interpolation via Meta-Learning [PDF] 摘要

30. Consistent Multiple Sequence Decoding [PDF] 摘要

31. Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences [PDF] 摘要

32. Robust Single Rotation Averaging [PDF] 摘要

33. Memory-Efficient Incremental Learning Through Feature Adaptation [PDF] 摘要

34. Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition [PDF] 摘要

35. Adversarial Learning for Personalized Tag Recommendation [PDF] 摘要

36. Generalized Zero-Shot Learning Via Over-Complete Distribution [PDF] 摘要

37. Synchronizing Probability Measures on Rotations via Optimal Transport [PDF] 摘要

38. Background Matting: The World is Your Green Screen [PDF] 摘要

39. GraphChallenge.org Sparse Deep Neural Network Performance [PDF] 摘要

40. Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline [PDF] 摘要

41. Introducing Anisotropic Minkowski Functionals for Local Structure Analysis and Prediction of Biomechanical Strength of Proximal Femur Specimens [PDF] 摘要

42. Multi-Modal Video Forensic Platform for Investigating Post-Terrorist Attack Scenarios [PDF] 摘要

43. Deep-n-Cheap: An Automated Search Framework for Low Complexity Deep Learning [PDF] 摘要

44. Learning Representations For Images With Hierarchical Labels [PDF] 摘要

45. Go Fetch: Mobile Manipulation in Unstructured Environments [PDF] 摘要

46. End-To-End Convolutional Neural Network for 3D Reconstruction of Knee Bones From Bi-Planar X-Ray Images [PDF] 摘要

47. Image Denoising Using Sparsifying Transform Learning and Weighted Singular Values Minimization [PDF] 摘要

48. Object-Centric Image Generation with Factored Depths, Locations, and Appearances [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-04-03

发表于 2020-04-03 分类于 arxiv ， CL 18k 30 分钟

目录

1. Causal Inference of Script Knowledge [PDF] 摘要

2. NUBES: A Corpus of Negation and Uncertainty in Spanish Clinical Texts [PDF] 摘要

3. Revisiting the linearity in cross-lingual embedding mappings: from a perspective of word analogies [PDF] 摘要

4. How Furiously Can Colourless Green Ideas Sleep? Sentence Acceptability in Context [PDF] 摘要

5. Mapping Languages and Demographics with Georeferenced Corpora [PDF] 摘要

6. Mapping Languages: The Corpus of Global Language Use [PDF] 摘要

7. Igbo-English Machine Translation: An Evaluation Benchmark [PDF] 摘要

8. Improving the Utility of Knowledge Graph Embeddings with Calibration [PDF] 摘要

9. Learning to cooperate: Emergent communication in multi-agent navigation [PDF] 摘要

10. MCEN: Bridging Cross-Modal Gap between Cooking Recipes and Dish Images with Latent Variable Model [PDF] 摘要

11. Pruned Wasserstein Index Generation Model and wigpy Package [PDF] 摘要

12. DeepSumm -- Deep Code Summaries using Neural Transformer Architecture [PDF] 摘要

13. Pixel-BERT: Aligning Image Pixels with Text by Deep Multi-Modal Transformers [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-02

发表于 2020-04-02 分类于 arxiv ， CV 99k 2:46

目录

1. Evading Deepfake-Image Detectors with White- and Black-Box Attacks [PDF] 摘要

2. Articulation-aware Canonical Surface Mapping [PDF] 摘要

3. EPOS: Estimating 6D Pose of Objects with Symmetries [PDF] 摘要

4. Robust Image Reconstruction with Misaligned Structural Information [PDF] 摘要

5. Symmetry and Group in Attribute-Object Compositions [PDF] 摘要

6. Boosting Deep Hyperspectral Image Classification with Spectral Unmixing [PDF] 摘要

7. LGVTON: A Landmark Guided Approach to Virtual Try-On [PDF] 摘要

8. Feature-Driven Super-Resolution for Object Detection [PDF] 摘要

9. Physically Realizable Adversarial Examples for LiDAR Object Detection [PDF] 摘要

10. Future Video Synthesis with Object Motion Prediction [PDF] 摘要

11. Medical-based Deep Curriculum Learning for Improved Fracture Classification [PDF] 摘要

12. PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization [PDF] 摘要

13. Spatio-temporal Tubelet Feature Aggregation and Object Linking in Videos [PDF] 摘要

14. Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy [PDF] 摘要

15. Learning to Cluster Faces via Confidence and Connectivity Estimation [PDF] 摘要

16. Semantic Drift Compensation for Class-Incremental Learning [PDF] 摘要

17. Long-tail Visual Relationship Recognition with a Visiolinguistic Hubless Loss [PDF] 摘要

18. M2m: Imbalanced Classification via Major-to-minor Translation [PDF] 摘要

19. Image Demoireing with Learnable Bandpass Filters [PDF] 摘要

20. Two-shot Spatially-varying BRDF and Shape Estimation [PDF] 摘要

21. More Grounded Image Captioning by Distilling Image-Text Matching Model [PDF] 摘要

22. Single Image Optical Flow Estimation with an Event Camera [PDF] 摘要

23. Digit Recognition Using Convolution Neural Network [PDF] 摘要

24. Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation [PDF] 摘要

25. SoftSMPL: Data-driven Modeling of Nonlinear Soft-tissue Dynamics for Parametric Humans [PDF] 摘要

26. Learning to Select Base Classes for Few-shot Classification [PDF] 摘要

27. Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes [PDF] 摘要

28. High-Performance Long-Term Tracking with Meta-Updater [PDF] 摘要

29. Transfer Learning of Photometric Phenotypes in Agriculture Using Metadata [PDF] 摘要

30. Evaluation of Model Selection for Kernel Fragment Recognition in Corn Silage [PDF] 摘要

31. CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition [PDF] 摘要

32. Creating Something from Nothing: Unsupervised Knowledge Distillation for Cross-Modal Hashing [PDF] 摘要

33. Graph Structured Network for Image-Text Matching [PDF] 摘要

34. An Efficient Agreement Mechanism in CapsNets By Pairwise Product [PDF] 摘要

35. Progressive Multi-Stage Learning for Discriminative Tracking [PDF] 摘要

36. Pose-guided Visible Part Matching for Occluded Person ReID [PDF] 摘要

37. Synthesis and Edition of Ultrasound Images via Sketch Guided Progressive Growing GANs [PDF] 摘要

38. Video Anomaly Detection for Smart Surveillance [PDF] 摘要

39. NBDT: Neural-Backed Decision Trees [PDF] 摘要

40. BCNet: Learning Body and Cloth Shape from A Single Image [PDF] 摘要

41. Region Proposal Network with Graph Prior and IoU-Balance Loss for Landmark Detection in 3D Ultrasound [PDF] 摘要

42. Shared Cross-Modal Trajectory Prediction for Autonomous Driving [PDF] 摘要

43. Semi-Supervised Cervical Dysplasia Classification With Learnable Graph Convolutional Network [PDF] 摘要

44. Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds [PDF] 摘要

45. Spatio-Temporal Action Detection with Multi-Object Interaction [PDF] 摘要

46. Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge [PDF] 摘要

47. Manifold-Aware CycleGAN for High Resolution Structural-to-DTI Synthesis [PDF] 摘要

48. The Edge of Depth: Explicit Constraints between Segmentation and Depth [PDF] 摘要

49. Towards Lifelong Self-Supervision For Unpaired Image-to-Image Translation [PDF] 摘要

50. Deep Semantic Matching with Foreground Detection and Cycle-Consistency [PDF] 摘要

51. Learning Generative Models of Tissue Organization with Supervised GANs [PDF] 摘要

52. Revisiting Few-shot Activity Detection with Class Similarity Control [PDF] 摘要

53. EOLO: Embedded Object Segmentation only Look Once [PDF] 摘要

54. StyleRig: Rigging StyleGAN for 3D Control over Portrait Images [PDF] 摘要

55. Graph Domain Adaptation for Alignment-Invariant Brain Surface Segmentation [PDF] 摘要

56. Conditional Channel Gated Networks for Task-Aware Continual Learning [PDF] 摘要

57. HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation [PDF] 摘要

58. In-Domain GAN Inversion for Real Image Editing [PDF] 摘要

59. PointAR: Efficient Lighting Estimation for Mobile Augmented Reality [PDF] 摘要

60. Sign Language Translation with Transformers [PDF] 摘要

61. Self-Augmentation: Generalizing Deep Networks to Unseen Classes for Few-Shot Learning [PDF] 摘要

62. MetaPoison: Practical General-purpose Clean-label Data Poisoning [PDF] 摘要

63. 3D Deep Learning on Medical Images: A Review [PDF] 摘要

64. A theory of independent mechanisms for extrapolation in generative models [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-04-02

发表于 2020-04-02 分类于 arxiv ， CL 31k 51 分钟

目录

1. Sign Language Translation with Transformers [PDF] 摘要

2. Deep Learning Approach for Enhanced Cyber Threat Indicators in Twitter Stream [PDF] 摘要

3. Deep Learning Approach for Intelligent Named Entity Recognition of Cyber Security [PDF] 摘要

4. Parasitic Neural Network for Zero-Shot Relation Extraction [PDF] 摘要

5. An Improved Classification Model for Igbo Text Using N-Gram And K-Nearest Neighbour Approaches [PDF] 摘要

6. Enriching Consumer Health Vocabulary Using Enhanced GloVe Word Embedding [PDF] 摘要

7. A Swiss German Dictionary: Variation in Speech and Writing [PDF] 摘要

8. Automatic Extraction of Bengali Root Verbs using Paninian Grammar [PDF] 摘要

9. A Clustering Framework for Lexical Normalization of Roman Urdu [PDF] 摘要

10. Assessing Human Translations from French to Bambara for Machine Learning: a Pilot Study [PDF] 摘要

11. Multilingual Stance Detection: The Catalonia Independence Corpus [PDF] 摘要

12. Give your Text Representation Models some Love: the Case for Basque [PDF] 摘要

13. Deep Entity Matching with Pre-Trained Language Models [PDF] 摘要

14. More Grounded Image Captioning by Distilling Image-Text Matching Model [PDF] 摘要

15. Adversarial Transfer Learning for Punctuation Restoration [PDF] 摘要

16. AM-MobileNet1D: A Portable Model for Speaker Recognition [PDF] 摘要

17. Improvement of electronic Governance and mobile Governance in Multilingual Countries with Digital Etymology using Sanskrit Grammar [PDF] 摘要

18. Unification-based Reconstruction of Explanations for Science Questions [PDF] 摘要

19. Information Leakage in Embedding Models [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-01

发表于 2020-04-01 分类于 arxiv ， CV 132k 3:40

目录

1. Optical Non-Line-of-Sight Physics-based 3D Human Pose Estimation [PDF] 摘要

2. Probabilistic Pixel-Adaptive Refinement Networks [PDF] 摘要

3. TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting [PDF] 摘要

4. UniformAugment: A Search-free Probabilistic Data Augmentation Approach [PDF] 摘要

5. How Useful is Self-Supervised Pretraining for Visual Tasks? [PDF] 摘要

6. Du$^2$Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels [PDF] 摘要

7. Take the Scenic Route: Improving Generalization in Vision-and-Language Navigation [PDF] 摘要

8. SCT: Set Constrained Temporal Transformer for Set Supervised Action Segmentation [PDF] 摘要

9. DPGN: Distribution Propagation Graph Network for Few-shot Learning [PDF] 摘要

10. Straight to the Point: Fast-forwarding Videos via Reinforcement Learning Using Textual Data [PDF] 摘要

11. Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation [PDF] 摘要

12. DISIR: Deep Image Segmentation with Interactive Refinement [PDF] 摘要

13. Attention-based Assisted Excitation for Salient Object Segmentation [PDF] 摘要

14. GAST-Net: Graph Attention Spatio-temporal Convolutional Networks for 3D Human Pose Estimation in Video [PDF] 摘要

15. Recognizing Characters in Art History Using Deep Learning [PDF] 摘要

16. Pix2Shape -- Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation [PDF] 摘要

17. Look-into-Object: Self-supervised Structure Modeling for Object Recognition [PDF] 摘要

18. Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition [PDF] 摘要

19. Real-Time Camera Pose Estimation for Sports Fields [PDF] 摘要

20. Learning Cross-domain Semantic-Visual Relation for Transductive Zero-Shot Learning [PDF] 摘要

21. X-Linear Attention Networks for Image Captioning [PDF] 摘要

22. Long Short-Term Relation Networks for Video Action Detection [PDF] 摘要

23. Inverting Gradients -- How easy is it to break privacy in federated learning? [PDF] 摘要

24. 3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior [PDF] 摘要

25. Prediction Confidence from Neighbors [PDF] 摘要

26. Distance in Latent Space as Novelty Measure [PDF] 摘要

27. SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings [PDF] 摘要

28. PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation [PDF] 摘要

29. BANet: Bidirectional Aggregation Network with Occlusion Handling for Panoptic Segmentation [PDF] 摘要

30. Distilled Semantics for Comprehensive Scene Understanding from Videos [PDF] 摘要

31. Learning Human-Object Interaction Detection using Interaction Points [PDF] 摘要

32. SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints [PDF] 摘要

33. FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction [PDF] 摘要

34. Fashion Meets Computer Vision: A Survey [PDF] 摘要

35. DeepLPF: Deep Local Parametric Filters for Image Enhancement [PDF] 摘要

36. Multi-Modal Graph Neural Network for Joint Reasoning on Vision and Scene Text [PDF] 摘要

37. Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model [PDF] 摘要

38. FGN: Fully Guided Network for Few-Shot Instance Segmentation [PDF] 摘要

39. Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volume [PDF] 摘要

40. Segmenting Transparent Objects in the Wild [PDF] 摘要

41. A Simple Class Decision Balancing for Incremental Learning [PDF] 摘要

42. Spatio-Temporal Graph for Video Captioning with Knowledge Distillation [PDF] 摘要

43. EvolveGraph: Heterogeneous Multi-Agent Multi-Modal Trajectory Prediction with Evolving Interaction Graphs [PDF] 摘要

44. Y-net: Multi-scale feature aggregation network with wavelet structure similarity loss function for single image dehazing [PDF] 摘要

45. Proxy Anchor Loss for Deep Metric Learning [PDF] 摘要

46. Attention-based Multi-modal Fusion Network for Semantic Scene Completion [PDF] 摘要

47. Learning Oracle Attention for High-fidelity Face Completion [PDF] 摘要

48. Edge Guided GANs with Semantic Preserving for Semantic Image Synthesis [PDF] 摘要

49. TITAN: Future Forecast using Action Priors [PDF] 摘要

50. MUXConv: Information Multiplexing in Convolutional Neural Networks [PDF] 摘要

51. RetinaTrack: Online Single Stage Joint Detection and Tracking [PDF] 摘要

52. 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation [PDF] 摘要

53. Semi-supervised Learning for Few-shot Image-to-Image Translation [PDF] 摘要

54. Can Deep Learning Recognize Subtle Human Activities? [PDF] 摘要

55. AvatarMe: Realistically Renderable 3D Facial Reconstruction "in-the-wild" [PDF] 摘要

56. ActGAN: Flexible and Efficient One-shot Face Reenactment [PDF] 摘要

57. Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions [PDF] 摘要

58. Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation [PDF] 摘要

59. Co-occurrence of deep convolutional features for image search [PDF] 摘要

60. When to Use Convolutional Neural Networks for Inverse Problems [PDF] 摘要

61. Domain Balancing: Face Recognition on Long-Tailed Domains [PDF] 摘要

62. Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction [PDF] 摘要

63. Understanding the impact of mistakes on background regions in crowd counting [PDF] 摘要

64. Combining detection and tracking for human pose estimation in videos [PDF] 摘要

65. Certifiable Relative Pose Estimation [PDF] 摘要

66. COVID-ResNet: A Deep Learning Framework for Screening of COVID19 from Radiographs [PDF] 摘要

67. Automated Methods for Detection and Classification Pneumonia based on X-Ray Images Using Deep Learning [PDF] 摘要

68. Learning from Small Data Through Sampling an Implicit Conditional Generative Latent Optimization Model [PDF] 摘要

69. Radiologist-level stroke classification on non-contrast CT scans with Deep U-Net [PDF] 摘要

70. Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation [PDF] 摘要

71. MTL-NAS: Task-Agnostic Neural Architecture Search towards General-Purpose Multi-Task Learning [PDF] 摘要

72. Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes [PDF] 摘要

73. A Thorough Comparison Study on Adversarial Attacks and Defenses for Common Thorax Disease Classification in Chest X-rays [PDF] 摘要

74. Regularizing Class-wise Predictions via Self-knowledge Distillation [PDF] 摘要

75. Recurrent Neural Networks with Longitudinal Pooling and Consistency Regularization [PDF] 摘要

76. Ranger: Boosting Error Resilience of Deep Neural Networks through Range Restriction [PDF] 摘要

77. Lesion Conditional Image Generation for Improved Segmentation of Intracranial Hemorrhage from CT Images [PDF] 摘要

78. Dataless Model Selection with the Deep Frame Potential [PDF] 摘要

79. COVID-CT-Dataset: A CT Scan Dataset about COVID-19 [PDF] 摘要

80. Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network [PDF] 摘要

81. Non-dimensional Star-Identification [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-04-01

发表于 2020-04-01 分类于 arxiv ， CL 26k 44 分钟

目录

1. Low Resource Neural Machine Translation: A Benchmark for Five African Languages [PDF] 摘要

2. Evaluating Amharic Machine Translation [PDF] 摘要

3. On the Integration of LinguisticFeatures into Statistical and Neural Machine Translation [PDF] 摘要

4. Graph Enhanced Representation Learning for News Recommendation [PDF] 摘要

5. Inherent Dependency Displacement Bias of Transition-Based Algorithms [PDF] 摘要

6. Appraisal Theories for Emotion Classification in Text [PDF] 摘要

7. Understanding Cross-Lingual Syntactic Transfer in Multilingual Recurrent Neural Networks [PDF] 摘要

8. MULTEXT-East [PDF] 摘要

9. SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases [PDF] 摘要

10. Procedural Reading Comprehension with Attribute-Aware Context Flow [PDF] 摘要

11. The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe [PDF] 摘要

12. Span-based discontinuous constituency parsing: a family of exact chart-based algorithms with time complexities from O(n^6) down to O(n^3) [PDF] 摘要

13. Semantic-based End-to-End Learning for Typhoon Intensity Prediction [PDF] 摘要

14. Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement [PDF] 摘要

15. A Hierarchical Transformer for Unsupervised Parsing [PDF] 摘要

16. Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation [PDF] 摘要

17. Amharic Abstractive Text Summarization [PDF] 摘要

阅读全文 »