【arxiv论文】 Computation and Language 2020-04-17

发表于 2020-04-17 分类于 arxiv ， CL 37k 1:02

目录

1. Classification Benchmarks for Under-resourced Bengali Language based on Multichannel Convolutional-LSTM Network [PDF] 摘要

2. Kvistur 2.0: a BiLSTM Compound Splitter for Icelandic [PDF] 摘要

3. Cross-lingual Contextualized Topic Models with Zero-shot Learning [PDF] 摘要

4. Do sequence-to-sequence VAEs learn global features of sentences? [PDF] 摘要

5. Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation [PDF] 摘要

6. Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection [PDF] 摘要

7. Towards Instance-Level Parser Selection for Cross-Lingual Transfer of Dependency Parsers [PDF] 摘要

8. Recognizing Long Grammatical Sequences Using Recurrent Networks Augmented With An External Differentiable Stack [PDF] 摘要

9. Suicidal Ideation and Mental Disorder Detection with Attentive Relation Networks [PDF] 摘要

10. LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation [PDF] 摘要

11. TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition [PDF] 摘要

12. Paraphrase Augmented Task-Oriented Dialog Generation [PDF] 摘要

13. The Right Tool for the Job: Matching Model and Instance Complexities [PDF] 摘要

14. Non-Autoregressive Machine Translation with Latent Alignments [PDF] 摘要

15. Neural Data-to-Text Generation with Dynamic Content Planning [PDF] 摘要

16. HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data [PDF] 摘要

17. Building a Multi-domain Neural Machine Translation Model using Knowledge Distillation [PDF] 摘要

18. Learning Structured Embeddings of Knowledge Graphs with Adversarial Learning Framework [PDF] 摘要

19. There is Strength in Numbers: Avoiding the Hypothesis-Only Bias in Natural Language Inference via Ensemble Adversarial Training [PDF] 摘要

20. Deep Generation of Coq Lemma Names Using Elaborated Terms [PDF] 摘要

21. A Methodology for Creating Question Answering Corpora Using Inverse Data Annotation [PDF] 摘要

22. Trakhtenbrot's Theorem in Coq, A Constructive Approach to Finite Model Theory [PDF] 摘要

23. A Discriminator Improves Unconditional Text Generation without Updating the Generator [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-16

发表于 2020-04-16 分类于 arxiv ， CV 68k 1:53

目录

1. Using Player's Body-Orientation to Model Pass Feasibility in Soccer [PDF] 摘要

2. A Transductive Approach for Video Object Segmentation [PDF] 摘要

3. Bias in Multimodal AI: Testbed for Fair Automatic Recruitment [PDF] 摘要

4. A recurrent cycle consistency loss for progressive face-to-face synthesis [PDF] 摘要

5. A Novel CNN-based Method for Accurate Ship Detection in HR Optical Remote Sensing Images via Rotated Bounding Box [PDF] 摘要

6. Fully Convolutional Online Tracking [PDF] 摘要

7. DeeSCo: Deep heterogeneous ensemble with Stochastic Combinatory loss for gaze estimation [PDF] 摘要

8. Seeing Red: PPG Biometrics Using Smartphone Cameras [PDF] 摘要

9. Contextual Pyramid Attention Network for Building Segmentation in Aerial Imagery [PDF] 摘要

10. Code-Aligned Autoencoders for Unsupervised Change Detection in Multimodal Remote Sensing Images [PDF] 摘要

11. Visual Descriptor Learning from Monocular Video [PDF] 摘要

12. Self-Supervised training for blind multi-frame video denoising [PDF] 摘要

13. Explaining Regression Based Neural Network Model [PDF] 摘要

14. Combining Visible Light and Infrared Imaging for Efficient Detection of Respiratory Infections such as COVID-19 on Portable Device [PDF] 摘要

15. Continuous learning of face attribute synthesis [PDF] 摘要

16. A Practical Blockchain Framework using Image Hashing for Image Authentication [PDF] 摘要

17. Intuitive, Interactive Beard and Hair Synthesis with Generative Models [PDF] 摘要

18. Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision [PDF] 摘要

19. RoboTHOR: An Open Simulation-to-Real Embodied AI Platform [PDF] 摘要

20. Cascaded Structure Tensor Framework for Robust Identification of Heavily Occluded Baggage Items from X-ray Scans [PDF] 摘要

21. Line Art Correlation Matching Network for Automatic Animation Colorization [PDF] 摘要

22. On Box-Cox Transformation for Image Normality and Pattern Classification [PDF] 摘要

23. BabyAI++: Towards Grounded-Language Learning beyond Memorization [PDF] 摘要

24. Residual-driven Fuzzy C-Means Clustering for Image Segmentation [PDF] 摘要

25. Image Segmentation Using Hybrid Representations [PDF] 摘要

26. Fully Automated Myocardial Strain Estimation from CMR Tagged Images using a Deep Learning Framework in the UK Biobank [PDF] 摘要

27. JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation [PDF] 摘要

28. Extending Unsupervised Neural Image Compression With Supervised Multitask Learning [PDF] 摘要

29. 4DFlowNet: Super-Resolution 4D Flow MRI using Deep Learning and Computational Fluid Dynamics [PDF] 摘要

30. MXR-U-Nets for Real Time Hyperspectral Reconstruction [PDF] 摘要

31. ActionSpotter: Deep Reinforcement Learning Framework for Temporal Action Spotting in Videos [PDF] 摘要

32. Roommate Compatibility Detection Through Machine Learning Techniques [PDF] 摘要

33. Exploration of Indoor Environments Predicting the Layout of Partially Observed Rooms [PDF] 摘要

34. Unified Dynamic Convolutional Network for Super-Resolution with Variational Degradations [PDF] 摘要

35. Light Weight Residual Dense Attention Net for Spectral Reconstruction from RGB Images [PDF] 摘要

36. Analysis of Scoliosis From Spinal X-Ray Images [PDF] 摘要

37. Effect of Input Noise Dimension in GANs [PDF] 摘要

38. Mosaic Super-resolution via Sequential Feature Pyramid Networks [PDF] 摘要

39. Melanoma Detection using Adversarial Training and Deep Transfer Learning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-04-16

发表于 2020-04-16 分类于 arxiv ， CL 27k 45 分钟

目录

1. Entities as Experts: Sparse Memory Access with Entity Supervision [PDF] 摘要

2. Document-level Representation Learning using Citation-informed Transformers [PDF] 摘要

3. PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation [PDF] 摘要

4. Bayesian Hierarchical Words Representation Learning [PDF] 摘要

5. Analyzing analytical methods: The case of phonology in neural models of spoken language [PDF] 摘要

6. Gestalt: a Stacking Ensemble for SQuAD2.0 [PDF] 摘要

7. Exploring Probabilistic Soft Logic as a framework for integrating top-down and bottom-up processing of language in a task context [PDF] 摘要

8. Framing COVID-19: How we conceptualize and discuss the pandemic on Twitter [PDF] 摘要

9. ToD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogues [PDF] 摘要

10. Coreferential Reasoning Learning for Language Representation [PDF] 摘要

11. On the Linguistic Capacity of Real-Time Counter Automata [PDF] 摘要

12. A Human Evaluation of AMR-to-English Generation Systems [PDF] 摘要

13. Mining Coronavirus (COVID-19) Posts in Social Media [PDF] 摘要

14. A Simple Yet Strong Pipeline for HotpotQA [PDF] 摘要

15. Balancing Training for Multilingual Neural Machine Translation [PDF] 摘要

16. lamBERT: Language and Action Learning Using Multimodal BERT [PDF] 摘要

17. A hybrid classical-quantum workflow for natural language processing [PDF] 摘要

18. Probabilistic Model of Narratives Over Topical Trends in Social Media: A Discrete Time Model [PDF] 摘要

19. Speaker Diarization with Lexical Information [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-15

发表于 2020-04-15 分类于 arxiv ， CV 70k 1:56

目录

1. Deformable Siamese Attention Networks for Visual Object Tracking [PDF] 摘要

2. FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding [PDF] 摘要

3. DialGraph: Sparse Graph Learning Networks for Visual Dialog [PDF] 摘要

4. A Transfer Learning approach to Heatmap Regression for Action Unit intensity estimation [PDF] 摘要

5. An Attention-Based System for Damage Assessment Using Satellite Imagery [PDF] 摘要

6. Distilling Localization for Self-Supervised Representation Learning [PDF] 摘要

7. InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics [PDF] 摘要

8. Walk the Lines: Object Contour Tracing CNN for Contour Completion of Ships [PDF] 摘要

9. Improving Calibration and Out-of-Distribution Detection in Medical Image Segmentation with Convolutional Neural Networks [PDF] 摘要

10. Decentralized Differentially Private Segmentation with PATE [PDF] 摘要

11. Deep Entwined Learning Head Pose and Face Alignment Inside an Attentional Cascade with Doubly-Conditional fusion [PDF] 摘要

12. Unsupervised Performance Analysis of 3D Face Alignment [PDF] 摘要

13. Contrastive Examples for Addressing the Tyranny of the Majority [PDF] 摘要

14. Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning [PDF] 摘要

15. Self6D: Self-Supervised Monocular 6D Object Pose Estimation [PDF] 摘要

16. Divergence-Based Adaptive Extreme Video Completion [PDF] 摘要

17. Kinship Identification through Joint Learning Using Kinship Verification Ensemble [PDF] 摘要

18. Footprints and Free Space from a Single Color Image [PDF] 摘要

19. A Primal-Dual Solver for Large-Scale Tracking-by-Assignment [PDF] 摘要

20. Exact MAP-Inference by Confining Combinatorial Search with LP Relaxation [PDF] 摘要

21. Simple Multi-Resolution Representation Learning for Human Pose Estimation [PDF] 摘要

22. WQT and DG-YOLO: towards domain generalization in underwater object detection [PDF] 摘要

23. A2D2: Audi Autonomous Driving Dataset [PDF] 摘要

24. VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification [PDF] 摘要

25. Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors [PDF] 摘要

26. Smart Inference for Multidigit Convolutional Neural Network based Barcode Decoding [PDF] 摘要

27. Bidirectional Graph Reasoning Network for Panoptic Segmentation [PDF] 摘要

28. The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification [PDF] 摘要

29. RealMonoDepth: Self-Supervised Monocular Depth Estimation for General Scenes [PDF] 摘要

30. End-to-End Estimation of Multi-Person 3D Poses from Multiple Cameras [PDF] 摘要

31. Embedded Large-Scale Handwritten Chinese Character Recognition [PDF] 摘要

32. Relation Transformer Network [PDF] 摘要

33. Challenges and Opportunities for Computer Vision in Real-life Soccer Analytics [PDF] 摘要

34. Event detection in coarsely annotated sports videos via parallel multi receptive field 1D convolutions [PDF] 摘要

35. Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks [PDF] 摘要

36. An Efficient UAV-based Artificial Intelligence Framework for Real-Time Visual Tasks [PDF] 摘要

37. SpeedNet: Learning the Speediness in Videos [PDF] 摘要

38. Weakly Supervised Deep Learning for COVID-19 Infection Detection and Classification from CT Images [PDF] 摘要

39. End-to-End Variational Networks for Accelerated MRI Reconstruction [PDF] 摘要

40. Rapid Damage Assessment Using Social Media Images by Combining Human and Machine Intelligence [PDF] 摘要

41. An automatic COVID-19 CT segmentation based on U-Net with attention mechanism [PDF] 摘要

42. Transfer Learning with Deep Convolutional Neural Network (CNN) for Pneumonia Detection using Chest X-ray [PDF] 摘要

43. Robust Generalised Quadratic Discriminant Analysis [PDF] 摘要

44. Learning a low dimensional manifold of real cancer tissue with PathologyGAN [PDF] 摘要

45. SpaceNet 6: Multi-Sensor All Weather Mapping Dataset [PDF] 摘要

46. StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardization [PDF] 摘要

47. Stochastic batch size for adaptive regularization in deep network optimization [PDF] 摘要

48. Automated Diabetic Retinopathy Grading using Deep Convolutional Neural Network [PDF] 摘要

49. A reinforcement learning application of guided Monte Carlo Tree Search algorithm for beam orientation selection in radiation therapy [PDF] 摘要

50. Imitation Learning for Fashion Style Based on Hierarchical Multimodal Representation [PDF] 摘要

51. Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networks [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-04-15

发表于 2020-04-15 分类于 arxiv ， CL 41k 1:08

目录

1. Multi-source Attention for Unsupervised Domain Adaptation [PDF] 摘要

2. Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity [PDF] 摘要

3. Multilingual Machine Translation: Closing the Gap between Shared and Language-specific Encoder-Decoders [PDF] 摘要

4. Multi-Ontology Refined Embeddings (MORE): A Hybrid Multi-Ontology and Corpus-based Semantic Representation for Biomedical Concepts [PDF] 摘要

5. What's so special about BERT's layers? A closer look at the NLP pipeline in monolingual and multilingual models [PDF] 摘要

6. Two halves of a meaningful text are statistically different [PDF] 摘要

7. Query-Variant Advertisement Text Generation with Association Knowledge [PDF] 摘要

8. Jointly Modeling Aspect and Sentiment with Dynamic Heterogeneous Graph Neural Networks [PDF] 摘要

9. Incorporating Uncertain Segmentation Information into Chinese NER for Social Media Text [PDF] 摘要

10. Speech Translation and the End-to-End Promise: Taking Stock of Where We Are [PDF] 摘要

11. Code Completion using Neural Attention and Byte Pair Encoding [PDF] 摘要

12. Quantifying Community Characteristics of Maternal Mortality Using Social Media [PDF] 摘要

13. Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpus [PDF] 摘要

14. Cascade Neural Ensemble for Identifying Scientifically Sound Articles [PDF] 摘要

15. Robustly Pre-trained Neural Model for Direct Temporal Relation Extraction [PDF] 摘要

16. Reverse Engineering Configurations of Neural Text Generation Models [PDF] 摘要

17. A Divide-and-Conquer Approach to the Summarization of Academic Articles [PDF] 摘要

18. PoKi: A Large Dataset of Poems by Children [PDF] 摘要

19. AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization [PDF] 摘要

20. DialGraph: Sparse Graph Learning Networks for Visual Dialog [PDF] 摘要

21. Weight Poisoning Attacks on Pre-trained Models [PDF] 摘要

22. Compass-aligned Distributional Embeddings for Studying Semantic Differences across Corpora [PDF] 摘要

23. Gender Detection on Social Networks using Ensemble Deep Learning [PDF] 摘要

24. Deep Learning Models for Multilingual Hate Speech Detection [PDF] 摘要

25. Transformer based Grapheme-to-Phoneme Conversion [PDF] 摘要

26. Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks [PDF] 摘要

27. Improving Scholarly Knowledge Representation: Evaluating BERT-based Models for Scientific Relation Classification [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-14

发表于 2020-04-14 分类于 arxiv ， CV 140k 3:53

目录

1. Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation [PDF] 摘要

2. Compositional Visual Generation and Inference with Energy Based Models [PDF] 摘要

3. Training End-to-end Single Image Generators without GANs [PDF] 摘要

4. Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training [PDF] 摘要

5. A Survey of Single-Scene Video Anomaly Detection [PDF] 摘要

6. Speak2Label: Using Domain Knowledge for Creating a Large Scale Driver Gaze Zone Estimation Dataset [PDF] 摘要

7. Dense Registration and Mosaicking of Fingerprints by Training an End-to-End Network [PDF] 摘要

8. CVPR 2019 WAD Challenge on Trajectory Prediction and 3D Perception [PDF] 摘要

9. Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks [PDF] 摘要

10. Unsupervised Facial Action Unit Intensity Estimation via Differentiable Optimization [PDF] 摘要

11. Regularizing Meta-Learning via Gradient Dropout [PDF] 摘要

12. SSP: Single Shot Future Trajectory Prediction [PDF] 摘要

13. SPCNet:Spatial Preserve and Content-aware Network for Human Pose Estimation [PDF] 摘要

14. Monocular Depth Estimation with Self-supervised Instance Adaptation [PDF] 摘要

15. MulayCap: Multi-layer Human Performance Capture Using A Monocular Video Camera [PDF] 摘要

16. Unsupervised Few-shot Learning via Distribution Shift-based Augmentation [PDF] 摘要

17. Learning Event-Based Motion Deblurring [PDF] 摘要

18. Towards Transferable Adversarial Attack against Deep Face Recognition [PDF] 摘要

19. UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders [PDF] 摘要

20. Self-supervised Feature Learning by Cross-modality and Cross-view Correspondences [PDF] 摘要

21. Enabling Incremental Knowledge Transfer for Object Detection at the Edge [PDF] 摘要

22. Deep Siamese Domain Adaptation Convolutional Neural Network for Cross-domain Change Detection in Multispectral Images [PDF] 摘要

23. Learning Spatial Relationships between Samples of Image Shapes [PDF] 摘要

24. A negative case analysis of visual grounding methods for VQA [PDF] 摘要

25. Low-Resolution Overhead Thermal Tripwire for Occupancy Estimation [PDF] 摘要

26. PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning [PDF] 摘要

27. MLCVNet: Multi-Level Context VoteNet for 3D Object Detection [PDF] 摘要

28. Which visual questions are difficult to answer? Analysis with Entropy of Answer Distributions [PDF] 摘要

29. Sharing Matters for Generalization in Deep Metric Learning [PDF] 摘要

30. Image Co-skeletonization via Co-segmentation [PDF] 摘要

31. YouMakeup VQA Challenge: Towards Fine-grained Action Understanding in Domain-Specific Videos [PDF] 摘要

32. Cross-domain Correspondence Learning for Exemplar-based Image Translation [PDF] 摘要

33. FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions [PDF] 摘要

34. Toward Hierarchical Self-Supervised Monocular Absolute Depth Estimation for Autonomous Driving Applications [PDF] 摘要

35. Feature Lenses: Plug-and-play Neural Modules for Transformation-Invariant Visual Representations [PDF] 摘要

36. OpenMix: Reviving Known Knowledge for Discovering Novel Visual Categories in An Open World [PDF] 摘要

37. Individual Tooth Detection and Identification from Dental Panoramic X-Ray Images via Point-wise Localization and Distance Regularization [PDF] 摘要

38. Self-Supervised Tuning for Few-Shot Segmentation [PDF] 摘要

39. Online Initialization and Extrinsic Spatial-Temporal Calibration for Monocular Visual-Inertial Odometry [PDF] 摘要

40. Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusion [PDF] 摘要

41. Density Map Guided Object Detection in Aerial Images [PDF] 摘要

42. A Novel Pose Proposal Network and Refinement Pipeline for Better Object Pose Estimation [PDF] 摘要

43. FDA: Fourier Domain Adaptation for Semantic Segmentation [PDF] 摘要

44. Learning to Manipulate Individual Objects in an Image [PDF] 摘要

45. Unveiling COVID-19 from Chest X-ray with deep learning: a hurdles race with small data [PDF] 摘要

46. Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring [PDF] 摘要

47. Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos [PDF] 摘要

48. Probabilistic Orientated Object Detection in Automotive Radar [PDF] 摘要

49. Inter-Region Affinity Distillation for Road Marking Segmentation [PDF] 摘要

50. From Quantized DNNs to Quantizable DNNs [PDF] 摘要

51. Multi-View Matching (MVM): Facilitating Multi-Person 3D Pose Estimation Learning with Action-Frozen People Video [PDF] 摘要

52. Towards Anomaly Detection in Dashcam Videos [PDF] 摘要

53. Attend and Decode: 4D fMRI Task State Decoding Using Attention Models [PDF] 摘要

54. End-to-end Learning Improves Static Object Geo-localization in Monocular Video [PDF] 摘要

55. Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review [PDF] 摘要

56. A Review on Deep Learning Techniques for Video Prediction [PDF] 摘要

57. Hamiltonian Dynamics for Real-World Shape Interpolation [PDF] 摘要

58. k-decay: A New Method For Learning Rate Schedule [PDF] 摘要

59. Revisiting Loss Landscape for Adversarial Robustness [PDF] 摘要

60. Analysis of The Ratio of $\ell_1$ and $\ell_2$ Norms in Compressed Sensing [PDF] 摘要

61. From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech [PDF] 摘要

62. Blockchain in the Internet of Things: Architectures and Implementation [PDF] 摘要

63. Multi-modal Datasets for Super-resolution [PDF] 摘要

64. Rethinking Differentiable Search for Mixed-Precision Neural Networks [PDF] 摘要

65. Deep Learning COVID-19 Features on CXR using Limited Training Data Sets [PDF] 摘要

66. A Comparison of Deep Learning Convolution Neural Networks for Liver Segmentation in Radial Turbo Spin Echo Images [PDF] 摘要

67. Principal Neighbourhood Aggregation for Graph Nets [PDF] 摘要

68. Towards an Efficient Deep Learning Model for COVID-19 Patterns Detection in X-ray Images [PDF] 摘要

69. Y-net: Biomedical Image Segmentation and Clustering [PDF] 摘要

70. Residual Attention U-Net for Automated Multi-Class Segmentation of COVID-19 Chest CT Images [PDF] 摘要

71. Relational Learning between Multiple Pulmonary Nodules via Deep Set Attention Transformers [PDF] 摘要

72. When Weak Becomes Strong: Robust Quantification of White Matter Hyperintensities in Brain MRI scans [PDF] 摘要

73. A Unified DNN Weight Compression Framework Using Reweighted Optimization Methods [PDF] 摘要

74. Gradients as Features for Deep Representation Learning [PDF] 摘要

75. DeepEDN: A Deep Learning-based Image Encryption and Decryption Network for Internet of Medical Things [PDF] 摘要

76. Verification of Deep Convolutional Neural Networks Using ImageStars [PDF] 摘要

77. MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment [PDF] 摘要

78. Farmland Parcel Delineation Using Spatio-temporal Convolutional Networks [PDF] 摘要

79. Detection of Covid-19 From Chest X-ray Images Using Artificial Intelligence: An Early Review [PDF] 摘要

80. Underwater Image Enhancement Based on Structure-Texture Reconstruction [PDF] 摘要

81. The Role of Stem Noise in Visual Perception and Image Quality Measurement [PDF] 摘要

82. Trajectory annotation using sequences of spatial perception [PDF] 摘要

83. Bayesian Surprise in Indoor Environments [PDF] 摘要

84. Exploring The Spatial Reasoning Ability of Neural Models in Human IQ Tests [PDF] 摘要

85. KD-MRI: A knowledge distillation framework for image reconstruction and image restoration in MRI workflow [PDF] 摘要

86. Object-oriented SLAM using Quadrics and Symmetry Properties for Indoor Environments [PDF] 摘要

87. Exploit Where Optimizer Explores via Residuals [PDF] 摘要

88. FLIVVER: Fly Lobula Inspired Visual Velocity Estimation & Ranging [PDF] 摘要

89. Shape Estimation for Elongated Deformable Object using B-spline Chained Multiple Random Matrices Model [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-04-14

发表于 2020-04-14 分类于 arxiv ， CL 56k 1:33

目录

1. Pretrained Transformers Improve Out-of-Distribution Robustness [PDF] 摘要

2. Adversarial Augmentation Policy Search for Domain and Cross-Lingual Generalization in Reading Comprehension [PDF] 摘要

3. BLEU might be Guilty but References are not Innocent [PDF] 摘要

4. Toward Subgraph Guided Knowledge Graph Question Generation with Graph Neural Networks [PDF] 摘要

5. A Simple Approach to Learning Unsupervised Multilingual Embeddings [PDF] 摘要

6. CLUE: A Chinese Language Understanding Evaluation Benchmark [PDF] 摘要

7. Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings? [PDF] 摘要

8. Keyword Assisted Topic Models [PDF] 摘要

9. Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples [PDF] 摘要

10. $\texttt{ArCOV-19}$: The First Arabic COVID-19 Twitter Dataset with Propagation Networks [PDF] 摘要

11. From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap [PDF] 摘要

12. Public Self-consciousness for Endowing Dialogue Agents with Consistent Persona [PDF] 摘要

13. MLR: A Two-stage Conversational Query Rewriting Model with Multi-task Learning [PDF] 摘要

14. Neural Machine Translation: Challenges, Progress and Future [PDF] 摘要

15. Unified Multi-Criteria Chinese Word Segmentation with BERT [PDF] 摘要

16. ProFormer: Towards On-Device LSH Projection Based Transformers [PDF] 摘要

17. Generating Fact Checking Explanations [PDF] 摘要

18. Reinforced Curriculum Learning on Pre-trained Neural Machine Translation Models [PDF] 摘要

19. Aspect and Opinion Aware Abstractive Review Summarization with Reinforced Hard Typed Decoder [PDF] 摘要

20. Integrated Eojeol Embedding for Erroneous Sentence Classification in Korean Chatbots [PDF] 摘要

21. VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification [PDF] 摘要

22. TinyMBERT: Multi-Stage Distillation Framework for Massive Multi-lingual NER [PDF] 摘要

23. AMR Parsing via Graph-Sequence Iterative Inference [PDF] 摘要

24. Explaining Question Answering Models through Text Generation [PDF] 摘要

25. Pre-training Text Representations as Meta Learning [PDF] 摘要

26. When Does Unsupervised Machine Translation Work? [PDF] 摘要

27. LAReQA: Language-agnostic answer retrieval from a multilingual pool [PDF] 摘要

28. Unsupervised Commonsense Question Answering with Self-Talk [PDF] 摘要

29. Classifying Constructive Comments [PDF] 摘要

30. End to End Chinese Lexical Fusion Recognition with Sememe Knowledge [PDF] 摘要

31. Annotating Social Determinants of Health Using Active Learning, and Characterizing Determinants Using Neural Event Extraction [PDF] 摘要

32. You Impress Me: Dialogue Generation via Mutual Persona Perception [PDF] 摘要

33. DeepSentiPers: Novel Deep Learning Models Trained Over Proposed Augmented Persian Sentiment Corpus [PDF] 摘要

34. Improving Disfluency Detection by Self-Training a Self-Attentive Model [PDF] 摘要

35. Joint translation and unit conversion for end-to-end localization [PDF] 摘要

36. On the Language Neutrality of Pre-trained Multilingual Representations [PDF] 摘要

37. Learning from Rules Generalizing Labeled Exemplars [PDF] 摘要

38. Data augmentation using generative networks to identify dementia [PDF] 摘要

39. Telling BERT's full story: from Local Attention to Global Aggregation [PDF] 摘要

40. Improved Speech Representations with Multi-Target Autoregressive Predictive Coding [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-13

发表于 2020-04-13 分类于 arxiv ， CV 63k 1:46

目录

1. Learning to Explore using Active Neural SLAM [PDF] 摘要

2. Model Uncertainty Quantification for Reliable Deep Vision Structural Health Monitoring [PDF] 摘要

3. Deep transfer learning for improving single-EEG arousal detection [PDF] 摘要

4. MA 3 : Model Agnostic Adversarial Augmentation for Few Shot learning [PDF] 摘要

5. Beyond Disentangled Representations: An Attentive Angular Distillation Approach to Large-scale Lightweight Age-Invariant Face Recognition [PDF] 摘要

6. ASL Recognition with Metric-Learning based Lightweight Network [PDF] 摘要

7. Hyperspectral Image Clustering with Spatially-Regularized Ultrametrics [PDF] 摘要

8. Parsing-based View-aware Embedding Network for Vehicle Re-Identification [PDF] 摘要

9. ModuleNet: Knowledge-inherited Neural Architecture Search [PDF] 摘要

10. Robust Line Segments Matching via Graph Convolution Networks [PDF] 摘要

11. Improved Residual Networks for Image and Video Recognition [PDF] 摘要

12. Spatiotemporal Fusion in 3D CNNs: A Probabilistic View [PDF] 摘要

13. Co-Saliency Spatio-Temporal Interaction Network for Person Re-Identification in Videos [PDF] 摘要

14. SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects [PDF] 摘要

15. Would Mega-scale Datasets Further Enhance Spatiotemporal 3D CNNs? [PDF] 摘要

16. Rephrasing visual questions by specifying the entropy of the answer distribution [PDF] 摘要

17. 3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds [PDF] 摘要

18. Boosting Semantic Human Matting with Coarse Annotations [PDF] 摘要

19. Learning to Visually Navigate in Photorealistic Environments Without any Supervision [PDF] 摘要

20. State-Relabeling Adversarial Active Learning [PDF] 摘要

21. ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection [PDF] 摘要

22. Real-world Person Re-Identification via Degradation Invariance Learning [PDF] 摘要

23. Phase Consistent Ecological Domain Adaptation [PDF] 摘要

24. Deep Residual Correction Network for Partial Domain Adaptation [PDF] 摘要

25. Person Re-Identification via Active Hard Sample Mining [PDF] 摘要

26. Analyze and Development System with Multiple Biometric Identification [PDF] 摘要

27. Spatial Priming for Detecting Human-Object Interactions [PDF] 摘要

28. Analysis on DeepLabV3+ Performance for Automatic Steel Defects Detection [PDF] 摘要

29. 6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference [PDF] 摘要

30. D-SRGAN: DEM Super-Resolution with Generative Adversarial Network [PDF] 摘要

31. Early Disease Diagnosis for Rice Crop [PDF] 摘要

32. CNN Encoder to Reduce the Dimensionality of Data Image for Motion Planning [PDF] 摘要

33. Weakly supervised multiple instance learning histopathological tumor segmentation [PDF] 摘要

34. Multimodal Categorization of Crisis Events in Social Media [PDF] 摘要

35. Socioeconomic correlations of urban patterns inferred from aerial images: interpreting activation maps of Convolutional Neural Networks [PDF] 摘要

36. MRQy: An Open-Source Tool for Quality Control of MR Imaging Data [PDF] 摘要

37. Latent regularization for feature selection using kernel methods in tumor classification [PDF] 摘要

38. Exemplar VAEs for Exemplar based Generation and Data Augmentation [PDF] 摘要

39. Capsules for Biomedical Image Segmentation [PDF] 摘要

阅读全文 »