【arxiv论文】 Computation and Language 2020-05-15

发表于 2020-05-15 分类于 arxiv ， CL 63k 1:44

目录

1. Estimating predictive uncertainty for rumour verification models [PDF] 摘要

2. NAT: Noise-Aware Training for Robust Neural Sequence Labeling [PDF] 摘要

3. Named Entity Recognition as Dependency Parsing [PDF] 摘要

4. Distilling neural networks into skipgram-level decision lists [PDF] 摘要

5. ZeroShotCeres: Zero-Shot Relation Extraction from Semi-Structured Webpages [PDF] 摘要

6. Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning [PDF] 摘要

7. 4chan & 8chan embeddings [PDF] 摘要

8. NIT-Agartala-NLP-Team at SemEval-2020 Task 8: Building Multimodal Classifiers to tackle Internet Humor [PDF] 摘要

9. DRTS Parsing with Structure-Aware Encoding and Decoding [PDF] 摘要

10. Mitigating Gender Bias in Machine Learning Data Sets [PDF] 摘要

11. A Category Theory Approach to Interoperability [PDF] 摘要

12. Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions [PDF] 摘要

13. A Rate-Distortion view of human pragmatic reasoning [PDF] 摘要

14. Detecting Adverse Drug Reactions from Twitter through Domain-Specific Preprocessing and BERT Ensembling [PDF] 摘要

15. SCAT: Second Chance Autoencoder for Textual Data [PDF] 摘要

16. schuBERT: Optimizing Elements of BERT [PDF] 摘要

17. CrisisBERT: Robust Transformer for Crisis Classification and Contextual Crisis Embedding [PDF] 摘要

18. Cyberbullying Detection with Fairness Constraints [PDF] 摘要

19. Comparative Analysis of Text Classification Approaches in Electronic Health Records [PDF] 摘要

20. ImpactCite: An XLNet-based method for Citation Impact Analysis [PDF] 摘要

21. Neural Machine Translation for South Africa's Official Languages [PDF] 摘要

22. Understanding and Detecting Dangerous Speech in Social Media [PDF] 摘要

23. Improving Aspect-Level Sentiment Analysis with Aspect Extraction [PDF] 摘要

24. Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation [PDF] 摘要

25. An Improved Topic Masking Technique for Authorship Analysis [PDF] 摘要

26. CIRCE at SemEval-2020 Task 1: Ensembling Context-Free and Context-Dependent Word Representations [PDF] 摘要

27. Unlocking the Power of Deep PICO Extraction: Step-wise Medical NER Identification [PDF] 摘要

28. A Comprehensive Survey of Grammar Error Correction [PDF] 摘要

29. PERLEX: A Bilingual Persian-English Gold Dataset for Relation Extraction [PDF] 摘要

30. Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding [PDF] 摘要

31. Arabic Dialect Identification in the Wild [PDF] 摘要

32. Validation and Normalization of DCS corpus using Sanskrit Heritage tools to build a tagged Gold Corpus [PDF] 摘要

33. Deep Learning for Political Science [PDF] 摘要

34. A Mixture of $h-1$ Heads is Better than $h$ Heads [PDF] 摘要

35. A Survey on Temporal Reasoning for Temporal Information Extraction from Text (Extended Abstract) [PDF] 摘要

36. You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation [PDF] 摘要

37. DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation [PDF] 摘要

38. Converting Anyone's Emotion: Towards Speaker-Independent Emotional Voice Conversion [PDF] 摘要

39. Mining Public Opinion on Twitter about Natural Disaster Response Using Machine Learning Techniques [PDF] 摘要

40. A Multi-Perspective Architecture for Semantic Code Search [PDF] 摘要

41. S2IGAN: Speech-to-Image Generation via Adversarial Learning [PDF] 摘要

42. India nudges to contain COVID-19 pandemic: a reactive public policy analysis using machine-learning based topic modelling [PDF] 摘要

43. Towards Socially Responsible AI: Cognitive Bias-Aware Multi-Objective Learning [PDF] 摘要

44. A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM [PDF] 摘要

45. Entity-Enriched Neural Models for Clinical Question Answering [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-14

发表于 2020-05-14 分类于 arxiv ， CV 47k 1:19

目录

1. Multiple Attentional Pyramid Networks for Chinese Herbal Recognition [PDF] 摘要

2. Designing a Color Filter via Optimization of Vora-Value for Making a Camera more Colorimetric [PDF] 摘要

3. FaR-GAN for One-Shot Face Reenactment [PDF] 摘要

4. SRDA-Net: Super-Resolution Domain Adaptation Networks for Semantic Segmentation [PDF] 摘要

5. Binarizing MobileNet via Evolution-based Searching [PDF] 摘要

6. Pose Proposal Critic: Robust Pose Refinement by Learning Reprojection Errors [PDF] 摘要

7. DAugNet: Unsupervised, Multi-source, Multi-target, and Life-long Domain Adaptation for Semantic Segmentation of Satellite Images [PDF] 摘要

8. On the uncertainty of self-supervised monocular depth estimation [PDF] 摘要

9. Mean Oriented Riesz Features for Micro Expression Classification [PDF] 摘要

10. Attribute-guided Feature Extraction and Augmentation Robust Learning for Vehicle Re-identification [PDF] 摘要

11. 3D Scene Geometry-Aware Constraint for Camera Localization with Deep Learning [PDF] 摘要

12. Self-Supervised Deep Visual Odometry with Online Adaptation [PDF] 摘要

13. RISE Video Dataset: Recognizing Industrial Smoke Emissions [PDF] 摘要

14. Adversarial examples are useful too! [PDF] 摘要

15. Apple Defect Detection Using Deep Learning Based Object Detection For Better Post Harvest Handling [PDF] 摘要

16. Class-Incremental Learning for Semantic Segmentation Re-Using Neither Old Data Nor Old Labels [PDF] 摘要

17. Compositional Few-Shot Recognition with Primitive Discovery and Enhancing [PDF] 摘要

18. Occlusion-Adaptive Deep Network for Robust Facial Expression Recognition [PDF] 摘要

19. Computer Vision Toolkit for Non-invasive Monitoring of Factory Floor Artifacts [PDF] 摘要

20. Increased-confidence adversarial examples for improved transferability of Counter-Forensic attacks [PDF] 摘要

21. Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing [PDF] 摘要

22. Local Fiber Orientation from X-ray Region-of-Interest Computed Tomography of large Fiber Reinforced Composite Components [PDF] 摘要

23. Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA [PDF] 摘要

24. Towards segmentation and spatial alignment of the human embryonic brain using deep learning for atlas-based registration [PDF] 摘要

25. Neural Architecture Search for Gliomas Segmentation on Multimodal Magnetic Resonance Imaging [PDF] 摘要

26. Multi-modal Embedding Fusion-based Recommender [PDF] 摘要

27. A Survey on Patch-based Synthesis: GPU Implementation and Optimization [PDF] 摘要

28. Mitigating Gender Bias Amplification in Distribution by Posterior Regularization [PDF] 摘要

29. Context Learning for Bone Shadow Exclusion in CheXNet Accuracy Improvement [PDF] 摘要

30. Generalized Multi-view Shared Subspace Learning using View Bootstrapping [PDF] 摘要

31. Monotone Boolean Functions, Feasibility/Infeasibility, LP-type problems and MaxCon [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-05-14

发表于 2020-05-14 分类于 arxiv ， CL 32k 54 分钟

目录

1. The Unstoppable Rise of Computational Linguistics in Deep Learning [PDF] 摘要

2. Dense-Caption Matching and Frame-Selection Gating for Temporal Localization in VideoQA [PDF] 摘要

3. Sanskrit Segmentation Revisited [PDF] 摘要

4. End-to-end Semantics-based Summary Quality Assessment for Single-document Summarization [PDF] 摘要

5. BIOMRC: A Dataset for Biomedical Machine Reading Comprehension [PDF] 摘要

6. Towards Hate Speech Detection at Large via Deep Generative Modeling [PDF] 摘要

7. Reasoning with Latent Structure Refinement for Document-Level Relation Extraction [PDF] 摘要

8. Smart To-Do : Automatic Generation of To-Do Items from Emails [PDF] 摘要

9. Mitigating Gender Bias Amplification in Distribution by Posterior Regularization [PDF] 摘要

10. Machine Reading Comprehension: The Role of Contextualized Language Models and Beyond [PDF] 摘要

11. Parallel Corpus Filtering via Pre-trained Language Models [PDF] 摘要

12. Response-Anticipated Memory for On-Demand Knowledge Integration in Response Generation [PDF] 摘要

13. Screenplay Quality Assessment: Can We Predict Who Gets Nominated? [PDF] 摘要

14. INFOTABS: Inference on Tables as Semi-structured Data [PDF] 摘要

15. Large Scale Multi-Actor Generative Dialog Modeling [PDF] 摘要

16. Automated Extraction of Socio-political Events from News (AESPEN): Workshop and Shared Task Report [PDF] 摘要

17. A computational model implementing subjectivity with the 'Room Theory'. The case of detecting Emotion from Text [PDF] 摘要

18. That is a Known Lie: Detecting Previously Fact-Checked Claims [PDF] 摘要

19. Cross-Modality Relevance for Reasoning on Language and Vision [PDF] 摘要

20. Which bills are lobbied? Predicting and interpreting lobbying activity in the US [PDF] 摘要

21. Automatic Estimation of Inteligibility Measure for Consonants in Speech [PDF] 摘要

22. Mega-COV: A Billion-Scale Dataset of 65 Languages For COVID-19 [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-13

发表于 2020-05-13 分类于 arxiv ， CV 74k 2:03

目录

1. Efficient and Interpretable Infrared and Visible Image Fusion Via Algorithm Unrolling [PDF] 摘要

2. Latent Fingerprint Registration via Matching Densely Sampled Points [PDF] 摘要

3. Recurrent and Spiking Modeling of Sparse Surgical Kinematics [PDF] 摘要

4. Neural Architecture Transfer [PDF] 摘要

5. Probabilistic Semantic Segmentation Refinement by Monte Carlo Region Growing [PDF] 摘要

6. Bayesian Fusion for Infrared and Visible Images [PDF] 摘要

7. A Novel Distributed Approximate Nearest Neighbor Method for Real-time Face Recognition [PDF] 摘要

8. One-Shot Recognition of Manufacturing Defects in Steel Surfaces [PDF] 摘要

9. HDD-Net: Hybrid Detector Descriptor with Mutual Interactive Learning [PDF] 摘要

10. Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting [PDF] 摘要

11. ReadNet:Towards Accurate ReID with Limited and Noisy Samples [PDF] 摘要

12. Skeleton-Aware Networks for Deep Motion Retargeting [PDF] 摘要

13. IterDet: Iterative Scheme for ObjectDetection in Crowded Environments [PDF] 摘要

14. Automatic clustering of Celtic coins based on 3D point cloud pattern analysis [PDF] 摘要

15. RetinotopicNet: An Iterative Attention Mechanism Using Local Descriptors with Global Context [PDF] 摘要

16. Stillleben: Realistic Scene Synthesis for Deep Learning in Robotics [PDF] 摘要

17. Detecting CNN-Generated Facial Images in Real-World Scenarios [PDF] 摘要

18. Unsupervised Multi-label Dataset Generation from Web Data [PDF] 摘要

19. Discriminative Multi-modality Speech Recognition [PDF] 摘要

20. Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients [PDF] 摘要

21. DeepFaceLab: A simple, flexible and extensible face swapping framework [PDF] 摘要

22. PSDet: Efficient and Universal Parking Slot Detection [PDF] 摘要

23. A Novel Granular-Based Bi-Clustering Method of Deep Mining the Co-Expressed Genes [PDF] 摘要

24. Real-time Facial Expression Recognition "In The Wild'' by Disentangling 3D Expression from Identity [PDF] 摘要

25. 3DV: 3D Dynamic Voxel for Action Recognition in Depth Video [PDF] 摘要

26. Train and Deploy an Image Classifier for Disaster Response [PDF] 摘要

27. Combining Deep Learning with Geometric Features for Image based Localization in the Gastrointestinal Tract [PDF] 摘要

28. VIDIT: Virtual Image Dataset for Illumination Transfer [PDF] 摘要

29. Online Monitoring for Neural Network Based Monocular Pedestrian Pose Estimation [PDF] 摘要

30. Target-Independent Domain Adaptation for WBC Classification using Generative Latent Search [PDF] 摘要

31. Optimizing Vessel Trajectory Compression [PDF] 摘要

32. A Parallel Hybrid Technique for Multi-Noise Removal from Grayscale Medical Images [PDF] 摘要

33. Planning to Explore via Self-Supervised World Models [PDF] 摘要

34. Localized convolutional neural networks for geospatial wind forecasting [PDF] 摘要

35. Adipose Tissue Segmentation in Unlabeled Abdomen MRI using Cross Modality Domain Adaptation [PDF] 摘要

36. Unpaired Motion Style Transfer from Video to Animation [PDF] 摘要

37. Very High Resolution Land Cover Mapping of Urban Areas at Global Scale with Convolutional Neural Networks [PDF] 摘要

38. Invertible Image Rescaling [PDF] 摘要

39. Understanding and Correcting Low-quality Retinal Fundus Images for Clinical Analysis [PDF] 摘要

40. Multi-Channel Transfer Learning of Chest X-ray Images for Screening of COVID-19 [PDF] 摘要

41. High-Fidelity Accelerated MRI Reconstruction by Scan-Specific Fine-Tuning of Physics-Based Neural Networks [PDF] 摘要

42. Making Robots Draw A Vivid Portrait In Two Minutes [PDF] 摘要

43. Jigsaw-VAE: Towards Balancing Features in Variational Autoencoders [PDF] 摘要

44. Deep Medical Image Analysis with Representation Learning and Neuromorphic Computing [PDF] 摘要

45. Identifying Mechanical Models through Differentiable Simulations [PDF] 摘要

46. MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-05-13

发表于 2020-05-13 分类于 arxiv ， CL 49k 1:21

目录

1. Semantic Scaffolds for Pseudocode-to-Code Generation [PDF] 摘要

2. Intersectional Bias in Hate Speech and Abusive Language Datasets [PDF] 摘要

3. TextAttack: A Framework for Adversarial Attacks in Natural Language Processing [PDF] 摘要

4. Exploiting Syntactic Structure for Better Language Modeling: A Syntactic Distance Approach [PDF] 摘要

5. Prta: A System to Support the Analysis of Propaganda Techniques in the News [PDF] 摘要

6. A Report on the 2020 Sarcasm Detection Shared Task [PDF] 摘要

7. Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension [PDF] 摘要

8. Reassessing Claims of Human Parity and Super-Human Performance in Machine Translation at WMT 2019 [PDF] 摘要

9. Dynamic Memory Induction Networks for Few-Shot Text Classification [PDF] 摘要

10. Detecting Multiword Expression Type Helps Lexical Complexity Assessment [PDF] 摘要

11. On the Robustness of Language Encoders against Grammatical Errors [PDF] 摘要

12. Learning and Evaluating Emotion Lexicons for 91 Languages [PDF] 摘要

13. A Frobenius Algebraic Analysis for Parasitic Gaps [PDF] 摘要

14. SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis [PDF] 摘要

15. Neighborhood Matching Network for Entity Alignment [PDF] 摘要

16. Simultaneous paraphrasing and translation by fine-tuning Transformer models [PDF] 摘要

17. DiscreTalk: Text-to-Speech as a Machine Translation Problem [PDF] 摘要

18. Psychometric Analysis and Coupling of Emotions Between State Bulletins and Twitter in India during COVID-19 Infodemic [PDF] 摘要

19. A Framework for Hierarchical Multilingual Machine Translation [PDF] 摘要

20. Exploring TTS without T Using Biologically/Psychologically Motivated Neural Network Modules (ZeroSpeech 2020) [PDF] 摘要

21. Schema-Guided Natural Language Generation [PDF] 摘要

22. Neural Polysynthetic Language Modelling [PDF] 摘要

23. Luganda Text-to-Speech Machine [PDF] 摘要

24. On the Generation of Medical Dialogues for COVID-19 [PDF] 摘要

25. Segmenting Scientific Abstracts into Discourse Categories: A Deep Learning-Based Approach for Sparse Labeled Data [PDF] 摘要

26. MART: Memory-Augmented Recurrent Transformer for Coherent Video Paragraph Captioning [PDF] 摘要

27. Enabling Language Models to Fill in the Blanks [PDF] 摘要

28. Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis [PDF] 摘要

29. COVID-19Base: A knowledgebase to explore biomedical entities related to COVID-19 [PDF] 摘要

30. WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge [PDF] 摘要

31. Do not let the history haunt you -- Mitigating Compounding Errors in Conversational Question Answering [PDF] 摘要

32. AdaDurIAN: Few-shot Adaptation for Neural Text-to-Speech with DurIAN [PDF] 摘要

33. Discriminative Multi-modality Speech Recognition [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-12

发表于 2020-05-12 分类于 arxiv ， CV 121k 3:22

目录

1. Using Computer Vision to enhance Safety of Workforce in Manufacturing in a Post COVID World [PDF] 摘要

2. Normalized Convolutional Neural Network [PDF] 摘要

3. Deep-Learning-based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images [PDF] 摘要

4. On the Transferability of Winning Tickets in Non-Natural Image Datasets [PDF] 摘要

5. Reference-Based Sketch Image Colorization using Augmented-Self Reference and Dense Semantic Correspondence [PDF] 摘要

6. Reference Pose Generation for Visual Localization via Learned Features and View Synthesis [PDF] 摘要

7. FroDO: From Detections to 3D Objects [PDF] 摘要

8. Fine-Grained Visual Classification with Efficient End-to-end Localization [PDF] 摘要

9. HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment [PDF] 摘要

10. Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices [PDF] 摘要

11. Prototypical Contrastive Learning of Unsupervised Representations [PDF] 摘要

12. Fake Face Detection via Adaptive Residuals Extraction Network [PDF] 摘要

13. Conditional Image Generation and Manipulation for User-Specified Content [PDF] 摘要

14. An Inductive Transfer Learning Approach using Cycle-consistent Adversarial Domain Adaptation with Application to Brain Tumor Segmentation [PDF] 摘要

15. Celeganser: Automated Analysis of Nematode Morphology and Age [PDF] 摘要

16. Scope Head for Accurate Localizationin Object Detection [PDF] 摘要

17. Non-iterative Simultaneous Rigid Registration Method for Serial Sections of Biological Tissue [PDF] 摘要

18. Learning Descriptors Invariance Through Equivalence Relations Within Manifold: A New Approach to Expression Invariant 3D Face Recognition [PDF] 摘要

19. The Visual Social Distancing Problem [PDF] 摘要

20. A numerical method to estimate uncertainty in non-rigid structure from motion [PDF] 摘要

21. Photometric Multi-View Mesh Refinement for High-Resolution Satellite Images [PDF] 摘要

22. A Simple Semi-Supervised Learning Framework for Object Detection [PDF] 摘要

23. A Generalized Kernel Risk Sensitive Loss for Robust Two-Dimensional Singular Value Decomposition [PDF] 摘要

24. Domain Adaptation for Image Dehazing [PDF] 摘要

25. A Simple and Scalable Shape Representation for 3D Reconstruction [PDF] 摘要

26. A Comparison of Few-Shot Learning Methods for Underwater Optical and Sonar Image Classification [PDF] 摘要

27. A Unified Weight Learning and Low-Rank Regression Model for Robust Face Recognition [PDF] 摘要

28. MOMBAT: Heart Rate Monitoring from Face Video using Pulse Modeling and Bayesian Tracking [PDF] 摘要

29. Variational Clustering: Leveraging Variational Autoencoders for Image Clustering [PDF] 摘要

30. Robust Tensor Decomposition for Image Representation Based on Generalized Correntropy [PDF] 摘要

31. Class-Aware Domain Adaptation for Improving Adversarial Robustness [PDF] 摘要

32. Compact Neural Representation Using Attentive Network Pruning [PDF] 摘要

33. Epipolar Transformers [PDF] 摘要

34. A Robust Matching Pursuit Algorithm Using Information Theoretic Learning [PDF] 摘要

35. Generative Model-driven Structure Aligning Discriminative Embeddings for Transductive Zero-shot Learning [PDF] 摘要

36. Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events [PDF] 摘要

37. Visually Impaired Aid using Convolutional Neural Networks, Transfer Learning, and Particle Competition and Cooperation [PDF] 摘要

38. Vehicle Re-Identification Based on Complementary Features [PDF] 摘要

39. Understanding Dynamic Scenes using Graph Convolution Networks [PDF] 摘要

40. Memory-Augmented Relation Network for Few-Shot Learning [PDF] 摘要

41. High Resolution Face Age Editing [PDF] 摘要

42. Photo style transfer with consistency losses [PDF] 摘要

43. A Weighted Difference of Anisotropic and Isotropic Total Variation for Relaxed Mumford-Shah Color and Multiphase Image Segmentation [PDF] 摘要

44. ICE-GAN: Identity-aware and Capsule-Enhanced GAN for Micro-Expression Recognition and Synthesis [PDF] 摘要

45. Attentional Bottleneck: Towards an Interpretable Deep Driving Network [PDF] 摘要

46. VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation [PDF] 摘要

47. View Invariant Human Body Detection and Pose Estimation from Multiple Depth Sensors [PDF] 摘要

48. STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction [PDF] 摘要

49. Fundus2Angio: A Novel Conditional GAN Architecture for Generating Fluorescein Angiography Images from Retinal Fundus Photography [PDF] 摘要

50. iUNets: Fully invertible U-Nets with Learnable Up- and Downsampling [PDF] 摘要

51. Medical Image Segmentation Using a U-Net type of Architecture [PDF] 摘要

52. A Contrast-Adaptive Method for Simultaneous Whole-Brain and Lesion Segmentation in Multiple Sclerosis [PDF] 摘要

53. A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms [PDF] 摘要

54. Autonomous Tissue Scanning under Free-Form Motion for Intraoperative Tissue Characterisation [PDF] 摘要

55. Deep Reinforcement Learning for Organ Localization in CT [PDF] 摘要

56. Learning to hash with semantic similarity metrics and empirical KL divergence [PDF] 摘要

57. Gleason Score Prediction using Deep Learning in Tissue Microarray Image [PDF] 摘要

58. The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes [PDF] 摘要

59. Hierarchical Regression Network for Spectral Reconstruction from RGB Images [PDF] 摘要

60. Segmentation of Macular Edema Datasets with Small Residual 3D U-Net Architectures [PDF] 摘要

61. Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning [PDF] 摘要

62. Learning Context-Based Non-local Entropy Modeling for Image Compression [PDF] 摘要

63. BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps [PDF] 摘要

64. Duality in Persistent Homology of Images [PDF] 摘要

65. A Hybrid Swarm and Gravitation based feature selection algorithm for Handwritten Indic Script Classification problem [PDF] 摘要

66. An Integrated Enhancement Solution for 24-hour Colorful Imaging [PDF] 摘要

67. A Survey on Deep Learning for Neuroimaging-based Brain Disorder Analysis [PDF] 摘要

68. Non-recurrent Traffic Congestion Detection with a Coupled Scalable Bayesian Robust Tensor Factorization Model [PDF] 摘要

69. Efficient Privacy Preserving Edge Computing Framework for Image Classification [PDF] 摘要

70. Building a Manga Dataset "Manga109" with Annotations for Multimedia Applications [PDF] 摘要

71. Comment on "No-Reference Video Quality Assessment Based on the Temporal Pooling of Deep Features" [PDF] 摘要

72. Enhancing LGMD's Looming Selectivity for UAVs with Spatial-temporal Distributed Presynaptic Connection [PDF] 摘要

73. AutoCLINT: The Winning Method in AutoCV Challenge 2019 [PDF] 摘要

74. An Investigation of Why Overparameterization Exacerbates Spurious Correlations [PDF] 摘要

75. ST-MNIST -- The Spiking Tactile MNIST Neuromorphic Dataset [PDF] 摘要

76. Progressive Adversarial Semantic Segmentation [PDF] 摘要

77. Measuring the Algorithmic Efficiency of Neural Networks [PDF] 摘要

78. Deep Residual Network based food recognition for enhanced Augmented Reality application [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-05-12

发表于 2020-05-12 分类于 arxiv ， CL 61k 1:42

目录

1. SOLOIST: Few-shot Task-Oriented Dialog with A Single Pre-trained Auto-regressive Model [PDF] 摘要

2. Multidirectional Associative Optimization of Function-Specific Word Representations [PDF] 摘要

3. A Dataset for Statutory Reasoning in Tax Law Entailment and Question Answering [PDF] 摘要

4. Reinforced Rewards Framework for Text Style Transfer [PDF] 摘要

5. Toward Better Storylines with Sentence-Level Language Models [PDF] 摘要

6. A Self-Training Method for Machine Reading Comprehension with Soft Evidence Extraction [PDF] 摘要

7. Evaluating Sparse Interpretable Word Embeddings for Biomedical Domain [PDF] 摘要

8. A Deep Learning Approach for Automatic Detection of Fake News [PDF] 摘要

9. Towards logical negation for compositional distributional semantics [PDF] 摘要

10. Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation [PDF] 摘要

11. A SentiWordNet Strategy for Curriculum Learning in Sentiment Analysis [PDF] 摘要

12. Towards Robustifying NLI Models Against Lexical Dataset Biases [PDF] 摘要

13. CTC-synchronous Training for Monotonic Attention Model [PDF] 摘要

14. Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning [PDF] 摘要

15. From Standard Summarization to New Tasks and Beyond: Summarization with Manifold Information [PDF] 摘要

16. How Context Affects Language Models' Factual Predictions [PDF] 摘要

17. Posterior Control of Blackbox Generation [PDF] 摘要

18. Article citation study: Context enhanced citation sentiment detection [PDF] 摘要

19. What Was Written vs. Who Read It: News Media Profiling Using Text Analysis and Social Media Context [PDF] 摘要

20. Finding Universal Grammatical Relations in Multilingual BERT [PDF] 摘要

21. Empowering Active Learning to Jointly Optimize System and User Demands [PDF] 摘要

22. The Structured Weighted Violations MIRA [PDF] 摘要

23. Generating Pertinent and Diversified Comments with Topic-aware Pointer-Generator Networks [PDF] 摘要

24. Semi-Supervised Dialogue Policy Learning via Stochastic Reward Estimation [PDF] 摘要

25. It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations [PDF] 摘要

26. Diversifying Dialogue Generation with Non-Conversational Text [PDF] 摘要

27. Generalizing Outside the Training Set: When Can Neural Networks Learn Identity Effects? [PDF] 摘要

28. LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation [PDF] 摘要

29. Probing Linguistic Systematicity [PDF] 摘要

30. Temporal Common Sense Acquisition with Minimal Supervision [PDF] 摘要

31. Adversarial Learning for Supervised and Semi-supervised Relation Extraction in Biomedical Literature [PDF] 摘要

32. ConvoKit: A Toolkit for the Analysis of Conversations [PDF] 摘要

33. Balancing Objectives in Counseling Conversations: Advancing Forwards or Looking Backwards [PDF] 摘要

34. Text-Based Ideal Points [PDF] 摘要

35. The Safari of Update Structures: Visiting the Lens and Quantum Enclosures [PDF] 摘要

36. Commonsense Evidence Generation and Injection in Reading Comprehension [PDF] 摘要

37. End-To-End Speech Synthesis Applied to Brazilian Portuguese [PDF] 摘要

38. Listen Attentively, and Spell Once: Whole Sentence Generation via a Non-Autoregressive Architecture for Low-Latency Speech Recognition [PDF] 摘要

39. The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes [PDF] 摘要

40. Knowledge Graph semantic enhancement of input data for improving AI [PDF] 摘要

41. Chirp Complex Cepstrum-based Decomposition for Asynchronous Glottal Analysis [PDF] 摘要

42. BabyWalk: Going Farther in Vision-and-Language Navigation by Taking Baby Steps [PDF] 摘要

43. Transformer-Based Language Models for Similar Text Retrieval and Ranking [PDF] 摘要

44. Incremental Learning for End-to-End Automatic Speech Recognition [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-11

发表于 2020-05-11 分类于 arxiv ， CV 78k 2:11

目录

1. Condensed Movies: Story Based Retrieval with Contextual Embeddings [PDF] 摘要

2. Hyperspectral Image Restoration via Global Total Variation Regularized Local nonconvex Low-Rank matrix Approximation [PDF] 摘要

3. Data-Free Network Quantization With Adversarial Knowledge Distillation [PDF] 摘要

4. NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results [PDF] 摘要

5. Sparsely-Labeled Source Assisted Domain Adaptation [PDF] 摘要

6. A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye View [PDF] 摘要

7. Fast Automatic Visibility Optimization for Thermal Synthetic Aperture Visualization [PDF] 摘要

8. TSDM: Tracking by SiamRPN++ with a Depth-refiner and a Mask-generator [PDF] 摘要

9. Introduction of a new Dataset and Method for Detecting and Counting the Pistachios based on Deep Learning [PDF] 摘要

10. On Vocabulary Reliance in Scene Text Recognition [PDF] 摘要

11. RetinaMask: A Face Mask detector [PDF] 摘要

12. Efficient convolutional neural networks with smaller filters for human activity recognition using wearable sensors [PDF] 摘要

13. Learning Generalized Spoof Cues for Face Anti-spoofing [PDF] 摘要

14. OpenEDS2020: Open Eyes Dataset [PDF] 摘要

15. Point Cloud Completion by Skip-attention Network with Hierarchical Folding [PDF] 摘要

16. Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching [PDF] 摘要

17. Synchronous Bidirectional Learning for Multilingual Lip Reading [PDF] 摘要

18. SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving [PDF] 摘要

19. Projection & Probability-Driven Black-Box Attack [PDF] 摘要

20. One-Shot Object Detection without Fine-Tuning [PDF] 摘要

21. Text Synopsis Generation for Egocentric Videos [PDF] 摘要

22. A Gaussian Process Upsampling Model for Improvements in Optical Character Recognition [PDF] 摘要

23. Recognizing Magnification Levels in Microscopic Snapshots [PDF] 摘要

24. Effective Data Fusion with Generalized Vegetation Index: Evidence from Land Cover Segmentation in Agriculture [PDF] 摘要

25. Neural Object Learning for 6D Pose Estimation Using a Few Cluttered Images [PDF] 摘要

26. Regularized Pooling [PDF] 摘要

27. Source-Relaxed Domain Adaptation for Image Segmentation [PDF] 摘要

28. Preprint: Using RF-DNA Fingerprints To Classify OFDM Transmitters Under Rayleigh Fading Conditions [PDF] 摘要

29. A Hybrid Method for Training Convolutional Neural Networks [PDF] 摘要

30. Multi-Phase Cross-modal Learning for Noninvasive Gene Mutation Prediction in Hepatocellular Carcinoma [PDF] 摘要

31. Hypergraph Learning for Identification of COVID-19 with CT Imaging [PDF] 摘要

32. Convolutional Sparse Support Estimator Based Covid-19 Recognition from X-ray Images [PDF] 摘要

33. DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation [PDF] 摘要

34. Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximation [PDF] 摘要

35. Beyond CNNs: Exploiting Further Inherent Symmetries in Medical Images for Segmentation [PDF] 摘要

36. Is an Affine Constraint Needed for Affine Subspace Clustering? [PDF] 摘要

37. Synergistic Learning of Lung Lobe Segmentation and Hierarchical Multi-Instance Classification for Automated Severity Assessment of COVID-19 in CT Images [PDF] 摘要

38. Y-Net for Chest X-Ray Preprocessing: Simultaneous Classification of Geometry and Segmentation of Annotations [PDF] 摘要

39. Blind Backdoors in Deep Learning Models [PDF] 摘要

40. MLGaze: Machine Learning-Based Analysis of Gaze Error Patterns in Consumer Eye Tracking Systems [PDF] 摘要

41. Federated Generative Adversarial Learning [PDF] 摘要

42. ProSelfLC: Progressive Self Label Correction for Target Revising in Label Noise [PDF] 摘要

43. Planning from Images with Deep Latent Gaussian Process Dynamics [PDF] 摘要

44. A Hand Motion-guided Articulation and Segmentation Estimation [PDF] 摘要

45. Learning to Segment Actions from Observation and Narration [PDF] 摘要

阅读全文 »