【arxiv论文】 Computation and Language 2020-11-09

发表于 2020-11-09 分类于 arxiv ， CL 33k 55 分钟

目录

1. An Unsupervised method for OCR Post-Correction and Spelling Normalisation for Finnish [PDF] 摘要

2. Practical and Ethical Considerations in the Effective use of Emotion and Sentiment Lexicons [PDF] 摘要

3. Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English [PDF] 摘要

4. Answer Span Correction in Machine Reading Comprehension [PDF] 摘要

5. Fighting an Infodemic: COVID-19 Fake News Dataset [PDF] 摘要

6. Learning to Respond with Your Favorite Stickers: A Framework of Unifying Multi-Modality and User Preference in Multi-Turn Dialog [PDF] 摘要

7. Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning [PDF] 摘要

8. The ApposCorpus: A new multilingual, multi-domain dataset for factual appositive generation [PDF] 摘要

9. Semi-Supervised Low-Resource Style Transfer of Indonesian Informal to Formal Language with Iterative Forward-Translation [PDF] 摘要

10. Corpora Compared: The Case of the Swedish Gigaword & Wikipedia Corpora [PDF] 摘要

11. Alquist 3.0: Alexa Prize Bot Using Conversational Knowledge Graph [PDF] 摘要

12. Alquist 2.0: Alexa Prize Socialbot Based on Sub-Dialogue Models [PDF] 摘要

13. OP-IMS @ DIACR-Ita: Back to the Roots: SGNS+OP+CD still rocks Semantic Change Detection [PDF] 摘要

14. From Dataset Recycling to Multi-Property Extraction and Beyond [PDF] 摘要

15. Unleashing the Power of Neural Discourse Parsers -- A Context and Structure Aware Approach Using Large Scale Pretraining [PDF] 摘要

16. What's New? Summarizing Contributions in Scientific Literature [PDF] 摘要

17. Semi-supervised URL Segmentation with Recurrent Neural NetworksPre-trained on Knowledge Graph Entities [PDF] 摘要

18. Improving RNN Transducer Based ASR with Auxiliary Tasks [PDF] 摘要

19. Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering [PDF] 摘要

20. Machine Generation and Detection of Arabic Manipulated and Fake News [PDF] 摘要

21. HoVer: A Dataset for Many-Hop Fact Extraction And Claim Verification [PDF] 摘要

22. EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answering [PDF] 摘要

23. Alignment Restricted Streaming Recurrent Neural Network Transducer [PDF] 摘要

24. PubSqueezer: A Text-Mining Web Tool to Transform Unstructured Documents into Structured Data [PDF] 摘要

25. Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-11-04

发表于 2020-11-04 分类于 arxiv ， CV 75k 2:04

目录

1. Learning Visual Representations for Transfer Learning by Suppressing Texture [PDF] 摘要

2. RealHePoNet: a robust single-stage ConvNet for head pose estimation in the wild [PDF] 摘要

3. Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification [PDF] 摘要

4. Learning unbiased registration and joint segmentation: evaluation on longitudinal diffusion MRI [PDF] 摘要

5. Semi-supervised AU Intensity Estimation with Contrastive Learning [PDF] 摘要

6. Learning Representations from Audio-Visual Spatial Alignment [PDF] 摘要

7. Attention Beam: An Image Captioning Approach [PDF] 摘要

8. Learning a Generative Motion Model from Image Sequences based on a Latent Motion Matrix [PDF] 摘要

9. Exploring DeshuffleGANs in Self-Supervised Generative Adversarial Networks [PDF] 摘要

10. A spatial hue similarity measure for assessment of colourisation [PDF] 摘要

11. The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals [PDF] 摘要

12. Relational Graph Learning on Visual and Kinematics Embeddings for Accurate Gesture Recognition in Robotic Surgery [PDF] 摘要

13. A Deep Temporal Fusion Framework for Scene Flow Using a Learnable Motion Model and Occlusions [PDF] 摘要

14. Cross-Media Keyphrase Prediction: A Unified Framework with Multi-Modality Multi-Head Attention and Image Wordings [PDF] 摘要

15. CooGAN: A Memory-Efficient Framework for High-Resolution Facial Attribute Editing [PDF] 摘要

16. 3D-LaneNet+: Anchor Free Lane Detection using a Semi-Local Representation [PDF] 摘要

17. SelfPose: 3D Egocentric Pose Estimation from a Headset Mounted Camera [PDF] 摘要

18. VEGA: Towards an End-to-End Configurable AutoML Pipeline [PDF] 摘要

19. Wheat Crop Yield Prediction Using Deep LSTM Model [PDF] 摘要

20. Kernel Two-Dimensional Ridge Regression for Subspace Clustering [PDF] 摘要

21. Distribution-aware Margin Calibration for Medical Image Segmentation [PDF] 摘要

22. Learning Effective Representations from Global and Local Features for Cross-View Gait Recognition [PDF] 摘要

23. Learning Deformable Tetrahedral Meshes for 3D Reconstruction [PDF] 摘要

24. Developing High Quality Training Samples for Deep Learning Based Local Climate Classification in Korea [PDF] 摘要

25. "You eat with your eyes first": Optimizing Yelp Image Advertising [PDF] 摘要

26. In Defense of Feature Mimicking for Knowledge Distillation [PDF] 摘要

27. Content-based Analysis of the Cultural Differences between TikTok and Douyin [PDF] 摘要

28. Out-of-Distribution Detection for Automotive Perception [PDF] 摘要

29. BIGPrior: Towards Decoupling Learned Prior Hallucination and Data Fidelity in Image Restoration [PDF] 摘要

30. Faraway-Frustum: Dealing with Lidar Sparsity for 3D Object Detection using Fusion [PDF] 摘要

31. Parameter Efficient Deep Neural Networks with Bilinear Projections [PDF] 摘要

32. Dual Attention on Pyramid Feature Maps for Image Captioning [PDF] 摘要

33. Unsupervised Monocular Depth Learning with Integrated Intrinsics and Spatio-Temporal Constraints [PDF] 摘要

34. Recyclable Waste Identification Using CNN Image Recognition and Gaussian Clustering [PDF] 摘要

35. Revisiting Adaptive Convolutions for Video Frame Interpolation [PDF] 摘要

36. Generating Unobserved Alternatives: A Case Study through Super-Resolution and Decompression [PDF] 摘要

37. Classifier Pool Generation based on a Two-level Diversity Approach [PDF] 摘要

38. Deep Joint Transmission-Recognition for Multi-View Cameras [PDF] 摘要

39. A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks [PDF] 摘要

40. Point of Care Image Analysis for COVID-19 [PDF] 摘要

41. Predicting intubation support requirement of patients using Chest X-ray with Deep Representation Learning [PDF] 摘要

42. Solving Inverse Problems with Hybrid Deep Image Priors: the challenge of preventing overfitting [PDF] 摘要

43. Convolution Neural Networks for Semantic Segmentation: Application to Small Datasets of Biomedical Images [PDF] 摘要

44. Generalized Wasserstein Dice Score, Distributionally Robust Deep Learning, and Ranger for brain tumor segmentation: BraTS 2020 challenge [PDF] 摘要

45. Recent Advances in Understanding Adversarial Robustness of Deep Neural Networks [PDF] 摘要

46. MACE: Model Agnostic Concept Extractor for Explaining Image Classification Networks [PDF] 摘要

47. Self-semi-supervised Learning to Learn from NoisyLabeled Data [PDF] 摘要

48. Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-11-03

发表于 2020-11-03 分类于 arxiv ， CV 170k 4:44

目录

1. Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors [PDF] 摘要

2. Pushing the Envelope of Rotation Averaging for Visual SLAM [PDF] 摘要

3. Reducing the Annotation Effort for Video Object Segmentation Datasets [PDF] 摘要

4. SLAM in the Field: An Evaluation of Monocular Mapping and Localization on Challenging Dynamic Agricultural Environment [PDF] 摘要

5. Facial Keypoint Sequence Generation from Audio [PDF] 摘要

6. Multi-Task Learning for Calorie Prediction on a Novel Large-Scale Recipe Dataset Enriched with Nutritional Information [PDF] 摘要

7. Image Inpainting with Learnable Feature Imputation [PDF] 摘要

8. CABiNet: Efficient Context Aggregation Network for Low-Latency Semantic Segmentation [PDF] 摘要

9. PBP-Net: Point Projection and Back-Projection Network for 3D Point Cloud Segmentation [PDF] 摘要

10. 3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data [PDF] 摘要

11. Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals [PDF] 摘要

12. Diverse Image Captioning with Context-Object Split Latent Spaces [PDF] 摘要

13. Learning a Deep Reinforcement Learning Policy Over the Latent Space of a Pre-trained GAN for Semantic Age Manipulation [PDF] 摘要

14. Point Transformer [PDF] 摘要

15. Boost Image Captioning with Knowledge Reasoning [PDF] 摘要

16. MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis [PDF] 摘要

17. Facial UV Map Completion for Pose-invariant Face Recognition: A Novel Adversarial Approach based on Coupled Attention Residual UNets [PDF] 摘要

18. Efficient texture mapping via a non-iterative global texture alignment [PDF] 摘要

19. Receptive Field Size Optimization with Continuous Time Pooling [PDF] 摘要

20. Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs [PDF] 摘要

21. Predicting Brain Degeneration with a Multimodal Siamese Neural Network [PDF] 摘要

22. PV-NAS: Practical Neural Architecture Search for Video Recognition [PDF] 摘要

23. Data-free Knowledge Distillation for Segmentation using Data-Enriching GAN [PDF] 摘要

24. CaCL: Class-aware Codebook Learning for Weakly Supervised Segmentation on Diffuse Image Patterns [PDF] 摘要

25. A topological approach to exploring convolutional neural networks [PDF] 摘要

26. Deep Representation Decomposition for Feature Disentanglement [PDF] 摘要

27. Actor and Action Modular Network for Text-based Video Segmentation [PDF] 摘要

28. Context-based Image Segment Labeling (CBISL) [PDF] 摘要

29. Set Augmented Triplet Loss for Video Person Re-Identification [PDF] 摘要

30. Deep Feature Augmentation for Occluded Image Classification [PDF] 摘要

31. Mutual Information-based Disentangled Neural Networks for Classifying Unseen Categories in Different Domains: Application to Fetal Ultrasound Imaging [PDF] 摘要

32. CNN-Driven Quasiconformal Model for Large Deformation Image Registration [PDF] 摘要

33. Road Damage Detection using Deep Ensemble Learning [PDF] 摘要

34. Multi-Modal Active Learning for Automatic Liver Fibrosis Diagnosis based on Ultrasound Shear Wave Elastography [PDF] 摘要

35. Highway Driving Dataset for Semantic Video Segmentation [PDF] 摘要

36. Multi-View Adaptive Fusion Network for 3D Object Detection [PDF] 摘要

37. Unsupervised Metric Relocalization Using Transform Consistency Loss [PDF] 摘要

38. COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning [PDF] 摘要

39. FusiformNet: Extracting Discriminative Facial Features on Different Levels [PDF] 摘要

40. Human Leg Motion Tracking by Fusing IMUs and RGB Camera Data Using Extended Kalman Filter [PDF] 摘要

41. DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation [PDF] 摘要

42. LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networks [PDF] 摘要

43. Memory Group Sampling Based Online Action Recognition Using Kinetic Skeleton Features [PDF] 摘要

44. Adversarial Self-Supervised Scene Flow Estimation [PDF] 摘要

45. Autonomous Extraction of Gleason Patterns for Grading Prostate Cancer using Multi-Gigapixel Whole Slide Images [PDF] 摘要

46. HM4: Hidden Markov Model with Memory Management for Visual Place Recognition [PDF] 摘要

47. A Parallel Approach for Real-Time Face Recognition from a Large Database [PDF] 摘要

48. Efficient Pipelines for Vision-Based Context Sensing [PDF] 摘要

49. Dark Reciprocal-Rank: Boosting Graph-Convolutional Self-Localization Network via Teacher-to-student Knowledge Transfer [PDF] 摘要

50. Temporally-Continuous Probabilistic Prediction using Polynomial Trajectory Parameterization [PDF] 摘要

51. IndRNN Based Long-term Temporal Recognition in the Spatial and Frequency Domain [PDF] 摘要

52. Real-Time Text Detection and Recognition [PDF] 摘要

53. A Survey on Contrastive Self-supervised Learning [PDF] 摘要

54. TartanVO: A Generalizable Learning-based VO [PDF] 摘要

55. Unsupervised Deep Persistent Monocular Visual Odometry and Depth Estimation in Extreme Environments [PDF] 摘要

56. Self-paced and self-consistent co-training for semi-supervised image segmentation [PDF] 摘要

57. Scene Flow from Point Clouds with or without Learning [PDF] 摘要

58. General Data Analytics With Applications To Visual Information Analysis: A Provable Backward-Compatible Semisimple Paradigm Over T-Algebra [PDF] 摘要

59. Pose Randomization for Weakly Paired Image Style Translation [PDF] 摘要

60. LandmarkGAN: Synthesizing Faces from Landmarks [PDF] 摘要

61. ProxylessKD: Direct Knowledge Distillation with Inherited Classifier for Face Recognition [PDF] 摘要

62. Temporal Smoothing for 3D Human Pose Estimation and Localization for Occluded People [PDF] 摘要

63. Enhanced Balancing GAN: Minority-class Image Generation [PDF] 摘要

64. Self-supervised Representation Learning for Evolutionary Neural Architecture Search [PDF] 摘要

65. Exploring Severe Occlusion: Multi-Person 3D Pose Estimation with Gated Convolution [PDF] 摘要

66. Learning Open Set Network with Discriminative Reciprocal Points [PDF] 摘要

67. Multimodal and self-supervised representation learning for automatic gesture recognition in surgical robotics [PDF] 摘要

68. Automatic Chronic Degenerative Diseases Identification Using Enteric Nervous System Images [PDF] 摘要

69. Weakly Supervised 3D Classification of Chest CT using Aggregated Multi-Resolution Deep Segmentation Features [PDF] 摘要

70. Leveraging Adaptive Color Augmentation in Convolutional Neural Networks for Deep Skin Lesion Segmentation [PDF] 摘要

71. Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation [PDF] 摘要

72. (Un)Masked COVID-19 Trends from Social Media [PDF] 摘要

73. Pose-based Body Language Recognition for Emotion and Psychiatric Symptom Interpretation [PDF] 摘要

74. A Deep Learning Study on Osteosarcoma Detection from Histological Images [PDF] 摘要

75. Perceive, Attend, and Drive: Learning Spatial Attention for Safe Self-Driving [PDF] 摘要

76. Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds [PDF] 摘要

77. U-Net and its variants for medical image segmentation: theory and applications [PDF] 摘要

78. Top 10 BraTS 2020 challenge solution: Brain tumor segmentation with self-ensembled, deeply-supervised 3D-Unet like neural networks [PDF] 摘要

79. Depth Ranging Performance Evaluation and Improvement for RGB-D Cameras on Field-Based High-Throughput Phenotyping Robots [PDF] 摘要

80. AVECL-UMONS database for audio-visual event classification and localization [PDF] 摘要

81. ASIST: Annotation-free synthetic instance segmentation and tracking for microscope video analysis [PDF] 摘要

82. Deep Learning in Computer-Aided Diagnosis and Treatment of Tumors: A Survey [PDF] 摘要

83. nnU-Net for Brain Tumor Segmentation [PDF] 摘要

84. Bifurcated Autoencoder for Segmentation of COVID-19 Infected Regions in CT Images [PDF] 摘要

85. Brain Tumor Classification Using Medial Residual Encoder Layers [PDF] 摘要

86. Tracking Partially-Occluded Deformable Objects while Enforcing Geometric Constraints [PDF] 摘要

87. Triage of Potential COVID-19 Patients from Chest X-ray Images using Hierarchical Convolutional Networks [PDF] 摘要

88. Learning Euler's Elastica Model for Medical Image Segmentation [PDF] 摘要

89. Generating Correct Answers for Progressive Matrices Intelligence Tests [PDF] 摘要

90. Dynamic radiomics: a new methodology to extract quantitative time-related features from tomographic images [PDF] 摘要

91. Two-layer clustering-based sparsifying transform learning for low-dose CT reconstruction [PDF] 摘要

92. Using Monte Carlo dropout and bootstrap aggregation for uncertainty estimation in radiation therapy dose prediction with deep learning neural networks [PDF] 摘要

93. Segmentation of Infrared Breast Images Using MultiResUnet Neural Network [PDF] 摘要

94. Pose Estimation of Specular and Symmetrical Objects [PDF] 摘要

95. DL-Reg: A Deep Learning Regularization Technique using Linear Regression [PDF] 摘要

96. Deep learning in the ultrasound evaluation of neonatal respiratory status [PDF] 摘要

97. Encoding Clinical Priori in 3D Convolutional Neural Networks for Prostate Cancer Detection in bpMRI [PDF] 摘要

98. Meta-Learning with Adaptive Hyperparameters [PDF] 摘要

99. Combining Domain-Specific Meta-Learners in the Parameter Space for Cross-Domain Few-Shot Classification [PDF] 摘要

100. Evaluation of Inference Attack Models for Deep Learning on Medical Data [PDF] 摘要

101. Dense Pixel-wise Micro-motion Estimation of Object Surface by using Low Dimensional Embedding of Laser Speckle Pattern [PDF] 摘要

102. Integer Programming-based Error-Correcting Output Code Design for Robust Classification [PDF] 摘要

103. EDCNN: Edge enhancement-based Densely Connected Network with Compound Loss for Low-Dose CT Denoising [PDF] 摘要

104. Multi-stage transfer learning for lung segmentation using portable X-ray devices for patients with COVID-19 [PDF] 摘要

105. C-Net: A Reliable Convolutional Neural Network for Biomedical Image Classification [PDF] 摘要

106. 83% ImageNet Accuracy in One Hour [PDF] 摘要

107. Adversarial Robust Training in MRI Reconstruction [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-11-03

发表于 2020-11-03 分类于 arxiv ， CL 129k 3:35

目录

1. The Devil is in the Details: Evaluating Limitations of Transformer-based Methods for Granular Tasks [PDF] 摘要

2. QMUL-SDS at SardiStance2020: Leveraging Network Interactions to Boost Performance on Stance Detection using Knowledge Graphs [PDF] 摘要

3. Introducing various Semantic Models for Amharic: Experimentation and Evaluation with multiple Tasks and Datasets [PDF] 摘要

4. Automated Transcription of Non-Latin Script Periodicals: A Case Study in the Ottoman Turkish Print Archive [PDF] 摘要

5. Improving Variational Autoencoder for Text Modelling with Timestep-Wise Regularisation [PDF] 摘要

6. Generating Knowledge Graphs by Employing Natural Language Processing and Machine Learning Techniques within the Scholarly Domain [PDF] 摘要

7. Exploring Question-Specific Rewards for Generating Deep Questions [PDF] 摘要

8. Enabling Zero-shot Multilingual Spoken Language Translation with Language-Specific Encoders and Decoders [PDF] 摘要

9. Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps [PDF] 摘要

10. Biased TextRank: Unsupervised Graph-Based Content Extraction [PDF] 摘要

11. DNN-Based Semantic Model for Rescoring N-best Speech Recognition List [PDF] 摘要

12. Combining Event Semantics and Degree Semantics for Natural Language Inference [PDF] 摘要

13. A Closer Look at Linguistic Knowledge in Masked Language Models: The Case of Relative Clauses in American English [PDF] 摘要

14. An Empirical Study of Contextual Data Augmentation for Japanese Zero Anaphora Resolution [PDF] 摘要

15. How Far Does BERT Look At:Distance-based Clustering and Analysis of BERTś Attention [PDF] 摘要

16. Emergent Communication Pretraining for Few-Shot Machine Translation [PDF] 摘要

17. Comparison by Conversion: Reverse-Engineering UCCA from Syntax and Lexical Semantics [PDF] 摘要

18. Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation [PDF] 摘要

19. Context Dependent Semantic Parsing: A Survey [PDF] 摘要

20. Adapting Pretrained Transformer to Lattices for Spoken Language Understanding [PDF] 摘要

21. COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering [PDF] 摘要

22. Context-Aware Cross-Attention for Non-Autoregressive Translation [PDF] 摘要

23. Reducing Confusion in Active Learning for Part-Of-Speech Tagging [PDF] 摘要

24. I Know What You Asked: Graph Path Learning using AMR for Commonsense Reasoning [PDF] 摘要

25. ÚFAL at MRP 2020: Permutation-invariant Semantic Parsing in PERIN [PDF] 摘要

26. Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation [PDF] 摘要

27. Abstracting Influence Paths for Explaining (Contextualization of) BERT Models [PDF] 摘要

28. Semi-supervised Autoencoding Projective Dependency Parsing [PDF] 摘要

29. ABNIRML: Analyzing the Behavior of Neural IR Models [PDF] 摘要

30. How Domain Terminology Affects Meeting Summarization Performance [PDF] 摘要

31. Sequence-to-Sequence Networks Learn the Meaning of Reflexive Anaphora [PDF] 摘要

32. Event-Related Bias Removal for Real-time Disaster Events [PDF] 摘要

33. Liputan6: A Large-scale Indonesian Dataset for Text Summarization [PDF] 摘要

34. Investigating Catastrophic Forgetting During Continual Training for Neural Machine Translation [PDF] 摘要

35. IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP [PDF] 摘要

36. Targeted Poisoning Attacks on Black-Box Neural Machine Translation [PDF] 摘要

37. Reasoning Over History: Context Aware Visual Dialog [PDF] 摘要

38. Aspect-Based Argument Mining [PDF] 摘要

39. Social Chemistry 101: Learning to Reason about Social and Moral Norms [PDF] 摘要

40. Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning [PDF] 摘要

41. Bracketing Encodings for 2-Planar Dependency Parsing [PDF] 摘要

42. MixKD: Towards Efficient Distillation of Large-scale Language Models [PDF] 摘要

43. Vec2Sent: Probing Sentence Embeddings with Natural Language Generation [PDF] 摘要

44. A Unifying Theory of Transition-based and Sequence Labeling Parsing [PDF] 摘要

45. ASAD: A Twitter-based Benchmark Arabic Sentiment Analysis Dataset [PDF] 摘要

46. Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey [PDF] 摘要

47. WLV-RIT at HASOC-Dravidian-CodeMix-FIRE2020: Offensive Language Identification in Code-switched YouTube Comments [PDF] 摘要

48. SMRT Chatbots: Improving Non-Task-Oriented Dialog with Simulated Multiple Reference Training [PDF] 摘要

49. Semantic coordinates analysis reveals language changes in the AI field [PDF] 摘要

50. Deep Diacritization: Efficient Hierarchical Recurrence for Improved Arabic Diacritization [PDF] 摘要

51. CHIME: Cross-passage Hierarchical Memory Network for Generative Review Question Answering [PDF] 摘要

52. Deconstruct to Reconstruct a Configurable Evaluation Metric for Open-Domain Dialogue Systems [PDF] 摘要

53. Transformer-based Multi-Aspect Modeling for Multi-Aspect Multi-Sentiment Analysis [PDF] 摘要

54. Opinion Transmission Network for Jointly Improving Aspect-oriented Opinion Words Extraction and Sentiment Classification [PDF] 摘要

55. Seeing Both the Forest and the Trees: Multi-head Attention for Joint Classification on Different Compositional Levels [PDF] 摘要

56. Fake or Real? A Study of Arabic Satirical Fake News [PDF] 摘要

57. Improving Cyberbully Detection with User Interaction [PDF] 摘要

58. Analyzing the Effect of Multi-task Learning for Biomedical Named Entity Recognition [PDF] 摘要

59. Deep Learning for Text Attribute Transfer: A Survey [PDF] 摘要

60. Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies [PDF] 摘要

61. Towards A Friendly Online Community: An Unsupervised Style Transfer Framework for Profanity Redaction [PDF] 摘要

62. Investigation of BERT Model on Biomedical Relation Extraction Based on Revised Fine-tuning Mechanism [PDF] 摘要

63. Be More with Less: Hypergraph Attention Networks for Inductive Text Classification [PDF] 摘要

64. Efficient Arabic emotion recognition using deep neural networks [PDF] 摘要

65. Aspectuality Across Genre: A Distributional Semantics Approach [PDF] 摘要

66. Pick a Fight or Bite your Tongue: Investigation of Gender Differences in Idiomatic Language Usage [PDF] 摘要

67. Effective Approach to Develop a Sentiment Annotator For Legal Domain in a Low Resource Setting [PDF] 摘要

68. Method of the coherence evaluation of Ukrainian text [PDF] 摘要

69. Neural Coreference Resolution for Arabic [PDF] 摘要

70. Rumor Detection on Twitter Using Multiloss Hierarchical BiLSTM with an Attenuation Factor [PDF] 摘要

71. Free the Plural: Unrestricted Split-Antecedent Anaphora Resolution [PDF] 摘要

72. Evaluating Bias In Dutch Word Embeddings [PDF] 摘要

73. Personalized Multimodal Feedback Generation in Education [PDF] 摘要

74. Understanding Pre-trained BERT for Aspect-based Sentiment Analysis [PDF] 摘要

75. Improving Dialogue Breakdown Detection with Semi-Supervised Learning [PDF] 摘要

76. Learning Structured Representations of Entity Names using Active Learning and Weak Supervision [PDF] 摘要

77. Joint Masked CPC and CTC Training for ASR [PDF] 摘要

78. Analyzing Gender Bias within Narrative Tropes [PDF] 摘要

79. Dynamic Data Selection for Curriculum Learning via Ability Estimation [PDF] 摘要

80. A New Neural Search and Insights Platform for Navigating and Organizing AI Research [PDF] 摘要

81. A Sui Generis QA Approach using RoBERTa for Adverse Drug Event Identification [PDF] 摘要

82. Streaming Simultaneous Speech Translation with Augmented Memory Transformer [PDF] 摘要

83. Speaker anonymisation using the McAdams coefficient [PDF] 摘要

84. Evaluation of Siamese Networks for Semantic Code Search [PDF] 摘要

85. Unification of HDP and LDA Models for Optimal Topic Clustering of Subject Specific Question Banks [PDF] 摘要

86. The 2020s Political Economy of Machine Translation [PDF] 摘要

87. Advanced Semantics for Commonsense Knowledge Extraction [PDF] 摘要

88. Learning from Non-Binary Constituency Trees via Tensor Decomposition [PDF] 摘要

89. COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning [PDF] 摘要

90. DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation [PDF] 摘要

91. The xx205 System for the VoxCeleb Speaker Recognition Challenge 2020 [PDF] 摘要

92. Semantic similarity-based approach to enhance supervised classification learning accuracy [PDF] 摘要

93. Directional ASR: A New Paradigm for E2E Multi-Speaker Speech Recognition with Source Localization [PDF] 摘要

阅读全文 »

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

发表于 2020-11-02 分类于 arxiv ， CV 71k 1:59

目录

1. MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing [PDF] 摘要

2. Unsupervised Monocular Depth Learning in Dynamic Scenes [PDF] 摘要

3. What's in a Loss Function for Image Classification? [PDF] 摘要

4. Emotion Understanding in Videos Through Body, Context, and Visual-Semantic Embedding Loss [PDF] 摘要

5. Automatic Counting and Identification of Train Wagons Based on Computer Vision and Deep Learning [PDF] 摘要

6. All-Weather Object Recognition Using Radar and Infrared Sensing [PDF] 摘要

7. 3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations [PDF] 摘要

8. Exploring Dynamic Context for Multi-path Trajectory Prediction [PDF] 摘要

9. Experimental design for MRI by greedy policy search [PDF] 摘要

10. HOI Analysis: Integrating and Decomposing Human-Object Interaction [PDF] 摘要

11. Statistical Analysis of Signal-Dependent Noise: Application in Blind Localization of Image Splicing Forgery [PDF] 摘要

12. End-to-end Animal Image Matting [PDF] 摘要

13. Small Noisy and Perspective Face Detection using Deformable Symmetric Gabor Wavelet Network [PDF] 摘要

14. Auto-Panoptic: Cooperative Multi-Component Architecture Search for Panoptic Segmentation [PDF] 摘要

15. PyraPose: Feature Pyramids for Fast and Accurate Object Pose Estimation under Domain Shift [PDF] 摘要

16. An Unsupervised Approach towards Varying Human Skin Tone Using Generative Adversarial Networks [PDF] 摘要

17. Correspondence Matrices are Underrated [PDF] 摘要

18. LIFI: Towards Linguistically Informed Frame Interpolation [PDF] 摘要

19. Volumetric Medical Image Segmentation: A 3D Deep Coarse-to-fine Framework and Its Adversarial Examples [PDF] 摘要

20. CNN based Multistage Gated Average Fusion (MGAF) for Human Action Recognition Using Depth and Inertial Sensors [PDF] 摘要

21. SMOT: Single-Shot Multi Object Tracking [PDF] 摘要

22. Loss-rescaling VQA: Revisiting Language Prior Problem from a Class-imbalance View [PDF] 摘要

23. Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks? [PDF] 摘要

24. PAL : Pretext-based Active Learning [PDF] 摘要

25. Detecting small polyps using a Dynamic SSD-GAN [PDF] 摘要

26. A Comprehensive Comparison of End-to-End Approaches for Handwritten Digit String Recognition [PDF] 摘要

27. Perception Matters: Exploring Imperceptible and Transferable Anti-forensics for GAN-generated Fake Face Imagery Detection [PDF] 摘要

28. Development and Evaluation of a Deep Neural Network for Histologic Classification of Renal Cell Carcinoma on Biopsy and Surgical Resection Slides [PDF] 摘要

29. Domain-Specific Lexical Grounding in Noisy Visual-Textual Documents [PDF] 摘要

30. DeepWay: a Deep Learning Estimator for Unmanned Ground Vehicle Global Path Planning [PDF] 摘要

31. Learning Vision-based Reactive Policies for Obstacle Avoidance [PDF] 摘要

32. Automatic Myocardial Infarction Evaluation from Delayed-Enhancement Cardiac MRI using Deep Convolutional Networks [PDF] 摘要

33. Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices [PDF] 摘要

34. Bayesian Optimization Meets Laplace Approximation for Robotic Introspection [PDF] 摘要

35. Classifying Malware Images with Convolutional Neural Network Models [PDF] 摘要

36. CT-CAPS: Feature Extraction-based Automated Framework for COVID-19 Disease Identification from Chest CT Scans using Capsule Networks [PDF] 摘要

37. COVID-FACT: A Fully-Automated Capsule Network-based Framework for Identification of COVID-19 Cases from Chest CT scans [PDF] 摘要

38. FLANNEL: Focal Loss Based Neural Network Ensemble for COVID-19 Detection [PDF] 摘要

39. PIINET: A 360-degree Panoramic Image Inpainting Network Using a Cube Map [PDF] 摘要

40. AutoAtlas: Neural Network for 3D Unsupervised Partitioning and Representation Learning [PDF] 摘要

41. Human versus Machine Attention in Deep Reinforcement Learning Tasks [PDF] 摘要

42. Multi-agent Trajectory Prediction with Fuzzy Query Attention [PDF] 摘要

43. Ink Marker Segmentation in Histopathology Images Using Deep Learning [PDF] 摘要

阅读全文 »

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

发表于 2020-11-02 分类于 arxiv ， CL 51k 1:25

目录

1. Artificial Intelligence (AI) in Action: Addressing the COVID-19 Pandemic with Natural Language Processing (NLP) [PDF] 摘要

2. Mere account mein kitna balance hai? -- On building voice enabled Banking Services for Multilingual Communities [PDF] 摘要

3. Semi-supervised Relation Extraction via Incremental Meta Self-Training [PDF] 摘要

4. Sentiment Analysis for Roman Urdu Text over Social Media, a Comparative Study [PDF] 摘要

5. TopicBERT for Energy Efficient Document Classification [PDF] 摘要

6. Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition [PDF] 摘要

7. Domain-Specific Lexical Grounding in Noisy Visual-Textual Documents [PDF] 摘要

8. A Cross-lingual Natural Language Processing Framework for Infodemic Management [PDF] 摘要

9. Topic-Preserving Synthetic News Generation: An Adversarial Deep Reinforcement Learning Approach [PDF] 摘要

10. A Critical Assessment of State-of-the-Art in Entity Alignment [PDF] 摘要

11. Towards Accurate and Consistent Evaluation: A Dataset for Distantly-Supervised Relation Extraction [PDF] 摘要

12. SLM: Learning a Discourse Language Representation with Sentence Unshuffling [PDF] 摘要

13. "Thy algorithm shalt not bear false witness": An Evaluation of Multiclass Debiasing Methods on Word Embeddings [PDF] 摘要

14. Biomedical Concept Relatedness -- A large EHR-based benchmark [PDF] 摘要

15. HyperText: Endowing FastText with Hyperbolic Geometry [PDF] 摘要

16. Target Word Masking for Location Metonymy Resolution [PDF] 摘要

17. Cross-Domain Sentiment Classification With Contrastive Learning and Mutual Information Maximization [PDF] 摘要

18. Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification [PDF] 摘要

19. Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction [PDF] 摘要

20. Generating Radiology Reports via Memory-driven Transformer [PDF] 摘要

21. VECO: Variable Encoder-decoder Pre-training for Cross-lingual Understanding and Generation [PDF] 摘要

22. CliniQG4QA: Generating Diverse Questions for Domain Adaptation of Clinical Question Answering [PDF] 摘要

23. AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts [PDF] 摘要

24. RuREBus: a Case Study of Joint Named Entity Recognition and Relation Extraction from e-Government Domain [PDF] 摘要

25. RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark [PDF] 摘要

26. How Many Pages? Paper Length Prediction from the Metadata [PDF] 摘要

27. Learning as Abduction: Trainable Natural Logic Theorem Prover for Natural Language Inference [PDF] 摘要

28. Less is More: Data-Efficient Complex Question Answering over Knowledge Bases [PDF] 摘要

29. Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning [PDF] 摘要

30. Leveraging Extracted Model Adversaries for Improved Black Box Attacks [PDF] 摘要

31. Comparison of Speaker Role Recognition and Speaker Enrollment Protocol for conversational Clinical Interviews [PDF] 摘要

32. T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model [PDF] 摘要

33. Systolic Computing on GPUs for Productive Performance [PDF] 摘要

34. Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-10-30

发表于 2020-10-30 分类于 arxiv ， CL 30k 50 分钟

目录

1. Contextual BERT: Conditioning the Language Model Using a Global State [PDF] 摘要

2. Explainable Automated Coding of Clinical Notes using Hierarchical Label-wise Attention Networks and Label Embedding Initialisation [PDF] 摘要

3. May I Ask Who's Calling? Named Entity Recognition on Call Center Transcripts for Privacy Law Compliance [PDF] 摘要

4. Unbabel's Participation in the WMT20 Metrics Shared Task [PDF] 摘要

5. Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information [PDF] 摘要

6. Named Entity Recognition for Social Media Texts with Semantic Augmentation [PDF] 摘要

7. Memory Attentive Fusion: External Language Model Integration for Transformer-based Sequence-to-Sequence Model [PDF] 摘要

8. Tilde at WMT 2020: News Task Systems [PDF] 摘要

9. Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management [PDF] 摘要

10. Combining Self-Training and Self-Supervised Learning for Unsupervised Disfluency Detection [PDF] 摘要

11. Multiple Sclerosis Severity Classification From Clinical Text [PDF] 摘要

12. "where is this relationship going?": Understanding Relationship Trajectories in Narrative Text [PDF] 摘要

13. Uncovering Latent Biases in Text: Method and Application to Peer Review [PDF] 摘要

14. CopyNext: Explicit Span Copying and Alignment in Sequence to Sequence Models [PDF] 摘要

15. A Visuospatial Dataset for Naturalistic Verb Learning [PDF] 摘要

16. DeSMOG: Detecting Stance in Media On Global Warming [PDF] 摘要

17. Semi-Supervised Speech Recognition via Graph-based Temporal Classification [PDF] 摘要

18. Designing learning experiences for online teaching and learning [PDF] 摘要

19. Three computational models and its equivalence [PDF] 摘要

20. Self-supervised Pre-training Reduces Label Permutation Instability of Speech Separation [PDF] 摘要

21. Fusion Models for Improved Visual Captioning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-10-29

发表于 2020-10-29 分类于 arxiv ， CV 61k 1:42

目录

1. Generative Adversarial Networks in Human Emotion Synthesis:A Review [PDF] 摘要

2. Data Agnostic Filter Gating for Efficient Deep Networks [PDF] 摘要

3. Road Damage Detection and Classification with Detectron2 and Faster R-CNN [PDF] 摘要

4. Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection [PDF] 摘要

5. Real-time Tropical Cyclone Intensity Estimation by Handling Temporally Heterogeneous Satellite Data [PDF] 摘要

6. Object Hider: Adversarial Patch Attack Against Object Detectors [PDF] 摘要

7. Leveraging Visual Question Answering to Improve Text-to-Image Synthesis [PDF] 摘要

8. MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis [PDF] 摘要

9. Multimodal End-to-End Learning for Autonomous Steering in Adverse Road and Weather Conditions [PDF] 摘要

10. Transferable Universal Adversarial Perturbations Using Generative Models [PDF] 摘要

11. Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation [PDF] 摘要

12. Micro Stripes Analyses for Iris Presentation Attack Detection [PDF] 摘要

13. Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets [PDF] 摘要

14. Cycle-Contrast for Self-Supervised Video Representation Learning [PDF] 摘要

15. AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem? [PDF] 摘要

16. SFU-Store-Nav: A Multimodal Dataset for Indoor Human Navigation [PDF] 摘要

17. Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation [PDF] 摘要

18. ElderSim: A Synthetic Data Generation Platform for Human Action Recognition in Eldercare Applications [PDF] 摘要

19. MultiMix: Sparingly Supervised, Extreme Multitask Learning From Medical Images [PDF] 摘要

20. Differentiable Channel Pruning Search [PDF] 摘要

21. CompRess: Self-Supervised Learning by Compressing Representations [PDF] 摘要

22. Quantified Facial Temporal-Expressiveness Dynamics for Affect Analysis [PDF] 摘要

23. Deformable Convolutional LSTM for Human Body Emotion Recognition [PDF] 摘要

24. Stereo Frustums: A Siamese Pipeline for 3D Object Detection [PDF] 摘要

25. Nested Grassmanns for Dimensionality Reduction [PDF] 摘要

26. Contour Integration using Graph-Cut and Non-Classical Receptive Field [PDF] 摘要

27. Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning [PDF] 摘要

28. Perception for Autonomous Systems (PAZ) [PDF] 摘要

29. Forgery Blind Inspection for Detecting Manipulations of Gel Electrophoresis Images [PDF] 摘要

30. Attribution Preservation in Network Compression for Reliable Network Interpretation [PDF] 摘要

31. Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases [PDF] 摘要

32. Generative Tomography Reconstruction [PDF] 摘要

33. Medical Deep Learning -- A systematic Meta-Review [PDF] 摘要

34. Deep Manifold Computing and Visualization [PDF] 摘要

35. Large-Scale MIDI-based Composer Classification [PDF] 摘要

36. Classification Beats Regression: Counting of Cells from Greyscale Microscopic Images based on Annotation-free Training Samples [PDF] 摘要

37. Scaling Laws for Autoregressive Generative Modeling [PDF] 摘要

38. Unsupervised Domain Adaptation for Visual Navigation [PDF] 摘要

39. Neural Architecture Search of SPD Manifold Networks [PDF] 摘要

阅读全文 »