【arxiv论文】 Computation and Language 2020-05-21

发表于 2020-05-21 分类于 arxiv ， CL 36k 1:01

目录

1. Sentence level estimation of psycholinguistic norms using joint multidimensional annotations [PDF] 摘要

2. BlaBla: Linguistic Feature Extraction for Clinical Analysis in Multiple Languages [PDF] 摘要

3. Applying the Transformer to Character-level Transduction [PDF] 摘要

4. BERTweet: A pre-trained language model for English Tweets [PDF] 摘要

5. Examining the State-of-the-Art in News Timeline Summarization [PDF] 摘要

6. A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portal [PDF] 摘要

7. Enhancing Word Embeddings with Knowledge Extracted from Lexical Resources [PDF] 摘要

8. Leveraging Graph to Improve Abstractive Multi-Document Summarization [PDF] 摘要

9. GM-CTSC at SemEval-2020 Task 1: Gaussian Mixtures Cross Temporal Similarity Clustering [PDF] 摘要

10. Positive emotions help rank negative reviews in e-commerce [PDF] 摘要

11. Modelling Grocery Retail Topic Distributions: Evaluation, Interpretability and Stability [PDF] 摘要

12. A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition [PDF] 摘要

13. Investigation of Large-Margin Softmax in Neural Language Modeling [PDF] 摘要

14. On embedding Lambek calculus into commutative categorial grammars [PDF] 摘要

15. Early Stage LM Integration Using Local and Global Log-Linear Combination [PDF] 摘要

16. Creative Artificial Intelligence -- Algorithms vs. humans in an incentivized writing competition [PDF] 摘要

17. Relative Positional Encoding for Speech Recognition and Direct Translation [PDF] 摘要

18. End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors [PDF] 摘要

19. A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition [PDF] 摘要

20. PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASR [PDF] 摘要

21. A Computational Analysis of Polarization on Indian and Pakistani Social Media [PDF] 摘要

22. GLEAKE: Global and Local Embedding Automatic Keyphrase Extraction [PDF] 摘要

23. Exploring Transformers for Large-Scale Speech Recognition [PDF] 摘要

24. Embeddings-Based Clustering for Target Specific Stances: The Case of a Polarized Turkey [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-20

发表于 2020-05-20 分类于 arxiv ， CV 76k 2:06

目录

1. Focus on defocus: bridging the synthetic to real domain gap for depth estimation [PDF] 摘要

2. CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks [PDF] 摘要

3. Ultrasound Video Summarization using Deep Reinforcement Learning [PDF] 摘要

4. Differentiable Mapping Networks: Learning Structured Map Representations for Sparse Visual Localization [PDF] 摘要

5. Toward Automated Classroom Observation: Multimodal Machine Learning to Estimate CLASS Positive Climate and Negative Climate [PDF] 摘要

6. RoadText-1K: Text Detection & Recognition Dataset for Driving Videos [PDF] 摘要

7. Built Infrastructure Monitoring and Inspection Using UAVs and Vision-based Algorithms [PDF] 摘要

8. Self-supervised Transfer Learning for Instance Segmentation through Physical Interaction [PDF] 摘要

9. MaskFace: multi-task face and landmark detector [PDF] 摘要

10. Uncertainty Estimation in Deep 2D Echocardiography Segmentation [PDF] 摘要

11. Localizing Firearm Carriers by Identifying Human-Object Pairs [PDF] 摘要

12. Patch Attack for Automatic Check-out [PDF] 摘要

13. On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law [PDF] 摘要

14. An Auto-Context Deformable Registration Network for Infant Brain MRI [PDF] 摘要

15. Holistic Parameteric Reconstruction of Building Models from Point Clouds [PDF] 摘要

16. Deep Learning Guided Building Reconstruction from Satellite Imagery-derived Point Clouds [PDF] 摘要

17. Retrieving and Highlighting Action with Spatiotemporal Reference [PDF] 摘要

18. MOTS: Multiple Object Tracking for General Categories Based On Few-Shot Method [PDF] 摘要

19. Learning from a Lightweight Teacher for Efficient Knowledge Distillation [PDF] 摘要

20. Adversarial Attacks for Embodied Agents [PDF] 摘要

21. Sketch-BERT: Learning Sketch Bidirectional Encoder Representation from Transformers by Self-supervised Learning of Sketch Gestalt [PDF] 摘要

22. Associating Multi-Scale Receptive Fields for Fine-grained Recognition [PDF] 摘要

23. Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural Networks [PDF] 摘要

24. Domain Adaptive Relational Reasoning for 3D Multi-Organ Segmentation [PDF] 摘要

25. Two-View Fine-grained Classification of Plant Species [PDF] 摘要

26. Cross-filter compression for CNN inference acceleration [PDF] 摘要

27. Efficient Image Gallery Representations at Scale Through Multi-Task Learning [PDF] 摘要

28. A Novel Technique Combining Image Processing, Plant Development Properties, and the Hungarian Algorithm, to Improve Leaf Detection in Maize [PDF] 摘要

29. Patch based Colour Transfer using SIFT Flow [PDF] 摘要

30. U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection [PDF] 摘要

31. Identifying Statistical Bias in Dataset Replication [PDF] 摘要

32. Advances in Computer Vision in Gastric Cancer: Potential Efficient Tools for Diagnosis [PDF] 摘要

33. The Skincare project, an interactive deep learning system for differential diagnosis of malignant skin lesions. Technical Report [PDF] 摘要

34. hidden markov random fields and cuckoo search method for medical image segmentation [PDF] 摘要

35. Learning to segment clustered amoeboid cells from brightfield microscopy via multi-task learning with adaptive weight selection [PDF] 摘要

36. AdaptiveWeighted Attention Network with Camera Spectral Sensitivity Prior for Spectral Reconstruction from RGB Images [PDF] 摘要

37. Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models [PDF] 摘要

38. Assertion Detection in Multi-Label Clinical Text using Scope Localization [PDF] 摘要

39. Structural Residual Learning for Single Image Rain Removal [PDF] 摘要

40. A Self-ensembling Framework for Semi-supervised Knee Osteoarthritis Localization and Classification with Dual-Consistency [PDF] 摘要

41. Regularization Methods for Generative Adversarial Networks: An Overview of Recent Studies [PDF] 摘要

42. A New Validity Index for Fuzzy-Possibilistic C-Means Clustering [PDF] 摘要

43. Improve robustness of DNN for ECG signal classification:a noise-to-signal ratio perspective [PDF] 摘要

44. An Artificial-intelligence/Statistics Solution to Quantify Material Distortion for Thermal Compensation in Additive Manufacturing [PDF] 摘要

45. Translating Video Recordings of Mobile App Usages into Replayable Scenarios [PDF] 摘要

46. On the effectiveness of GAN generated cardiac MRIs for segmentation [PDF] 摘要

47. Saving the Sonorine: Audio Recovery Using Image Processing and Computer Vision [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-05-20

发表于 2020-05-20 分类于 arxiv ， CL 46k 1:17

目录

1. A Recipe for Creating Multimodal Aligned Datasets for Sequential Tasks [PDF] 摘要

2. Comparing Transformers and RNNs on predicting human sentence processing data [PDF] 摘要

3. Functorial Language Games for Question Answering [PDF] 摘要

4. Embeddings as representation for symbolic music [PDF] 摘要

5. Closing the Gap: Joint De-Identification and Concept Extraction in the Clinical Domain [PDF] 摘要

6. Adversarial Alignment of Multilingual Models for Extracting Temporal Expressions from Text [PDF] 摘要

7. On the Choice of Auxiliary Languages for Improved Sequence Tagging [PDF] 摘要

8. Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text [PDF] 摘要

9. Staying True to Your Word: (How) Can Attention Become Explanation? [PDF] 摘要

10. Matching Questions and Answers in Dialogues from Online Forums [PDF] 摘要

11. Improving Accent Conversion with Reference Encoder and End-To-End Text-To-Speech [PDF] 摘要

12. Iterative Pseudo-Labeling for Speech Recognition [PDF] 摘要

13. Cross-lingual Transfer Learning for Dialogue Act Recognition [PDF] 摘要

14. NEJM-enzh: A Parallel Corpus for English-Chinese Translation in the Biomedical Domain [PDF] 摘要

15. Neural Generation of Dialogue Response Timings [PDF] 摘要

16. GPT-too: A language-model-first approach for AMR-to-text generation [PDF] 摘要

17. Contextual Embeddings: When Are They Worth It? [PDF] 摘要

18. (Re)construing Meaning in NLP [PDF] 摘要

19. Are All Languages Created Equal in Multilingual BERT? [PDF] 摘要

20. P-SIF: Document Embeddings Using Partition Averaging [PDF] 摘要

21. Question-Driven Summarization of Answers to Consumer Health Questions [PDF] 摘要

22. Arabic Offensive Language Detection Using Machine Learning and Ensemble Machine Learning Approaches [PDF] 摘要

23. Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge [PDF] 摘要

24. Enhancing Monotonic Multihead Attention for Streaming ASR [PDF] 摘要

25. Investigations on Phoneme-Based End-To-End Speech Recognition [PDF] 摘要

26. ISeeU2: Visually Interpretable ICU mortality prediction using deep learning and free-text medical notes [PDF] 摘要

27. Bayesian Subspace HMM for the Zerospeech 2020 Challenge [PDF] 摘要

28. Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech Recognition [PDF] 摘要

29. Assertion Detection in Multi-Label Clinical Text using Scope Localization [PDF] 摘要

30. The Effect of Moderation on Online Mental Health Conversations [PDF] 摘要

31. Table Search Using a Deep Contextualized Language Model [PDF] 摘要

32. Quantifying the Uncertainty of Precision Estimates for Rule based Text Classifiers [PDF] 摘要

33. Retrieving and Highlighting Action with Spatiotemporal Reference [PDF] 摘要

34. Fast, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces [PDF] 摘要

35. Weak-Attention Suppression For Transformer Based Speech Recognition [PDF] 摘要

36. On the Power of Unambiguity in Büchi Complementation [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-19

发表于 2020-05-19 分类于 arxiv ， CV 140k 3:54

目录

1. Joint Multi-Dimension Pruning [PDF] 摘要

2. Portrait Shadow Manipulation [PDF] 摘要

3. Generative Tweening: Long-term Inbetweening of 3D Human Motions [PDF] 摘要

4. MMFashion: An Open-Source Toolbox for Visual Fashion Analysis [PDF] 摘要

5. Visual Memorability for Robotic Interestingness Prediction via Unsupervised Online Learning [PDF] 摘要

6. Hierarchical and Efficient Learning for Person Re-Identification [PDF] 摘要

7. Niose-Sampling Cross Entropy Loss: Improving Disparity Regression Via Cost Volume Aware Regularizer [PDF] 摘要

8. Classification of Spam Emails through Hierarchical Clustering and Supervised Learning [PDF] 摘要

9. A Statistical Story of Visual Illusions [PDF] 摘要

10. Evaluating Performance of an Adult Pornography Classifier for Child Sexual Abuse Detection [PDF] 摘要

11. Towards Better Graph Representation: Two-Branch Collaborative Graph Neural Networks for Multimodal Marketing Intention Detection [PDF] 摘要

12. A Biologically Inspired Feature Enhancement Framework for Zero-Shot Learning [PDF] 摘要

13. A global method to identify trees inside and outside of forests with medium-resolution satellite imagery [PDF] 摘要

14. Development of a New Image-to-text Conversion System for Pashto, Farsi and Traditional Chinese [PDF] 摘要

15. A Detailed Look At CNN-based Approaches In Facial Landmark Detection [PDF] 摘要

16. Preterm infants' pose estimation with spatio-temporal features [PDF] 摘要

17. Character Matters: Video Story Understanding with Character-Aware Relations [PDF] 摘要

18. Multi-Task Learning in Histo-pathology for Widely Generalizable Model [PDF] 摘要

19. Intracranial Hemorrhage Detection Using Neural Network Based Methods With Federated Learning [PDF] 摘要

20. Atom Search Optimization with Simulated Annealing -- a Hybrid Metaheuristic Approach for Feature Selection [PDF] 摘要

21. Deep Learning Based Vehicle Tracking System Using License Plate Detection And Recognition [PDF] 摘要

22. End-to-End Lane Marker Detection via Row-wise Classification [PDF] 摘要

23. Supervision and Source Domain Impact on Representation Learning: A Histopathology Case Study [PDF] 摘要

24. Synthetic Image Augmentation for Damage Region Segmentation using Conditional GAN with Structure Edge [PDF] 摘要

25. A Spontaneous Driver Emotion Facial Expression (DEFE) Dataset for Intelligent Vehicles [PDF] 摘要

26. A model-based Gait Recognition Method based on Gait Graph Convolutional Networks and Joints Relationship Pyramid Mapping [PDF] 摘要

27. Learn Class Hierarchy using Convolutional Neural Networks [PDF] 摘要

28. Decoder Modulation for Indoor Depth Completion [PDF] 摘要

29. End-to-End Lip Synchronisation [PDF] 摘要

30. DDD20 End-to-End Event Camera Driving Dataset: Fusing Frames and Events with Deep Learning for Improved Steering Prediction [PDF] 摘要

31. Omni-supervised Facial Expression Recognition: A Simple Baseline [PDF] 摘要

32. Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction [PDF] 摘要

33. VecQ: Minimal Loss DNN Model Compression With Vectorized Weight Quantization [PDF] 摘要

34. Context-aware and Scale-insensitive Temporal Repetition Counting [PDF] 摘要

35. Feature Transformation Ensemble Model with Batch Spectral Regularization for Cross-Domain Few-Shot Classification [PDF] 摘要

36. Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels [PDF] 摘要

37. Cross-Task Transfer for Multimodal Aerial Scene Recognition [PDF] 摘要

38. Single-sample writers -- "Document Filter" and their impacts on writer identification [PDF] 摘要

39. T-VSE: Transformer-Based Visual Semantic Embedding [PDF] 摘要

40. Detecting Forged Facial Videos using convolutional neural network [PDF] 摘要

41. Facial Action Unit Detection using 3D Facial Landmarks [PDF] 摘要

42. Impact of multiple modalities on emotion recognition: investigation into 3d facial landmarks, action units, and physiological data [PDF] 摘要

43. Subject Identification Across Large Expression Variations Using 3D Facial Landmarks [PDF] 摘要

44. A Survey on Unknown Presentation Attack Detection for Fingerprint [PDF] 摘要

45. AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction [PDF] 摘要

46. A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer [PDF] 摘要

47. FuCiTNet: Improving the generalization of deep learning networks by the fusion of learned class-inherent transformations [PDF] 摘要

48. Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation [PDF] 摘要

49. Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis [PDF] 摘要

50. Hyperspectral Image Classification Based on Sparse Modeling of Spectral Blocks [PDF] 摘要

51. Co-occurrence Based Texture Synthesis [PDF] 摘要

52. Neural Networks for Fashion Image Classification and Visual Search [PDF] 摘要

53. FA-GANs: Facial Attractiveness Enhancement with Generative Adversarial Networks on Frontal Faces [PDF] 摘要

54. Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator [PDF] 摘要

55. High-dimensional Convolutional Networks for Geometric Pattern Recognition [PDF] 摘要

56. Train in Germany, Test in The USA: Making 3D Object Detectors Generalize [PDF] 摘要

57. VPR-Bench: An Open-Source Visual Place Recognition Evaluation Framework with Quantifiable Viewpoint and Appearance Change [PDF] 摘要

58. From Boundaries to Bumps: when closed (extremal) contours are critical [PDF] 摘要

59. Mutual Information Maximization for Robust Plannable Representations [PDF] 摘要

60. Analytic Signal Phase in $N-D$ by Linear Symmetry Tensor--fingerprint modeling [PDF] 摘要

61. Single-Stage Semantic Segmentation from Image Labels [PDF] 摘要

62. Universal Adversarial Perturbations: A Survey [PDF] 摘要

63. A Deep Learning based Wearable Healthcare IoT Device for AI-enabled Hearing Assistance Automation [PDF] 摘要

64. Visual Relationship Detection using Scene Graphs: A Survey [PDF] 摘要

65. Towards in-store multi-person tracking using head detection and track heatmaps [PDF] 摘要

66. Deep Lighting Environment Map Estimation from Spherical Panoramas [PDF] 摘要

67. Non-Linearities Improve OrigiNet based on Active Imaging for Micro Expression Recognition [PDF] 摘要

68. JNCD-Based Perceptual Compression of RGB 4:4:4 Image Data [PDF] 摘要

69. Deep feature fusion for self-supervised monocular depth prediction [PDF] 摘要

70. Attribute2Font: Creating Fonts You Want From Attributes [PDF] 摘要

71. COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification [PDF] 摘要

72. Partial Domain Adaptation Using Graph Convolutional Networks [PDF] 摘要

73. FuSSI-Net: Fusion of Spatio-temporal Skeletons for Intention Prediction Network [PDF] 摘要

74. WW-Nets: Dual Neural Networks for Object Detection [PDF] 摘要

75. Transformation Based Deep Anomaly Detection in Astronomical Images [PDF] 摘要

76. C3VQG: Category Consistent Cyclic Visual Question Generation [PDF] 摘要

77. Disentangling in Latent Space by Harnessing a Pretrained Generator [PDF] 摘要

78. Semantic Photo Manipulation with a Generative Image Prior [PDF] 摘要

79. Deep Snow: Synthesizing Remote Sensing Imagery with Generative Adversarial Nets [PDF] 摘要

80. Deep Implicit Volume Compression [PDF] 摘要

81. Learning Spatial-Spectral Prior for Super-Resolution of Hyperspectral Imagery [PDF] 摘要

82. Improving Named Entity Recognition in Tor Darknet with Local Distance Neighbor Feature [PDF] 摘要

83. Building BROOK: A Multi-modal and Facial Video Database for Human-Vehicle Interaction Research [PDF] 摘要

84. Universalization of any adversarial attack using very few test examples [PDF] 摘要

85. Learning to Model and Calibrate Optics via a Differentiable Wave Optics Simulator [PDF] 摘要

86. Bayesian convolutional neural network based MRI brain extraction on nonhuman primates [PDF] 摘要

87. Deep Convolutional Sparse Coding Networks for Image Fusion [PDF] 摘要

88. Deep Learning and Bayesian Deep Learning Based Gender Prediction in Multi-Scale Brain Functional Connectivity [PDF] 摘要

89. Improving Robustness using Joint Attention Network For Detecting Retinal Degeneration From Optical Coherence Tomography Images [PDF] 摘要

90. Various Total Variation for Snapshot Video Compressive Imaging [PDF] 摘要

91. Extreme Low-Light Imaging with Multi-granulation Cooperative Networks [PDF] 摘要

92. Revisiting Agglomerative Clustering [PDF] 摘要

93. Multi-level Feature Fusion-based CNN for Local Climate Zone Classification from Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset [PDF] 摘要

94. The Power of Triply Complementary Priors for Image Compressive Sensing [PDF] 摘要

95. Multi-scale Grouped Dense Network for VVC Intra Coding [PDF] 摘要

96. Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation [PDF] 摘要

97. A Learning-from-noise Dilated Wide Activation Network for denoising Arterial Spin Labeling (ASL) Perfusion Images [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-05-19

发表于 2020-05-19 分类于 arxiv ， CL 113k 3:09

目录

1. Reconstructing Maps from Text [PDF] 摘要

2. Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations [PDF] 摘要

3. Grammatical gender associations outweigh topical gender bias in crosslinguistic word embeddings [PDF] 摘要

4. Inflecting when there's no majority: Limitations of encoder-decoder neural networks as cognitive models for German plurals [PDF] 摘要

5. Interaction Matching for Long-Tail Multi-Label Classification [PDF] 摘要

6. Corpus of Chinese Dynastic Histories: Gender Analysis over Two Millennia [PDF] 摘要

7. Improving Named Entity Recognition in Tor Darknet with Local Distance Neighbor Feature [PDF] 摘要

8. The presence of occupational structure in online texts based on word embedding NLP models [PDF] 摘要

9. Efficient Wait-k Models for Simultaneous Machine Translation [PDF] 摘要

10. SemEval-2020 Task 5: Detecting Counterfactuals by Disambiguation [PDF] 摘要

11. Towards Question Format Independent Numerical Reasoning: A Set of Prerequisite Tasks [PDF] 摘要

12. Text Classification with Few Examples using Controlled Generalization [PDF] 摘要

13. Syntax-guided Controlled Generation of Paraphrases [PDF] 摘要

14. MixingBoard: a Knowledgeable Stylized Integrated Text Generation Platform [PDF] 摘要

15. Cross-Lingual Word Embeddings for Turkic Languages [PDF] 摘要

16. Context-Based Quotation Recommendation [PDF] 摘要

17. TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data [PDF] 摘要

18. Support-BERT: Predicting Quality of Question-Answer Pairs in MSDN using Deep Bidirectional Transformer [PDF] 摘要

19. LiSSS: A toy corpus of Literary Spanish Sentences Sentiment for Emotions Detection [PDF] 摘要

20. Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillation [PDF] 摘要

21. Building a Hebrew Semantic Role Labeling Lexical Resource from Parallel Movie Subtitles [PDF] 摘要

22. How much complexity does an RNN architecture need to learn syntax-sensitive dependencies? [PDF] 摘要

23. Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce [PDF] 摘要

24. Multi-modal Automated Speech Scoring using Attention Fusion [PDF] 摘要

25. IMoJIE: Iterative Memory-Based Joint Open Information Extraction [PDF] 摘要

26. Encodings of Source Syntax: Similarities in NMT Representations Across Target Languages [PDF] 摘要

27. Adversarial Training for Commonsense Inference [PDF] 摘要

28. Semi-Automating Knowledge Base Construction for Cancer Genetics [PDF] 摘要

29. RPD: A Distance Function Between Word Embeddings [PDF] 摘要

30. Learning Probabilistic Sentence Representations from Paraphrases [PDF] 摘要

31. Layer-Wise Cross-View Decoding for Sequence-to-Sequence Learning [PDF] 摘要

32. Recurrent Chunking Mechanisms for Long-Text Machine Reading Comprehensio [PDF] 摘要

33. IntelliCode Compose: Code Generation Using Transformer [PDF] 摘要

34. A Text Reassembling Approach to NaturalLanguage Generation [PDF] 摘要

35. Unsupervised Embedding-based Detection of Lexical Semantic Changes [PDF] 摘要

36. Logical Inferences with Comparatives and Generalized Quantifiers [PDF] 摘要

37. ApplicaAI at SemEval-2020 Task 11: On RoBERTa-CRF, Span CLS and Whether Self-Training Helps Them [PDF] 摘要

38. Sequential Sentence Matching Network for Multi-turn Response Selection in Retrieval-based Chatbots [PDF] 摘要

39. Integrating Semantic and Structural Information with Graph Convolutional Network for Controversy Detection [PDF] 摘要

40. MicroNet for Efficient Language Modeling [PDF] 摘要

41. Neural Multi-Task Learning for Teacher Question Detection in Online Classrooms [PDF] 摘要

42. KEIS@JUST at SemEval-2020 Task 12: Identifying Multilingual Offensive Tweets Using Weighted Ensemble and Fine-Tuned BERT [PDF] 摘要

43. A Scientific Information Extraction Dataset for Nature Inspired Engineering [PDF] 摘要

44. In Layman's Terms: Semi-Open Relation Extraction from Scientific Texts [PDF] 摘要

45. Uncovering Gender Bias in Media Coverage of Politicians with Machine Learning [PDF] 摘要

46. Critical Impact of Social Networks Infodemic on Defeating Coronavirus COVID-19 Pandemic: Twitter-Based Study and Research Directions [PDF] 摘要

47. Machine learning on Big Data from Twitter to understand public reactions to COVID-19 [PDF] 摘要

48. Conversational Search -- A Report from Dagstuhl Seminar 19461 [PDF] 摘要

49. Design Choices for X-vector Based Speaker Anonymization [PDF] 摘要

50. Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation [PDF] 摘要

51. Audio-visual Multi-channel Recognition of Overlapped Speech [PDF] 摘要

52. Robust Training of Vector Quantized Bottleneck Models [PDF] 摘要

53. Attention-based Transducer for Online Speech Recognition [PDF] 摘要

54. An Effective End-to-End Modeling Approach for Mispronunciation Detection [PDF] 摘要

55. The NTNU System at the Interspeech 2020 Non-Native Children's Speech ASR Challenge [PDF] 摘要

56. Content analysis of Persian/Farsi Tweets during COVID-19 pandemic in Iran using NLP [PDF] 摘要

57. Vector-Quantized Autoregressive Predictive Coding [PDF] 摘要

58. Fixed Point Semantics for Stream Reasoning [PDF] 摘要

59. Wake Word Detection with Alignment-Free Lattice-Free MMI [PDF] 摘要

60. A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer [PDF] 摘要

61. On the Combined Use of Extrinsic Semantic Resources for Medical Information Search [PDF] 摘要

62. Dual Learning: Theoretical Study and an Algorithmic Extension [PDF] 摘要

63. #Coronavirus or #Chinesevirus?!: Understanding the negative sentiment reflected in Tweets with racist hashtags across the development of COVID-19 [PDF] 摘要

64. That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages [PDF] 摘要

65. Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models [PDF] 摘要

66. Streaming Transformer-based Acoustic Models Using Self-attention with Augmented Memory [PDF] 摘要

67. Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation [PDF] 摘要

68. AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition [PDF] 摘要

69. Reducing Spelling Inconsistencies in Code-Switching ASR using Contextualized CTC Loss [PDF] 摘要

70. Spike-Triggered Non-Autoregressive Transformer for End-to-End Speech Recognition [PDF] 摘要

71. Oscillating Statistical Moments for Speech Polarity Detection [PDF] 摘要

72. Glottal Source Estimation using an Automatic Chirp Decomposition [PDF] 摘要

73. Large scale weakly and semi-supervised learning for low-resource video ASR [PDF] 摘要

74. Speaker Re-identification with Speaker Dependent Speech Enhancement [PDF] 摘要

75. Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification [PDF] 摘要

76. Feature Fusion Strategies for End-to-End Evaluation of Cognitive Behavior Therapy Sessions [PDF] 摘要

77. JDI-T: Jointly trained Duration Informed Transformer for Text-To-Speech without Explicit Alignment [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-18

发表于 2020-05-18 分类于 arxiv ， CV 54k 1:30

目录

1. Optimizing Neural Architecture Search using Limited GPU Time in a Dynamic Search Space: A Gene Expression Programming Approach [PDF] 摘要

2. Guided interactive image segmentation using machine learning and color based data set clustering [PDF] 摘要

3. ResMoNet: A Residual Mobile-based Network for Facial Emotion Recognition in Resource-Limited Systems [PDF] 摘要

4. HNAS: Hierarchical Neural Architecture Search on Mobile Devices [PDF] 摘要

5. Temperate Fish Detection and Classification: a Deep Learning based Approach [PDF] 摘要

6. History for Visual Dialog: Do we really need it? [PDF] 摘要

7. Convex Shape Prior for Deep Neural Convolution Network based Eye Fundus Images Segmentation [PDF] 摘要

8. PrimiTect: Fast Continuous Hough Voting for Primitive Detection [PDF] 摘要

9. A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection [PDF] 摘要

10. Persistent Map Saving for Visual Localization for Autonomous Vehicles: An ORB-SLAM Extension [PDF] 摘要

11. Exploring the Capabilities and Limits of 3D Monocular Object Detection -- A Study on Simulation and Real World Data [PDF] 摘要

12. Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Model [PDF] 摘要

13. Resisting the Distracting-factors in Pedestrian Detection [PDF] 摘要

14. ViTAA: Visual-Textual Attributes Alignment in Person Search by Natural Language [PDF] 摘要

15. Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models [PDF] 摘要

16. Investigating Bias in Deep Face Analysis: The KANFace Dataset and Empirical Study [PDF] 摘要

17. DeepFaceFlow: In-the-wild Dense 3D Facial Motion Estimation [PDF] 摘要

18. Taskology: Utilizing Task Relations at Scale [PDF] 摘要

19. SUPER: A Novel Lane Detection System [PDF] 摘要

20. Bi3D: Stereo Depth Estimation via Binary Classifications [PDF] 摘要

21. Direction-aware Residual Network for Road Extraction in VHR Remote Sensing Images [PDF] 摘要

22. Evolved Explainable Classifications for Lymph Node Metastases [PDF] 摘要

23. Small-brain neural networks rapidly solve inverse problems with vortex Fourier encoders [PDF] 摘要

24. Grounding Language in Play [PDF] 摘要

25. 3D deformable registration of longitudinal abdominopelvic CT images using unsupervised deep learning [PDF] 摘要

26. Enhancing Perceptual Loss with Adversarial Feature Matching for Super-Resolution [PDF] 摘要

27. TripletUNet: Multi-Task U-Net with Online Voxel-Wise Learning for Precise CT Prostate Segmentation [PDF] 摘要

28. Near-duplicate video detection featuring coupled temporal and perceptual visual structures and logical inference based matching [PDF] 摘要

29. Visual Perception Model for Rapid and Adaptive Low-light Image Enhancement [PDF] 摘要

30. SAGE: Sequential Attribute Generator for Analyzing Glioblastomas using Limited Dataset [PDF] 摘要

31. Cycle-Consistent Adversarial Networks for Realistic Pervasive Change Generation in Remote Sensing Imagery [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-05-18

发表于 2020-05-18 分类于 arxiv ， CL 36k 1:01

目录

1. An Evaluation of Recent Neural Sequence Tagging Models in Turkish Named Entity Recognition [PDF] 摘要

2. Movement Pruning: Adaptive Sparsity by Fine-Tuning [PDF] 摘要

3. Recent Advances in SQL Query Generation: A Survey [PDF] 摘要

4. Analyzing Temporal Relationships between Trending Terms on Twitter and Urban Dictionary Activity [PDF] 摘要

5. Challenges in Emotion Style Transfer: An Exploration with a Lexical Substitution Pipeline [PDF] 摘要

6. Neural Entity Linking on Technical Service Tickets [PDF] 摘要

7. Parallel Data Augmentation for Formality Style Transfer [PDF] 摘要

8. Corpus and Models for Lemmatisation and POS-tagging of Classical French Theatre [PDF] 摘要

9. COVID-Twitter-BERT: A Natural Language Processing Model to Analyse COVID-19 Content on Twitter [PDF] 摘要

10. Adaptive Transformers for Learning Multimodal Representations [PDF] 摘要

11. Cross-lingual Transfer of Twitter Sentiment Models Using a Common Vector Space [PDF] 摘要

12. Spelling Error Correction with Soft-Masked BERT [PDF] 摘要

13. Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model [PDF] 摘要

14. Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation [PDF] 摘要

15. A chatbot architecture for promoting youth resilience [PDF] 摘要

16. OSACT4 Shared Task on Offensive Language Detection: Intensive Preprocessing-Based Approach [PDF] 摘要

17. VirAAL: Virtual Adversarial Active Learning [PDF] 摘要

18. A pre-training technique to localize medical BERT and enhance BioBERT [PDF] 摘要

19. Benchmarking neural embeddings for link prediction in knowledge graphs under semantic and structural changes [PDF] 摘要

20. Grounding Language in Play [PDF] 摘要

21. Finding Experts in Transformer Models [PDF] 摘要

22. History for Visual Dialog: Do we really need it? [PDF] 摘要

23. Predicting User Emotional Tone in Mental Disorder Online Communities [PDF] 摘要

24. Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models [PDF] 摘要

25. Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenario [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-15

发表于 2020-05-15 分类于 arxiv ， CV 58k 1:37

目录

1. Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition [PDF] 摘要

2. PENNI: Pruned Kernel Sharing for Efficient CNN Inference [PDF] 摘要

3. Robust On-Manifold Optimization for Uncooperative Space Relative Navigation with a Single Camera [PDF] 摘要

4. Ambient Sound Helps: Audiovisual Crowd Counting in Extreme Conditions [PDF] 摘要

5. Recognition of 26 Degrees of Freedom of Hands Using Model-based approach and Depth-Color Images [PDF] 摘要

6. Reinforced Coloring for End-to-End Instance Segmentation [PDF] 摘要

7. ZynqNet: An FPGA-Accelerated Embedded Convolutional Neural Network [PDF] 摘要

8. A multicenter study on radiomic features from T$_2$-weighted images of a customized MR pelvic phantom setting the basis for robust radiomic models in clinics [PDF] 摘要

9. Detection and Retrieval of Out-of-Distribution Objects in Semantic Segmentation [PDF] 摘要

10. A Semi-Supervised Assessor of Neural Architectures [PDF] 摘要

11. TAM: Temporal Adaptive Module for Video Recognition [PDF] 摘要

12. Large Scale Font Independent Urdu Text Recognition System [PDF] 摘要

13. The Information & Mutual Information Ratio for Counting Image Features and Their Matches [PDF] 摘要

14. Dense-Resolution Network for Point Cloud Classification and Segmentation [PDF] 摘要

15. Domain Conditioned Adaptation Network [PDF] 摘要

16. Exploiting Multi-Layer Grid Maps for Surround-View Semantic Segmentation of Sparse LiDAR Data [PDF] 摘要

17. Flexible Example-based Image Enhancement with Task Adaptive Global Feature Self-Guided Network [PDF] 摘要

18. Structured Query-Based Image Retrieval Using Scene Graphs [PDF] 摘要

19. Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations [PDF] 摘要

20. Pedestrian Action Anticipation using Contextual Feature Fusion in Stacked RNNs [PDF] 摘要

21. Robust Visual Object Tracking with Two-Stream Residual Convolutional Networks [PDF] 摘要

22. 3D Face Anti-spoofing with Factorized Bilinear Coding [PDF] 摘要

23. OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression [PDF] 摘要

24. Bayesian Bits: Unifying Quantization and Pruning [PDF] 摘要

25. FaceFilter: Audio-visual speech separation using still images [PDF] 摘要

26. On Learned Operator Correction [PDF] 摘要

27. Subsampled Fourier Ptychography using Pretrained Invertible and Untrained Network Priors [PDF] 摘要

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

29. Classification of Arrhythmia by Using Deep Learning with 2-D ECG Spectral Image Representation [PDF] 摘要

30. RegQCNET: Deep Quality Control for Image-to-template Brain MRI Registration [PDF] 摘要

31. Low-Dose CT Image Denoising Using Parallel-Clone Networks [PDF] 摘要

32. Enhanced Residual Networks for Context-based Image Outpainting [PDF] 摘要

33. Noise Homogenization via Multi-Channel Wavelet Filtering for High-Fidelity Sample Generation in GANs [PDF] 摘要

34. W-Cell-Net: Multi-frame Interpolation of Cellular Microscopy Videos [PDF] 摘要

35. Detector-SegMentor Network for Skin Lesion Localization and Segmentation [PDF] 摘要

36. Generative Models for Generic Light Field Reconstruction [PDF] 摘要

阅读全文 »