【arxiv论文】 Computation and Language 2020-09-17

发表于 2020-09-17 分类于 arxiv ， CL 62k 1:43

目录

1. Text Generation by Learning from Off-Policy Demonstrations [PDF] 摘要

2. CoDEx: A Comprehensive Knowledge Graph Completion Benchmark [PDF] 摘要

3. Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule [PDF] 摘要

4. GLUCOSE: GeneraLized and COntextualized Story Explanations [PDF] 摘要

5. Multilingual Music Genre Embeddings for Effective Cross-Lingual Music Item Annotation [PDF] 摘要

6. Automated Source Code Generation and Auto-completion Using Deep Learning: Comparing and Discussing Current Language-Model-Related Approaches [PDF] 摘要

7. NABU -- Multilingual Graph-based Neural RDF Verbalizer [PDF] 摘要

8. Leveraging Semantic Parsing for Relation Linking over Knowledge Bases [PDF] 摘要

9. Knowledge Graphs for Multilingual Language Translation and Generation [PDF] 摘要

10. Reasoning about Goals, Steps, and Temporal Ordering with WikiHow [PDF] 摘要

11. Parallel Interactive Networks for Multi-Domain Dialogue State Generation [PDF] 摘要

12. Neural Dialogue State Tracking with Temporally Expressive Networks [PDF] 摘要

13. Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMT [PDF] 摘要

14. UNION: An Unreferenced Metric for Evaluating Open-ended Story Generation [PDF] 摘要

15. Group-wise Contrastive Learning for Neural Dialogue Generation [PDF] 摘要

16. Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction [PDF] 摘要

17. Contextualized Perturbation for Textual Adversarial Attack [PDF] 摘要

18. Are Interpretations Fairly Evaluated? A Definition Driven Pipeline for Post-Hoc Interpretability [PDF] 摘要

19. Graph-to-Sequence Neural Machine Translation [PDF] 摘要

20. Unsupervised Summarization by Jointly Extracting Sentences and Keywords [PDF] 摘要

21. Solomon at SemEval-2020 Task 11: Ensemble Architecture for Fine-Tuned Propaganda Detection in News Articles [PDF] 摘要

22. DDRQA: Dynamic Document Reranking for Open-domain Multi-hop Question Answering [PDF] 摘要

23. Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP [PDF] 摘要

24. Retrofitting Structure-aware Transformer Language Model for End Tasks [PDF] 摘要

25. Tag and Correct: Question aware Open Information Extraction with Two-stage Decoding [PDF] 摘要

26. Asking Complex Questions with Multi-hop Answer-focused Reasoning [PDF] 摘要

27. Arabic Opinion Mining Using a Hybrid Recommender System Approach [PDF] 摘要

28. Grounded Adaptation for Zero-shot Executable Semantic Parsing [PDF] 摘要

29. Pardon the Interruption: An Analysis of Gender and Turn-Taking in U.S. Supreme Court Oral Arguments [PDF] 摘要

30. Multi-span Style Extraction for Generative Reading Comprehension [PDF] 摘要

31. Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction [PDF] 摘要

32. Fast semantic parsing with well-typedness guarantees [PDF] 摘要

33. An information theoretic view on selecting linguistic probes [PDF] 摘要

34. Cascaded Models for Better Fine-Grained Named Entity Recognition [PDF] 摘要

35. Simultaneous Machine Translation with Visual Context [PDF] 摘要

36. Transformer Based Multi-Source Domain Adaptation [PDF] 摘要

37. Deep Learning Approaches for Extracting Adverse Events and Indications of Dietary Supplements from Clinical Text [PDF] 摘要

38. Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News [PDF] 摘要

39. Adoption of Twitter's New Length Limit: Is 280 the New 140? [PDF] 摘要

40. RDF2Vec Light -- A Lightweight Approachfor Knowledge Graph Embeddings [PDF] 摘要

41. CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation [PDF] 摘要

42. Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-09-16

发表于 2020-09-16 分类于 arxiv ， CV 86k 2:23

目录

1. Understanding Deformable Alignment in Video Super-Resolution [PDF] 摘要

2. PointIso: Point Cloud Based Deep Learning Model for Detecting Arbitrary-Precision Peptide Features in LC-MS Map through Attention Based Segmentation [PDF] 摘要

3. 3D_DEN: Open-ended 3D Object Recognition using Dynamically Expandable Networks [PDF] 摘要

4. Switching Gradient Directions for Query-Efficient Black-Box Adversarial Attacks [PDF] 摘要

5. ResNet-like Architecture with Low Hardware Requirements [PDF] 摘要

6. AMRNet: Chips Augmentation in Areial Images Object Detection [PDF] 摘要

7. HGCN-GJS: Hierarchical Graph Convolutional Network with Groupwise Joint Sampling for Trajectory Prediction [PDF] 摘要

8. A Mobile App for Wound Localization using Deep Learning [PDF] 摘要

9. Polyp-artifact relationship analysis using graph inductive learned representations [PDF] 摘要

10. CSI2Image: Image Reconstruction from Channel State Information Using Generative Adversarial Networks [PDF] 摘要

11. Old Photo Restoration via Deep Latent Space Translation [PDF] 摘要

12. TCDesc: Learning Topology Consistent Descriptors for Image Matching [PDF] 摘要

13. SA-Net: A deep spectral analysis network for image clustering [PDF] 摘要

14. FairCVtest Demo: Understanding Bias in Multimodal Learning with a Testbed in Fair Automatic Recruitment [PDF] 摘要

15. Decision-based Universal Adversarial Attack [PDF] 摘要

16. Group-Level Emotion Recognition Using a Unimodal Privacy-Safe Non-Individual Approach [PDF] 摘要

17. Promoting Connectivity of Network-Like Structures by Enforcing Region Separation [PDF] 摘要

18. Optimal Use of Multi-spectral Satellite Data with Convolutional Neural Networks [PDF] 摘要

19. Gravitational Models Explain Shifts on Human Visual Attention [PDF] 摘要

20. 360-Degree Gaze Estimation in the Wild Using Multiple Zoom Scales [PDF] 摘要

21. Multi-scale Attention U-Net (MsAUNet): A Modified U-Net Architecture for Scene Segmentation [PDF] 摘要

22. A Self Contour-based Rotation and Translation-Invariant Transformation for Point Clouds Recognition [PDF] 摘要

23. Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition [PDF] 摘要

24. 3DPVNet: Patch-level 3D Hough Voting Network for 6D Pose Estimation [PDF] 摘要

25. Attention-SLAM: A Visual Monocular SLAM Learning from Human Gaze [PDF] 摘要

26. Leveraging Domain Knowledge using Machine Learning for Image Compression in Internet-of-Things [PDF] 摘要

27. Methods of the Vehicle Re-identification [PDF] 摘要

28. SML: Semantic Meta-learning for Few-shot Semantic Segmentation [PDF] 摘要

29. Data Augmentation and Clustering for Vehicle Make/Model Classification [PDF] 摘要

30. WDRN : A Wavelet Decomposed RelightNet for Image Relighting [PDF] 摘要

31. F3RNet: Full-Resolution Residual Registration Network for Multimodal Image Registration [PDF] 摘要

32. Image Based Artificial Intelligence in Wound Assessment: A Systematic Review [PDF] 摘要

33. Multi-structure bone segmentation in pediatric MR images with combined regularization from shape priors and adversarial network [PDF] 摘要

34. RaLL: End-to-end Radar Localization on Lidar Map Using Differentiable Measurement Model [PDF] 摘要

35. Deep Transparent Prediction through Latent Representation Analysis [PDF] 摘要

36. Light Can Hack Your Face! Black-box Backdoor Attack on Face Recognition Systems [PDF] 摘要

37. Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup [PDF] 摘要

38. AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results [PDF] 摘要

39. Learning a Single Model with a Wide Range of Quality Factors for JPEG Image Artifacts Removal [PDF] 摘要

40. Ensemble learning of diffractive optical networks [PDF] 摘要

41. Deep Reinforcement Learning for Unknown Anomaly Detection [PDF] 摘要

42. Microscope Based HER2 Scoring System [PDF] 摘要

43. Short-term synaptic plasticity optimally models continuous environments [PDF] 摘要

44. Qutrit-inspired Fully Self-supervised Shallow Quantum Learning Network for Brain Tumor Segmentation [PDF] 摘要

45. Simultaneous Denoising and Motion Estimation for Low-dose Gated PET using a Siamese Adversarial Network with Gate-to-Gate Consistency Learning [PDF] 摘要

46. Efficient Transformers: A Survey [PDF] 摘要

47. Hold Tight and Never Let Go: Security of Deep Learning based Automated Lane Centering under Physical-World Attack [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-09-16

发表于 2020-09-16 分类于 arxiv ， CL 39k 1:05

目录

1. Autoregressive Knowledge Distillation through Imitation Learning [PDF] 摘要

2. A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation [PDF] 摘要

3. Lessons Learned from Applying off-the-shelf BERT: There is no SilverBullet [PDF] 摘要

4. Event Presence Prediction Helps Trigger Detection Across Languages [PDF] 摘要

5. Critical Thinking for Language Models [PDF] 摘要

6. Iterative Refinement in the Continuous Space for Non-Autoregressive Neural Machine Translation [PDF] 摘要

7. Multimodal Joint Attribute Prediction and Value Extraction for E-commerce Product [PDF] 摘要

8. Cascaded Semantic and Positional Self-Attention Network for Document Classification [PDF] 摘要

9. Improving Joint Layer RNN based Keyphrase Extraction by Using Syntactical Features [PDF] 摘要

10. It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners [PDF] 摘要

11. Multi-Referenced Training for Dialogue Response Generation [PDF] 摘要

12. MLMLM: Link Prediction with Mean Likelihood Masked Language Model [PDF] 摘要

13. Noisy Self-Knowledge Distillation for Text Summarization [PDF] 摘要

14. Dialogue Response Ranking Training with Large-Scale Human Feedback Data [PDF] 摘要

15. High-order Refining for End-to-end Chinese Semantic Role Labeling [PDF] 摘要

16. Attention-Aware Inference for Neural Abstractive Summarization [PDF] 摘要

17. Current Limitations of Language Models: What You Need is Retrieval [PDF] 摘要

18. Unsupervised Abstractive Dialogue Summarization for Tete-a-Tetes [PDF] 摘要

19. Achieving Real-Time Execution of Transformer-based Large-scale Models on Mobile with Compiler-aware Neural Architecture Optimization [PDF] 摘要

20. MatScIE: An automated tool for the generation of databases of methods and parameters used in the computational materials science literature [PDF] 摘要

21. Using Known Words to Learn More Words: A Distributional Analysis of Child Vocabulary Development [PDF] 摘要

22. WNTRAC: Artificial Intelligence Assisted Tracking of Non-pharmaceutical Interventions Implemented Worldwide for COVID-19 [PDF] 摘要

23. Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models [PDF] 摘要

24. The Devil is the Classifier: Investigating Long Tail Relation Classification with Decoupling Analysis [PDF] 摘要

25. Controllable neural text-to-speech synthesis using intuitive prosodic features [PDF] 摘要

26. Efficient Transformers: A Survey [PDF] 摘要

27. What the Future Brings: Investigating the Impact of Lookahead for Incremental Neural TTS [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-09-15

发表于 2020-09-15 分类于 arxiv ， CV 137k 3:49

目录

1. High-Resolution Deep Image Matting [PDF] 摘要

2. Adaptive Text Recognition through Visual Matching [PDF] 摘要

3. GIA-Net: Global Information Aware Network for Low-light Imaging [PDF] 摘要

4. Collaborative Attention Mechanism for Multi-View Action Recognition [PDF] 摘要

5. Zero-shot Synthesis with Group-Supervised Learning [PDF] 摘要

6. Beyond Weak Perspective for Monocular 3D Human Pose Estimation [PDF] 摘要

7. Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space [PDF] 摘要

8. A Study of Human Gaze Behavior During Visual Crowd Counting [PDF] 摘要

9. Fast Implementation of 4-bit Convolutional Neural Networks for Mobile Devices [PDF] 摘要

10. Unsupervised Domain Adaptation by Uncertain Feature Alignment [PDF] 摘要

11. EfficientSeg: An Efficient Semantic Segmentation Network [PDF] 摘要

12. Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions [PDF] 摘要

13. Adaptive Label Smoothing [PDF] 摘要

14. Completely Self-Supervised Crowd Counting via Distribution Matching [PDF] 摘要

15. Synbols: Probing Learning Algorithms with Synthetic Datasets [PDF] 摘要

16. Adaptive Convolution Kernel for Artificial Neural Networks [PDF] 摘要

17. P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributions [PDF] 摘要

18. 4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving [PDF] 摘要

19. PRAFlow_RVC: Pyramid Recurrent All-Pairs Field Transforms for Optical Flow Estimation in Robust Vision Challenge 2020 [PDF] 摘要

20. DeepWriteSYN: On-Line Handwriting Synthesis via Deep Short-Term Representations [PDF] 摘要

21. Deep intrinsic decomposition trained on surreal scenes yet with realistic light effects [PDF] 摘要

22. AIM 2020 Challenge on Video Extreme Super-Resolution: Methods and Results [PDF] 摘要

23. Unsupervised learning for vascular heterogeneity assessment of glioblastoma based on magnetic resonance imaging: The Hemodynamic Tissue Signature [PDF] 摘要

24. Accurate and Lightweight Image Super-Resolution with Model-Guided Deep Unfolding Network [PDF] 摘要

25. Prior Knowledge about Attributes: Learning a More Effective Potential Space for Zero-Shot Recognition [PDF] 摘要

26. Cascade Network for Self-Supervised Monocular Depth Estimation [PDF] 摘要

27. Residual Learning for Effective joint Demosaicing-Denoising [PDF] 摘要

28. Learning from Multimodal and Multitemporal Earth Observation Data for Building Damage Mapping [PDF] 摘要

29. RelativeNAS: Relative Neural Architecture Search via Slow-Fast Learning [PDF] 摘要

30. 3D Object Detection and Tracking Based on Streaming Data [PDF] 摘要

31. One-bit Supervision for Image Classification [PDF] 摘要

32. GINet: Graph Interaction Network for Scene Parsing [PDF] 摘要

33. SCOUTER: Slot Attention-based Classifier for Explainable Image Recognition [PDF] 摘要

34. Accelerating COVID-19 Differential Diagnosis with Explainable Ultrasound Image Analysis [PDF] 摘要

35. Multi-channel MRI Embedding: An EffectiveStrategy for Enhancement of Human Brain WholeTumor Segmentation [PDF] 摘要

36. Cosine meets Softmax: A tough-to-beat baseline for visual grounding [PDF] 摘要

37. Pairwise-GAN: Pose-based View Synthesis through Pair-Wise Training [PDF] 摘要

38. A Review of Visual Descriptors and Classification Techniques Used in Leaf Species Identification [PDF] 摘要

39. Semantic Segmentation of Surface from Lidar Point Cloud [PDF] 摘要

40. Calibration Venus: An Interactive Camera Calibration Method Based on Search Algorithm and Pose Decomposition [PDF] 摘要

41. Improving Deep Video Compression by Resolution-adaptive Flow Coding [PDF] 摘要

42. SSKD: Self-Supervised Knowledge Distillation for Cross Domain Adaptive Person Re-Identification [PDF] 摘要

43. Semi-supervised dictionary learning with graph regularization and active points [PDF] 摘要

44. Interpretation of smartphone-captured radiographs utilizing a deep learning-based approach [PDF] 摘要

45. Synthesizing brain tumor images and annotations by combining progressive growing GAN and SPADE [PDF] 摘要

46. PolSAR Image Classification Based on Robust Low-Rank Feature Extraction and Markov Random Field [PDF] 摘要

47. Coding Facial Expressions with Gabor Wavelets (IVC Special Issue) [PDF] 摘要

48. Deep Detection for Face Manipulation [PDF] 摘要

49. An approach to human iris recognition using quantitative analysis of image features and machine learning [PDF] 摘要

50. A Unified Approach to Kinship Verification [PDF] 摘要

51. Exploring the Hierarchy in Relation Labels for Scene Graph Generation [PDF] 摘要

52. Map-merging Algorithms for Visual SLAM: Feasibility Study and Empirical Evaluation [PDF] 摘要

53. Learning semantic Image attributes using Image recognition and knowledge graph embeddings [PDF] 摘要

54. Revisiting the Threat Space for Vision-based Keystroke Inference Attacks [PDF] 摘要

55. A CNN Based Approach for the Near-Field Photometric Stereo Problem [PDF] 摘要

56. Micro-Facial Expression Recognition Based on Deep-Rooted Learning Algorithm [PDF] 摘要

57. Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning [PDF] 摘要

58. Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion [PDF] 摘要

59. Multi-Spectral Image Synthesis for Crop/Weed Segmentation in Precision Farming [PDF] 摘要

60. Smoothness Sensor: Adaptive Smoothness-Transition Graph Convolutions for Attributed Graph Clustering [PDF] 摘要

61. Monitoring Spatial Sustainable Development: semi-automated analysis of Satellite and Aerial Images for Energy Transition and Sustainability Indicators [PDF] 摘要

62. Abstractive Information Extraction from Scanned Invoices (AIESI) using End-to-end Sequential Approach [PDF] 摘要

63. Generator Versus Segmentor: Pseudo-healthy Synthesis [PDF] 摘要

64. Short-Term and Long-Term Context Aggregation Network for Video Inpainting [PDF] 摘要

65. YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design [PDF] 摘要

66. RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization [PDF] 摘要

67. AttnGrounder: Talking to Cars with Attention [PDF] 摘要

68. A Progressive Sub-Network Searching Framework for Dynamic Inference [PDF] 摘要

69. Inverse mapping of face GANs [PDF] 摘要

70. KSM: Fast Multiple Task Adaption via Kernel-wise Soft Mask Learning [PDF] 摘要

71. Deep Hiearchical Multi-Label Classification Applied to Chest X-Ray Abnormality Taxonomies [PDF] 摘要

72. 3D Reconstruction and Segmentation of Dissection Photographs for MRI-free Neuropathology [PDF] 摘要

73. Label-Free Segmentation of COVID-19 Lesions in Lung CT [PDF] 摘要

74. Automatic elimination of the pectoral muscle in mammograms based on anatomical features [PDF] 摘要

75. A Multisensory Learning Architecture for Rotation-invariant Object Recognition [PDF] 摘要

76. VC-Net: Deep Volume-Composition Networks for Segmentation and Visualization of Highly Sparse and Noisy Image Data [PDF] 摘要

77. Mathematical Morphology via Category Theory [PDF] 摘要

78. Towards the Quantification of Safety Risks in Deep Neural Networks [PDF] 摘要

79. Extracting Optimal Solution Manifolds using Constrained Neural Optimization [PDF] 摘要

80. Attention Cube Network for Image Restoration [PDF] 摘要

81. How Much Can We Really Trust You? Towards Simple, Interpretable Trust Quantification Metrics for Deep Neural Networks [PDF] 摘要

82. Multi-Channel Potts-Based Reconstruction for Multi-Spectral Computed Tomography [PDF] 摘要

83. Segmentation of Lungs in Chest X-Ray Image Using Generative Adversarial Networks [PDF] 摘要

84. Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-09-15

发表于 2020-09-15 分类于 arxiv ， CL 65k 1:49

目录

1. Hearings and mishearings: decrypting the spoken word [PDF] 摘要

2. At your Command! An Empirical Study on How LaypersonsTeach Robots New Functions [PDF] 摘要

3. Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue [PDF] 摘要

4. EasyASR: A Distributed Machine Learning Platform for End-to-end Automatic Speech Recognition [PDF] 摘要

5. Development of a Dataset and a Deep Learning Baseline Named Entity Recognizer for Three Low Resource Languages: Bhojpuri, Maithili and Magahi [PDF] 摘要

6. Time-Aware Evidence Ranking for Fact-Checking [PDF] 摘要

7. Multi-Hop Fact Checking of Political Claims [PDF] 摘要

8. Analysis and representation of Igbo text document for a text-based system [PDF] 摘要

9. EdinburghNLP at WNUT-2020 Task 2: Leveraging Transformers with Generalized Augmentation for Identifying Informativeness in COVID-19 Tweets [PDF] 摘要

10. Not-NUTs at W-NUT 2020 Task 2: A BERT-based System in Identifying Informative COVID-19 English Tweets [PDF] 摘要

11. Searching for a Search Method: Benchmarking Search Algorithms for Generating NLP Adversarial Examples [PDF] 摘要

12. GeDi: Generative Discriminator Guided Sequence Generation [PDF] 摘要

13. Improving Language Generation with Sentence Coherence Objective [PDF] 摘要

14. QED: A Framework and Dataset for Explanations in Question Answering [PDF] 摘要

15. Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues [PDF] 摘要

16. A Comparison of Two Fluctuation Analyses for Natural Language Clustering Phenomena: Taylor and Ebeling & Neiman Methods [PDF] 摘要

17. Contrastive Triple Extraction with Generative Transformer [PDF] 摘要

18. Can Fine-tuning Pre-trained Models Lead to Perfect NLP? A Study of the Generalizability of Relation Extraction [PDF] 摘要

19. Composing Answer from Multi-spans for Reading Comprehension [PDF] 摘要

20. Identity-Based Patterns in Deep Convolutional Networks: Generative Adversarial Phonology and Reduplication [PDF] 摘要

21. Cluster-Former: Clustering-based Sparse Transformer for Long-Range Dependency Encoding [PDF] 摘要

22. Span-based Semantic Parsing for Compositional Generalization [PDF] 摘要

23. BoostingBERT:Integrating Multi-Class Boosting into BERT for NLP Tasks [PDF] 摘要

24. Pow-Wow: A Dataset and Study on Collaborative Communication in Pommerman [PDF] 摘要

25. Combining Word and Character Vector Representation on Neural Machine Translation [PDF] 摘要

26. Fine-tuning Pre-trained Contextual Embeddings for Citation Content Analysis in Scholarly Publication [PDF] 摘要

27. Improving Machine Reading Comprehension with Contextualized Commonsense Knowledge [PDF] 摘要

28. CIA_NITT at WNUT-2020 Task 2: Classification of COVID-19 Tweets Using Pre-trained Language Models [PDF] 摘要

29. Intent Detection with WikiHow [PDF] 摘要

30. Syntax Role for Neural Semantic Role Labeling [PDF] 摘要

31. Improving Bi-LSTM Performance for Indonesian Sentiment Analysis Using Paragraph Vector [PDF] 摘要

32. Improving Indonesian Text Classification Using Multilingual Language Model [PDF] 摘要

33. Relation Detection for Indonesian Language using Deep Neural Network -- Support Vector Machine [PDF] 摘要

34. Investigating Bi-LSTM and CRF with POS Tag Embedding for Indonesian Named Entity Tagger [PDF] 摘要

35. Coreference Resolution System for Indonesian Text with Mention Pair Method and Singleton Exclusion using Convolutional Neural Network [PDF] 摘要

36. Solving Math Word Problems by Scoring Equations with Recursive Neural Networks [PDF] 摘要

37. UPB at SemEval-2020 Task 6: Pretrained Language Models for DefinitionExtraction [PDF] 摘要

38. Cosine meets Softmax: A tough-to-beat baseline for visual grounding [PDF] 摘要

39. Differentially Private Language Models Benefit from Public Pre-training [PDF] 摘要

40. Exploring the Hierarchy in Relation Labels for Scene Graph Generation [PDF] 摘要

41. Country Image in COVID-19 Pandemic: A Case Study of China [PDF] 摘要

42. An Atlas of Cultural Commonsense for Machine Reasoning [PDF] 摘要

43. Unit Test Case Generation with Transformers [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-09-14

发表于 2020-09-14 分类于 arxiv ， CV 83k 2:18

目录

1. TP-LSD: Tri-Points Based Line Segment Detector [PDF] 摘要

2. MRZ code extraction from visa and passport documents using convolutional neural networks [PDF] 摘要

3. Heterogeneous Domain Generalization via Domain Mixup [PDF] 摘要

4. ODIN: Automated Drift Detection and Recovery in Video Analytics [PDF] 摘要

5. Semi-Supervised Active Learning for COVID-19 Lung Ultrasound Multi-symptom Classification [PDF] 摘要

6. Evaluation of the Robustness of Visual SLAM Methods in Different Environments [PDF] 摘要

7. ZooBuilder: 2D and 3D Pose Estimation for Quadrupeds Using Synthetic Data [PDF] 摘要

8. Automatic cinematography for 360 video [PDF] 摘要

9. Hybrid Space Learning for Language-based Video Retrieval [PDF] 摘要

10. Critical analysis on the reproducibility of visual quality assessment using deep features [PDF] 摘要

11. Meta Learning for Few-Shot One-class Classification [PDF] 摘要

12. The PREVENTION Challenge: How Good Are Humans Predicting Lane Changes? [PDF] 摘要

13. SoFAr: Shortcut-based Fractal Architectures for Binary Convolutional Neural Networks [PDF] 摘要

14. A Density-Aware PointRCNN for 3D Objection Detection in Point Clouds [PDF] 摘要

15. Enabling Image Recognition on Constrained Devices Using Neural Network Pruning and a CycleGAN [PDF] 摘要

16. Unsupervised Partial Point Set Registration via Joint Shape Completion and Registration [PDF] 摘要

17. Attribute-conditioned Layout GAN for Automatic Graphic Design [PDF] 摘要

18. Fairness Matters -- A Data-Driven Framework Towards Fair and High Performing Facial Recognition Systems [PDF] 摘要

19. AFP-SRC: Identification of Antifreeze Proteins Using Sparse Representation Classifier [PDF] 摘要

20. Image Conditioned Keyframe-Based Video Summarization Using Object Detection [PDF] 摘要

21. PiaNet: A pyramid input augmented convolutional neural network for GGO detection in 3D lung CT scans [PDF] 摘要

22. Novel and Effective CNN-Based Binarization for Historically Degraded As-built Drawing Maps [PDF] 摘要

23. Devil's in the Detail: Graph-based Key-point Alignment and Embedding for Person Re-ID [PDF] 摘要

24. Optimizing Convolutional Neural Network Architecture via Information Field [PDF] 摘要

25. Spectral Analysis Network for Deep Representation Learning and Image Clustering [PDF] 摘要

26. An unsupervised deep learning framework via integrated optimization of representation learning and GMM-based modeling [PDF] 摘要

27. Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation [PDF] 摘要

28. HAA500: Human-Centric Atomic Action Dataset with Curated Videos [PDF] 摘要

29. Adversarial Learning for Zero-shot Domain Adaptation [PDF] 摘要

30. Variance Loss: A Confidence-Based Reweighting Strategy for Coarse Semantic Segmentation [PDF] 摘要

31. OCR Graph Features for Manipulation Detection in Documents [PDF] 摘要

32. A new heuristic algorithm for fast k-segmentation [PDF] 摘要

33. Practical Cross-modal Manifold Alignment for Grounded Language [PDF] 摘要

34. Auto-encoders for Track Reconstruction in Drift Chambers for CLAS12 [PDF] 摘要

35. SWP-Leaf NET: a novel multistage approach for plant leaf identification based on deep learning [PDF] 摘要

36. 1st Place Solution to Google Landmark Retrieval 2020 [PDF] 摘要

37. Dynamic Future Net: Diversified Human Motion Generation [PDF] 摘要

38. Bayesian Geodesic Regression onRiemannian Manifolds [PDF] 摘要

39. Efficiently Constructing Adversarial Examples by Feature Watermarking [PDF] 摘要

40. What am I allowed to do here?: Online Learning of Context-Specific Norms by Pepper [PDF] 摘要

41. Emotion-Based End-to-End Matching Between Image and Music in Valence-Arousal Space [PDF] 摘要

42. Data-Level Recombination and Lightweight Fusion Scheme for RGB-D Salient Object Detection [PDF] 摘要

43. Vision at A Glance: Interplay between Fine and Coarse Information Processing Pathways [PDF] 摘要

44. Adversarial score matching and improved sampling for image generation [PDF] 摘要

45. Object Recognition for Economic Development from Daytime Satellite Imagery [PDF] 摘要

46. Embodied Visual Navigation with Automatic Curriculum Learning in Real Environments [PDF] 摘要

47. Phase Sampling Profilometry [PDF] 摘要

48. COVIDNet-CT: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest CT Images [PDF] 摘要

49. Disentangling Neural Architectures and Weights: A Case Study in Supervised Classification [PDF] 摘要

50. Visually Analyzing and Steering Zero Shot Learning [PDF] 摘要

51. Defending Against Multiple and Unforeseen Adversarial Videos [PDF] 摘要

52. Weakly Supervised Content Selection for Improved Image Captioning [PDF] 摘要

53. COVID CT-Net: Predicting Covid-19 From Chest CT Images Using Attentional Convolutional Network [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-09-14

发表于 2020-09-14 分类于 arxiv ， CL 24k 41 分钟

目录

1. Robust Neural Machine Translation: Modeling Orthographic and Interpunctual Variation [PDF] 摘要

2. WOLI at SemEval-2020 Task 12: Arabic Offensive Language Identification on Different Twitter Datasets [PDF] 摘要

3. A Comparison of LSTM and BERT for Small Corpus [PDF] 摘要

4. Deep Learning for Semantic Relations [PDF] 摘要

5. IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding [PDF] 摘要

6. UPB at SemEval-2020 Task 11: Propaganda Detection with Domain-Specific Trained BERT [PDF] 摘要

7. Weakly Supervised Content Selection for Improved Image Captioning [PDF] 摘要

8. Sparsifying Transformer Models with Differentiable Representation Pooling [PDF] 摘要

9. Accelerating Real-Time Question Answering via Question Generation [PDF] 摘要

10. FILTER: An Enhanced Fusion Method for Cross-lingual Language Understanding [PDF] 摘要

11. Rank over Class: The Untapped Potential of Ranking in Natural Language Processing [PDF] 摘要

12. RadLex Normalization in Radiology Reports [PDF] 摘要

13. Dialogue Relation Extraction with Document-level Heterogeneous Graph Attention Networks [PDF] 摘要

14. Narratives and Needs: Analyzing Experiences of Cyclone Amphan Using Twitter Discourse [PDF] 摘要

15. Systematic Generalization on gSCAN with Language Conditioned Embedding [PDF] 摘要

16. RECOApy: Data recording, pre-processing and phonetic transcription for end-to-end speech-based applications [PDF] 摘要

17. Patient Cohort Retrieval using Transformer Language Models [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-09-10

发表于 2020-09-10 分类于 arxiv ， CV 46k 1:16

目录

1. Semi-supervised Medical Image Segmentation through Dual-task Consistency [PDF] 摘要

2. Plant Diseases recognition on images using Convolutional Neural Networks: A Systematic Review [PDF] 摘要

3. HSFM-$Σ$nn: Combining a Feedforward Motion Prediction Network and Covariance Prediction [PDF] 摘要

4. Online trajectory recovery from offline handwritten Japanese kanji characters [PDF] 摘要

5. Unsupervised Part Discovery by Unsupervised Disentanglement [PDF] 摘要

6. Binarized Neural Architecture Search for Efficient Object Recognition [PDF] 摘要

7. Temporal Attribute-Appearance Learning Network for Video-based Person Re-Identification [PDF] 摘要

8. MU-GAN: Facial Attribute Editing based on Multi-attention Mechanism [PDF] 摘要

9. Diversified Mutual Learning for Deep Metric Learning [PDF] 摘要

10. One-shot Text Field Labeling using Attention and Belief Propagation for Structure Information Extraction [PDF] 摘要

11. Real-time Plant Health Assessment Via Implementing Cloud-based Scalable Transfer Learning On AWS DeepLens [PDF] 摘要

12. Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach for Feature Embedding [PDF] 摘要

13. View-consistent 4D Light Field Depth Estimation [PDF] 摘要

14. Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classification [PDF] 摘要

15. Unconstrained Text Detection in Manga: a New Dataset and Baseline [PDF] 摘要

16. Modeling Wildfire Perimeter Evolution using Deep Neural Networks [PDF] 摘要

17. Joint Pose and Shape Estimation of Vehicles from LiDAR Data [PDF] 摘要

18. Towards Unique and Informative Captioning of Images [PDF] 摘要

19. Map-Adaptive Goal-Based Trajectory Prediction [PDF] 摘要

20. not-so-BigGAN: Generating High-Fidelity Images on a Small Compute Budget [PDF] 摘要

21. Cephalogram Synthesis and Landmark Detection in Dental Cone-Beam CT Systems [PDF] 摘要

22. NTGAN: Learning Blind Image Denoising without Clean Reference [PDF] 摘要

23. Small-floating Target Detection in Sea Clutter via Visual Feature Classifying in the Time-Doppler Spectra [PDF] 摘要

24. Revealing Lung Affections from CTs. A Comparative Analysis of Various Deep Learning Approaches for Dealing with Volumetric Data [PDF] 摘要

25. Single Image Super-Resolution for Domain-Specific Ultra-Low Bandwidth Image Transmission [PDF] 摘要

26. Generalizing Complex/Hyper-complex Convolutions to Vector Map Convolutions [PDF] 摘要

27. Learning joint segmentation of tissues and brain lesions from task-specific hetero-modal domain-shifted datasets [PDF] 摘要

28. Fuzzy Unique Image Transformation: Defense Against Adversarial Attacks On Deep COVID-19 Models [PDF] 摘要

29. Tangent Space Based Alternating Projections for Nonnegative Low Rank Matrix Approximation [PDF] 摘要

阅读全文 »