【arxiv论文】 Computation and Language 2020-09-23

发表于 2020-09-23 分类于 arxiv ， CL 39k 1:04

目录

1. Let's Stop Incorrect Comparisons in End-to-end Relation Extraction! [PDF] 摘要

2. AutoRC: Improving BERT Based Relation Classification Models via Architecture Search [PDF] 摘要

3. GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis [PDF] 摘要

4. Context-theoretic Semantics for Natural Language: an Algebraic Framework [PDF] 摘要

5. SUMBT+LaRL: End-to-end Neural Task-oriented Dialog System with Reinforcement Learning [PDF] 摘要

6. CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking [PDF] 摘要

7. Dual Learning for Dialogue State Tracking [PDF] 摘要

8. Logical foundations for hybrid type-logical grammars [PDF] 摘要

9. Global-to-Local Neural Networks for Document-Level Relation Extraction [PDF] 摘要

10. Structured Hierarchical Dialogue Policy with Graph Neural Networks [PDF] 摘要

11. Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management [PDF] 摘要

12. Deep Reinforcement Learning for On-line Dialogue State Tracking [PDF] 摘要

13. PodSumm -- Podcast Audio Summarization [PDF] 摘要

14. Event Coreference Resolution via a Multi-loss Neural Network without Using Argument Information [PDF] 摘要

15. Towards Causal Explanation Detection with Pyramid Salient-Aware Network [PDF] 摘要

16. Constructing interval variables via faceted Rasch measurement and multitask deep learning: a hate speech application [PDF] 摘要

17. ALICE: Active Learning with Contrastive Natural Language Explanations [PDF] 摘要

18. An Empirical Study on Neural Keyphrase Generation [PDF] 摘要

19. The Persian Dependency Treebank Made Universal [PDF] 摘要

20. SSMBA: Self-Supervised Manifold Based Data Augmentation for Improving Out-of-Domain Robustness [PDF] 摘要

21. "When they say weed causes depression, but it's your fav antidepressant": Knowledge-aware Attention Framework for Relationship Extraction [PDF] 摘要

22. A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition Baseline [PDF] 摘要

23. End-to-End Speech Recognition and Disfluency Removal [PDF] 摘要

24. CodeBLEU: a Method for Automatic Evaluation of Code Synthesis [PDF] 摘要

25. SQuARE: Semantics-based Question Answering and Reasoning Engine [PDF] 摘要

26. A Finitist's Manifesto: Do we need to Reformulate the Foundations of Mathematics? [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-09-22

发表于 2020-09-22 更新于 2020-09-24 分类于 arxiv ， CV 33k 54 分钟

目录

1. Improving Person Re-identification with Iterative Impression Aggregation [PDF] 摘要

2. Exploring Intensity Invariance in Deep Neural Networks for Brain Image Registration [PDF] 摘要

3. Regularizing Attention Networks for Anomaly Detection in Visual Question Answering [PDF] 摘要

4. Visual-Semantic Embedding Model Informed by Structured Knowledge [PDF] 摘要

5. Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild [PDF] 摘要

6. Joint and Progressive Subspace Analysis (JPSA) with Spatial-Spectral Manifold Alignment for Semi-Supervised Hyperspectral Dimensionality Reduction [PDF] 摘要

7. TRECVID 2019: An Evaluation Campaign to Benchmark Video Activity Detection, Video Captioning and Matching, and Video Search & Retrieval [PDF] 摘要

8. DR2S : Deep Regression with Region Selection for Camera Quality Evaluation [PDF] 摘要

9. Depth-Adapted CNN for RGB-D cameras [PDF] 摘要

10. Line Flow based SLAM [PDF] 摘要

11. Towards Fast, Accurate and Stable 3D Dense Face Alignment [PDF] 摘要

12. PP-OCR: A Practical Ultra Lightweight OCR System [PDF] 摘要

13. CNNPruner: Pruning Convolutional Neural Networks with Visual Analytics [PDF] 摘要

14. Automatic Target Recognition (ATR) from SAR Imaginary by Using Machine Learning Techniques [PDF] 摘要

15. Is each layer non-trivial in CNN? [PDF] 摘要

16. Applying a random projection algorithm to optimize machine learning model for breast lesion classification [PDF] 摘要

17. Prune Responsibly [PDF] 摘要

18. Monocular Depth Estimation Using Multi Scale Neural Network And Feature Fusion [PDF] 摘要

19. PESAO: Psychophysical Experimental Setup for Active Observers [PDF] 摘要

20. Supervised Learning with Projected Entangled Pair States [PDF] 摘要

21. CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions [PDF] 摘要

22. Deep Neural Network Approach for Annual Luminance Simulations [PDF] 摘要

23. Cross-Modal Alignment with Mixture Experts Neural Network for Intral-City Retail Recommendation [PDF] 摘要

24. Multi-species Seagrass Detection and Classification from Underwater Images [PDF] 摘要

25. Beyond Identity: What Information Is Stored in Biometric Face Templates? [PDF] 摘要

26. A Deep Neural Network Tool for Automatic Segmentation of Human Body Parts in Natural Scenes [PDF] 摘要

27. Clustering COVID-19 Lung Scans [PDF] 摘要

28. Efficient Computation of Higher Order 2D Image Moments using the Discrete Radon Transform [PDF] 摘要

29. LiPo-LCD: Combining Lines and Points for Appearance-based Loop Closure Detection [PDF] 摘要

30. Decontextualized learning for interpretable hierarchical representations of visual patterns [PDF] 摘要

31. Haar Wavelet based Block Autoregressive Flows for Trajectories [PDF] 摘要

32. DeepActsNet: Spatial and Motion features from Face, Hands, and Body Combined with Convolutional and Graph Networks for Improved Action Recognition [PDF] 摘要

33. Multi-Modal Reasoning Graph for Scene-Text Based Fine-Grained Image Classification and Retrieval [PDF] 摘要

34. Generating Adversarial yet Inconspicuous Patches with a Single Image [PDF] 摘要

35. Conditional Automated Channel Pruning for Deep Neural Networks [PDF] 摘要

36. MFIF-GAN: A New Generative Adversarial Network for Multi-Focus Image Fusion [PDF] 摘要

37. The High-Quality Wide Multi-Channel Attack (HQ-WMCA) database [PDF] 摘要

38. Batch Coherence-Driven Network for Part-aware Person Re-Identification [PDF] 摘要

39. Feed-Forward On-Edge Fine-tuning Using Static Synthetic Gradient Modules [PDF] 摘要

40. Discriminative Segmentation Tracking Using Dual Memory Banks [PDF] 摘要

41. Feature Flow: In-network Feature Flow Estimation for Video Object Detection [PDF] 摘要

42. 3D-FUTURE: 3D Furniture shape with TextURE [PDF] 摘要

43. Improving Ensemble Robustness by Collaboratively Promoting and Demoting Adversarial Robustness [PDF] 摘要

44. A Novel Transferability Attention Neural Network Model for EEG Emotion Recognition [PDF] 摘要

45. Semi-supervised Semantic Segmentation of Organs at Risk on 3D Pelvic CT Images [PDF] 摘要

46. SSCR: Iterative Language-Based Image Editing via Self-Supervised Counterfactual Reasoning [PDF] 摘要

47. ES Attack: Model Stealing against Deep Neural Networks without Data Hurdles [PDF] 摘要

48. PIE: Portrait Image Embedding for Semantic Control [PDF] 摘要

49. Remote sensing image fusion based on Bayesian GAN [PDF] 摘要

50. Implicit Feature Networks for Texture Completion from Partial 3D Data [PDF] 摘要

51. Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition [PDF] 摘要

52. Renovating Parsing R-CNN for Accurate Multiple Human Parsing [PDF] 摘要

53. Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling [PDF] 摘要

54. ContourCNN: convolutional neural network for contour data classification [PDF] 摘要

55. MARS: Mixed Virtual and Real Wearable Sensors for Human Activity Recognition with Multi-Domain Deep Learning Model [PDF] 摘要

56. DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition [PDF] 摘要

57. Transform Domain Pyramidal Dilated Convolution Networks For Restoration of Under Display Camera Images [PDF] 摘要

58. Real-time Lane detection and Motion Planning in Raspberry Pi and Arduino for an Autonomous Vehicle Prototype [PDF] 摘要

59. Deriving Visual Semantics from Spatial Context: An Adaptation of LSA and Word2Vec to generate Object and Scene Embeddings from Images [PDF] 摘要

60. $pi_t$- Enhancing the Precision of Eye Tracking using Iris Feature Motion Vectors [PDF] 摘要

61. Predicting Geographic Information with Neural Cellular Automata [PDF] 摘要

62. Dual-path CNN with Max Gated block for Text-Based Person Re-identification [PDF] 摘要

63. Factorized Deep Generative Models for Trajectory Generation with Spatiotemporal-Validity Constraints [PDF] 摘要

64. High-Resolution Augmentation for Automatic Template-Based Matching of Human Models [PDF] 摘要

65. Features based Mammogram Image Classification using Weighted Feature Support Vector Machine [PDF] 摘要

66. Adversarial Consistent Learning on Partial Domain Adaptation of PlantCLEF 2020 Challenge [PDF] 摘要

67. Subverting Privacy-Preserving GANs: Hiding Secrets in Sanitized Images [PDF] 摘要

68. Making Images Undiscoverable from Co-Saliency Detection [PDF] 摘要

69. City-Scale Visual Place Recognition with Deep Local Features Based on Multi-Scale Ordered VLAD Pooling [PDF] 摘要

70. EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining [PDF] 摘要

71. AAA: Adaptive Aggregation of Arbitrary Online Trackers with Theoretical Performance Guarantee [PDF] 摘要

72. Combining Shape Features with Multiple Color Spaces in Open-Ended 3D Object Recognition [PDF] 摘要

73. Adversarial Exposure Attack on Diabetic Retinopathy Imagery [PDF] 摘要

74. FakeRetouch: Evading DeepFakes Detection via the Guidance of Deliberate Noise [PDF] 摘要

75. Neural Architecture Search Using Stable Rank of Convolutional Layers [PDF] 摘要

76. It's Raining Cats or Dogs? Adversarial Rain Attack on DNN Perception [PDF] 摘要

77. Weak-shot Fine-grained Classification via Similarity Transfer [PDF] 摘要

78. Multi-Level Graph Convolutional Network with Automatic Graph Learning for Hyperspectral Image Classification [PDF] 摘要

79. A Review of Visual Odometry Methods and Its Applications for Autonomous Driving [PDF] 摘要

80. ENAS4D: Efficient Multi-stage CNN Architecture Search for Dynamic Inference [PDF] 摘要

81. Recognizing Micro-expression in Video Clip with Adaptive Key-frame Mining [PDF] 摘要

82. BargainNet: Background-Guided Domain Translation for Image Harmonization [PDF] 摘要

83. Introspective Learning by Distilling Knowledge from Online Self-explanation [PDF] 摘要

84. An Efficient Language-Independent Multi-Font OCR for Arabic Script [PDF] 摘要

85. Holistic Grid Fusion Based Stop Line Estimation [PDF] 摘要

86. Psoriasis Severity Assessment with a Similarity-Clustering Machine Learning Approach Reduces Intra- and Inter-observation variation [PDF] 摘要

87. Grasp-type Recognition Leveraging Object Affordance [PDF] 摘要

88. Overfit Neural Networks as a Compact Shape Representation [PDF] 摘要

89. Learning Audio-Visual Representations with Active Contrastive Coding [PDF] 摘要

90. Defending against substitute model black box adversarial attacks with the 01 loss [PDF] 摘要

91. Multi-Task Learning with Deep Neural Networks: A Survey [PDF] 摘要

92. Impact of lung segmentation on the diagnosis and explanation of COVID-19 in chest X-ray images [PDF] 摘要

93. Weight Training Analysis of Sportsmen with Kinect Bioinformatics for Form Improvement [PDF] 摘要

94. Improving Automated COVID-19 Grading with Convolutional Neural Networks in Computed Tomography Scans: An Ablation Study [PDF] 摘要

95. When Healthcare Meets Off-the-Shelf WiFi: A Non-Wearable and Low-Costs Approach for In-Home Monitoring [PDF] 摘要

96. Contrastive Clustering [PDF] 摘要

97. Modeling Score Distributions and Continuous Covariates: A Bayesian Approach [PDF] 摘要

98. Reconstruct high-resolution multi-focal plane images from a single 2D wide field image [PDF] 摘要

99. Learning Soft Labels via Meta Learning [PDF] 摘要

100. Scale-Localized Abstract Reasoning [PDF] 摘要

101. Learning a Lie Algebra from Unlabeled Data Pairs [PDF] 摘要

102. Efficient Certification of Spatial Robustness [PDF] 摘要

103. Reducing false-positive biopsies with deep neural networks that utilize local and global information in screening mammograms [PDF] 摘要

104. Humans learn too: Better Human-AI Interaction using Optimized Human Inputs [PDF] 摘要

105. Bias Field Poses a Threat to DNN-based X-Ray Recognition [PDF] 摘要

106. Few-shot learning using pre-training and shots, enriched by pre-trained samples [PDF] 摘要

107. Lossless White Balance For Improved Lossless CFA Image and Video Compression [PDF] 摘要

108. Kernel Ridge Regression Using Importance Sampling with Application to Seismic Response Prediction [PDF] 摘要

109. Pose Correction Algorithm for Relative Frames between Keyframes in SLAM [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-09-22

发表于 2020-09-22 更新于 2020-09-24 分类于 arxiv ， CL 82k 2:17

目录

1. Composed Variational Natural Language Generation for Few-shot Intents [PDF] 摘要

2. Latin BERT: A Contextual Language Model for Classical Philology [PDF] 摘要

3. UCD-CS at W-NUT 2020 Shared Task-3: A Text to Text Approach for COVID-19 Event Extraction on Social Media [PDF] 摘要

4. Adjusting for Confounders with Text: Challenges and an Empirical Evaluation Framework for Causal Inference [PDF] 摘要

5. WESSA at SemEval-2020 Task 9: Code-Mixed Sentiment Analysis using Transformers [PDF] 摘要

6. Content Planning for Neural Story Generation with Aristotelian Rescoring [PDF] 摘要

7. Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems [PDF] 摘要

8. SDST: Successive Decoding for Speech-to-text Translation [PDF] 摘要

9. Multitask Pointer Network for Multi-Representational Parsing [PDF] 摘要

10. Empathetic Dialogue Generation via Knowledge Enhancing and Emotion Dependency Modeling [PDF] 摘要

11. TED: Triple Supervision Decouples End-to-end Speech-to-text Translation [PDF] 摘要

12. Profile Consistency Identification for Open-domain Dialogue Agents [PDF] 摘要

13. Accent Estimation of Japanese Words from Their Surfaces and Romanizations for Building Large Vocabulary Accent Dictionaries [PDF] 摘要

14. Alleviating the Inequality of Attention Heads for Neural Machine Translation [PDF] 摘要

15. Generative Imagination Elevates Machine Translation [PDF] 摘要

16. Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition [PDF] 摘要

17. Weakly Supervised Learning of Nuanced Frames for Analyzing Polarization in News Media [PDF] 摘要

18. Assessing the Severity of Health States based on Social Media Posts [PDF] 摘要

19. Improving Robustness and Generality of NLP Models Using Disentangled Representations [PDF] 摘要

20. Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding [PDF] 摘要

21. Relation Extraction from Biomedical and Clinical Text: Unified Multitask Learning Framework [PDF] 摘要

22. Persian Ezafe Recognition Using Transformers and Its Role in Part-Of-Speech Tagging [PDF] 摘要

23. Dialogue Distillation: Open-domain Dialogue Augmentation Using Unpaired Data [PDF] 摘要

24. F^2-Softmax: Diversifying Neural Text Generation via Frequency Factorized Softmax [PDF] 摘要

25. Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation [PDF] 摘要

26. Softmax Tempering for Training Neural Machine Translation Models [PDF] 摘要

27. Understanding Mention Detector-Linker Interaction for Neural Coreference Resolution [PDF] 摘要

28. Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation [PDF] 摘要

29. Biomedical Event Extraction on Graph Edge-conditioned Attention Networks with Hierarchical Knowledge Graphs [PDF] 摘要

30. Towards Computational Linguistics in Minangkabau Language: Studies on Sentiment Analysis and Machine Translation [PDF] 摘要

31. Word class flexibility: A deep contextualized approach [PDF] 摘要

32. BioALBERT: A Simple and Effective Pre-trained Language Model for Biomedical Named Entity Recognition [PDF] 摘要

33. Learning to Attack: Towards Textual Adversarial Attacking in Real-world Situations [PDF] 摘要

34. OpenAttack: An Open-source Textual Adversarial Attack Toolkit [PDF] 摘要

35. Aggressive Language Detection with Joint Text Normalization via Adversarial Multi-task Learning [PDF] 摘要

36. Nominal Compound Chain Extraction: A New Task for Semantic-enriched Lexical Chain [PDF] 摘要

37. Extracting Summary Knowledge Graphs from Long Documents [PDF] 摘要

38. CLEVR Parser: A Graph Parser Library for Geometric Learning on Language Grounded Image Scenes [PDF] 摘要

39. Weight Distillation: Transferring the Knowledge in Neural Network Parameters [PDF] 摘要

40. Enhancing Dialogue Generation via Multi-Level Contrastive Learning [PDF] 摘要

41. Prior Art Search and Reranking for Generated Patent Text [PDF] 摘要

42. Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translation [PDF] 摘要

43. Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing [PDF] 摘要

44. Will it Unblend? [PDF] 摘要

45. Tradeoffs in Sentence Selection Techniques for Open-Domain Question Answering [PDF] 摘要

46. Deliberate Self-Attention Network with Uncertainty Estimation for Multi-Aspect Review Rating Prediction [PDF] 摘要

47. A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect Detection [PDF] 摘要

48. Looking Beyond Sentence-Level Natural Language Inference for Downstream Tasks [PDF] 摘要

49. COMET: A Neural Framework for MT Evaluation [PDF] 摘要

50. Presenting Simultaneous Translation in Limited Space [PDF] 摘要

51. Visual-Semantic Embedding Model Informed by Structured Knowledge [PDF] 摘要

52. Finding Influential Instances for Distantly Supervised Relation Extraction [PDF] 摘要

53. DiffWave: A Versatile Diffusion Model for Audio Synthesis [PDF] 摘要

54. Exploring the Linear Subspace Hypothesis in Gender Bias Mitigation [PDF] 摘要

55. Can questions summarize a corpus? Using question generation for characterizing COVID-19 research [PDF] 摘要

56. Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect [PDF] 摘要

57. Active Learning for Product Type Ontology Enhancement in E-commerce [PDF] 摘要

58. An AI based talent acquisition and benchmarking for job [PDF] 摘要

59. Intimate Partner Violence and Injury Prediction From Radiology Reports [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-09-21

发表于 2020-09-21 分类于 arxiv ， CV 55k 1:32

目录

1. Preparing for the Worst: Making Networks Less Brittle with Adversarial Batch Normalization [PDF] 摘要

2. Light Direction and Color Estimation from Single Image with Deep Regression [PDF] 摘要

3. Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation [PDF] 摘要

4. Deep Learning for 3D Point Cloud Understanding: A Survey [PDF] 摘要

5. Learning Unseen Emotions from Gestures via Semantically-Conditioned Zero-Shot Perception with Adversarial Autoencoders [PDF] 摘要

6. Image Captioning with Attention for Smart Local Tourism using EfficientNet [PDF] 摘要

7. Faster Gradient-based NAS Pipeline Combining Broad Scalable Architecture with Confident Learning Rate [PDF] 摘要

8. PMVOS: Pixel-Level Matching-Based Video Object Segmentation [PDF] 摘要

9. Synthetic Convolutional Features for Improved Semantic Segmentation [PDF] 摘要

10. IDA: Improved Data Augmentation Applied to Salient Object Detection [PDF] 摘要

11. Densely Guided Knowledge Distillation using Multiple Teacher Assistants [PDF] 摘要

12. $σ^2$R Loss: a Weighted Loss by Multiplicative Factors using Sigmoidal Functions [PDF] 摘要

13. Commands 4 Autonomous Vehicles (C4AV) Workshop Summary [PDF] 摘要

14. DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta [PDF] 摘要

15. Moving object detection for visual odometry in a dynamic environment based on occlusion accumulation [PDF] 摘要

16. Contextual Semantic Interpretability [PDF] 摘要

17. Progressive Semantic-Aware Style Transformation for Blind Face Restoration [PDF] 摘要

18. Learning Emotional-Blinded Face Representations [PDF] 摘要

19. Searching for Low-Bit Weights in Quantized Neural Networks [PDF] 摘要

20. DeepRemaster: Temporal Source-Reference Attention Networks for Comprehensive Video Enhancement [PDF] 摘要

21. Conditional Image Generation with One-Vs-All Classifier [PDF] 摘要

22. Face Sketch Synthesis with Style Transfer using Pyramid Column Feature [PDF] 摘要

23. TopNet: Topology Preserving Metric Learning for Vessel Tree Reconstruction and Labelling [PDF] 摘要

24. Performance Monitoring of Object Detection During Deployment [PDF] 摘要

25. Identification of Abnormal States in Videos of Ants Undergoing Social Phase Change [PDF] 摘要

26. 6-DoF Grasp Planning using Fast 3D Reconstruction and Grasp Quality CNN [PDF] 摘要

27. Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos [PDF] 摘要

28. Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation [PDF] 摘要

29. Accelerating Search on Binary Codes in Weighted Hamming Space [PDF] 摘要

30. MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering [PDF] 摘要

31. Objective, Probabilistic, and Generalized Noise Level Dependent Classifications of sets of more or less 2D Periodic Images into Plane Symmetry Groups [PDF] 摘要

32. Smartphone Camera De-identification while Preserving Biometric Utility [PDF] 摘要

33. Predicting molecular phenotypes from histopathology images: a transcriptome-wide expression-morphology analysis in breast cancer [PDF] 摘要

34. AdderSR: Towards Energy Efficient Image Super-Resolution [PDF] 摘要

35. Multi-modal Experts Network for Autonomous Driving [PDF] 摘要

36. Classification and Region Analysis of COVID-19 Infection using Lung CT Images and Deep Convolutional Neural Networks [PDF] 摘要

37. Search and Rescue with Airborne Optical Sectioning [PDF] 摘要

38. Fused Deep Convolutional Neural Network for Precision Diagnosis of COVID-19 Using Chest X-Ray Images [PDF] 摘要

39. Residual Spatial Attention Network for Retinal Vessel Segmentation [PDF] 摘要

40. An Analysis by Synthesis Method that Allows Accurate Spatial Modeling of Thickness of Cortical Bone from Clinical QCT [PDF] 摘要

41. Pruning Neural Networks at Initialization: Why are We Missing the Mark? [PDF] 摘要

42. SCREENet: A Multi-view Deep Convolutional Neural Network for Classification of High-resolution Synthetic Mammographic Screening Scans [PDF] 摘要

43. The Next Big Thing(s) in Unsupervised Machine Learning: Five Lessons from Infant Learning [PDF] 摘要

44. Keep off the Grass: Permissible Driving Routes from Radar with Weak Audio Supervision [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-09-21

发表于 2020-09-21 分类于 arxiv ， CL 30k 49 分钟

目录

1. Generating similes <effortlessly> like a Pro: A Style Transfer Approach for Simile Generation [PDF] 摘要

2. Principal Components of the Meaning [PDF] 摘要

3. FarsTail: A Persian Natural Language Inference Dataset [PDF] 摘要

4. Document-level Neural Machine Translation with Document Embeddings [PDF] 摘要

5. The birth of Romanian BERT [PDF] 摘要

6. RECON: Relation Extraction using Knowledge Graph Context in a Graph Neural Network [PDF] 摘要

7. Dr. Summarize: Global Summarization of Medical Dialogue by Exploiting Local Structures [PDF] 摘要

8. Hierarchical GPT with Congruent Transformers for Multi-Sentence Language Models [PDF] 摘要

9. fastHan: A BERT-based Joint Many-Task Toolkit for Chinese NLP [PDF] 摘要

10. Unsupervised Parallel Corpus Mining on Web Data [PDF] 摘要

11. NEU at WNUT-2020 Task 2: Data Augmentation To Tell BERT That Death Is Not Necessarily Informative [PDF] 摘要

12. Small but Mighty: New Benchmarks for Split and Rephrase [PDF] 摘要

13. Generation-Augmented Retrieval for Open-domain Question Answering [PDF] 摘要

14. Structured Attention for Unsupervised Dialogue Structure Induction [PDF] 摘要

15. PhenoTagger: A Hybrid Method for Phenotype Concept Recognition using Human Phenotype Ontology [PDF] 摘要

16. A Study of Genetic Algorithms for Hyperparameter Optimization of Neural Networks in Machine Translation [PDF] 摘要

17. Image Captioning with Attention for Smart Local Tourism using EfficientNet [PDF] 摘要

18. SciBERT-based Semantification of Bioassays in the Open Research Knowledge Graph [PDF] 摘要

19. Towards Full-line Code Completion with Neural Language Models [PDF] 摘要

20. MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-09-18

发表于 2020-09-18 分类于 arxiv ， CV 91k 2:32

目录

1. MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks [PDF] 摘要

2. Radar-Camera Sensor Fusion for Joint Object Detection and Distance Estimation in Autonomous Vehicles [PDF] 摘要

3. Dynamic Regions Graph Neural Networks for Spatio-Temporal Reasoning [PDF] 摘要

4. A Multimodal Memes Classification: A Survey and Open Research Issues [PDF] 摘要

5. Microtubule Tracking in Electron Microscopy Volumes [PDF] 摘要

6. Face Mask Detection using Transfer Learning of InceptionV3 [PDF] 摘要

7. S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning [PDF] 摘要

8. Noisy Concurrent Training for Efficient Learning under Label Noise [PDF] 摘要

9. Novel View Synthesis from Single Images via Point Cloud Transformation [PDF] 摘要

10. Low-Rank Matrix Recovery from Noisy via an MDL Framework-based Atomic Norm [PDF] 摘要

11. Learning to Identify Physical Parameters from Video Using Differentiable Physics [PDF] 摘要

12. Back to Event Basics: Self-Supervised Learning of Image Reconstruction for Event Cameras via Photometric Constancy [PDF] 摘要

13. A Linked Aggregate Code for Processing Faces (Revised Version) [PDF] 摘要

14. Video based real-time positional tracker [PDF] 摘要

15. Counterfactual Generation and Fairness Evaluation Using Adversarially Learned Inference [PDF] 摘要

16. Adversarial Image Composition with Auxiliary Illumination [PDF] 摘要

17. Dynamic Edge Weights in Graph Neural Networks for 3D Object Detection [PDF] 摘要

18. Parallax Attention for Unsupervised Stereo Correspondence Learning [PDF] 摘要

19. Learning a Deep Part-based Representation by Preserving Data Distribution [PDF] 摘要

20. Label Smoothing and Adversarial Robustness [PDF] 摘要

21. Deep Learning Approaches to Classification of Production Technology for 19th Century Books [PDF] 摘要

22. Vax-a-Net: Training-time Defence Against Adversarial Patch Attacks [PDF] 摘要

23. Deploying machine learning to assist digital humanitarians: making image annotation in OpenStreetMap more efficient [PDF] 摘要

24. DLBCL-Morph: Morphological features computed using deep learning for an annotated digital DLBCL image set [PDF] 摘要

25. Collaborative Training between Region Proposal Localization and Classi?cation for Domain Adaptive Object Detection [PDF] 摘要

26. Online Alternate Generator against Adversarial Attacks [PDF] 摘要

27. Crossing You in Style: Cross-modal Style Transfer from Music to Visual Arts [PDF] 摘要

28. Image Retrieval for Structure-from-Motion via Graph Convolutional Network [PDF] 摘要

29. High-precision target positioning system for unmanned vehicles based on binocular vision [PDF] 摘要

30. Word Segmentation from Unconstrained Handwritten Bangla Document Images using Distance Transform [PDF] 摘要

31. DanceIt: Music-inspired Dancing Video Synthesis [PDF] 摘要

32. LDNet: End-to-End Lane Detection Approach usinga Dynamic Vision Sensor [PDF] 摘要

33. An Algorithm to Attack Neural Network Encoder-based Out-Of-Distribution Sample Detector [PDF] 摘要

34. Deep Momentum Uncertainty Hashing [PDF] 摘要

35. Arbitrary Video Style Transfer via Multi-Channel Correlation [PDF] 摘要

36. MoPro: Webly Supervised Learning with Momentum Prototypes [PDF] 摘要

37. AAG: Self-Supervised Representation Learning by Auxiliary Augmentation with GNT-Xent Loss [PDF] 摘要

38. Skeletonization and Reconstruction based on Graph Morphological Transformations [PDF] 摘要

39. Using Sensory Time-cue to enable Unsupervised Multimodal Meta-learning [PDF] 摘要

40. Tropical time series, iterated-sums signatures and quasisymmetric functions [PDF] 摘要

41. Large Norms of CNN Layers Do Not Hurt Adversarial Robustness [PDF] 摘要

42. Population Mapping in Informal Settlements with High-Resolution Satellite Imagery and Equitable Ground-Truth [PDF] 摘要

43. Modeling human visual search: A combined Bayesian searcher and saliency map approach for eye movement guidance in natural scenes [PDF] 摘要

44. Review: Deep Learning in Electron Microscopy [PDF] 摘要

45. Decoupling Representation Learning from Reinforcement Learning [PDF] 摘要

46. Deforming the Loss Surface to Affect the Behaviour of the Optimizer [PDF] 摘要

47. Single Frame Deblurring with Laplacian Filters [PDF] 摘要

48. Holistic Filter Pruning for Efficient Deep Neural Networks [PDF] 摘要

49. POMP: Pomcp-based Online Motion Planning for active visual search in indoor environments [PDF] 摘要

50. Multidimensional Scaling, Sammon Mapping, and Isomap: Tutorial and Survey [PDF] 摘要

51. Few-Shot Unsupervised Continual Learning through Meta-Examples [PDF] 摘要

52. MultAV: Multiplicative Adversarial Videos [PDF] 摘要

53. ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis [PDF] 摘要

54. Model-based approach for analyzing prevalence of nuclear cataracts in elderly residents [PDF] 摘要

55. Deep Collective Learning: Learning Optimal Inputs and Weights Jointly in Deep Neural Networks [PDF] 摘要

56. Noise-Aware Merging of High Dynamic Range Image Stacks without Camera Calibration [PDF] 摘要

57. Analysis of Generalizability of Deep Neural Networks Based on the Complexity of Decision Boundary [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-09-18

发表于 2020-09-18 分类于 arxiv ， CL 45k 1:16

目录

1. Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks [PDF] 摘要

2. A Computational Approach to Understanding Empathy Expressed in Text-Based Mental Health Support [PDF] 摘要

3. Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction [PDF] 摘要

4. Evaluating Interactive Summarization: an Expansion-Based Framework [PDF] 摘要

5. More Embeddings, Better Sequence Labelers? [PDF] 摘要

6. Compositional and Lexical Semantics in RoBERTa, BERT and DistilBERT: A Case Study on CoQA [PDF] 摘要

7. What if we had no Wikipedia? Domain-independent Term Extraction from a Large News Corpus [PDF] 摘要

8. Fast and Accurate Sequence Labeling with Approximate Inference Network [PDF] 摘要

9. Generating Label Cohesive and Well-Formed Adversarial Claims [PDF] 摘要

10. DSC IIT-ISM at SemEval-2020 Task 6: Boosting BERT with Dependencies for Definition Extraction [PDF] 摘要

11. ISCAS at SemEval-2020 Task 5: Pre-trained Transformers for Counterfactual Statement Modeling [PDF] 摘要

12. End-to-End Neural Event Coreference Resolution [PDF] 摘要

13. FewJoint: A Few-shot Learning Benchmark for Joint Language Understanding [PDF] 摘要

14. Multi^2OIE: Multilingual Open Information Extraction based on Multi-Head Attention with BERT [PDF] 摘要

15. A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning [PDF] 摘要

16. A Deep Learning Approach to Geographical Candidate Selection through Toponym Matching [PDF] 摘要

17. Code-switching pre-training for neural machine translation [PDF] 摘要

18. On the Transferability of Minimal Prediction Preserving Inputs in Question Answering [PDF] 摘要

19. Efficient Transformer-based Large Scale Language Representations using Hardware-friendly Block Structured Pruning [PDF] 摘要

20. Self-supervised pre-training and contrastive representation learning for multiple-choice video QA [PDF] 摘要

21. Towards Fully 8-bit Integer Inference for the Transformer Model [PDF] 摘要

22. Multi-modal Summarization for Video-containing Documents [PDF] 摘要

23. State-Machine-Based Dialogue Agents with Few-Shot Contextual Semantic Parsers [PDF] 摘要

24. Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis [PDF] 摘要

25. How to marry a star: probabilistic constraints for meaning in context [PDF] 摘要

26. A Multimodal Memes Classification: A Survey and Open Research Issues [PDF] 摘要

27. Impact and dynamics of hate and counter speech online [PDF] 摘要

28. GraphCodeBERT: Pre-training Code Representations with Data Flow [PDF] 摘要

29. Understanding Effects of Editing Tweets for News Sharing by Media Accounts through a Causal Inference Framework [PDF] 摘要

30. Type-augmented Relation Prediction in Knowledge Graphs [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-09-17

发表于 2020-09-17 分类于 arxiv ， CV 92k 2:33

目录

1. FairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognition [PDF] 摘要

2. Layered Neural Rendering for Retiming People in Video [PDF] 摘要

3. Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing [PDF] 摘要

4. GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network [PDF] 摘要

5. HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking [PDF] 摘要

6. TreeGAN: Incorporating Class Hierarchy into Image Generation [PDF] 摘要

7. Evaluating Self-Supervised Pretraining Without Using Labels [PDF] 摘要

8. Domain-invariant Similarity Activation Map Metric Learning for Retrieval-based Long-term Visual Localization [PDF] 摘要

9. Relative Attribute Classification with Deep Rank SVM [PDF] 摘要

10. Calibrating Self-supervised Monocular Depth Estimation [PDF] 摘要

11. Eating Habits Discovery in Egocentric Photo-streams [PDF] 摘要

12. BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation [PDF] 摘要

13. ChoreoNet: Towards Music to Dance Synthesis with Choreographic Action Unit [PDF] 摘要

14. The FaceChannel: A Fast & Furious Deep Neural Network for Facial Expression Recognition [PDF] 摘要

15. Multi-Stage CNN Architecture for Face Mask Detection [PDF] 摘要

16. Perceiving Traffic from Aerial Images [PDF] 摘要

17. Compressing Facial Makeup Transfer Networks by Collaborative Distillation and Kernel Decomposition [PDF] 摘要

18. Red Carpet to Fight Club: Partially-supervised Domain Transfer for Face Recognition in Violent Videos [PDF] 摘要

19. Hierarchical brain parcellation with uncertainty [PDF] 摘要

20. Domain Adaptation for Outdoor Robot Traversability Estimation from RGB data with Safety-Preserving Loss [PDF] 摘要

21. Similarity-based data mining for online domain adaptation of a sonar ATR system [PDF] 摘要

22. SLGAN: Style- and Latent-guided Generative Adversarial Network for Desirable Makeup Transfer and Removal [PDF] 摘要

23. Hybrid-Attention Guided Network with Multiple Resolution Features for Person Re-Identification [PDF] 摘要

24. DRL-FAS: A Novel Framework Based on Deep Reinforcement Learning for Face Anti-Spoofing [PDF] 摘要

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

26. The 1st Tiny Object Detection Challenge:Methods and Results [PDF] 摘要

27. UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation [PDF] 摘要

28. Dual Semantic Fusion Network for Video Object Detection [PDF] 摘要

29. Robust Person Re-Identification through Contextual Mutual Boosting [PDF] 摘要

30. Pooling Methods in Deep Neural Networks, a Review [PDF] 摘要

31. A Convolutional LSTM based Residual Network for Deepfake Video Detection [PDF] 摘要

32. Knowledge Guided Learning: Towards Open Domain Egocentric Action Recognition with Zero Supervision [PDF] 摘要

33. Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning [PDF] 摘要

34. Exploring Font-independent Features for Scene Text Recognition [PDF] 摘要

35. Weakly-Supervised Online Hashing [PDF] 摘要

36. A New Approach for Texture based Script Identification At Block Level using Quad Tree Decomposition [PDF] 摘要

37. Handwritten Script Identification from Text Lines [PDF] 摘要

38. Multi-Label Activity Recognition using Activity-specific Features [PDF] 摘要

39. DAER to Reject Seeds with Dual-loss Additional Error Regression [PDF] 摘要

40. EfficientNet-eLite: Extremely Lightweight and Efficient CNN Models for Edge Devices by Network Candidate Search [PDF] 摘要

41. Creation and Validation of a Chest X-Ray Dataset with Eye-tracking and Report Dictation for AI Tool Development [PDF] 摘要

42. BOP Challenge 2020 on 6D Object Localization [PDF] 摘要

43. Comparison of Spatiotemporal Networks for Learning Video Related Tasks [PDF] 摘要

44. Semantically Sensible Video Captioning (SSVC) [PDF] 摘要

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

46. Multi-Sensor Data Fusion for Cloud Removal in Global and All-Season Sentinel-2 Imagery [PDF] 摘要

47. Contrastive Cross-site Learning with Redesigned Net for COVID-19 CT Classification [PDF] 摘要

48. Deep Learning in Photoacoustic Tomography: Current approaches and future directions [PDF] 摘要

49. RCNN for Region of Interest Detection in Whole Slide Images [PDF] 摘要

50. m-arcsinh: An Efficient and Reliable Function for SVM and MLP in scikit-learn [PDF] 摘要

51. Deep Sinogram Completion with Image Prior for Metal Artifact Reduction in CT Images [PDF] 摘要

52. PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line [PDF] 摘要

53. MSP: An FPGA-Specific Mixed-Scheme, Multi-Precision Deep Neural Network Quantization Framework [PDF] 摘要

54. Surgical Video Motion Magnification with Suppression of Instrument Artefacts [PDF] 摘要

55. Geometric Uncertainty in Patient-Specific Cardiovascular Modeling with Convolutional Dropout Networks [PDF] 摘要

56. Generative models with kernel distance in data space [PDF] 摘要

阅读全文 »