【arxiv论文】 Computation and Language 2020-10-29

发表于 2020-10-29 分类于 arxiv ， CL 53k 1:28

目录

1. Handling Class Imbalance in Low-Resource Dialogue Systems by Combining Few-Shot Classification and Interpolation [PDF] 摘要

2. Graph-based Topic Extraction from Vector Embeddings of Text Documents: Application to a Corpus of News Articles [PDF] 摘要

3. A Comprehensive Survey on Word Representation Models: From Classical to State-Of-The-Art Word Representation Language Models [PDF] 摘要

4. Towards Ethics by Design in Online Abusive Content Detection [PDF] 摘要

5. Bridging the Modality Gap for Speech-to-Text Translation [PDF] 摘要

6. Bayesian Methods for Semi-supervised Text Annotation [PDF] 摘要

7. The Volctrans Machine Translation System for WMT20 [PDF] 摘要

8. A Chinese Text Classification Method With Low Hardware Requirement Based on Improved Model Concatenation [PDF] 摘要

9. Fine-grained Information Status Classification Using Discourse Context-Aware BERT [PDF] 摘要

10. DisenE: Disentangling Knowledge Graph Embeddings [PDF] 摘要

11. Second-Order Unsupervised Neural Dependency Parsing [PDF] 摘要

12. TopicModel4J: A Java Package for Topic Models [PDF] 摘要

13. Character Entropy in Modern and Historical Texts: Comparison Metrics for an Undeciphered Manuscript [PDF] 摘要

14. What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation [PDF] 摘要

15. Transformer in action: a comparative study of transformer-based acoustic models for large scale speech recognition applications [PDF] 摘要

16. DualTKB: A Dual Learning Bridge between Text and Knowledge Base [PDF] 摘要

17. Learning Contextualised Cross-lingual Word Embeddings for Extremely Low-Resource Languages Using Parallel Corpora [PDF] 摘要

18. On the diminishing return of labeling clinical reports [PDF] 摘要

19. Predicting Themes within Complex Unstructured Texts: A Case Study on Safeguarding Reports [PDF] 摘要

20. WNUT-2020 Task 1 Overview: Extracting Entities and Relations from Wet Lab Protocols [PDF] 摘要

21. Language ID in the Wild: Unexpected Challenges on the Path to a Thousand-Language Web Text Corpus [PDF] 摘要

22. Strongly Incremental Constituency Parsing with Graph Neural Networks [PDF] 摘要

23. DGST: a Dual-Generator Network for Text Style Transfer [PDF] 摘要

24. Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias [PDF] 摘要

25. The geometry of integration in text classification RNNs [PDF] 摘要

26. Fixed-Length Protein Embeddings using Contextual Lenses [PDF] 摘要

27. Measuring non-trivial compositionality in emergent communication [PDF] 摘要

28. Non-Autoregressive Transformer ASR with CTC-Enhanced Decoder Input [PDF] 摘要

29. A Cyclic Proof System for HFLN [PDF] 摘要

30. INT8 Winograd Acceleration for Conv1D Equipped ASR Models Deployed on Mobile Devices [PDF] 摘要

31. PPG-based singing voice conversion with adversarial representation learning [PDF] 摘要

32. Decoupling Pronunciation and Language for End-to-end Code-switching Automatic Speech Recognition [PDF] 摘要

33. Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset [PDF] 摘要

34. CASS-NAT: CTC Alignment-based Single Step Non-autoregressive Transformer for Speech Recognition [PDF] 摘要

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

36. Cascaded encoders for unifying streaming and non-streaming ASR [PDF] 摘要

37. A Comprehensive Dictionary and Term Variation Analysis for COVID-19 and SARS-CoV-2 [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-10-28

发表于 2020-10-28 分类于 arxiv ， CV 69k 1:55

目录

1. Robust Skeletonization for Plant Root Structure Reconstruction from MRI [PDF] 摘要

2. Structured Visual Search via Composition-aware Learning [PDF] 摘要

3. Improving Word Recognition using Multiple Hypotheses and Deep Embeddings [PDF] 摘要

4. Pixel-based Facial Expression Synthesis [PDF] 摘要

5. Learning to Infer Unseen Attribute-Object Compositions [PDF] 摘要

6. SIRI: Spatial Relation Induced Network For Spatial Description Resolution [PDF] 摘要

7. Ice Monitoring in Swiss Lakes from Optical Satellites and Webcams using Machine Learning [PDF] 摘要

8. Fast Local Attack: Generating Local Adversarial Examples for Object Detectors [PDF] 摘要

9. A Method of Generating Measurable Panoramic Image for Indoor Mobile Measurement System [PDF] 摘要

10. End-to-end trainable network for degraded license plate detection via vehicle-plate relation mining [PDF] 摘要

11. A Simple and Efficient Registration of 3D Point Cloud and Image Data for Indoor Mobile Mapping System [PDF] 摘要

12. Reconstruction of Voxels with Position- and Angle-Dependent Weightings [PDF] 摘要

13. Mining Generalized Features for Detecting AI-Manipulated Fake Faces [PDF] 摘要

14. Co-attentional Transformers for Story-Based Video Understanding [PDF] 摘要

15. A Multi-task Two-stream Spatiotemporal Convolutional Neural Network for Convective Storm Nowcasting [PDF] 摘要

16. MMFT-BERT: Multimodal Fusion Transformer with BERT Encodings for Visual Question Answering [PDF] 摘要

17. $P^2$ Net: Augmented Parallel-Pyramid Net for Attention Guided Pose Estimation [PDF] 摘要

18. Synthetic Training for Monocular Human Mesh Recovery [PDF] 摘要

19. Cross-directional Feature Fusion Network for Building Damage Assessment from Satellite Imagery [PDF] 摘要

20. Decentralized Attribution of Generative Models [PDF] 摘要

21. Developing Univariate Neurodegeneration Biomarkers with Low-Rank and Sparse Subspace Decomposition [PDF] 摘要

22. Neural Unsigned Distance Fields for Implicit Function Learning [PDF] 摘要

23. Processing of incomplete images by (graph) convolutional neural networks [PDF] 摘要

24. Multi-Class Zero-Shot Learning for Artistic Material Recognition [PDF] 摘要

25. Enhancing road signs segmentation using photometric invariants [PDF] 摘要

26. Peak Detection On Data Independent Acquisition Mass Spectrometry Data With Semisupervised Convolutional Transformers [PDF] 摘要

27. Application of sequential processing of computer vision methods for solving the problem of detecting the edges of a honeycomb block [PDF] 摘要

28. Wavelet Flow: Fast Training of High Resolution Normalizing Flows [PDF] 摘要

29. Detector Algorithms of Bounding Box and Segmentation Mask of a Mask R-CNN Model [PDF] 摘要

30. Memory Optimization for Deep Networks [PDF] 摘要

31. Artificial intelligence based writer identification generates new evidence for the unknown scribes of the Dead Sea Scrolls exemplified by the Great Isaiah Scroll (1QIsaa) [PDF] 摘要

32. Deep Probabilistic Imaging: Uncertainty Quantification and Multi-modal Solution Characterization for Computational Imaging [PDF] 摘要

33. On the Transfer of Disentangled Representations in Realistic Settings [PDF] 摘要

34. Fourth-Order Nonlocal Tensor Decomposition Model for Spectral Computed Tomography [PDF] 摘要

35. CT Reconstruction with PDF: Parameter-Dependent Framework for Multiple Scanning Geometries and Dose Levels [PDF] 摘要

36. Fit to Measure: Reasoning about Sizes for Robust Object Recognition [PDF] 摘要

37. Robust Odometry and Mapping for Multi-LiDAR Systems with Online Extrinsic Calibration [PDF] 摘要

38. Hyperspectral Anomaly Change Detection Based on Auto-encoder [PDF] 摘要

39. Micro-CT Synthesis and Inner Ear Super Resolution via Bayesian Generative Adversarial Networks [PDF] 摘要

40. Triple-view Convolutional Neural Networks for COVID-19 Diagnosis with Chest X-ray [PDF] 摘要

41. Impact of Spherical Coordinates Transformation Pre-processing in Deep Convolution Neural Networks for Brain Tumor Segmentation and Survival Prediction [PDF] 摘要

42. MELD: Meta-Reinforcement Learning from Images via Latent State Models [PDF] 摘要

43. Improved Supervised Training of Physics-Guided Deep Learning Image Reconstruction with Multi-Masking [PDF] 摘要

44. Diptychs of human and machine perceptions [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-10-28

发表于 2020-10-28 分类于 arxiv ， CL 3.8k 6 分钟

目录

1. Fast Interleaved Bidirectional Sequence Generation [PDF] 摘要

2. It's All in the Name: A Character Based Approach To Infer Religion [PDF] 摘要

3. Evaluating Gender Bias in Speech Translation [PDF] 摘要

4. Discovering and Interpreting Conceptual Biases in Online Communities [PDF] 摘要

5. Differentiable Open-Ended Commonsense Reasoning [PDF] 摘要

6. Listener's Social Identity Matters in Personalised Response Generation [PDF] 摘要

7. Multitask Training with Text Data for End-to-End Speech Recognition [PDF] 摘要

8. Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation [PDF] 摘要

9. Improving Reinforcement Learning for Neural Relation Extraction with Hierarchical Memory Extractor [PDF] 摘要

10. Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles [PDF] 摘要

11. Global Sentiment Analysis Of COVID-19 Tweets Over Time [PDF] 摘要

12. Event Detection: Gate Diversity and Syntactic Importance Scoresfor Graph Convolution Neural Networks [PDF] 摘要

13. Emotion recognition by fusing time synchronous and time asynchronous representations [PDF] 摘要

14. Multi-Domain Dialogue State Tracking -- A Purely Transformer-Based Generative Approach [PDF] 摘要

15. To BERT or Not to BERT: Comparing Task-specific and Task-agnostic Semi-Supervised Approaches for Sequence Tagging [PDF] 摘要

16. Volctrans Parallel Corpus Filtering System for WMT 2020 [PDF] 摘要

17. Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learning [PDF] 摘要

18. Interpretation of NLP models through input marginalization [PDF] 摘要

19. Predict and Use Latent Patterns for Short-Text Conversation [PDF] 摘要

20. Reading Between the Lines: Exploring Infilling in Visual Narratives [PDF] 摘要

21. Improving Limited Labeled Dialogue State Tracking with Self-Supervision [PDF] 摘要

22. Probing Task-Oriented Dialogue Representation from Language Models [PDF] 摘要

23. Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer [PDF] 摘要

24. Word Frequency Does Not Predict Grammatical Knowledge in Language Models [PDF] 摘要

25. Data Troubles in Sentence Level Confidence Estimation for Machine Translation [PDF] 摘要

26. Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining [PDF] 摘要

27. PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction [PDF] 摘要

28. Is it Great or Terrible? Preserving Sentiment in Neural Machine Translation of Arabic Reviews [PDF] 摘要

29. Dynamic Boundary Time Warping for Sub-sequence Matching with Few Examples [PDF] 摘要

30. Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment [PDF] 摘要

31. Co-attentional Transformers for Story-Based Video Understanding [PDF] 摘要

32. VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-10-27

发表于 2020-10-27 分类于 arxiv ， CV 149k 4:08

目录

1. GreedyFool: Distortion-Aware Sparse Adversarial Attack [PDF] 摘要

2. GAN Mask R-CNN:Instance semantic segmentation benefits from generativeadversarial networks [PDF] 摘要

3. Handgun detection using combined human pose and weapon appearance [PDF] 摘要

4. Demo Abstract: Indoor Positioning System in Visually-Degraded Environments with Millimetre-Wave Radar and Inertial Sensors [PDF] 摘要

5. ActiveNet: A computer-vision based approach to determine lethargy [PDF] 摘要

6. Distributed Multi-Target Tracking in Camera Networks [PDF] 摘要

7. Face Frontalization Based on Robustly Fitting a Deformable Shape Model to 3D Landmarks [PDF] 摘要

8. SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion [PDF] 摘要

9. Fewer is More: A Deep Graph Metric Learning Perspective Using Fewer Proxies [PDF] 摘要

10. Classification of Important Segments in Educational Videos using Multimodal Features [PDF] 摘要

11. SHARP 2020: The 1st Shape Recovery from Partial Textured 3D Scans Challenge Results [PDF] 摘要

12. Hierarchical Neural Architecture Search for Deep Stereo Matching [PDF] 摘要

13. Activation Map Adaptation for Effective Knowledge Distillation [PDF] 摘要

14. A Centroid Loss for Weakly Supervised Semantic Segmentation in Quality Control and Inspection Application [PDF] 摘要

15. Multi-object tracking with self-supervised associating network [PDF] 摘要

16. Lane detection in complex scenes based on end-to-end neural network [PDF] 摘要

17. Residual Recurrent CRNN for End-to-End Optical Music Recognition on Monophonic Scores [PDF] 摘要

18. Flexible Piecewise Curves Estimation for Photo Enhancement [PDF] 摘要

19. Video-based Facial Expression Recognition using Graph Convolutional Networks [PDF] 摘要

20. Where to Look and How to Describe: Fashion Image Retrieval with an Attentional Heterogeneous Bilinear Network [PDF] 摘要

21. PSF-LO: Parameterized Semantic Features Based Lidar Odometry [PDF] 摘要

22. Semi supervised segmentation and graph-based tracking of 3D nuclei in time-lapse microscopy [PDF] 摘要

23. EDNet: Improved DispNet for Efficient Disparity Estimation [PDF] 摘要

24. Robust Pre-Training by Adversarial Contrastive Learning [PDF] 摘要

25. View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose [PDF] 摘要

26. Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations [PDF] 摘要

27. Structural Prior Driven Regularized Deep Learning for Sonar Image Classification [PDF] 摘要

28. AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild [PDF] 摘要

29. Global Image Segmentation Process using Machine Learning algorithm & Convolution Neural Network method for Self- Driving Vehicles [PDF] 摘要

30. Attack Agnostic Adversarial Defense via Visual Imperceptible Bound [PDF] 摘要

31. MixNet for Generalized Face Presentation Attack Detection [PDF] 摘要

32. Generalized Iris Presentation Attack Detection Algorithm under Cross-Database Settings [PDF] 摘要

33. Human or Machine? It Is Not What You Write, But How You Write It [PDF] 摘要

34. Weakly-Supervised Amodal Instance Segmentation with Compositional Priors [PDF] 摘要

35. Neuron Merging: Compensating for Pruned Neurons [PDF] 摘要

36. Correspondence Learning via Linearly-invariant Embedding [PDF] 摘要

37. Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce model [PDF] 摘要

38. Empowering Knowledge Distillation via Open Set Recognition for Robust 3D Point Cloud Classification [PDF] 摘要

39. Scribble-based Weakly Supervised Deep Learning for Road Surface Extraction from Remote Sensing Images [PDF] 摘要

40. Coherent Loss: A Generic Framework for Stable Video Segmentation [PDF] 摘要

41. Fast and Accurate Light Field Saliency Detection through Feature Extraction [PDF] 摘要

42. Applying convolutional neural networks to extremely sparse image datasets using an image subdivision approach [PDF] 摘要

43. CLRGaze: Contrastive Learning of Representations for Eye Movement Signals [PDF] 摘要

44. APB2FaceV2: Real-Time Audio-Guided Multi-Face Reenactment [PDF] 摘要

45. Classification of Spot-welded Joints in Laser Thermography Data using Convolutional Neural Networks [PDF] 摘要

46. Deep Denoising For Scientific Discovery: A Case Study In Electron Microscopy [PDF] 摘要

47. Video Understanding based on Human Action and Group Activity Recognition [PDF] 摘要

48. Advancing Non-Contact Vital Sign Measurement using Synthetic Avatars [PDF] 摘要

49. RUArt: A Novel Text-Centered Solution for Text-Based Visual Question Answering [PDF] 摘要

50. Classifying Eye-Tracking Data Using Saliency Maps [PDF] 摘要

51. Discriminative feature generation for classification of imbalanced data [PDF] 摘要

52. Persian Handwritten Digit, Character, and Words Recognition by Using Deep Learning Methods [PDF] 摘要

53. Beyond VQA: Generating Multi-word Answer and Rationale to Visual Questions [PDF] 摘要

54. REDE: End-to-end Object 6D Pose Robust Estimation Using Differentiable Outliers Elimination [PDF] 摘要

55. Improving the generalization of network based relative pose regression: dimension reduction as a regularizer [PDF] 摘要

56. Real-time Non-line-of-Sight imaging of dynamic scenes [PDF] 摘要

57. Investigating Saturation Effects in Integrated Gradients [PDF] 摘要

58. Unsupervised Dense Shape Correspondence using Heat Kernels [PDF] 摘要

59. 3DBooSTeR: 3D Body Shape and Texture Recovery [PDF] 摘要

60. Position and Rotation Invariant Sign Language Recognition from 3D Point Cloud Data with Recurrent Neural Networks [PDF] 摘要

61. Attention-Guided Network for Iris Presentation Attack Detection [PDF] 摘要

62. Exemplary Natural Images Explain CNN Activations Better than Feature Visualizations [PDF] 摘要

63. ST-GREED: Space-Time Generalized Entropic Differences for Frame Rate Dependent Video Quality Prediction [PDF] 摘要

64. Deep Low-rank plus Sparse Network for Dynamic MR Imaging [PDF] 摘要

65. A ReLU Dense Layer to Improve the Performance of Neural Networks [PDF] 摘要

66. Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks [PDF] 摘要

67. Robust Disentanglement of a Few Factors at a Time [PDF] 摘要

68. Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index [PDF] 摘要

69. VoteNet++: Registration Refinement for Multi-Atlas Segmentation [PDF] 摘要

70. Does contextual information improve 3D U-Net based brain tumor segmentation? [PDF] 摘要

71. Matthews Correlation Coefficient Loss for Deep Convolutional Networks: Application to Skin Lesion Segmentation [PDF] 摘要

72. On Embodied Visual Navigation in Real Environments Through Habitat [PDF] 摘要

73. What is the best data augmentation approach for brain tumor segmentation using 3D U-Net? [PDF] 摘要

74. Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracy [PDF] 摘要

75. Deep Sequential Learning for Cervical Spine Fracture Detection on Computed Tomography Imaging [PDF] 摘要

76. A Dark and Bright Channel Prior Guided Deep Network for Retinal Image Quality Assessment [PDF] 摘要

77. Geometrically Matched Multi-source Microscopic Image Synthesis Using Bidirectional Adversarial Networks [PDF] 摘要

78. Interpreting Uncertainty in Model Predictions For COVID-19 Diagnosis [PDF] 摘要

79. Co-embedding of Nodes and Edges with Graph Neural Networks [PDF] 摘要

80. Self-Supervised Training For Low Dose CT Reconstruction [PDF] 摘要

81. SUREMap: Predicting Uncertainty in CNN-based Image Reconstruction Using Stein's Unbiased Risk Estimate [PDF] 摘要

82. Gestop : Customizable Gesture Control of Computer Systems [PDF] 摘要

83. Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modelling [PDF] 摘要

84. Unsupervised Super-Resolution: Creating High-Resolution Medical Images from Low-Resolution Anisotropic Examples [PDF] 摘要

85. Context Aware 3D UNet for Brain Tumor Segmentation [PDF] 摘要

86. Dynamic Adversarial Patch for Evading Object Detection Models [PDF] 摘要

87. Automated triage of COVID-19 from various lung abnormalities using chest CT features [PDF] 摘要

88. LagNetViP: A Lagrangian Neural Network for Video Prediction [PDF] 摘要

89. Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration [PDF] 摘要

90. Weakly-supervised VisualBERT: Pre-training without Parallel Images and Captions [PDF] 摘要

91. Modularity Improves Out-of-Domain Instruction Following [PDF] 摘要

92. The RobotSlang Benchmark: Dialog-guided Robot Localization and Navigation [PDF] 摘要

93. S2cGAN: Semi-Supervised Training of Conditional GANs with Fewer Labels [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-10-27

发表于 2020-10-27 分类于 arxiv ， CL 166k 4:37

目录

1. A Survey of Embedding Space Alignment Methods for Language and Knowledge Graphs [PDF] 摘要

2. A Corpus for Argumentative Writing Support in German [PDF] 摘要

3. Exploiting Neural Query Translation into Cross Lingual Information Retrieval [PDF] 摘要

4. Constraint Translation Candidates: A Bridge between Neural Query Translation and Cross-lingual Information Retrieval [PDF] 摘要

5. Dutch Humor Detection by Generating Negative Examples [PDF] 摘要

6. Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification [PDF] 摘要

7. UPB at SemEval-2020 Task 12: Multilingual Offensive Language Detection on Social Media by Fine-tuning a Variety of BERT-based Models [PDF] 摘要

8. Curious Case of Language Generation Evaluation Metrics: A Cautionary Tale [PDF] 摘要

9. Interpreting convolutional networks trained on textual data [PDF] 摘要

10. Hierarchical Metadata-Aware Document Categorization under Weak Supervision [PDF] 摘要

11. Meta-Learning for Neural Relation Classification with Distant Supervision [PDF] 摘要

12. Syllabification of the Divine Comedy [PDF] 摘要

13. TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking [PDF] 摘要

14. Robust and Consistent Estimation of Word Embedding for Bangla Language by fine-tuning Word2Vec Model [PDF] 摘要

15. Graph Transformer Networks with Syntactic and Semantic Structures for Event Argument Extraction [PDF] 摘要

16. Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation [PDF] 摘要

17. FastFormers: Highly Efficient Transformer Models for Natural Language Understanding [PDF] 摘要

18. Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning [PDF] 摘要

19. LXPER Index 2.0: Improving Text Readability Assessment for L2 English Learners in South Korea [PDF] 摘要

20. The LMU Munich System for the WMT 2020 Unsupervised Machine Translation Shared Task [PDF] 摘要

21. Fair Embedding Engine: A Library for Analyzing and Mitigating Gender Bias in Word Embeddings [PDF] 摘要

22. Two-stage Textual Knowledge Distillation to Speech Encoder for Spoken Language Understanding [PDF] 摘要

23. Autoencoding Improves Pre-trained Word Embeddings [PDF] 摘要

24. Transgender Community Sentiment Analysis from Social Media Data: A Natural Language Processing Approach [PDF] 摘要

25. Contextualized Word Embeddings Encode Aspects of Human-Like Word Sense Knowledge [PDF] 摘要

26. Commonsense knowledge adversarial dataset that challenges ELECTRA [PDF] 摘要

27. Orthros: Non-autoregressive End-to-end Speech Translation with Dual-decoder [PDF] 摘要

28. Fine-tuning ERNIE for chest abnormal imaging signs extraction [PDF] 摘要

29. Towards Medical Knowmetrics: Representing and Computing Medical Knowledge using Semantic Predications as the Knowledge Unit and the Uncertainty as the Knowledge Context [PDF] 摘要

30. CRAB: Class Representation Attentive BERT for Hate Speech Identification in Social Media [PDF] 摘要

31. Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference [PDF] 摘要

32. Pre-trained Summarization Distillation [PDF] 摘要

33. Unsupervised Learning of Disentangled Speech Content and Style Representation [PDF] 摘要

34. Neural Compound-Word (Sandhi) Generation and Splitting in Sanskrit Language [PDF] 摘要

35. A Benchmark Corpus and Neural Approach for Sanskrit Derivative Nouns Analysis [PDF] 摘要

36. Disease Normalization with Graph Embeddings [PDF] 摘要

37. Causal Effects of Linguistic Properties [PDF] 摘要

38. Word Embeddings for Chemical Patent Natural Language Processing [PDF] 摘要

39. Unsupervised Paraphrase Generation via Dynamic Blocking [PDF] 摘要

40. NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints [PDF] 摘要

41. FedE: Embedding Knowledge Graphs in Federated Setting [PDF] 摘要

42. Revisiting Neural Language Modelling with Syllables [PDF] 摘要

43. Learning Contextualized Knowledge Structures for Commonsense Reasoning [PDF] 摘要

44. Learning to Deceive Knowledge Graph Augmented Models via Targeted Perturbation [PDF] 摘要

45. Large Scale Legal Text Classification Using Transformer Models [PDF] 摘要

46. Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine Translation [PDF] 摘要

47. Efficiently Mitigating Classification Bias via Transfer Learning [PDF] 摘要

48. When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language Models [PDF] 摘要

49. ReadOnce Transformers: Reusable Representations of Text for Transformers [PDF] 摘要

50. CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers [PDF] 摘要

51. FLIN: A Flexible Natural Language Interface for Web Navigation [PDF] 摘要

52. Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation [PDF] 摘要

53. Go Figure! A Meta Evaluation of Factuality in Summarization [PDF] 摘要

54. Weakly-supervised VisualBERT: Pre-training without Parallel Images and Captions [PDF] 摘要

55. Cross-Modal Transfer Learning for Multilingual Speech-to-Text Translation [PDF] 摘要

56. Keyphrase Extraction with Dynamic Graph Convolutional Networks and Diversified Inference [PDF] 摘要

57. Context-aware Decoder for Neural Machine Translation using a Target-side Document-Level Language Model [PDF] 摘要

58. Text Editing by Command [PDF] 摘要

59. Cross-neutralising: Probing for joint encoding of linguistic information in multilingual models [PDF] 摘要

60. Rethinking embedding coupling in pre-trained language models [PDF] 摘要

61. "Nice Try, Kiddo": Ad Hominems in Dialogue Systems [PDF] 摘要

62. Inducing Taxonomic Knowledge from Pretrained Transformers [PDF] 摘要

63. A Frustratingly Easy Approach for Joint Entity and Relation Extraction [PDF] 摘要

64. Paired Representation Learning for Event and Entity Coreference [PDF] 摘要

65. COUGH: A Challenge Dataset and Models for COVID-19 FAQ Retrieval [PDF] 摘要

66. CaM-Gen:Causally-aware Metric-guided Text Generation [PDF] 摘要

67. X-Class: Text Classification with Extremely Weak Supervision [PDF] 摘要

68. Exploration of NLU: disassemble the information represented by Natural Language, based on the understanding of the internal structure of information, modeling the storage and processing system of information [PDF] 摘要

69. Efficient End-to-end Learning of Cross-event Dependencies for Document-level Event Extraction [PDF] 摘要

70. Measuring the `I don't know' Problem through the Lens of Gricean Quantity [PDF] 摘要

71. Clustering Contextualized Representations of Text for Unsupervised Syntax Induction [PDF] 摘要

72. Open-Domain Dialogue Generation Based on Pre-trained Language Models [PDF] 摘要

73. Fair Hate Speech Detection through Evaluation of Social Group Counterfactuals [PDF] 摘要

74. Improving Multilingual Models with Language-Clustered Vocabularies [PDF] 摘要

75. Improved Synthetic Training for Reading Comprehension [PDF] 摘要

76. Structure-Grounded Pretraining for Text-to-SQL [PDF] 摘要

77. On Learning Text Style Transfer with Direct Rewards [PDF] 摘要

78. Conversational Semantic Parsing for Dialog State Tracking [PDF] 摘要

79. Modularity Improves Out-of-Domain Instruction Following [PDF] 摘要

80. Measuring Association Between Labels and Free-Text Rationales [PDF] 摘要

81. NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions [PDF] 摘要

82. Adding Chit-Chats to Enhance Task-Oriented Dialogues [PDF] 摘要

83. Effective Distant Supervision for Temporal Relation Extraction [PDF] 摘要

84. Temporal Reasoning on Implicit Events from Distant Supervision [PDF] 摘要

85. Text Style Transfer: A Review and Experiment Evaluation [PDF] 摘要

86. An Evaluation Protocol for Generative Conversational Systems [PDF] 摘要

87. Char2Subword: Extending the Subword Embedding Space from Pre-trained Models Using Robust Character Compositionality [PDF] 摘要

88. ANLIzing the Adversarial Natural Language Inference Dataset [PDF] 摘要

89. Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both? [PDF] 摘要

90. Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation [PDF] 摘要

91. Word2vec Conjecture and A Limitative Result [PDF] 摘要

92. A Caption Is Worth A Thousand Images: Investigating Image Captions for Multimodal Named Entity Recognition [PDF] 摘要

93. Improving Classification through Weak Supervision in Context-specific Conversational Agent Development for Teacher Education [PDF] 摘要

94. Learning to Recognize Dialect Features [PDF] 摘要

95. Graph-Based Universal Dependency Parsing in the Age of the Transformer: What Works, and What Doesn't [PDF] 摘要

96. AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization [PDF] 摘要

97. Large Scale Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-training [PDF] 摘要

98. Dynamic Contextualized Word Embeddings [PDF] 摘要

99. Robust Document Representations using Latent Topics and Metadata [PDF] 摘要

100. A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing [PDF] 摘要

101. Overcoming Conflicting Data for Model Updates [PDF] 摘要

102. On Minimum Word Error Rate Training of the Hybrid Autoregressive Transducer [PDF] 摘要

103. Generating Adequate Distractors for Multiple-Choice Questions [PDF] 摘要

104. Rapid Domain Adaptation for Machine Translation with Monolingual Data [PDF] 摘要

105. Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering [PDF] 摘要

106. Posterior Differential Regularization with f-divergence for Improving Model Robustness [PDF] 摘要

107. Domain Specific Complex Sentence (DCSC) Semantic Similarity Dataset [PDF] 摘要

108. Did You Ask a Good Question? A Cross-Domain Question Intention Classification Benchmark for Text-to-SQL [PDF] 摘要

109. Anchor-based Bilingual Word Embeddings for Low-Resource Languages [PDF] 摘要

110. Topic Modeling with Contextualized Word Representation Clusters [PDF] 摘要

111. Unsupervised Multi-hop Question Answering by Question Generation [PDF] 摘要

112. Ranking Creative Language Characteristics in Small Data Scenarios [PDF] 摘要

113. Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence [PDF] 摘要

114. Speaker Anonymization with Distribution-Preserving X-Vector Generation for the VoicePrivacy Challenge 2020 [PDF] 摘要

115. Improved Mask-CTC for Non-Autoregressive End-to-End ASR [PDF] 摘要

116. ExplanationLP: Abductive Reasoning for Explainable Science Question Answering [PDF] 摘要

117. Neural Code Completion with Anonymized Variable Names [PDF] 摘要

118. Long Document Ranking with Query-Directed Sparse Transformer [PDF] 摘要

119. The RobotSlang Benchmark: Dialog-guided Robot Localization and Navigation [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-10-26

发表于 2020-10-26 更新于 2020-10-28 分类于 arxiv ， CV 89k 2:29

目录

1. A modified Bayesian Convolutional Neural Network for Breast Histopathology Image Classification and Uncertainty Quantification [PDF] 摘要

2. Object-aware Feature Aggregation for Video Object Detection [PDF] 摘要

3. High-Throughput Image-Based Plant Stand Count Estimation Using Convolutional Neural Networks [PDF] 摘要

4. ResNet or DenseNet? Introducing Dense Shortcuts to ResNet [PDF] 摘要

5. Primal-Dual Mesh Convolutional Neural Networks [PDF] 摘要

6. LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration [PDF] 摘要

7. Importance-Aware Semantic Segmentation in Self-Driving with Discrete Wasserstein Training [PDF] 摘要

8. BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo [PDF] 摘要

9. Pathological Visual Question Answering [PDF] 摘要

10. Unsupervised Domain Adaptation without Source Data by Casting a BAIT [PDF] 摘要

11. DLDL: Dynamic Label Dictionary Learning via Hypergraph Regularization [PDF] 摘要

12. SAHDL: Sparse Attention Hypergraph Regularized Dictionary Learning [PDF] 摘要

13. RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor [PDF] 摘要

14. Efficient grouping for keypoint detection [PDF] 摘要

15. Spherical Harmonics for Shape-Constrained 3D Cell Segmentation [PDF] 摘要

16. Fusion of Dual Spatial Information for Hyperspectral Image Classification [PDF] 摘要

17. Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence [PDF] 摘要

18. Error Bounds of Projection Models in Weakly Supervised 3D Human Pose Estimation [PDF] 摘要

19. Matching the Clinical Reality: Accurate OCT-Based Diagnosis From Few Labels [PDF] 摘要

20. Self-Learning Transformations for Improving Gaze and Head Redirection [PDF] 摘要

21. Show and Speak: Directly Synthesize Spoken Description of Images [PDF] 摘要

22. IPU-Net: Multi Scale Identity-Preserved U-Net for Low Resolution Face Recognition [PDF] 摘要

23. Domain Adaptation in LiDAR Semantic Segmentation [PDF] 摘要

24. Hard Example Generation by Texture Synthesis for Cross-domain Shape Similarity Learning [PDF] 摘要

25. Temporal Attention-Augmented Graph Convolutional Network for Efficient Skeleton-Based Human Action Recognition [PDF] 摘要

26. A Teacher-Student Framework for Semi-supervised Medical Image Segmentation From Mixed Supervision [PDF] 摘要

27. Feature matching in Ultrasound images [PDF] 摘要

28. The Analysis of Facial Feature Deformation using Optical Flow Algorithm [PDF] 摘要

29. Learn Robust Features via Orthogonal Multi-Path [PDF] 摘要

30. Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation [PDF] 摘要

31. Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation [PDF] 摘要

32. AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting [PDF] 摘要

33. Rethinking the competition between detection and ReID in Multi-Object Tracking [PDF] 摘要

34. Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation [PDF] 摘要

35. Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization [PDF] 摘要

36. GPS-Denied Navigation Using SAR Images and Neural Networks [PDF] 摘要

37. Few-shot Image Recognition with Manifolds [PDF] 摘要

38. Contrastive Learning with Adversarial Examples [PDF] 摘要

39. Keep your Eyes on the Lane: Attention-guided Lane Detection [PDF] 摘要

40. Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection [PDF] 摘要

41. AutoPruning for Deep Neural Network with Dynamic Channel Masking [PDF] 摘要

42. Unsupervised deep learning for grading of age-related macular degeneration using retinal fundus images [PDF] 摘要

43. Noise2Same: Optimizing A Self-Supervised Bound for Image Denoising [PDF] 摘要

44. Non-convex Super-resolution of OCT images via sparse representation [PDF] 摘要

45. CLOUD: Contrastive Learning of Unsupervised Dynamics [PDF] 摘要

46. Estimation of Cardiac Valve Annuli Motion with Deep Learning [PDF] 摘要

47. Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising [PDF] 摘要

48. Segmentation of the cortical plate in fetal brain MRI with a topological loss [PDF] 摘要

49. Checkerboard-Artifact-Free Image-Enhancement Network Considering Local and Global Features [PDF] 摘要

50. Tele-operative Robotic Lung Ultrasound Scanning Platform for Triage of COVID-19 Patients [PDF] 摘要

51. Population Gradients improve performance across data-sets and architectures in object classification [PDF] 摘要

52. Coping with Label Shift via Distributionally Robust Optimisation [PDF] 摘要

53. Tensor Reordering for CNN Compression [PDF] 摘要

54. Language-Conditioned Imitation Learning for Robot Manipulation Tasks [PDF] 摘要

55. Zoom on the Keystrokes: Exploiting Video Calls for Keystroke Inference Attacks [PDF] 摘要

56. A generalized deep learning model for multi-disease Chest X-Ray diagnostics [PDF] 摘要

57. Simple Neighborhood Representative Pre-processing Boosts Outlier Detectors [PDF] 摘要

58. Using Deep Image Priors to Generate Counterfactual Explanations [PDF] 摘要

59. Deep Image Prior for Sparse-sampling Photoacoustic Microscopy [PDF] 摘要

60. Automating Abnormality Detection in Musculoskeletal Radiographs through Deep Learning [PDF] 摘要

61. Towards falsifiable interpretability research [PDF] 摘要

62. CellCycleGAN: Spatiotemporal Microscopy Image Synthesis of Cell Populations using Statistical Shape Models and Conditional GANs [PDF] 摘要

63. Characterizing Datasets for Social Visual Question Answering, and the New TinySocial Dataset [PDF] 摘要

64. Investigating Cultural Aspects in the Fundamental Diagram using Convolutional Neural Networks and Simulation [PDF] 摘要

65. MTGAT: Multimodal Temporal Graph Attention Networks for Unaligned Human Multimodal Language Sequences [PDF] 摘要

66. Deep Convolutional Neural Networks Model-based Brain Tumor Detection in Brain MRI Images [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-10-26

发表于 2020-10-26 更新于 2020-10-28 分类于 arxiv ， CL 82k 2:16

目录

1. DICT-MLM: Improved Multilingual Pre-Training using Bilingual Dictionaries [PDF] 摘要

2. Customizing Triggers with Concealed Data Poisoning [PDF] 摘要

3. On the Transformer Growth for Progressive BERT Training [PDF] 摘要

4. Multilingual BERT Post-Pretraining Alignment [PDF] 摘要

5. GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method [PDF] 摘要

6. Retrieve, Rerank, Read, then Iterate: Answering Open-Domain Questions of Arbitrary Complexity from Text [PDF] 摘要

7. Neural Passage Retrieval with Improved Negative Contrast [PDF] 摘要

8. Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification [PDF] 摘要

9. Improving Robustness by Augmenting Training Sentences with Predicate-Argument Structures [PDF] 摘要

10. Helping users discover perspectives: Enhancing opinion mining with joint topic models [PDF] 摘要

11. Understanding the Extent to which Summarization Evaluation Metrics Measure the Information Quality of Summaries [PDF] 摘要

12. Intrinsic Quality Assessment of Arguments [PDF] 摘要

13. HateBERT: Retraining BERT for Abusive Language Detection in English [PDF] 摘要

14. Natural Language Processing Chains Inside a Cross-lingual Event-Centric Knowledge Pipeline for European Union Under-resourced Languages [PDF] 摘要

15. Evaluating Language Tools for Fifteen EU-official Under-resourced Languages [PDF] 摘要

16. TweetEval: Unified Benchmark and Comparative Evaluation for Tweet Classification [PDF] 摘要

17. Deep Learning Framework for Measuring the Digital Strategy of Companies from Earnings Calls [PDF] 摘要

18. SmBoP: Semi-autoregressive Bottom-up Semantic Parsing [PDF] 摘要

19. UNER: Universal Named-Entity RecognitionFramework [PDF] 摘要

20. Unsupervised Cross-lingual Adaptation for Sequence Tagging and Beyond [PDF] 摘要

21. Pretraining and Fine-Tuning Strategies for Sentiment Analysis of Latvian Tweets [PDF] 摘要

22. NLNDE at CANTEMIST: Neural Sequence Labeling and Parsing Approaches for Clinical Concept Extraction [PDF] 摘要

23. BARThez: a Skilled Pretrained French Sequence-to-Sequence Model [PDF] 摘要

24. A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios [PDF] 摘要

25. Adversarial Learning of Feature-based Meta-Embeddings [PDF] 摘要

26. ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding [PDF] 摘要

27. Pre-trained Model for Chinese Word Segmentation with Meta Learning [PDF] 摘要

28. A Scalable Framework for Learning From Implicit User Feedback to Improve Natural Language Understanding in Large-Scale Conversational AI Systems [PDF] 摘要

29. Proof-theoretic aspects of NL$λ$ [PDF] 摘要

30. Domain Divergences: a Survey and Empirical Analysis [PDF] 摘要

31. Identifying Similar Movie Characters Quickly but Effectively Using Non-exhaustive Pair-wise Attention [PDF] 摘要

32. KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi [PDF] 摘要

33. Attention Transfer Network for Aspect-level Sentiment Classification [PDF] 摘要

34. ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding [PDF] 摘要

35. Summarizing Utterances from Japanese Assembly Minutes using Political Sentence-BERT-based Method for QA Lab-PoliInfo-2 Task of NTCIR-15 [PDF] 摘要

36. Multilingual Synthetic Question and Answer Generation for Cross-Lingual Reading Comprehension [PDF] 摘要

37. Meta-Learning for Domain Generalization in Semantic Parsing [PDF] 摘要

38. MTGAT: Multimodal Temporal Graph Attention Networks for Unaligned Human Multimodal Language Sequences [PDF] 摘要

39. The Turking Test: Can Language Models Understand Instructions? [PDF] 摘要

40. A Joint Learning Approach based on Self-Distillation for Keyphrase Extraction from Scientific Documents [PDF] 摘要

41. Rediscovering the Slavic Continuum in Representations Emerging from Neural Models of Spoken Language Identification [PDF] 摘要

42. Language Models are Open Knowledge Graphs [PDF] 摘要

43. Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled Data [PDF] 摘要

44. A Differentially Private Text Perturbation Method Using a Regularized Mahalanobis Metric [PDF] 摘要

45. EML System Description for VoxCeleb Speaker Diarization Challenge 2020 [PDF] 摘要

46. An Analysis of LIME for Text Data [PDF] 摘要

47. Show and Speak: Directly Synthesize Spoken Description of Images [PDF] 摘要

48. Any-to-One Sequence-to-Sequence Voice Conversion using Self-Supervised Discrete Speech Representations [PDF] 摘要

49. Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer [PDF] 摘要

50. Transformer-based End-to-End Speech Recognition with Local Dense Synthesizer Attention [PDF] 摘要

51. Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation [PDF] 摘要

52. Knowledge Graph Embedding with Atrous Convolution and Residual Learning [PDF] 摘要

53. How Phonotactics Affect Multilingual and Zero-shot ASR Performance [PDF] 摘要

54. Improving Streaming Automatic Speech Recognition With Non-Streaming Model Distillation On Unsupervised Data [PDF] 摘要

55. Language-Conditioned Imitation Learning for Robot Manipulation Tasks [PDF] 摘要

56. Characterizing Datasets for Social Visual Question Answering, and the New TinySocial Dataset [PDF] 摘要

57. The HUAWEI Speaker Diarisation System for the VoxCeleb Speaker Diarisation Challenge [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-10-23

发表于 2020-10-23 分类于 arxiv ， CV 127k 3:32

目录

1. Few-Shot Adaptation of Generative Adversarial Networks [PDF] 摘要

2. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale [PDF] 摘要

3. GAZED- Gaze-guided Cinematic Editing of Wide-Angle Monocular Video Recordings [PDF] 摘要

4. AEGIS: A real-time multimodal augmented reality computer vision based system to assist facial expression recognition for individuals with autism spectrum disorder [PDF] 摘要

5. Spatio-temporal Features for Generalized Detection of Deepfake Videos [PDF] 摘要

6. Blind Video Temporal Consistency via Deep Video Prior [PDF] 摘要

7. Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Free [PDF] 摘要

8. Castle in the Sky: Dynamic Sky Replacement and Harmonization in Videos [PDF] 摘要

9. FasterRCNN Monitoring of Road Damages: Competition and Deployment [PDF] 摘要

10. Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition [PDF] 摘要

11. Self-Supervised Learning of Part Mobility from Point Cloud Sequence [PDF] 摘要

12. Identification of deep breath while moving forward based on multiple body regions and graph signal analysis [PDF] 摘要

13. A Cluster-Matching-Based Method for Video Face Recognition [PDF] 摘要

14. Vision-Based Layout Detection from Scientific Literature using Recurrent Convolutional Neural Networks [PDF] 摘要

15. What do CNN neurons learn: Visualization & Clustering [PDF] 摘要

16. LID 2020: The Learning from Imperfect Data Challenge Results [PDF] 摘要

17. Restoring Negative Information in Few-Shot Object Detection [PDF] 摘要

18. Using Conditional Generative Adversarial Networks to Reduce the Effects of Latency in Robotic Telesurgery [PDF] 摘要

19. Fast and Incremental Loop Closure Detection with Deep Features and Proximity Graphs [PDF] 摘要

20. MLOD: Awareness of Extrinsic Perturbation in Multi-LiDAR 3D Object Detection for Autonomous Driving [PDF] 摘要

21. Spatial Attention as an Interface for Image Captioning Models [PDF] 摘要

22. On Benchmarking Iris Recognition within a Head-mounted Display for AR/VR Application [PDF] 摘要

23. Generative Model-Enhanced Human Motion Prediction [PDF] 摘要

24. A Data Set and a Convolutional Model for Iconography Classification in Paintings [PDF] 摘要

25. BlendTorch: A Real-Time, Adaptive Domain Randomization Library [PDF] 摘要

26. Unsupervised Representation Learning by InvariancePropagation [PDF] 摘要

27. Conversion and Implementation of State-of-the-Art Deep Learning Algorithms for the Classification of Diabetic Retinopathy [PDF] 摘要

28. Tackling problems of marker-based augmented reality under water [PDF] 摘要

29. Cross-Spectral Iris Matching Using Conditional Coupled GAN [PDF] 摘要

30. DocStruct: A Multimodal Method to Extract Hierarchy Structure in Document for General Form Understanding [PDF] 摘要

31. Learning Panoptic Segmentation from Instance Contours [PDF] 摘要

32. DPAttack: Diffused Patch Attacks against Universal Object Detection [PDF] 摘要

33. Efficient Generalized Spherical CNNs [PDF] 摘要

34. Learning to Sort Image Sequences via Accumulated Temporal Differences [PDF] 摘要

35. Self-Supervised Shadow Removal [PDF] 摘要

36. Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization [PDF] 摘要

37. Face Hallucination Using Split-Attention in Split-Attention Network [PDF] 摘要

38. Fingerprint Orientation Estimation: Challenges and Opportunities [PDF] 摘要

39. Learning Dual Semantic Relations with Graph Attention for Image-Text Matching [PDF] 摘要

40. TLGAN: document Text Localization using Generative Adversarial Nets [PDF] 摘要

41. Convolutional Autoencoders for Human Motion Infilling [PDF] 摘要

42. F-Siamese Tracker: A Frustum-based Double Siamese Network for 3D Single Object Tracking [PDF] 摘要

43. 3D Meta-Registration: Learning to Learn Registration of 3D Point Clouds [PDF] 摘要

44. High resolution weakly supervised localization architectures for medical images [PDF] 摘要

45. An explainable deep vision system for animal classification and detection in trail-camera images with automatic post-deployment retraining [PDF] 摘要

46. Novel View Synthesis from only a 6-DoF Camera Pose by Two-stage Networks [PDF] 摘要

47. Fine-tuned Pre-trained Mask R-CNN Models for Surface Object Detection [PDF] 摘要

48. GAN based Unsupervised Segmentation: Should We Match the Exact Number of Objects [PDF] 摘要

49. Task-Adaptive Feature Transformer for Few-Shot Segmentation [PDF] 摘要

50. Efficient Scale-Permuted Backbone with Learned Resource Distribution [PDF] 摘要

51. Learning Loss for Test-Time Augmentation [PDF] 摘要

52. Learning Occupancy Function from Point Clouds for Surface Reconstruction [PDF] 摘要

53. Learning Graph-Based Priors for Generalized Zero-Shot Learning [PDF] 摘要

54. QISTA-Net: DNN Architecture to Solve $\ell_q$-norm Minimization Problem and Image Compressed Sensing [PDF] 摘要

55. Bandwidth-Adaptive Feature Sharing for Cooperative LIDAR Object Detection [PDF] 摘要

56. Voronoi Convolutional Neural Networks [PDF] 摘要

57. Performance Prediction for Convolutional Neural Networks in Edge Devices [PDF] 摘要

58. Unrolling of Deep Graph Total Variation for Image Denoising [PDF] 摘要

59. Shedding Light on Blind Spots: Developing a Reference Architecture to Leverage Video Data for Process Mining [PDF] 摘要

60. Neural Star Domain as Primitive Representation [PDF] 摘要

61. Learning Black-Box Attackers with Transferable Priors and Query Feedback [PDF] 摘要

62. OCT-GAN: Single Step Shadow and Noise Removal from Optical Coherence Tomography Images of the Human Optic Nerve Head [PDF] 摘要

63. Automatic Data Augmentation for 3D Medical Image Segmentation [PDF] 摘要

64. PlenoptiCam v1.0: A light-field imaging framework [PDF] 摘要

65. A Very Compact Embedded CNN Processor Design Based on Logarithmic Computing [PDF] 摘要

66. Disentangling Action Sequences: Discovering Correlated Samples [PDF] 摘要

67. Lung Nodule Classification Using Biomarkers, Volumetric Radiomics and 3D CNNs [PDF] 摘要

68. Motion Planning Combines Psychological Safety and Motion Prediction for a Sense Motive Robot [PDF] 摘要

69. On the Power of Deep but Naive Partial Label Learning [PDF] 摘要

70. Defense-guided Transferable Adversarial Attacks [PDF] 摘要

71. Malaria detection from RBC images using shallow Convolutional Neural Networks [PDF] 摘要

72. SEG-MAT: 3D Shape Segmentation Using Medial Axis Transform [PDF] 摘要

73. DeepCSR: A 3D Deep Learning Approach for Cortical Surface Reconstruction [PDF] 摘要

74. Rethinking pooling in graph neural networks [PDF] 摘要

75. DPD-InfoGAN: Differentially Private Distributed InfoGAN [PDF] 摘要

76. Deep Learning for Distinguishing Normal versus Abnormal Chest Radiographs and Generalization to Unseen Diseases [PDF] 摘要

77. Class-Conditional Defense GAN Against End-to-End Speech Attacks [PDF] 摘要

78. AttendAffectNet: Self-Attention based Networks for Predicting Affective Responses from Movies [PDF] 摘要

79. Product Manifold Learning [PDF] 摘要

阅读全文 »