【arxiv论文】 Computation and Language 2020-07-31

发表于 2020-07-31 分类于 arxiv ， CL 22k 36 分钟

目录

1. Neural Modeling for Named Entities and Morphology (NEMO^2) [PDF] 摘要

2. The optimality of syntactic dependency distances [PDF] 摘要

3. Leverage Unlabeled Data for Abstractive Speech Summarization with Self-Supervised Learning and Back-Summarization [PDF] 摘要

4. Photon: A Robust Cross-Domain Text-to-SQL System [PDF] 摘要

5. NeuralQA: A Usable Library for Question Answering (Contextual Query Expansion + BERT) on Large Datasets [PDF] 摘要

6. MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering [PDF] 摘要

7. The Return of Lexical Dependencies: Neural Lexicalized PCFGs [PDF] 摘要

8. Exploiting stance hierarchies for cost-sensitive stance detection of Web documents [PDF] 摘要

9. Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification [PDF] 摘要

10. An Experimental Study of The Effects of Position Bias on Emotion CauseExtraction [PDF] 摘要

11. AI-based Monitoring and Response System for Hospital Preparedness towards COVID-19 in Southeast Asia [PDF] 摘要

12. Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability [PDF] 摘要

13. Fast, Structured Clinical Documentation via Contextual Autocomplete [PDF] 摘要

14. Exploiting Cross-Lingual Knowledge in Unsupervised Acoustic Modeling for Low-Resource Languages [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-07-30

发表于 2020-07-30 分类于 arxiv ， CV 104k 2:53

目录

1. Simultaneously Learning Corrections and Error Models for Geometry-based Visual Odometry Methods [PDF] 摘要

2. Learning Video Representations from Textual Web Supervision [PDF] 摘要

3. Dynamic Character Graph via Online Face Clustering for Movie Analysis [PDF] 摘要

4. Linear Attention Mechanism: An Efficient Attention for Semantic Segmentation [PDF] 摘要

5. MessyTable: Instance Association in Multiple Camera Views [PDF] 摘要

6. Spatio-temporal Consistency to Detect Potential Aedes aegypti Breeding Grounds in Aerial Video Sequences [PDF] 摘要

7. Difficulty-aware Glaucoma Classification with Multi-Rater Consensus Modeling [PDF] 摘要

8. What My Motion tells me about Your Pose: Self-Supervised Fine-Tuning of Observed Vehicle Orientation Angle [PDF] 摘要

9. Face2Face: Real-time Face Capture and Reenactment of RGB Videos [PDF] 摘要

10. SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation [PDF] 摘要

11. Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition [PDF] 摘要

12. Enriching Video Captions With Contextual Text [PDF] 摘要

13. Stylized Adversarial Defense [PDF] 摘要

14. Meta-Learning with Context-Agnostic Initialisations [PDF] 摘要

15. Solving the Blind Perspective-n-Point Problem End-To-End With Robust Differentiable Geometric Optimization [PDF] 摘要

16. Deep Multi-Scale Resemblance Network for the Sub-class Differentiation of Adrenal Masses on Computed Tomography Images [PDF] 摘要

17. Translate the Facial Regions You Like Using Region-Wise Normalization [PDF] 摘要

18. A SLAM Map Restoration Algorithm Based on Submaps and an Undirected Connected Graph [PDF] 摘要

19. Pooling Regularized Graph Neural Network for fMRI Biomarker Analysis [PDF] 摘要

20. Composer Style Classification of Piano Sheet Music Images Using Language Model Pretraining [PDF] 摘要

21. Camera-Based Piano Sheet Music Identification [PDF] 摘要

22. Realistic Video Summarization through VISIOCITY: A New Benchmark and Evaluation Framework [PDF] 摘要

23. BiTraP: Bi-directional Pedestrian Trajectory Prediction with Multi-modal Goal Estimation [PDF] 摘要

24. Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking [PDF] 摘要

25. Compare and Select: Video Summarization with Multi-Agent Reinforcement Learning [PDF] 摘要

26. Online Visual Place Recognition via Saliency Re-identification [PDF] 摘要

27. A Deep Learning Framework for Generation and Analysis of Driving Scenario Trajectories [PDF] 摘要

28. $S^3$Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data [PDF] 摘要

29. Families In Wild Multimedia (FIW-MM): A Multi-Modal Database for Recognizing Kinship [PDF] 摘要

30. Unsupervised Learning of Particle Image Velocimetry [PDF] 摘要

31. Color-complexity enabled exhaustive color-dots identification and spatial patterns testing in images [PDF] 摘要

32. Automated Intracranial Artery Labeling using a Graph Neural Network and Hierarchical Refinement [PDF] 摘要

33. Towards 3D Visualization of Video from Frames [PDF] 摘要

34. Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation [PDF] 摘要

35. Cassandra: Detecting Trojaned Networks from Adversarial Perturbations [PDF] 摘要

36. A Convolutional Neural Network for gaze preference detection: A potential tool for diagnostics of autism spectrum disorder in children [PDF] 摘要

37. AiR: Attention with Reasoning Capability [PDF] 摘要

38. Neural Network-based Reconstruction in Compressed Sensing MRI Without Fully-sampled Training Data [PDF] 摘要

39. Advancing Visual Specification of Code Requirements for Graphs [PDF] 摘要

40. Force myography benchmark data for hand gesture recognition and transfer learning [PDF] 摘要

41. Reliable Tuberculosis Detection using Chest X-ray with Deep Learning, Segmentation and Visualization [PDF] 摘要

42. Between Subjectivity and Imposition: Power Dynamics in Data Annotation for Computer Vision [PDF] 摘要

43. TR-GAN: Topology Ranking GAN with Triplet Loss for Retinal Artery/Vein Classification [PDF] 摘要

44. An Uncertainty-aware Transfer Learning-based Framework for Covid-19 Diagnosis [PDF] 摘要

45. Efficient OCT Image Segmentation Using Neural Architecture Search [PDF] 摘要

46. PDCOVIDNet: A Parallel-Dilated Convolutional Neural Network Architecture for Detecting COVID-19 from Chest X-Ray Images [PDF] 摘要

47. On the unreasonable effectiveness of CNNs [PDF] 摘要

48. CommuNety: A Deep Learning System for the Prediction of Cohesive Social Communities [PDF] 摘要

49. Multimodal Spatial Attention Module for Targeting Multimodal PET-CT Lung Tumor Segmentation [PDF] 摘要

50. Video compression with low complexity CNN-based spatial resolution adaptation [PDF] 摘要

51. Sample Efficient Interactive End-to-End Deep Learning for Self-Driving Cars with Selective Multi-Class Safe Dataset Aggregation [PDF] 摘要

52. COVID-19 CT Image Synthesis with a Conditional Generative Adversarial Network [PDF] 摘要

53. Object-and-Action Aware Model for Visual Language Navigation [PDF] 摘要

54. Solving Phase Retrieval with a Learned Reference [PDF] 摘要

55. Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation [PDF] 摘要

56. 3D Fusion of Infrared Images with Dense RGB Reconstruction from Multiple Views -- with Application to Fire-fighting Robots [PDF] 摘要

57. A regularized deep matrix factorized model of matrix completion for image restoration [PDF] 摘要

58. Accurate 2D soft segmentation of medical image via SoftGAN network [PDF] 摘要

59. Group Knowledge Transfer: Collaborative Training of Large CNNs on the Edge [PDF] 摘要

60. Decompose X-ray Images for Bone and Soft Tissue [PDF] 摘要

61. Learning to predict metal deformations in hot-rolling processes [PDF] 摘要

62. Enhancement of Retinal Fundus Images via Pixel Color Amplification [PDF] 摘要

63. Extending LOUPE for K-space Under-sampling Pattern Optimization in Multi-coil MRI [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-07-30

发表于 2020-07-30 分类于 arxiv ， CL 18k 31 分钟

目录

1. Mirostat: A Perplexity-Controlled Neural Text Decoding Algorithm [PDF] 摘要

2. #Brexit: Leave or Remain? The Role of User's Community and Diachronic Evolution on Stance Detection [PDF] 摘要

3. Biomedical and Clinical English Model Packages in the Stanza Python NLP Library [PDF] 摘要

4. Object-and-Action Aware Model for Visual Language Navigation [PDF] 摘要

5. Development of POS tagger for English-Bengali Code-Mixed data [PDF] 摘要

6. GUIR at SemEval-2020 Task 12: Domain-Tuned Contextualized Models for Offensive Language Detection [PDF] 摘要

7. Measuring prominence of scientific work in online news as a proxy for impact [PDF] 摘要

8. Towards Ecologically Valid Research on Language User Interfaces [PDF] 摘要

9. Presentation and Analysis of a Multimodal Dataset for Grounded LanguageLearning [PDF] 摘要

10. Enriching Video Captions With Contextual Text [PDF] 摘要

11. Construction and Usage of a Human Body Common Coordinate Framework Comprising Clinical, Semantic, and Spatial Ontologies [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-07-28

发表于 2020-07-28 分类于 arxiv ， CV 154k 4:16

目录

1. Learning Lane Graph Representations for Motion Forecasting [PDF] 摘要

2. Noisy Agents: Self-supervised Exploration by Predicting Auditory Events [PDF] 摘要

3. Associative3D: Volumetric Reconstruction from Sparse Views [PDF] 摘要

4. The Unsupervised Method of Vessel Movement Trajectory Prediction [PDF] 摘要

5. WGANVO: Monocular Visual Odometry based on Generative Adversarial Networks [PDF] 摘要

6. A Closer Look at Art Mediums: The MAMe Image Classification Dataset [PDF] 摘要

7. Ordinary Differential Equation and Complex Matrix Exponential for Multi-resolution Image Registration [PDF] 摘要

8. 3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning [PDF] 摘要

9. Solving Linear Inverse Problems Using the Prior Implicit in a Denoiser [PDF] 摘要

10. Message Passing Least Squares Framework and its Application to Rotation Synchronization [PDF] 摘要

11. Black-Box Face Recovery from Identity Features [PDF] 摘要

12. Towards Accuracy-Fairness Paradox: Adversarial Example-based Data Augmentation for Visual Debiasing [PDF] 摘要

13. SparseTrain: Exploiting Dataflow Sparsity for Efficient Convolutional Neural Networks Training [PDF] 摘要

14. MADGAN: unsupervised Medical Anomaly Detection GAN using multiple adjacent brain MRI slice reconstruction [PDF] 摘要

15. Differentiable Manifold Reconstruction for Point Cloud Denoising [PDF] 摘要

16. Reconstruction Regularized Deep Metric Learning for Multi-label Image Classification [PDF] 摘要

17. A Novel adaptive optimization of Dual-Tree Complex Wavelet Transform for Medical Image Fusion [PDF] 摘要

18. The Effect of Wearing a Mask on Face Recognition Performance: an Exploratory Study [PDF] 摘要

19. Identity-Guided Human Semantic Parsing for Person Re-Identification [PDF] 摘要

20. Two-Level Residual Distillation based Triple Network for Incremental Object Detection [PDF] 摘要

21. Contraction Mapping of Feature Norms for Classifier Learning on the Data with Different Quality [PDF] 摘要

22. YOLOpeds: Efficient Real-Time Single-Shot Pedestrian Detection for Smart Camera Applications [PDF] 摘要

23. Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry [PDF] 摘要

24. NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination [PDF] 摘要

25. Decomposed Generation Networks with Structure Prediction for Recipe Generation from Food Images [PDF] 摘要

26. Part-Aware Data Augmentation for 3D Object Detection in Point Cloud [PDF] 摘要

27. Feature visualization of Raman spectrum analysis with deep convolutional neural network [PDF] 摘要

28. Self-Prediction for Joint Instance and Semantic Segmentation of Point Clouds [PDF] 摘要

29. Few-shot Knowledge Transfer for Fine-grained Cartoon Face Generation [PDF] 摘要

30. Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches [PDF] 摘要

31. Split Computing for Complex Object Detectors: Challenges and Preliminary Results [PDF] 摘要

32. K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations [PDF] 摘要

33. Reconstructing NBA Players [PDF] 摘要

34. Research Progress of Convolutional Neural Network and its Application in Object Detection [PDF] 摘要

35. Representation Learning with Video Deep InfoMax [PDF] 摘要

36. Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation [PDF] 摘要

37. REXUP: I REason, I EXtract, I UPdate with Structured Compositional Reasoning for Visual Question Answering [PDF] 摘要

38. Point-to-set distance functions for weakly supervised segmentation [PDF] 摘要

39. OASIS: A Large-Scale Dataset for Single Image 3D in the Wild [PDF] 摘要

40. Learning and aggregating deep local descriptors for instance-level recognition [PDF] 摘要

41. Deep Photometric Stereo for Non-Lambertian Surfaces [PDF] 摘要

42. Challenge-Aware RGBT Tracking [PDF] 摘要

43. Virtual Multi-view Fusion for 3D Semantic Segmentation [PDF] 摘要

44. Contrastive Visual-Linguistic Pretraining [PDF] 摘要

45. GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision [PDF] 摘要

46. Towards End-to-end Video-based Eye-Tracking [PDF] 摘要

47. SADet: Learning An Efficient and Accurate Pedestrian Detector [PDF] 摘要

48. Detection and Annotation of Plant Organs from Digitized Herbarium Scans using Deep Learning [PDF] 摘要

49. Towards Purely Unsupervised Disentanglement of Appearance and Shape for Person Images Generation [PDF] 摘要

50. U2-ONet: A Two-level Nested Octave U-structure with Multiscale Attention Mechanism for Moving Instances Segmentation [PDF] 摘要

51. SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction [PDF] 摘要

52. Approaches of large-scale images recognition with more than 50,000 categoris [PDF] 摘要

53. A Dual Iterative Refinement Method for Non-rigid Shape Matching [PDF] 摘要

54. Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve [PDF] 摘要

55. Style is a Distribution of Features [PDF] 摘要

56. HATNet: An End-to-End Holistic Attention Network for Diagnosis of Breast Biopsy Images [PDF] 摘要

57. Robust and Generalizable Visual Representation Learning via Random Convolutions [PDF] 摘要

58. GP-Aligner: Unsupervised Non-rigid Groupwise Point Set Registration Based On Optimized Group Latent Descriptor [PDF] 摘要

59. MRGAN: Multi-Rooted 3D Shape Generation with Unsupervised Part Disentanglement [PDF] 摘要

60. Gradient Regularized Contrastive Learning for Continual Domain Adaptation [PDF] 摘要

61. Video Super Resolution Based on Deep Learning: A comprehensive survey [PDF] 摘要

62. Crowdsourced 3D Mapping: A Combined Multi-View Geometry and Self-Supervised Learning Approach [PDF] 摘要

63. Approximated Bilinear Modules for Temporal Modeling [PDF] 摘要

64. Learning Disentangled Representations with Latent Variation Predictability [PDF] 摘要

65. MirrorNet: Bio-Inspired Adversarial Attack for Camouflaged Object Segmentation [PDF] 摘要

66. Applying Semantic Segmentation to Autonomous Cars in the Snowy Environment [PDF] 摘要

67. OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets [PDF] 摘要

68. A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds [PDF] 摘要

69. Counting Fish and Dolphins in Sonar Images Using Deep Learning [PDF] 摘要

70. Spatiotemporal Bundle Adjustment for Dynamic 3D Human Reconstruction in the Wild [PDF] 摘要

71. Dialog without Dialog Data: Learning Visual Dialog Agents from VQA Data [PDF] 摘要

72. Hard negative examples are hard, but useful [PDF] 摘要

73. Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation [PDF] 摘要

74. MMDF: Mobile Microscopy Deep Framework [PDF] 摘要

75. Cloud Detection through Wavelet Transforms in Machine Learning and Deep Learning [PDF] 摘要

76. Towards Learning Convolutions from Scratch [PDF] 摘要

77. Orpheus: A New Deep Learning Framework for Easy Deployment and Evaluation of Edge Inference [PDF] 摘要

78. Hardware Implementation of Hyperbolic Tangent Function using Catmull-Rom Spline Interpolation [PDF] 摘要

79. Attention-based Graph ResNet for Motor Intent Detection from Raw EEG signals [PDF] 摘要

80. Image-driven discriminative and generative machine learning algorithms for establishing microstructure-processing relationships [PDF] 摘要

81. XCAT-GAN for Synthesizing 3D Consistent Labeled Cardiac MR Images on Anatomically Variable XCAT Phantoms [PDF] 摘要

82. ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networks [PDF] 摘要

83. Dual Distribution Alignment Network for Generalizable Person Re-Identification [PDF] 摘要

84. Uniformizing Techniques to Process CT scans with 3D CNNs for Tuberculosis Prediction [PDF] 摘要

85. UIAI System for Short-Duration Speaker Verification Challenge 2020 [PDF] 摘要

86. Regularized Flexible Activation Function Combinations for Deep Neural Networks [PDF] 摘要

87. MACU-Net Semantic Segmentation from High-Resolution Remote Sensing Images [PDF] 摘要

88. A Preliminary Exploration into an Alternative CellLineNet: An Evolutionary Approach [PDF] 摘要

89. Tighter risk certificates for neural networks [PDF] 摘要

90. CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis [PDF] 摘要

91. 3D Neural Network for Lung Cancer Risk Prediction on CT Volumes [PDF] 摘要

92. Modal Uncertainty Estimation via Discrete Latent Representation [PDF] 摘要

93. Joint Featurewise Weighting and Lobal Structure Learning for Multi-view Subspace Clustering [PDF] 摘要

94. All-Optical Information Processing Capacity of Diffractive Surfaces [PDF] 摘要

95. Selection of Proper EEG Channels for Subject Intention Classification Using Deep Learning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-07-16

发表于 2020-07-16 分类于 arxiv ， CV 88k 2:27

目录

1. AdaptiveReID: Adaptive L2 Regularization in Person Re-Identification [PDF] 摘要

2. Transformation Consistency Regularization- A Semi-Supervised Paradigm for Image-to-Image Translation [PDF] 摘要

3. Few-shot Scene-adaptive Anomaly Detection [PDF] 摘要

4. VidCEP: Complex Event Processing Framework to Detect Spatiotemporal Patterns in Video Streams [PDF] 摘要

5. Data-Efficient Deep Learning Method for Image Classification Using Data Augmentation, Focal Cosine Loss, and Ensemble [PDF] 摘要

6. CANet: Context Aware Network for 3D Brain Tumor Segmentation [PDF] 摘要

7. Vision-Based Fall Event Detection in Complex Background Using Attention Guided Bi-directional LSTM [PDF] 摘要

8. Self-Supervised Representation Learning for Detection of ACL Tear Injury in Knee MRI [PDF] 摘要

9. Enhancing Generalized Zero-Shot Learning via Adversarial Visual-Semantic Interaction [PDF] 摘要

10. Finding Non-Uniform Quantization Schemes usingMulti-Task Gaussian Processes [PDF] 摘要

11. Attention as Activation [PDF] 摘要

12. PVSNet: Pixelwise Visibility-Aware Multi-View Stereo Network [PDF] 摘要

13. Lunar Terrain Relative Navigation Using a Convolutional Neural Network for Visual Crater Detection [PDF] 摘要

14. P$^{2}$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation [PDF] 摘要

15. Proof of Concept: Automatic Type Recognition [PDF] 摘要

16. End-to-end training of a two-stage neural network for defect detection [PDF] 摘要

17. Learning to Learn with Variational Information Bottleneck for Domain Generalization [PDF] 摘要

18. Learning Multiplicative Interactions with Bayesian Neural Networks for Visual-Inertial Odometry [PDF] 摘要

19. Visualizing Transfer Learning [PDF] 摘要

20. Fast and Robust Iterative Closet Point [PDF] 摘要

21. Temporal Distinct Representation Learning for Action Recognition [PDF] 摘要

22. Augmented Bi-path Network for Few-shot Learning [PDF] 摘要

23. CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions [PDF] 摘要

24. P2D: a self-supervised method for depth estimation from polarimetry [PDF] 摘要

25. Learning Part Boundaries from 3D Point Clouds [PDF] 摘要

26. Evaluation of Neural Network Classification Systems on Document Stream [PDF] 摘要

27. RobustScanner: Dynamically Enhancing Positional Clues for Robust Text Recognition [PDF] 摘要

28. Learning to Parse Wireframes in Images of Man-Made Environments [PDF] 摘要

29. Learning with Privileged Information for Efficient Image Super-Resolution [PDF] 摘要

30. Learning Visual Context by Comparison [PDF] 摘要

31. Decoding CNN based Object Classifier Using Visualization [PDF] 摘要

32. Explaining Deep Neural Networks using Unsupervised Clustering [PDF] 摘要

33. A cellular automata approach to local patterns for texture recognition [PDF] 摘要

34. Reorganizing local image features with chaotic maps: an application to texture recognition [PDF] 摘要

35. Graph-Based Social Relation Reasoning [PDF] 摘要

36. RGB-IR Cross-modality Person ReID based on Teacher-Student GAN Model [PDF] 摘要

37. ContourRend: A Segmentation Method for Improving Contours by Rendering [PDF] 摘要

38. COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder [PDF] 摘要

39. Comparing to Learn: Surpassing ImageNet Pretraining on Radiographs By Comparing Image Representations [PDF] 摘要

40. Automatic Image Labelling at Pixel Level [PDF] 摘要

41. Automatic extraction of road intersection points from USGS historical map series using deep convolutional neural networks [PDF] 摘要

42. Real-Time Drone Detection and Tracking With Visible, Thermal and Acoustic Sensors [PDF] 摘要

43. Tackling the Problem of Limited Data and Annotations in Semantic Segmentation [PDF] 摘要

44. TinyVIRAT: Low-resolution Video Action Recognition [PDF] 摘要

45. A Generalization of Otsu's Method and Minimum Error Thresholding [PDF] 摘要

46. COBE: Contextualized Object Embeddings from Narrated Instructional Video [PDF] 摘要

47. Privacy Preserving Text Recognition with Gradient-Boosting for Federated Learning [PDF] 摘要

48. Explore and Explain: Self-supervised Navigation and Recounting [PDF] 摘要

49. Non-greedy Gradient-based Hyperparameter Optimization Over Long Horizons [PDF] 摘要

50. Focus-and-Expand: Training Guidance Through Gradual Manipulation of Input Features [PDF] 摘要

51. Relative Pose Estimation of Calibrated Cameras with Known $\mathrm{SE}(3)$ Invariants [PDF] 摘要

52. SpaceNet: Make Free Space For Continual Learning [PDF] 摘要

53. Monocular Retinal Depth Estimation and Joint Optic Disc and Cup Segmentation using Adversarial Networks [PDF] 摘要

54. AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows [PDF] 摘要

55. Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics [PDF] 摘要

56. Concept Learners for Generalizable Few-Shot Learning [PDF] 摘要

57. Relaxed-Responsibility Hierarchical Discrete VAEs [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-07-16

发表于 2020-07-16 分类于 arxiv ， CL 31k 52 分钟

目录

1. Sinhala Language Corpora and Stopwords from a Decade of Sri Lankan Facebook [PDF] 摘要

2. Align then Summarize: Automatic Alignment Methods for Summarization Corpus Creation [PDF] 摘要

3. InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-Training [PDF] 摘要

4. Fine-Tune Longformer for Jointly Predicting Rumor Stance and Veracity [PDF] 摘要

5. AdapterHub: A Framework for Adapting Transformers [PDF] 摘要

6. Multimodal Word Sense Disambiguation in Creative Practice [PDF] 摘要

7. Dual Past and Future for Neural Machine Translation [PDF] 摘要

8. A Multilingual Parallel Corpora Collection Effort for Indian Languages [PDF] 摘要

9. UniTrans: Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data [PDF] 摘要

10. Logic Constrained Pointer Networks for Interpretable Textual Similarity [PDF] 摘要

11. Predicting Clinical Diagnosis from Patients Electronic Health Records Using BERT-based Neural Networks [PDF] 摘要

12. Are We There Yet? Evaluating State-of-the-Art Neural Network based Geoparsers Using EUPEG as a Benchmarking Platform [PDF] 摘要

13. Modeling Coherency in Generated Emails by Leveraging Deep Neural Learners [PDF] 摘要

14. Emoji Prediction: Extensions and Benchmarking [PDF] 摘要

15. Deep learning models for representing out-of-vocabulary words [PDF] 摘要

16. Using Holographically Compressed Embeddings in Question Answering [PDF] 摘要

17. Dialect Diversity in Text Summarization on Twitter [PDF] 摘要

18. Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset [PDF] 摘要

19. Intelligent requirements engineering from natural language and their chaining toward CAD models [PDF] 摘要

20. Cross-Lingual Speaker Verification with Domain-Balanced Hard Prototype Mining and Language-Dependent Score Normalization [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-07-15

发表于 2020-07-15 分类于 arxiv ， CV 146k 4:03

目录

1. Multiview Detection with Feature Perspective Transformation [PDF] 摘要

2. Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter [PDF] 摘要

3. Modeling Artistic Workflows for Image Generation and Editing [PDF] 摘要

4. Multitask Learning Strengthens Adversarial Robustness [PDF] 摘要

5. MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation [PDF] 摘要

6. Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis [PDF] 摘要

7. Alpha-Net: Architecture, Models, and Applications [PDF] 摘要

8. Learning Accurate and Human-Like Driving using Semantic Maps and Attention [PDF] 摘要

9. CenterNet3D:An Anchor free Object Detector for Autonomous Driving [PDF] 摘要

10. Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search [PDF] 摘要

11. Deep Heterogeneous Autoencoder for Subspace Clustering of Sequential Data [PDF] 摘要

12. Wavelet-Based Dual-Branch Network for Image Demoireing [PDF] 摘要

13. Towards Dense People Detection with Deep Learning and Depth images [PDF] 摘要

14. An Uncertainty-based Human-in-the-loop System for Industrial Tool Wear Analysis [PDF] 摘要

15. Re-ranking for Writer Identification and Writer Retrieval [PDF] 摘要

16. Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack [PDF] 摘要

17. Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation [PDF] 摘要

18. UDBNET: Unsupervised Document Binarization Network via Adversarial Game [PDF] 摘要

19. Towards Realistic 3D Embedding via View Alignment [PDF] 摘要

20. Unsupervised Human 3D Pose Representation with Viewpoint and Pose Disentanglement [PDF] 摘要

21. RGB-D Salient Object Detection with Cross-Modality Modulation and Selection [PDF] 摘要

22. Video Object Segmentation with Episodic Graph Memory Networks [PDF] 摘要

23. Correlation filter tracking with adaptive proposal selection for accurate scale estimation [PDF] 摘要

24. Pose2RGBD. Generating Depth and RGB images from absolute positions [PDF] 摘要

25. Improving Face Recognition by Clustering Unlabeled Faces in the Wild [PDF] 摘要

26. P-KDGAN: Progressive Knowledge Distillation with GANs for One-class Novelty Detection [PDF] 摘要

27. Learning Semantics-enriched Representation via Self-discovery, Self-classification, and Self-restoration [PDF] 摘要

28. Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance [PDF] 摘要

29. REPrune: Filter Pruning via Representative Election [PDF] 摘要

30. Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations [PDF] 摘要

31. A Graph-based Interactive Reasoning for Human-Object Interaction Detection [PDF] 摘要

32. AQD: Towards Accurate Quantized Object Detection [PDF] 摘要

33. 360$^\circ$ Depth Estimation from Multiple Fisheye Images with Origami Crown Representation of Icosahedron [PDF] 摘要

34. Joint Layout Analysis, Character Detection and Recognition for Historical Document Digitization [PDF] 摘要

35. Knowledge Distillation for Multi-task Learning [PDF] 摘要

36. JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds [PDF] 摘要

37. Visual Tracking by TridentAlign and Context Embedding [PDF] 摘要

38. Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets [PDF] 摘要

39. Alleviating Over-segmentation Errors by Detecting Action Boundaries [PDF] 摘要

40. BUNET: Blind Medical Image Segmentation Based on Secure UNET [PDF] 摘要

41. Topology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction [PDF] 摘要

42. Socially and Contextually Aware Human Motion and Pose Forecasting [PDF] 摘要

43. Face to Purchase: Predicting Consumer Choices with Structured Facial and Behavioral Traits Embedding [PDF] 摘要

44. Top-Related Meta-Learning Method for Few-Shot Detection [PDF] 摘要

45. A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection [PDF] 摘要

46. DeepMSRF: A novel Deep Multimodal Speaker Recognition framework with Feature selection [PDF] 摘要

47. TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning [PDF] 摘要

48. Meta-rPPG: Remote Heart Rate Estimation Using a Transductive Meta-Learner [PDF] 摘要

49. Vehicle Trajectory Prediction by Transfer Learning of Semi-Supervised Models [PDF] 摘要

50. Semi-supervised Learning with a Teacher-student Network for Generalized Attribute Prediction [PDF] 摘要

51. Patch-wise Attack for Fooling Deep Neural Network [PDF] 摘要

52. Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting [PDF] 摘要

53. JNR: Joint-based Neural Rig Representation for Compact 3D Face Modeling [PDF] 摘要

54. Water level prediction from social media images with a multi-task ranking approach [PDF] 摘要

55. DETCID: Detection of Elongated Touching Cells with Inhomogeneous Illumination using a Deep Adversarial Network [PDF] 摘要

56. Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI [PDF] 摘要

57. A Bayesian Evaluation Framework for Ground Truth-Free Visual Recognition Tasks [PDF] 摘要

58. Measuring Performance of Generative Adversarial Networks on Devanagari Script [PDF] 摘要

59. Deep Image Orientation Angle Detection [PDF] 摘要

60. CPL-SLAM: Efficient and Certifiably Correct Planar Graph-Based SLAM Using the Complex Number Representation [PDF] 摘要

61. Domain Adaptation for Robust Workload Classification using fNIRS [PDF] 摘要

62. Unsupervised object-centric video generation and decomposition in 3D [PDF] 摘要

63. UnRectDepthNet: Self-Supervised Monocular Depth Estimation using a Generic Framework for Handling Common Camera Distortion Models [PDF] 摘要

64. Learning Differential Diagnosis of Skin Conditions with Co-occurrence Supervision using Graph Convolutional Networks [PDF] 摘要

65. Improving Pixel Embedding Learning through Intermediate Distance Regression Supervision for Instance Segmentation [PDF] 摘要

66. Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization [PDF] 摘要

67. Storing Encoded Episodes as Concepts for Continual Learning [PDF] 摘要

68. Deep Doubly Supervised Transfer Network for Diagnosis of Breast Cancer with Imbalanced Ultrasound Imaging Modalities [PDF] 摘要

69. Path Signatures on Lie Groups [PDF] 摘要

70. Dense Crowds Detection and Counting with a Lightweight Architecture [PDF] 摘要

71. A new approach to descriptors generation for image retrieval by analyzing activations of deep neural network layers [PDF] 摘要

72. AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation [PDF] 摘要

73. Closed-Form Factorization of Latent Semantics in GANs [PDF] 摘要

74. Towards causal benchmarking of bias in face analysis algorithms [PDF] 摘要

75. Cross-Domain Medical Image Translation by Shared Latent Gaussian Mixture Model [PDF] 摘要

76. Conditional Image Retrieval [PDF] 摘要

77. MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering [PDF] 摘要

78. Nodule2vec: a 3D Deep Learning System for Pulmonary Nodule Retrieval Using Semantic Representation [PDF] 摘要

79. A Weakly Supervised Region-Based Active Learning Method for COVID-19 Segmentation in CT Images [PDF] 摘要

80. Automated Synthetic-to-Real Generalization [PDF] 摘要

81. Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer [PDF] 摘要

82. Our Evaluation Metric Needs an Update to Encourage Generalization [PDF] 摘要

83. From Symmetry to Geometry: Tractable Nonconvex Problems [PDF] 摘要

84. An Interpretable Baseline for Time Series Classification Without Intensive Learning [PDF] 摘要

85. Landslide Segmentation with U-Net: Evaluating Different Sampling Methods and Patch Sizes [PDF] 摘要

86. T-Basis: a Compact Representation for Neural Networks [PDF] 摘要

87. Inferring the 3D Standing Spine Posture from 2D Radiographs [PDF] 摘要

88. FocusLiteNN: High Efficiency Focus Quality Assessment for Digital Pathology [PDF] 摘要

89. Batch-level Experience Replay with Review for Continual Learning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-07-15

发表于 2020-07-15 分类于 arxiv ， CL 22k 37 分钟

目录

1. Investigation of Sentiment Controllable Chatbot [PDF] 摘要

2. COVID-19 Twitter Dataset with Latent Topics, Sentiments and Emotions Attributes [PDF] 摘要

3. Modeling Voting for System Combination in Machine Translation [PDF] 摘要

4. Contextualized Code Representation Learning for Commit Message Generation [PDF] 摘要

5. Questionnaire analysis to define the most suitable survey for port-noise investigation [PDF] 摘要

6. Language, communication and society: a gender based linguistics analysis [PDF] 摘要

7. Our Evaluation Metric Needs an Update to Encourage Generalization [PDF] 摘要

8. What's in a Name? Are BERT Named Entity Representations just as Good for any other Name? [PDF] 摘要

9. Calling Out Bluff: Attacking the Robustness of Automatic Scoring Systems with Simple Adversarial Testing [PDF] 摘要

10. An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Models [PDF] 摘要

11. Can neural networks acquire a structural bias from raw linguistic data? [PDF] 摘要

12. BERTERS: Multimodal Representation Learning for Expert Recommendation System with Transformer [PDF] 摘要

13. Extracting Structured Data from Physician-Patient Conversations By Predicting Noteworthy Utterances [PDF] 摘要

14. Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASR [PDF] 摘要

15. Compare and Reweight: Distinctive Image Captioning Using Similar Images Sets [PDF] 摘要

16. Sudo rm -rf: Efficient Networks for Universal Audio Source Separation [PDF] 摘要

阅读全文 »