【arxiv论文】 Computation and Language 2020-07-02

发表于 2020-07-02 分类于 arxiv ， CL 22k 36 分钟

目录

1. Knowledge-Aware Language Model Pretraining [PDF] 摘要

2. COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation [PDF] 摘要

3. Towards User Friendly Medication Mapping Using Entity-Boosted Two-Tower Neural Network [PDF] 摘要

4. Iterative Paraphrastic Augmentation with Discriminative Span Alignment [PDF] 摘要

5. Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering [PDF] 摘要

6. So What's the Plan? Mining Strategic Planning Document [PDF] 摘要

7. SemEval-2020 Task 4: Commonsense Validation and Explanation [PDF] 摘要

8. Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation [PDF] 摘要

9. Transferability of Natural Language Inference to Biomedical Question Answering [PDF] 摘要

10. Adversarial Mutual Information for Text Generation [PDF] 摘要

11. OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings [PDF] 摘要

12. Unsupervised Semantic Hashing with Pairwise Reconstruction [PDF] 摘要

13. Whole-Word Segmental Speech Recognition with Acoustic Word Embeddings [PDF] 摘要

14. Modality-Agnostic Attention Fusion for visual search with text feedback [PDF] 摘要

15. Multi-view Frequency LSTM: An Efficient Frontend for Automatic Speech Recognition [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-30

发表于 2020-06-30 分类于 arxiv ， CV 150k 4:10

目录

1. The Heterogeneity Hypothesis: Finding Layer-Wise Dissimilated Network Architecture [PDF] 摘要

2. The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization [PDF] 摘要

3. Self-Supervised MultiModal Versatile Networks [PDF] 摘要

4. Unsupervised Learning Consensus Model for Dynamic Texture Videos Segmentation [PDF] 摘要

5. Automatic Operating Room Surgical Activity Recognition for Robot-Assisted Surgery [PDF] 摘要

6. Human Activity Recognition based on Dynamic Spatio-Temporal Relations [PDF] 摘要

7. GramGAN: Deep 3D Texture Synthesis From 2D Exemplars [PDF] 摘要

8. Iris Recognition: Inherent Binomial Degrees of Freedom [PDF] 摘要

9. A Measurement of Transportation Ban inside Wuhan on the COVID-19 Epidemic by Vehicle Detection in Remote Sensing Imagery [PDF] 摘要

10. Layered Stereo by Cooperative Grouping with Occlusion [PDF] 摘要

11. Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation [PDF] 摘要

12. Forgery Detection in a Questioned Hyperspectral Document Image using K-means Clustering [PDF] 摘要

13. Visual Kinship Recognition: A Decade in the Making [PDF] 摘要

14. Creating Artificial Modalities to Solve RGB Liveness [PDF] 摘要

15. Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition [PDF] 摘要

16. MoNet3D: Towards Accurate Monocular 3D Object Localization in Real Time [PDF] 摘要

17. Explainable 3D Convolutional Neural Networks by Learning Temporal Transformations [PDF] 摘要

18. Adversarial Multi-Source Transfer Learning in Healthcare: Application to Glucose Prediction for Diabetic People [PDF] 摘要

19. Hybrid Tensor Decomposition in Neural Network Compression [PDF] 摘要

20. Improving Few-Shot Learning using Composite Rotation based Auxiliary Task [PDF] 摘要

21. Abnormal activity capture from passenger flow of elevator based on unsupervised learning and fine-grained multi-label recognition [PDF] 摘要

22. A Benchmark dataset for both underwater image enhancement and underwater object detection [PDF] 摘要

23. Active Ensemble Deep Learning for Polarimetric Synthetic Aperture Radar Image Classification [PDF] 摘要

24. EmotionNet Nano: An Efficient Deep Convolutional Neural Network Design for Real-time Facial Expression Recognition [PDF] 摘要

25. Roweisposes, Including Eigenposes, Supervised Eigenposes, and Fisherposes, for 3D Action Recognition [PDF] 摘要

26. Unsupervised Learning of Video Representations via Dense Trajectory Clustering [PDF] 摘要

27. Generalizable Cone Beam CT Esophagus Segmentation Using In Silico Data Augmentation [PDF] 摘要

28. Harvesting, Detecting, and Characterizing Liver Lesions from Large-scale Multi-phase CT Data via Deep Dynamic Texture Learning [PDF] 摘要

29. Geometry-Inspired Top-k Adversarial Perturbations [PDF] 摘要

30. Video Representations of Goals Emerge from Watching Failure [PDF] 摘要

31. Improving VQA and its Explanations \\ by Comparing Competing Explanations [PDF] 摘要

32. Offline Handwritten Chinese Text Recognition with Convolutional Neural Networks [PDF] 摘要

33. Analogical Image Translation for Fog Generation [PDF] 摘要

34. Shadow Removal by a Lightness-Guided Network with Training on Unpaired Data [PDF] 摘要

35. Localization Uncertainty Estimation for Anchor-Free Object Detection [PDF] 摘要

36. Multi-Person Pose Regression via Pose Filtering and Scoring [PDF] 摘要

37. MvMM-RegNet: A new image registration framework based on multivariate mixture model and neural network estimation [PDF] 摘要

38. Joint Hand-object 3D Reconstruction from a Single Image with Cross-branch Feature Fusion [PDF] 摘要

39. Dynamic Sampling Networks for Efficient Action Recognition in Videos [PDF] 摘要

40. SAR Image Despeckling by Deep Neural Networks: from a pre-trained model to an end-to-end training strategy [PDF] 摘要

41. DHARI Report to EPIC-Kitchens 2020 Object Detection Challenge [PDF] 摘要

42. Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion [PDF] 摘要

43. DeepACC:Automate Chromosome Classification based on Metaphase Images using Deep Learning Framework Fused with Prior Knowledge [PDF] 摘要

44. Few-Shot Class-Incremental Learning via Feature Space Composition [PDF] 摘要

45. Predictive and Generative Neural Networks for Object Functionality [PDF] 摘要

46. 2nd Place Solution for Waymo Open Dataset Challenge -- 2D Object Detection [PDF] 摘要

47. 1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking [PDF] 摘要

48. 1st Place Solution for Waymo Open Dataset Challenge -- 3D Detection and Domain Adaptation [PDF] 摘要

49. Video Representation Learning with Visual Tempo Consistency [PDF] 摘要

50. Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint Estimates [PDF] 摘要

51. Automated Stitching of Coral Reef Images and Extraction of Features for Damselfish Shoaling Behavior Analysis [PDF] 摘要

52. Frequency learning for image classification [PDF] 摘要

53. Interpretable Deepfake Detection via Dynamic Prototypes [PDF] 摘要

54. AerialMPTNet: Multi-Pedestrian Tracking in Aerial Imagery Using Temporal and Graphical Features [PDF] 摘要

55. On the generalization of learning-based 3D reconstruction [PDF] 摘要

56. Counting Out Time: Class Agnostic Video Repetition Counting in the Wild [PDF] 摘要

57. Improving Interpretability of CNN Models Using Non-Negative Concept Activation Vectors [PDF] 摘要

58. Deep Sea Robotic Imaging Simulator for UUV Development [PDF] 摘要

59. Light Pose Calibration for Camera-light Vision Systems [PDF] 摘要

60. MTStereo 2.0: improved accuracy of stereo depth estimation withMax-trees [PDF] 摘要

61. ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification [PDF] 摘要

62. An Evoked Potential-Guided Deep Learning Brain Representation For Visual Classification [PDF] 摘要

63. PCLNet: A Practical Way for Unsupervised Deep PolSAR Representations and Few-Shot Classification [PDF] 摘要

64. MiniNet: An extremely lightweight convolutional neural network for real-time unsupervised monocular depth estimation [PDF] 摘要

65. Compositional Video Synthesis with Action Graphs [PDF] 摘要

66. Interactive Deep Refinement Network for Medical Image Segmentation [PDF] 摘要

67. Making DensePose fast and light [PDF] 摘要

68. Region-of-interest guided Supervoxel Inpainting for Self-supervision [PDF] 摘要

69. Bookworm continual learning: beyond zero-shot learning and continual learning [PDF] 摘要

70. Large Deformation Diffeomorphic Image Registration with Laplacian Pyramid Networks [PDF] 摘要

71. Shape from Projections via Differentiable Forward Projector [PDF] 摘要

72. COVID-19 detection using Residual Attention Network an Artificial Intelligence approach [PDF] 摘要

73. Interpretable Deep Learning for Pattern Recognition in Brain Differences Between Men and Women [PDF] 摘要

74. Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNet [PDF] 摘要

75. Interpreting and Disentangling Feature Components of Various Complexity from DNNs [PDF] 摘要

76. OpenDVC: An Open Source Implementation of the DVC Video Compression Method [PDF] 摘要

77. End-to-End Differentiable Learning to HDR Image Synthesis for Multi-exposure Images [PDF] 摘要

78. Confidence-rich grid mapping [PDF] 摘要

79. Motion Pyramid Networks for Accurate and Efficient Cardiac Motion Estimation [PDF] 摘要

80. MIMC-VINS: A Versatile and Resilient Multi-IMU Multi-Camera Visual-Inertial Navigation System [PDF] 摘要

81. Simulation of Brain Resection for Cavity Segmentation Using Self-Supervised and Semi-Supervised Learning [PDF] 摘要

82. A lateral semicircular canal segmentation based geometric calibration for human temporal bone CT Image [PDF] 摘要

83. Fabric Image Representation Encoding Networks for Large-scale 3D Medical Image Analysis [PDF] 摘要

84. When and How Can Deep Generative Models be Inverted? [PDF] 摘要

85. Enhancement of a CNN-Based Denoiser Based on Spatial and Spectral Analysis [PDF] 摘要

86. Laplacian Regularized Few-Shot Learning [PDF] 摘要

87. Chroma Intra Prediction with attention-based CNN architectures [PDF] 摘要

88. A Tool for Automatic Estimation of Patient Position in Spinal CT Data [PDF] 摘要

89. Video-Grounded Dialogues with Pretrained Generation Language Models [PDF] 摘要

90. A Retinex based GAN Pipeline to Utilize Paired and Unpaired Datasets for Enhancing Low Light Images [PDF] 摘要

91. Compressive MR Fingerprinting reconstruction with Neural Proximal Gradient iterations [PDF] 摘要

92. Attention-Guided Generative Adversarial Network to Address Atypical Anatomy in Modality Transfer [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-06-30

发表于 2020-06-30 分类于 arxiv ， CL 35k 58 分钟

目录

1. Towards the Study of Morphological Processing of the Tangkhul Language [PDF] 摘要

2. Natural Backdoor Attack on Text Data [PDF] 摘要

3. Multichannel CNN with Attention for Text Classification [PDF] 摘要

4. Leveraging Subword Embeddings for Multinational Address Parsing [PDF] 摘要

5. Want to Identify, Extract and Normalize Adverse Drug Reactions in Tweets? Use RoBERTa [PDF] 摘要

6. Measuring Memorization Effect in Word-Level Neural Networks Probing [PDF] 摘要

7. Improving Sequence Tagging for Vietnamese Text Using Transformer-based Neural Models [PDF] 摘要

8. A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis [PDF] 摘要

9. Hinting Semantic Parsing with Statistical Word Sense Disambiguation [PDF] 摘要

10. Is Japanese gendered language used on Twitter ? A large scale study [PDF] 摘要

11. A Framework for Pre-processing of Social Media Feeds based on Integrated Local Knowledge Base [PDF] 摘要

12. Answering Questions on COVID-19 in Real-Time [PDF] 摘要

13. Combine Convolution with Recurrent Networks for Text Classification [PDF] 摘要

14. Mapping Topic Evolution Across Poetic Traditions [PDF] 摘要

15. Progressive Generation of Long Text [PDF] 摘要

16. Rethinking the Positional Encoding in Language Pre-training [PDF] 摘要

17. Self-Attention Networks for Intent Detection [PDF] 摘要

18. BOND: BERT-Assisted Open-Domain Named Entity Recognition with Distant Supervision [PDF] 摘要

19. A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity Rewards [PDF] 摘要

20. Mind The Facts: Knowledge-Boosted Coherent Abstractive Text Summarization [PDF] 摘要

21. String-based methods for tonal harmony: A corpus study of Haydn's string quartets [PDF] 摘要

22. Video-Grounded Dialogues with Pretrained Generation Language Models [PDF] 摘要

23. Uncertainty-aware Self-training for Text Classification with Few Labels [PDF] 摘要

24. BERTology Meets Biology: Interpreting Attention in Protein Language Models [PDF] 摘要

25. Data augmentation versus noise compensation for x- vector speaker recognition systems in noisy environments [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-29

发表于 2020-06-29 分类于 arxiv ， CV 72k 2:01

目录

1. An Advert Creation System for 3D Product Placements [PDF] 摘要

2. Person Re-identification by analyzing Dynamic Variations in Gait Sequences [PDF] 摘要

3. ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks [PDF] 摘要

4. End-to-end training of deep kernel map networks for image classification [PDF] 摘要

5. Cross-Ssupervised Object Detection [PDF] 摘要

6. High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Images [PDF] 摘要

7. SASO: Joint 3D Semantic-Instance Segmentation via Multi-scale Semantic Association and Salient Point Clustering Optimization [PDF] 摘要

8. Suggestive Annotation of Brain Tumour Images with Gradient-guided Sampling [PDF] 摘要

9. Fast Multi-Level Foreground Estimation [PDF] 摘要

10. Ensemble Transfer Learning for Emergency Landing Field Identification on Moderate Resource Heterogeneous Kubernetes Cluster [PDF] 摘要

11. RPM-Net: Recurrent Prediction of Motion and Parts from Point Cloud [PDF] 摘要

12. Domain Contrast for Domain Adaptive Object Detection [PDF] 摘要

13. Designing and Learning Trainable Priors with Non-Cooperative Games [PDF] 摘要

14. AutoSNAP: Automatically Learning Neural Architectures for Instrument Pose Estimation [PDF] 摘要

15. An Automatic Reader of Identity Documents [PDF] 摘要

16. Expandable YOLO: 3D Object Detection from RGB-D Images [PDF] 摘要

17. Few-Shot Anomaly Detection for Polyp Frames from Colonoscopy [PDF] 摘要

18. Text Detection on Roughly Placed Books by Leveraging a Learning-based Model Trained with Another Domain Data [PDF] 摘要

19. Ricci Curvature Based Volumetric Segmentation of the Auditory Ossicles [PDF] 摘要

20. Unsupervised Discovery of Object Landmarks via Contrastive Learning [PDF] 摘要

21. Blind Image Deconvolution using Student's-t Prior with Overlapping Group Sparsity [PDF] 摘要

22. Pushing the Limit of Unsupervised Learning for Ultrasound Image Artifact Removal [PDF] 摘要

23. Lesion Mask-based Simultaneous Synthesis of Anatomic and MolecularMR Images using a GAN [PDF] 摘要

24. Meta Deformation Network: Meta Functionals for Shape Correspondence [PDF] 摘要

25. Deepfake Detection using Spatiotemporal Convolutional Networks [PDF] 摘要

26. Unsupervised Video Decomposition using Spatio-temporal Iterative Inference [PDF] 摘要

27. CognitiveCNN: Mimicking Human Cognitive Models to resolve Texture-Shape Bias [PDF] 摘要

28. Investigating and Exploiting Image Resolution for Transfer Learning-based Skin Lesion Classification [PDF] 摘要

29. Perspective Plane Program Induction from a Single Image [PDF] 摘要

30. Learning Data Augmentation with Online Bilevel Optimization for Image Classification [PDF] 摘要

31. Adaptive additive classification-based loss for deep metric learning [PDF] 摘要

32. Duodepth: Static Gesture Recognition Via Dual Depth Sensors [PDF] 摘要

33. Fully Convolutional Open Set Segmentation [PDF] 摘要

34. SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scans [PDF] 摘要

35. Determining Image similarity with Quasi-Euclidean Metric [PDF] 摘要

36. Computing Light Transport Gradients using the Adjoint Method [PDF] 摘要

37. A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model [PDF] 摘要

38. Object-Centric Learning with Slot Attention [PDF] 摘要

39. SAR2SAR: a self-supervised despeckling algorithm for SAR images [PDF] 摘要

40. An Interactive Data Visualization and Analytics Tool to Evaluate Mobility and Sociability Trends During COVID-19 [PDF] 摘要

41. Orthogonal Deep Models As Defense Against Black-Box Attacks [PDF] 摘要

42. Not all Failure Modes are Created Equal: Training Deep Neural Networks for Explicable (Mis)Classification [PDF] 摘要

43. A survey of loss functions for semantic segmentation [PDF] 摘要

44. Point Proposal Network for Reconstructing 3D Particle Positions with Sub-Pixel Precision in Liquid Argon Time Projection Chambers [PDF] 摘要

45. Graph Optimal Transport for Cross-Domain Alignment [PDF] 摘要

46. Cascaded Convolutional Neural Networks with Perceptual Loss for Low Dose CT Denoising [PDF] 摘要

47. Deep Q-Network-Driven Catheter Segmentation in 3D US by Hybrid Constrained Semi-Supervised Learning and Dual-UNet [PDF] 摘要

48. Can 3D Adversarial Logos Cloak Humans? [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-06-29

发表于 2020-06-29 分类于 arxiv ， CL 17k 28 分钟

目录

1. Pre-training via Paraphrasing [PDF] 摘要

2. ProVe -- Self-supervised pipeline for automated product replacement and cold-starting based on neural language models [PDF] 摘要

3. What they do when in doubt: a study of inductive biases in seq2seq learners [PDF] 摘要

4. LSBert: A Simple Framework for Lexical Simplification [PDF] 摘要

5. Evaluation of Text Generation: A Survey [PDF] 摘要

6. Dialog as a Vehicle for Lifelong Learning [PDF] 摘要

7. Graph Optimal Transport for Cross-Domain Alignment [PDF] 摘要

8. THEaiTRE: Artificial Intelligence to Write a Theatre Play [PDF] 摘要

9. LPar -- A Distributed Multi Agent platform for building Polyglot, Omni Channel and Industrial grade Natural Language Interfaces [PDF] 摘要

10. TURL: Table Understanding through Representation Learning [PDF] 摘要

11. Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-26

发表于 2020-06-26 分类于 arxiv ， CV 76k 2:06

目录

1. Parametric Instance Classification for Unsupervised Visual Feature Learning [PDF] 摘要

2. An Analysis of SVD for Deep Rotation Estimation [PDF] 摘要

3. Layout Generation and Completion with Self-attention [PDF] 摘要

4. Space-Time Correspondence as a Contrastive Random Walk [PDF] 摘要

5. Learning to simulate complex scenes [PDF] 摘要

6. A causal view of compositional zero-shot recognition [PDF] 摘要

7. SmallBigNet: Integrating Core and Contextual Views for Video Classification [PDF] 摘要

8. Backdoor Attacks on Facial Recognition in the Physical World [PDF] 摘要

9. Dynamically Mitigating Data Discrepancy with Balanced Focal Loss for Replay Attack Detection [PDF] 摘要

10. Lifted Disjoint Paths with Application in Multiple Object Tracking [PDF] 摘要

11. Estimating Displaced Populations from Overhead [PDF] 摘要

12. One Thousand and One Hours: Self-driving Motion Prediction Dataset [PDF] 摘要

13. DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors [PDF] 摘要

14. Deep Convolutional GANs for Car Image Generation [PDF] 摘要

15. Discontinuous and Smooth Depth Completion with Binary Anisotropic Diffusion Tensor [PDF] 摘要

16. Audeo: Audio Generation for a Silent Performance Video [PDF] 摘要

17. Deep Learning for Cornea Microscopy Blind Deblurring [PDF] 摘要

18. PropagationNet: Propagate Points to Curve to Learn Structure Information [PDF] 摘要

19. Self-Segregating and Coordinated-Segregating Transformer for Focused Deep Multi-Modular Network for Visual Question Answering [PDF] 摘要

20. SACT: Self-Aware Multi-Space Feature Composition Transformer for Multinomial Attention for Video Captioning [PDF] 摘要

21. SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization [PDF] 摘要

22. Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks [PDF] 摘要

23. SRFlow: Learning the Super-Resolution Space with Normalizing Flow [PDF] 摘要

24. Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation [PDF] 摘要

25. Neural Architecture Design for GPU-Efficient Networks [PDF] 摘要

26. The flag manifold as a tool for analyzing and comparing data sets [PDF] 摘要

27. Time for a Background Check! Uncovering the impact of Background Features on Deep Neural Networks [PDF] 摘要

28. Road obstacles positional and dynamic features extraction combining object detection, stereo disparity maps and optical flow data [PDF] 摘要

29. Extended Labeled Faces in-the-Wild (ELFW): Augmenting Classes for Face Segmentation [PDF] 摘要

30. Diffusion-Weighted Magnetic Resonance Brain Images Generation with Generative Adversarial Networks and Variational Autoencoders: A Comparison Study [PDF] 摘要

31. Multimarginal Wasserstein Barycenter for Stain Normalization and Augmentation [PDF] 摘要

32. Anomaly Detection using Deep Reconstruction and Forecasting for Autonomous Systems [PDF] 摘要

33. Smooth Adversarial Training [PDF] 摘要

34. Does Adversarial Transferability Indicate Knowledge Transferability? [PDF] 摘要

35. Scalable Spectral Clustering with Nystrom Approximation: Practical and Theoretical Aspects [PDF] 摘要

36. A novel and reliable deep learning web-based tool to detect COVID-19 infection form chest CT-scan [PDF] 摘要

37. Training Variational Networks with Multi-Domain Simulations: Speed-of-Sound Image Reconstruction [PDF] 摘要

38. Epoch-evolving Gaussian Process Guided Learning [PDF] 摘要

39. Collaborative Boundary-aware Context Encoding Networks for Error Map Prediction [PDF] 摘要

40. Perfusion Quantification from Endoscopic Videos: Learning to Read Tumor Signatures [PDF] 摘要

41. Empirical Analysis of Overfitting and Mode Drop in GAN Training [PDF] 摘要

42. Fine granularity access in interactive compression of 360-degree images based on rate adaptive channel codes [PDF] 摘要

43. Deep Residual 3D U-Net for Joint Segmentation and Texture Classification of Nodules in Lung [PDF] 摘要

44. Block-matching in FPGA [PDF] 摘要

45. Blacklight: Defending Black-Box Adversarial Attacks on Deep Neural Networks [PDF] 摘要

46. Compositional Explanations of Neurons [PDF] 摘要

47. Minimum Cost Active Labeling [PDF] 摘要

48. On Mitigating Random and Adversarial Bit Errors [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-06-26

发表于 2020-06-26 分类于 arxiv ， CL 27k 45 分钟

目录

1. IIT Gandhinagar at SemEval-2020 Task 9: Code-Mixed Sentiment Classification Using Candidate Sentence Generation and Selection [PDF] 摘要

2. Learning Source Phrase Representations for Neural Machine Translation [PDF] 摘要

3. Analyzing Effect of Repeated Reading on Oral Fluency and Narrative Production for Computer-Assisted Language Learning [PDF] 摘要

4. Neural Machine Translation For Paraphrase Generation [PDF] 摘要

5. Automatic Domain Adaptation Outperforms Manual Domain Adaptation for Predicting Financial Outcomes [PDF] 摘要

6. A Simple Approach to Case-Based Reasoning in Knowledge Bases [PDF] 摘要

7. Neural Machine Translation for Multilingual Grapheme-to-Phoneme Conversion [PDF] 摘要

8. Explainable CNN-attention Networks (C-Attention Network) for Automated Detection of Alzheimer's Disease [PDF] 摘要

9. Normalizing Text using Language Modelling based on Phonetics and String Similarity [PDF] 摘要

10. XREF: Entity Linking for Chinese News Comments with Supplementary Article Reference [PDF] 摘要

11. Multilingual Jointly Trained Acoustic and Written Word Embeddings [PDF] 摘要

12. Unsupervised Cross-lingual Representation Learning for Speech Recognition [PDF] 摘要

13. Self-Segregating and Coordinated-Segregating Transformer for Focused Deep Multi-Modular Network for Visual Question Answering [PDF] 摘要

14. SACT: Self-Aware Multi-Space Feature Composition Transformer for Multinomial Attention for Video Captioning [PDF] 摘要

15. Riccati-based feedback stabilization for unstable Power system models [PDF] 摘要

16. Towards Differentially Private Text Representations [PDF] 摘要

17. The variation of the sum of edge lengths in linear arrangements of trees [PDF] 摘要

18. Compositional Explanations of Neurons [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-25

发表于 2020-06-25 分类于 arxiv ， CV 111k 3:05

目录

1. Improving task-specific representation via 1M unlabelled images without any extra knowledge [PDF] 摘要

2. 3DMotion-Net: Learning Continuous Flow Function for 3D Motion Prediction [PDF] 摘要

3. Feature-dependent Cross-Connections in Multi-Path Neural Networks [PDF] 摘要

4. Modelling the Statistics of Cyclic Activities by Trajectory Analysis on the Manifold of Positive-Semi-Definite Matrices [PDF] 摘要

5. Automatic Estimation of Self-Reported Pain by Interpretable Representations of Motion Dynamics [PDF] 摘要

6. Movement Tracking by Optical Flow Assisted Inertial Navigation [PDF] 摘要

7. DeepTracking-Net: 3D Tracking with Unsupervised Learning of Continuous Flow [PDF] 摘要

8. X-ModalNet: A Semi-Supervised Deep Cross-Modal Network for Classification of Remote Sensing Data [PDF] 摘要

9. Post-DAE: Anatomically Plausible Segmentation via Post-Processing with Denoising Autoencoders [PDF] 摘要

10. Neural Splines: Fitting 3D Surfaces with Infinitely-Wide Neural Networks [PDF] 摘要

11. Insights from the Future for Continual Learning [PDF] 摘要

12. PhishGAN: Data Augmentation and Identification of Homoglpyh Attacks [PDF] 摘要

13. Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness [PDF] 摘要

14. FBK-HUPBA Submission to the EPIC-Kitchens Action Recognition 2020 Challenge [PDF] 摘要

15. Artist-Guided Semiautomatic Animation Colorization [PDF] 摘要

16. Self-Convolution: A Highly-Efficient Operator for Non-Local Image Restoration [PDF] 摘要

17. Multi-view Drone-based Geo-localization via Style and Spatial Alignment [PDF] 摘要

18. Labelling unlabelled videos from scratch with multi-modal self-supervision [PDF] 摘要

19. Unifying Optimization Methods for Color Filter Design [PDF] 摘要

20. Recurrent Relational Memory Network for Unsupervised Image Captioning [PDF] 摘要

21. Comprehensive Information Integration Modeling Framework for Video Titling [PDF] 摘要

22. Retrospective Loss: Looking Back to Improve Training of Deep Neural Networks [PDF] 摘要

23. Large-scale detection and categorization of oil spills from SAR images with deep learning [PDF] 摘要

24. DISK: Learning local features with policy gradient [PDF] 摘要

25. NINEPINS: Nuclei Instance Segmentation with Point Annotations [PDF] 摘要

26. Defending against adversarial attacks on medical imaging AI system, classification or detection? [PDF] 摘要

27. Affinity Fusion Graph-based Framework for Natural Image Segmentation [PDF] 摘要

28. Towards Adversarial Planning for Indoor Scenes with Rotation [PDF] 摘要

29. 3D Pose Detection in Videos: Focusing on Occlusion [PDF] 摘要

30. Disentangle Perceptual Learning through Online Contrastive Learning [PDF] 摘要

31. Dynamic Functional Connectivity and Graph Convolution Network for Alzheimer's Disease Classification [PDF] 摘要

32. Learning Interclass Relations for Image Classification [PDF] 摘要

33. ATSO: Asynchronous Teacher-Student Optimizationfor Semi-Supervised Medical Image Segmentation [PDF] 摘要

34. IA-MOT: Instance-Aware Multi-Object Tracking with Motion Consistency [PDF] 摘要

35. Learning Semantically Enhanced Feature for Fine-Grained Image Classification [PDF] 摘要

36. Road surface detection and differentiation considering surface damages [PDF] 摘要

37. Rethinking Distributional Matching Based Domain Adaptation [PDF] 摘要

38. Applying Lie Groups Approaches for Rigid Registration of Point Clouds [PDF] 摘要

39. NASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search [PDF] 摘要

40. Image-to-image Mapping with Many Domains by Sparse Attribute Transfer [PDF] 摘要

41. Anomaly Detection with Deep Perceptual Autoencoders [PDF] 摘要

42. Rescaling Egocentric Vision [PDF] 摘要

43. Iris Presentation Attack Detection: Where Are We Now? [PDF] 摘要

44. Neural Non-Rigid Tracking [PDF] 摘要

45. Meta Transfer Learning for Emotion Recognition [PDF] 摘要

46. Malignancy-Aware Follow-Up Volume Prediction for Lung Nodules [PDF] 摘要

47. Microstructure Generation via Generative Adversarial Network for Heterogeneous, Topologically Complex 3D Materials [PDF] 摘要

48. Does Non-COVID19 Lung Lesion Help? Investigating Transferability in COVID-19 CT Image Segmentation [PDF] 摘要

49. COVIDLite: A depth-wise separable deep neural network with white balance and CLAHE for detection of COVID-19 [PDF] 摘要

50. Feedback Graph Attention Convolutional Network for Medical Image Enhancement [PDF] 摘要

51. Stacked Convolutional Neural Network for Diagnosis of COVID-19 Disease from X-ray Images [PDF] 摘要

52. Interpretable Deep Models for Cardiac Resynchronisation Therapy Response Prediction [PDF] 摘要

53. COVID-CXNet: Detecting COVID-19 in Frontal Chest X-ray Images using Deep Learning [PDF] 摘要

54. A Novel Approach for Correcting Multiple Discrete Rigid In-Plane Motions Artefacts in MRI Scans [PDF] 摘要

55. OvA-INN: Continual Learning with Invertible Neural Networks [PDF] 摘要

56. GMMLoc: Structure Consistent Visual Localization with Gaussian Mixture Models [PDF] 摘要

57. On the Empirical Neural Tangent Kernel of Standard Finite-Width Convolutional Neural Network Architectures [PDF] 摘要

58. Learning for Video Compression with Recurrent Auto-Encoder and Recurrent Probability Model [PDF] 摘要

59. Normalized Loss Functions for Deep Learning with Noisy Labels [PDF] 摘要

60. Flexible Image Denoising with Multi-layer Conditional Feature Modulation [PDF] 摘要

61. GIFnets: Differentiable GIF Encoding Framework [PDF] 摘要

62. Learning Disentangled Representations of Video with Missing Data [PDF] 摘要

63. Realistic Adversarial Data Augmentation for MR Image Segmentation [PDF] 摘要

64. 70 years of machine learning in geoscience in review [PDF] 摘要

65. Momentum Contrastive Learning for Few-Shot COVID-19 Diagnosis from Chest CT Images [PDF] 摘要

66. Was there COVID-19 back in 2012? Challenge for AI in Diagnosis with Similar Indications [PDF] 摘要

67. Robot Object Retrieval with Contextual Natural Language Queries [PDF] 摘要

68. Automated Detection of COVID-19 from CT Scans Using Convolutional Neural Networks [PDF] 摘要

阅读全文 »