【arxiv论文】 Computation and Language 2020-12-29

发表于 2020-12-29 分类于 arxiv ， CL 54k 1:29

目录

1. Universal Sentence Representation Learning with Conditional Masked Language Model [PDF] 摘要

2. DeepHateExplainer: Explainable Hate Speech Detection in Under-resourced Bengali Language [PDF] 摘要

3. BURT: BERT-inspired Universal Representation from Learning Meaningful Segment [PDF] 摘要

4. Panarchy: ripples of a boundary concept [PDF] 摘要

5. Towards Fully Automated Manga Translation [PDF] 摘要

6. Red Dragon AI at TextGraphs 2020 Shared Task: LIT : LSTM-Interleaved Transformer for Multi-Hop Explanation Ranking [PDF] 摘要

7. On Generating Extended Summaries of Long Documents [PDF] 摘要

8. Neural Text Generation with Artificial Negative Examples [PDF] 摘要

9. Syntax-Enhanced Pre-trained Model [PDF] 摘要

10. Pivot Through English: Reliably Answering Multilingual Questions without Document Retrieval [PDF] 摘要

11. Automatic Curriculum Learning With Over-repetition Penalty for Dialogue Policy Learning [PDF] 摘要

12. ALP-KD: Attention-Based Layer Projection for Knowledge Distillation [PDF] 摘要

13. SMART: A Situation Model for Algebra Story Problems via Attributed Grammar [PDF] 摘要

14. Explaining NLP Models via Minimal Contrastive Editing (MiCE) [PDF] 摘要

15. MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining [PDF] 摘要

16. Adaptive Convolution for Semantic Role Labeling [PDF] 摘要

17. SG-Net: Syntax Guided Transformer for Language Representation [PDF] 摘要

18. An Embarrassingly Simple Model for Dialogue Relation Extraction [PDF] 摘要

19. My Teacher Thinks The World Is Flat! Interpreting Automatic Essay Scoring Mechanism [PDF] 摘要

20. Learning Light-Weight Translation Models from Deep Transformer [PDF] 摘要

21. Inserting Information Bottlenecks for Attribution in Transformers [PDF] 摘要

22. Fine-grained Emotion and Intent Learning in Movie Dialogues [PDF] 摘要

23. LOREN: Logic Enhanced Neural Reasoning for Fact Verification [PDF] 摘要

24. Contextual Temperature for Language Modeling [PDF] 摘要

25. Towards a Universal Continuous Knowledge Base [PDF] 摘要

26. Why Neural Machine Translation Prefers Empty Outputs [PDF] 摘要

27. ThamizhiUDp: A Dependency Parser for Tamil [PDF] 摘要

28. Mechanism of Evolution Shared by Gene and Language [PDF] 摘要

29. The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes [PDF] 摘要

30. Neural document expansion for ad-hoc information retrieval [PDF] 摘要

31. Measuring University Impact: Wikipedia approach [PDF] 摘要

32. Improving Opinion Spam Detection by Cumulative Relative Frequency Distribution [PDF] 摘要

33. Translating Natural Language Instructions to Computer Programs for Robot Manipulation [PDF] 摘要

34. Spatial Reasoning from Natural Language Instructions for Robot Manipulation [PDF] 摘要

35. Social media data reveals signal for public consumer perceptions [PDF] 摘要

36. Learning by Fixing: Solving Math Word Problems with Weak Supervision [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-12-25

发表于 2020-12-25 分类于 arxiv ， CV 80k 2:13

目录

1. Deep Learning-Based Human Pose Estimation: A Survey [PDF] 摘要

2. Global Context Networks [PDF] 摘要

3. Unsupervised deep clustering and reinforcement learning can accurately segment MRI brain tumors with very small training sets [PDF] 摘要

4. Person Re-Identification using Deep Learning Networks: A Systematic Review [PDF] 摘要

5. Seed Phenotyping on Neural Networks using Domain Randomization and Transfer Learning [PDF] 摘要

6. Interpolating Points on a Non-Uniform Grid using a Mixture of Gaussians [PDF] 摘要

7. Dynamic Facial Expression Recognition under Partial Occlusion with Optical Flow Reconstruction [PDF] 摘要

8. Memory-Efficient Hierarchical Neural Architecture Search for Image Restoration [PDF] 摘要

9. Appearance-Invariant 6-DoF Visual Localization using Generative Adversarial Networks [PDF] 摘要

10. Control of computer pointer using hand gesture recognition in motion pictures [PDF] 摘要

11. Unveiling Real-Life Effects of Online Photo Sharing [PDF] 摘要

12. Adversarial Momentum-Contrastive Pre-Training [PDF] 摘要

13. Objective Class-based Micro-Expression Recognition through Simultaneous Action Unit Detection and Feature Aggregation [PDF] 摘要

14. A non-alternating graph hashing algorithm for large scale image search [PDF] 摘要

15. WEmbSim: A Simple yet Effective Metric for Image Captioning [PDF] 摘要

16. MRDet: A Multi-Head Network for Accurate Oriented Object Detection in Aerial Images [PDF] 摘要

17. Hausdorff Point Convolution with Geometric Priors [PDF] 摘要

18. FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training [PDF] 摘要

19. MobileSal: Extremely Efficient RGB-D Salient Object Detection [PDF] 摘要

20. EDN: Salient Object Detection via Extremely-Downsampled Network [PDF] 摘要

21. P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding [PDF] 摘要

22. Rotation Equivariant Siamese Networks for Tracking [PDF] 摘要

23. Task-Adaptive Negative Class Envision for Few-Shot Open-Set Recognition [PDF] 摘要

24. Union-net: A deep neural network model adapted to small data sets [PDF] 摘要

25. Private-Shared Disentangled Multimodal VAE for Learning of Hybrid Latent Representations [PDF] 摘要

26. Physics-based Shadow Image Decomposition for Shadow Removal [PDF] 摘要

27. Low-latency Perception in Off-Road Dynamical Low Visibility Environments [PDF] 摘要

28. Semantic Segmentation on Swiss3DCities: A Benchmark Study on Aerial Photogrammetric 3D Pointcloud Dataset [PDF] 摘要

29. SyNet: An Ensemble Network for Object Detection in UAV Images [PDF] 摘要

30. Convolutional Neural Network for Elderly Wandering Prediction in Indoor Scenarios [PDF] 摘要

31. Spatio-temporal Multi-task Learning for Cardiac MRI Left Ventricle Quantification [PDF] 摘要

32. Parallel-beam X-ray CT datasets of apples with internal defects and label balancing for machine learning [PDF] 摘要

33. AudioViewer: Learning to Visualize Sound [PDF] 摘要

34. Joint super-resolution and synthesis of 1 mm isotropic MP-RAGE volumes from clinical MRI exams with scans of different orientation, resolution and contrast [PDF] 摘要

35. LEUGAN:Low-Light Image Enhancement by Unsupervised Generative Attentional Networks [PDF] 摘要

36. Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder [PDF] 摘要

37. Detecting Hateful Memes Using a Multimodal Deep Ensemble [PDF] 摘要

38. Effective Deployment of CNNs for 3DoF Pose Estimation and Grasping in Industrial Settings [PDF] 摘要

39. UMLE: Unsupervised Multi-discriminator Network for Low Light Enhancement [PDF] 摘要

40. Global Convergence of Model Function Based Bregman Proximal Minimization Algorithms [PDF] 摘要

41. SubICap: Towards Subword-informed Image Captioning [PDF] 摘要

42. Improving the Certified Robustness of Neural Networks via Consistency Regularization [PDF] 摘要

43. White matter hyperintensities volume and cognition: Assessment of a deep learning based lesion detection and quantification algorithm on the Alzheimers Disease Neuroimaging Initiative [PDF] 摘要

44. Learning from Crowds by Modeling Common Confusions [PDF] 摘要

45. An Efficient Recurrent Adversarial Framework for Unsupervised Real-Time Video Enhancement [PDF] 摘要

46. General Domain Adaptation Through Proportional Progressive Pseudo Labeling [PDF] 摘要

47. Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge [PDF] 摘要

48. Learning by Self-Explanation, with Application to Neural Architecture Search [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-12-25

发表于 2020-12-25 分类于 arxiv ， CL 28k 47 分钟

目录

1. I like fish, especially dolphins: Addressing Contradictions in Dialogue Modelling [PDF] 摘要

2. To what extent do human explanations of model behavior align with actual model behavior? [PDF] 摘要

3. A Context Aware Approach for Generating Natural Language Attacks [PDF] 摘要

4. Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment Classification [PDF] 摘要

5. QUACKIE: A NLP Classification Task With Ground Truth Explanations [PDF] 摘要

6. Sentence-Based Model Agnostic NLP Interpretability [PDF] 摘要

7. REM-Net: Recursive Erasure Memory Network for Commonsense Evidence Refinement [PDF] 摘要

8. Gender Bias in Multilingual Neural Machine Translation: The Architecture Matters [PDF] 摘要

9. Cross-lingual Dependency Parsing as Domain Adaptation [PDF] 摘要

10. SubICap: Towards Subword-informed Image Captioning [PDF] 摘要

11. ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language [PDF] 摘要

12. Multi-modal Identification of State-Sponsored Propaganda on Social Media [PDF] 摘要

13. Disentangling semantics in language throughs VAEs and a certain architectural choice [PDF] 摘要

14. Speech Synthesis as Augmentation for Low-Resource ASR [PDF] 摘要

15. Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning [PDF] 摘要

16. Detecting Hateful Memes Using a Multimodal Deep Ensemble [PDF] 摘要

17. Unsupervised neural adaptation model based on optimal transport for spoken language identification [PDF] 摘要

18. WEmbSim: A Simple yet Effective Metric for Image Captioning [PDF] 摘要

19. Self-Supervised Hyperboloid Representations from Logical Queries over Knowledge Graphs [PDF] 摘要

20. Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-12-24

发表于 2020-12-24 分类于 arxiv ， CV 97k 2:42

目录

1. ANR: Articulated Neural Rendering for Virtual Avatars [PDF] 摘要

2. Vid2Actor: Free-viewpoint Animatable Person Synthesis from Video in the Wild [PDF] 摘要

3. Exploring Instance-Level Uncertainty for Medical Detection [PDF] 摘要

4. Training data-efficient image transformers & distillation through attention [PDF] 摘要

5. Focal Frequency Loss for Generative Models [PDF] 摘要

6. Warping of Radar Data into Camera Image for Cross-Modal Supervision in Automotive Applications [PDF] 摘要

7. Coarse-to-Fine Object Tracking Using Deep Features and Correlation Filters [PDF] 摘要

8. Principled network extraction from images [PDF] 摘要

9. Estimation of Driver's Gaze Region from Head Position and Orientation using Probabilistic Confidence Regions [PDF] 摘要

10. Multi-Modality Cut and Paste for 3D Object Detection [PDF] 摘要

11. SWA Object Detection [PDF] 摘要

12. On Calibration of Scene-Text Recognition Models [PDF] 摘要

13. Direct Estimation of Spinal Cobb Angles by Structured Multi-Output Regression [PDF] 摘要

14. ConvMath: A Convolutional Sequence Network for Mathematical Expression Recognition [PDF] 摘要

15. ICMSC: Intra- and Cross-modality Semantic Consistency for Unsupervised Domain Adaptation on Hip Joint Bone Segmentation [PDF] 摘要

16. Multi-grained Trajectory Graph Convolutional Networks for Habit-unrelated Human Motion Prediction [PDF] 摘要

17. A Survey on Visual Transformer [PDF] 摘要

18. Efficient video annotation with visual interpolation and frame selection guidance [PDF] 摘要

19. Unsupervised Domain Adaptation for Semantic Segmentation by Content Transfer [PDF] 摘要

20. The Translucent Patch: A Physical and Universal Attack on Object Detectors [PDF] 摘要

21. Vehicle Re-identification Based on Dual Distance Center Loss [PDF] 摘要

22. Towards Overcoming False Positives in Visual Relationship Detection [PDF] 摘要

23. Deep Semantic Dictionary Learning for Multi-label Image Classification [PDF] 摘要

24. Blur More To Deblur Better: Multi-Blur2Deblur For Efficient Video Deblurring [PDF] 摘要

25. Active Sampling for Accelerated MRI with Low-Rank Tensors [PDF] 摘要

26. Localization in the Crowd with Topological Constraints [PDF] 摘要

27. IIRC: Incremental Implicitly-Refined Classification [PDF] 摘要

28. CholecSeg8k: A Semantic Segmentation Dataset for Laparoscopic Cholecystectomy Based on Cholec80 [PDF] 摘要

29. Skeleton-based Approaches based on Machine Vision: A Survey [PDF] 摘要

30. MG-SAGC: A multiscale graph and its self-adaptive graph convolution network for 3D point clouds [PDF] 摘要

31. Correspondence Learning for Controllable Person Image Generation [PDF] 摘要

32. Pit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars [PDF] 摘要

33. Optical Braille Recognition Using Object Detection CNN [PDF] 摘要

34. Open source software for automatic subregional assessment of knee cartilage degradation using quantitative T2 relaxometry and deep learning [PDF] 摘要

35. Learning Joint 2D-3D Representations for Depth Completion [PDF] 摘要

36. Multi-Task Multi-Sensor Fusion for 3D Object Detection [PDF] 摘要

37. Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net [PDF] 摘要

38. DAGMapper: Learning to Map by Discovering Lane Topology [PDF] 摘要

39. A Structure-Aware Method for Direct Pose Estimation [PDF] 摘要

40. Seeing past words: Testing the cross-modal capabilities of pretrained V&L models [PDF] 摘要

41. Deep Unsupervised Image Hashing by Maximizing Bit Entropy [PDF] 摘要

42. Hierarchical Recurrent Attention Networks for Structured Online Maps [PDF] 摘要

43. Randomized RX for target detection [PDF] 摘要

44. Nonlinear Cook distance for Anomalous Change Detection [PDF] 摘要

45. Pattern Recognition Scheme for Large-Scale Cloud Detection over Landmarks [PDF] 摘要

46. Flexible deep transfer learning by separate feature embeddings and manifold alignment [PDF] 摘要

47. Generative Interventions for Causal Learning [PDF] 摘要

48. Noisy Labels Can Induce Good Representations [PDF] 摘要

49. Deep manifold learning reveals hidden dynamics of proteasome autoregulation [PDF] 摘要

50. Multiclass Spinal Cord Tumor Segmentation on MRI with Deep Learning [PDF] 摘要

51. Chest x-ray automated triage: a semiologic approach designed for clinical implementation, exploiting different types of labels through a combination of four Deep Learning architectures [PDF] 摘要

52. Prognostic Power of Texture Based Morphological Operations in a Radiomics Study for Lung Cancer [PDF] 摘要

53. GANDA: A deep generative adversarial network predicts the spatial distribution of nanoparticles in tumor pixelly [PDF] 摘要

54. StainNet: a fast and robust stain normalization network [PDF] 摘要

55. Analyzing Representations inside Convolutional Neural Networks [PDF] 摘要

56. Diabetic Retinopathy Grading System Based on Transfer Learning [PDF] 摘要

57. Small-Group Learning, with Application to Neural Architecture Search [PDF] 摘要

58. Towards Boosting the Channel Attention in Real Image Denoising : Sub-band Pyramid Attention [PDF] 摘要

59. Comparison of Classification Algorithms Towards Subject-Specific and Subject-Independent BCI [PDF] 摘要

60. Multi-Contrast Computed Tomography Healthy Kidney Atlas [PDF] 摘要

61. RAP-Net: Coarse-to-Fine Multi-Organ Segmentation with Single Random Anatomical Prior [PDF] 摘要

62. Stochastic Gradient Variance Reduction by Solving a Filtering Problem [PDF] 摘要

63. Towards Histopathological Stain Invariance by Unsupervised Domain Augmentation using Generative Adversarial Networks [PDF] 摘要

64. QuickTumorNet: Fast Automatic Multi-Class Segmentation of Brain Tumors [PDF] 摘要

65. Turn Signal Prediction: A Federated Learning Case Study [PDF] 摘要

66. Out-distribution aware Self-training in an Open World Setting [PDF] 摘要

67. On Frank-Wolfe Optimization for Adversarial Robustness and Interpretability [PDF] 摘要

68. Video Influencers: Unboxing the Mystique [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-12-24

发表于 2020-12-24 分类于 arxiv ， CL 28k 47 分钟

目录

1. A Multimodal Framework for the Detection of Hateful Memes [PDF] 摘要

2. Automatic Scansion of Spanish Poetry without Syllabification [PDF] 摘要

3. EmotionGIF-IITP-AINLPML: Ensemble-based Automated Deep Neural System for predicting category(ies) of a GIF response [PDF] 摘要

4. Negation in Cognitive Reasoning [PDF] 摘要

5. Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing [PDF] 摘要

6. Learning Dense Representations of Phrases at Scale [PDF] 摘要

7. Automated Lay Language Summarization of Biomedical Scientific Reviews [PDF] 摘要

8. Code Switching Language Model Using Monolingual Training Data [PDF] 摘要

9. Future-Guided Incremental Transformer for Simultaneous Translation [PDF] 摘要

10. TicketTalk: Toward human-level performance with end-to-end, transaction-based dialog systems [PDF] 摘要

11. Simple-QE: Better Automatic Quality Estimation for Text Simplification [PDF] 摘要

12. Multi-Head Self-Attention with Role-Guided Masks [PDF] 摘要

13. ActionBert: Leveraging User Actions for Semantic Understanding of User Interfaces [PDF] 摘要

14. Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective [PDF] 摘要

15. Software Pipelining for Quantum Loop Programs [PDF] 摘要

16. Seeing past words: Testing the cross-modal capabilities of pretrained V&L models [PDF] 摘要

17. Video Influencers: Unboxing the Mystique [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-12-23

发表于 2020-12-23 分类于 arxiv ， CV 99k 2:45

目录

1. Time-Travel Rephotography [PDF] 摘要

2. YolactEdge: Real-time Instance Segmentation on the Edge (Jetson AGX Xavier: 30 FPS, RTX 2080 Ti: 170 FPS) [PDF] 摘要

3. Underwater image filtering: methods, datasets and evaluation [PDF] 摘要

4. Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Deforming Scene from Monocular Video [PDF] 摘要

5. Unadversarial Examples: Designing Objects for Robust Vision [PDF] 摘要

6. Training Convolutional Neural Networks With Hebbian Principal Component Analysis [PDF] 摘要

7. Geometric robust descriptor for 3D point cloud [PDF] 摘要

8. Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detection [PDF] 摘要

9. Latent Feature Representation via Unsupervised Learning for Pattern Discovery in Massive Electron Microscopy Image Volumes [PDF] 摘要

10. Convolutional Recurrent Network for Road Boundary Extraction [PDF] 摘要

11. Image to Bengali Caption Generation Using Deep CNN and Bidirectional Gated Recurrent Unit [PDF] 摘要

12. Explainable Abstract Trains Dataset [PDF] 摘要

13. MOCCA: Multi-Layer One-Class Classification for Anomaly Detection [PDF] 摘要

14. Noise-Equipped Convolutional Neural Networks [PDF] 摘要

15. Convolutional Neural Networks from Image Markers [PDF] 摘要

16. Warped Gaussian Processes in Remote Sensing Parameter Estimation and Causal Inference [PDF] 摘要

17. A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data [PDF] 摘要

18. Predicting survival outcomes using topological features of tumor pathology images [PDF] 摘要

19. Estimating Crop Primary Productivity with Sentinel-2 and Landsat 8 using Machine Learning Methods Trained with Radiative Transfer Simulations [PDF] 摘要

20. Limitation of Acyclic Oriented Graphs Matching as Cell Tracking Accuracy Measure when Evaluating Mitosis [PDF] 摘要

21. Disentangling images with Lie group transformations and sparse coding [PDF] 摘要

22. Do We Really Need Scene-specific Pose Encoders? [PDF] 摘要

23. Multiple Instance Segmentation in Brachial Plexus Ultrasound Image Using BPMSegNet [PDF] 摘要

24. 3D Point-to-Keypoint Voting Network for 6D Pose Estimation [PDF] 摘要

25. A Hybrid VDV Model for Automatic Diagnosis of Pneumothorax using Class-Imbalanced Chest X-rays Dataset [PDF] 摘要

26. FcaNet: Frequency Channel Attention Networks [PDF] 摘要

27. Human Action Recognition from Various Data Modalities: A Review [PDF] 摘要

28. GuidedStyle: Attribute Knowledge Guided Style Manipulation for Semantic Face Editing [PDF] 摘要

29. Predicting Online Video Advertising Effects with Multimodal Deep Learning [PDF] 摘要

30. Adversarial Multiscale Feature Learning for Overlapping Chromosome Segmentation [PDF] 摘要

31. Subject-independent Human Pose Image Construction with Commodity Wi-Fi [PDF] 摘要

32. Progressive One-shot Human Parsing [PDF] 摘要

33. Learning Disentangled Semantic Representation for Domain Adaptation [PDF] 摘要

34. Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos [PDF] 摘要

35. Modeling Deep Learning Based Privacy Attacks on Physical Mail [PDF] 摘要

36. SERV-CT: A disparity dataset from CT for validation of endoscopic 3D reconstruction [PDF] 摘要

37. Power-SLIC: Diagram-based superpixel generation [PDF] 摘要

38. Contraband Materials Detection Within Volumetric 3D Computed Tomography Baggage Security Screening Imagery [PDF] 摘要

39. Training DNNs in O(1) memory with MEM-DFA using Random Matrices [PDF] 摘要

40. HDNET: Exploiting HD Maps for 3D Object Detection [PDF] 摘要

41. Image Captioning as an Assistive Technology: Lessons Learned from VizWiz 2020 Challenge [PDF] 摘要

42. Alleviating Noisy Data in Image Captioning with Cooperative Distillation [PDF] 摘要

43. Natural vs Balanced Distribution in Deep Learning on Whole Slide Images for Cancer Detection [PDF] 摘要

44. Smoothed Gaussian Mixture Models for Video Classification and Recommendation [PDF] 摘要

45. Learning Dynamic Network Using a Reuse Gate Function in Semi-supervised Video Object Segmentation [PDF] 摘要

46. FracBNN: Accurate and FPGA-Efficient Binary Neural Networks with Fractional Activations [PDF] 摘要

47. Automated Multi-Channel Segmentation for the 4D Myocardial Velocity Mapping Cardiac MR [PDF] 摘要

48. Cloud removal in remote sensing images using generative adversarial networks and SAR-to-optical image translation [PDF] 摘要

49. Deep Learning of Cell Classification using Microscope Images of Intracellular Microtubule Networks [PDF] 摘要

50. Prediction of Chronic Kidney Disease Using Deep Neural Network [PDF] 摘要

51. Unsupervised Spatial-spectral Network Learning for Hyperspectral Compressive Snapshot Reconstruction [PDF] 摘要

52. HDR Denoising and Deblurring by Learning Spatio-temporal Distortion Models [PDF] 摘要

53. A Feasibility study for Deep learning based automated brain tumor segmentation using Magnetic Resonance Images [PDF] 摘要

54. This is not the Texture you are looking for! Introducing Novel Counterfactual Explanations for Non-Experts using Generative Adversarial Learning [PDF] 摘要

55. Deep learning-based virtual refocusing of images using an engineered point-spread function [PDF] 摘要

56. Efficient and Visualizable Convolutional Neural Networks for COVID-19 Classification Using Chest CT [PDF] 摘要

57. Residual Matrix Product State for Machine Learning [PDF] 摘要

58. Objective Evaluation of Deep Uncertainty Predictions for COVID-19 Detection [PDF] 摘要

59. Dual-encoder Bidirectional Generative Adversarial Networks for Anomaly Detection [PDF] 摘要

60. Towards an Automatic System for Extracting Planar Orientations from Software Generated Point Clouds [PDF] 摘要

61. Social NCE: Contrastive Learning of Socially-aware Motion Representations [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-12-23

发表于 2020-12-23 分类于 arxiv ， CL 34k 56 分钟

目录

1. COVID-19 Emotion Monitoring as a Tool to Increase Preparedness for Disease Outbreaks in Developing Regions [PDF] 摘要

2. Applying wav2vec2.0 to Speech Recognition in various low-resource languages [PDF] 摘要

3. Domain Adaptation of NMT models for English-Hindi Machine Translation Task at AdapMT ICON 2020 [PDF] 摘要

4. Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition [PDF] 摘要

5. Pre-Training a Language Model Without Human Language [PDF] 摘要

6. Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation [PDF] 摘要

7. g2tmn at Constraint@AAAI2021: Exploiting CT-BERT and Ensembling Learning for COVID-19 Fake News Detection [PDF] 摘要

8. A Hierarchical Reasoning Graph Neural Network for The Automatic Scoring of Answer Transcriptions in Video Job Interviews [PDF] 摘要

9. Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems [PDF] 摘要

10. Few-Shot Text Generation with Pattern-Exploiting Training [PDF] 摘要

11. Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition [PDF] 摘要

12. Undivided Attention: Are Intermediate Layers Necessary for BERT? [PDF] 摘要

13. Recognizing Emotion Cause in Conversations [PDF] 摘要

14. Improved Biomedical Word Embeddings in the Transformer Era [PDF] 摘要

15. Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition [PDF] 摘要

16. Acronym Identification and Disambiguation shared tasksfor Scientific Document Understanding [PDF] 摘要

17. SChuBERT: Scholarly Document Chunks with BERT-encoding boost Citation Count Prediction [PDF] 摘要

18. Subword Sampling for Low Resource Word Alignment [PDF] 摘要

19. A Distributional Approach to Controlled Text Generation [PDF] 摘要

20. BERTChem-DDI : Improved Drug-Drug Interaction Prediction from text using Chemical Structure Information [PDF] 摘要

21. Event-Driven Query Expansion [PDF] 摘要

22. Neural Methods for Effective, Efficient, and Exposure-Aware Information Retrieval [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-12-21

发表于 2020-12-21 分类于 arxiv ， CV 65k 1:49

目录

1. PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection [PDF] 摘要

2. Learning Complex 3D Human Self-Contact [PDF] 摘要

3. Assessing Pattern Recognition Performance of Neuronal Cultures through Accurate Simulation [PDF] 摘要

4. Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion [PDF] 摘要

5. Trying Bilinear Pooling in Video-QA [PDF] 摘要

6. Temporal Bilinear Encoding Network of Audio-Visual Features at Low Sampling Rates [PDF] 摘要

7. SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation [PDF] 摘要

8. On Modality Bias in the TVQA Dataset [PDF] 摘要

9. LGENet: Local and Global Encoder Network for Semantic Segmentation of Airborne Laser Scanning Point Clouds [PDF] 摘要

10. STNet: Scale Tree Network with Multi-level Auxiliator for Crowd Counting [PDF] 摘要

11. A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection [PDF] 摘要

12. SCNet: Training Inference Sample Consistency for Instance Segmentation [PDF] 摘要

13. CodeVIO: Visual-Inertial Odometry with Learned Optimizable Dense Depth [PDF] 摘要

14. Hyperspectral Image Semantic Segmentation in Cityscapes [PDF] 摘要

15. Frequency Consistent Adaptation for Real World Super Resolution [PDF] 摘要

16. AU-Guided Unsupervised Domain Adaptive Facial Expression Recognition [PDF] 摘要

17. TDN: Temporal Difference Networks for Efficient Action Recognition [PDF] 摘要

18. PointINet: Point Cloud Frame Interpolation Network [PDF] 摘要

19. Content Masked Loss: Human-Like Brush Stroke Planning in a Reinforcement Learning Painting Agent [PDF] 摘要

20. 3D Object Classification on Partial Point Clouds: A Practical Perspective [PDF] 摘要

21. Self-supervised Learning with Fully Convolutional Networks [PDF] 摘要

22. Flow-based Generative Models for Learning Manifold to Manifold Mappings [PDF] 摘要

23. Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations [PDF] 摘要

24. Relightable 3D Head Portraits from a Smartphone Video [PDF] 摘要

25. Toward Transformer-Based Object Detection [PDF] 摘要

26. Learning Compositional Radiance Fields of Dynamic Human Heads [PDF] 摘要

27. Attention-based Image Upsampling [PDF] 摘要

28. Exploring Motion Boundaries in an End-to-End Network for Vision-based Parkinson's Severity Assessment [PDF] 摘要

29. Object Detection based on OcSaFPN in Aerial Images with Noise [PDF] 摘要

30. Separation and Concentration in Deep Networks [PDF] 摘要

31. Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: Evaluation in Alzheimer's disease [PDF] 摘要

32. Multimodal Transfer Learning-based Approaches for Retinal Vascular Segmentation [PDF] 摘要

33. Spectral Reflectance Estimation Using Projector with Unknown Spectral Power Distribution [PDF] 摘要

34. A Surrogate Lagrangian Relaxation-based Model Compression for Deep Neural Networks [PDF] 摘要

35. Information-Preserving Contrastive Learning for Self-Supervised Representations [PDF] 摘要

36. Treadmill Assisted Gait Spoofing (TAGS): An Emerging Threat to wearable Sensor-based Gait Authentication [PDF] 摘要

37. Fast 3-dimensional estimation of the Foveal Avascular Zone from OCTA [PDF] 摘要

阅读全文 »