【arxiv论文】 Computation and Language 2020-05-11

发表于 2020-05-11 分类于 arxiv ， CL 33k 55 分钟

目录

1. Evidence Inference 2.0: More Data, Better Models [PDF] 摘要

2. Quantum Natural Language Processing on Near-Term Quantum Computers [PDF] 摘要

3. Beyond Accuracy: Behavioral Testing of NLP models with CheckList [PDF] 摘要

4. SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics [PDF] 摘要

5. Literature Triage on Genomic Variation Publications by Knowledge-enhanced Multi-channel CNN [PDF] 摘要

6. Sentiment Analysis Using Simplified Long Short-term Memory Recurrent Neural Networks [PDF] 摘要

7. CAiRE-COVID: A Question Answering and Multi-Document Summarization System for COVID-19 Research [PDF] 摘要

8. Towards Conversational Recommendation over Multi-Type Dialogs [PDF] 摘要

9. Learning to Detect Unacceptable Machine Translations for Downstream Tasks [PDF] 摘要

10. Context-Sensitive Generation Network for Handing Unknown Slot Values in Dialogue State Tracking [PDF] 摘要

11. Detecting East Asian Prejudice on Social Media [PDF] 摘要

12. Distilling Knowledge from Pre-trained Language Models via Text Smoothing [PDF] 摘要

13. Comparative Analysis of Word Embeddings for Capturing Word Similarities [PDF] 摘要

14. Mapping Natural Language Instructions to Mobile UI Action Sequences [PDF] 摘要

15. Phonotactic Complexity and its Trade-offs [PDF] 摘要

16. FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization [PDF] 摘要

17. SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization [PDF] 摘要

18. LIIR at SemEval-2020 Task 12: A Cross-Lingual Augmentation Approach for Multilingual Offensive Language Identification [PDF] 摘要

19. A Systematic Assessment of Syntactic Generalization in Neural Language Models [PDF] 摘要

20. Learning to Segment Actions from Observation and Narration [PDF] 摘要

21. On Vocabulary Reliance in Scene Text Recognition [PDF] 摘要

22. Multi-Task Network for Noise-Robust Keyword Spotting and Speaker Verification using CTC-based Soft VAD and Global Query Attention [PDF] 摘要

23. Synchronous Bidirectional Learning for Multilingual Lip Reading [PDF] 摘要

24. Data-driven Modelling of Dynamical Systems Using Tree Adjoining Grammar and Genetic Programming [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-08

发表于 2020-05-08 分类于 arxiv ， CV 86k 2:24

目录

1. Seismic Shot Gather Noise Localization Using a Multi-Scale Feature-Fusion-Based Neural Network [PDF] 摘要

2. Enhancing Geometric Factors in Model Learning and Inference for Object Detection and Instance Segmentation [PDF] 摘要

3. NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images [PDF] 摘要

4. Heidelberg Colorectal Data Set for Surgical Data Science in the Sensor Operating Room [PDF] 摘要

5. Text Recognition in the Wild: A Survey [PDF] 摘要

6. NTIRE 2020 Challenge on NonHomogeneous Dehazing [PDF] 摘要

7. Kunster -- AR Art Video Maker -- Real time video neural style transfer on mobile devices [PDF] 摘要

8. Semantic Signatures for Large-scale Visual Localization [PDF] 摘要

9. Self-Supervised Human Depth Estimation from Monocular Videos [PDF] 摘要

10. DMCP: Differentiable Markov Channel Pruning for Neural Networks [PDF] 摘要

11. Regression Forest-Based Atlas Localization and Direction Specific Atlas Generation for Pancreas Segmentation [PDF] 摘要

12. Scene Text Image Super-Resolution in the Wild [PDF] 摘要

13. Wavelet Integrated CNNs for Noise-Robust Image Classification [PDF] 摘要

14. Deep Learning based Person Re-identification [PDF] 摘要

15. Multi-Target Deep Learning for Algal Detection and Classification [PDF] 摘要

16. Hierarchical Predictive Coding Models in a Deep-Learning Framework [PDF] 摘要

17. Deeply Supervised Active Learning for Finger Bones Segmentation [PDF] 摘要

18. End-to-End Domain Adaptive Attention Network for Cross-Domain Person Re-Identification [PDF] 摘要

19. Deep Learning Framework for Detecting Ground Deformation in the Built Environment using Satellite InSAR data [PDF] 摘要

20. Hierarchical Attention Network for Action Segmentation [PDF] 摘要

21. What comprises a good talking-head video generation?: A Survey and Benchmark [PDF] 摘要

22. Recognizing Exercises and Counting Repetitions in Real Time [PDF] 摘要

23. A Dynamical Perspective on Point Cloud Registration [PDF] 摘要

24. NTIRE 2020 Challenge on Image Demoireing: Methods and Results [PDF] 摘要

25. Deep Learning for Image-based Automatic Dial Meter Reading: Dataset and Baselines [PDF] 摘要

26. Scale-Equalizing Pyramid Convolution for Object Detection [PDF] 摘要

27. Deep Learning on Point Clouds for False Positive Reduction at Nodule Detection in Chest CT Scans [PDF] 摘要

28. Visualisation and knowledge discovery from interpretable models [PDF] 摘要

29. Efficient Exact Verification of Binarized Neural Networks [PDF] 摘要

30. Noisy Differentiable Architecture Search [PDF] 摘要

31. How Can CNNs Use Image Position for Segmentation? [PDF] 摘要

32. AIBench: Scenario-distilling AI Benchmarking [PDF] 摘要

33. Lifted Regression/Reconstruction Networks [PDF] 摘要

34. NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image [PDF] 摘要

35. Joint Prediction and Time Estimation of COVID-19 Developing Severe Symptoms using Chest CT Scan [PDF] 摘要

36. WSMN: An optimized multipurpose blind watermarking in Shearlet domain using MLP and NSGA-II [PDF] 摘要

37. Vid2Curve: Simultaneously Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video [PDF] 摘要

38. Scoring Root Necrosis in Cassava Using Semantic Segmentation [PDF] 摘要

39. DramaQA: Character-Centered Video Story Understanding with Hierarchical QA [PDF] 摘要

40. A Review of Computer Vision Methods in Network Security [PDF] 摘要

41. Encoding in the Dark Grand Challenge: An Overview [PDF] 摘要

42. Knowledge Enhanced Neural Fashion Trend Forecasting [PDF] 摘要

43. Multi-view data capture using edge-synchronised mobiles [PDF] 摘要

44. Adaptive Feature Selection Guided Deep Forest for COVID-19 Classification with Chest CT [PDF] 摘要

45. Subdomain Adaptation with Manifolds Discrepancy Alignment [PDF] 摘要

46. Collective Loss Function for Positive and Unlabeled Learning [PDF] 摘要

47. Diagnosis of Coronavirus Disease 2019 (COVID-19) with Structured Latent Multi-View Representation Learning [PDF] 摘要

48. Towards Frequency-Based Explanation for Robust CNN [PDF] 摘要

49. Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting [PDF] 摘要

50. Diagnosing the Environment Bias in Vision-and-Language Navigation [PDF] 摘要

51. Line Artefact Quantification in Lung Ultrasound Images of COVID-19 Patients via Non-Convex Regularisation [PDF] 摘要

52. CovidCTNet: An Open-Source Deep Learning Approach to Identify Covid-19 Using CT Image [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-05-08

发表于 2020-05-08 分类于 arxiv ， CL 42k 1:10

目录

1. On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation [PDF] 摘要

2. Where is Linked Data in Question Answering over Linked Data? [PDF] 摘要

3. Learning Robust Models for e-Commerce Product Search [PDF] 摘要

4. A Tale of Two Perplexities: Sensitivity of Neural Language Models to Lexical Retrieval Deficits in Dementia of the Alzheimer's Type [PDF] 摘要

5. Learning Implicit Text Generation via Feature Matching [PDF] 摘要

6. MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis [PDF] 摘要

7. The Danish Gigaword Project [PDF] 摘要

8. Practical Perspectives on Quality Estimation for Machine Translation [PDF] 摘要

9. Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization [PDF] 摘要

10. Fine-Grained Analysis of Cross-Linguistic Syntactic Divergences [PDF] 摘要

11. The Perceptimatic English Benchmark for Speech Perception Models [PDF] 摘要

12. Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation [PDF] 摘要

13. 2kenize: Tying Subword Sequences for Chinese Script Conversion [PDF] 摘要

14. JASS: Japanese-specific Sequence to Sequence Pre-training for Neural Machine Translation [PDF] 摘要

15. DramaQA: Character-Centered Video Story Understanding with Hierarchical QA [PDF] 摘要

16. Nakdan: Professional Hebrew Diacritizer [PDF] 摘要

17. Quda: Natural Language Queries for Visual Data Analytics [PDF] 摘要

18. Fact-based Dialogue Generation with Convergent and Divergent Decoding [PDF] 摘要

19. Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting [PDF] 摘要

20. Diagnosing the Environment Bias in Vision-and-Language Navigation [PDF] 摘要

21. Categorical Vector Space Semantics for Lambek Calculus with a Relevant Modality [PDF] 摘要

22. Weakly-Supervised Neural Response Selection from an Ensemble of Task-Specialised Dialogue Agents [PDF] 摘要

23. Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches [PDF] 摘要

24. Evaluating text coherence based on the graph of the consistency of phrases to identify symptoms of schizophrenia [PDF] 摘要

25. Successfully Applying the Stabilized Lottery Ticket Hypothesis to the Transformer Architecture [PDF] 摘要

26. Adaptive Dialog Policy Learning with Hindsight and User Modeling [PDF] 摘要

27. YANG2UML: Bijective Transformation and Simplification of YANG to UML [PDF] 摘要

28. RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions [PDF] 摘要

29. ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-07

发表于 2020-05-07 分类于 arxiv ， CV 49k 1:21

目录

1. DenoiSeg: Joint Denoising and Segmentation [PDF] 摘要

2. Generating Memorable Images Based on Human Visual Memory Schemas [PDF] 摘要

3. Manipulated Face Detector: Joint Spatial and Frequency Domain Attention Network [PDF] 摘要

4. GraCIAS: Grassmannian of Corrupted Images for Adversarial Security [PDF] 摘要

5. Automatic Detection and Recognition of Individuals in Patterned Species [PDF] 摘要

6. Automatic Plant Image Identification of Vietnamese species using Deep Learning Models [PDF] 摘要

7. UST: Unifying Spatio-Temporal Context for Trajectory Prediction in Autonomous Driving [PDF] 摘要

8. Design and Development of a Web-based Tool for Inpainting of Dissected Aortae in Angiography Images [PDF] 摘要

9. Probabilistic Color Constancy [PDF] 摘要

10. Fast Geometric Surface based Segmentation of Point Cloud from Lidar Data [PDF] 摘要

11. ProbaNet: Proposal-balanced Network for Object Detection [PDF] 摘要

12. Drosophila-Inspired 3D Moving Object Detection Based on Point Clouds [PDF] 摘要

13. Dual-Sampling Attention Network for Diagnosis of COVID-19 from Community Acquired Pneumonia [PDF] 摘要

14. CONFIG: Controllable Neural Face Image Generation [PDF] 摘要

15. Automated Transcription for Pre-Modern Japanese Kuzushiji Documents by Random Lines Erasure and Curriculum Learning [PDF] 摘要

16. Deep Recurrent Disease Progression Model for Conversion-Time Prediction of Alzheimer's Disease [PDF] 摘要

17. Low-shot Object Detection via Classification Refinement [PDF] 摘要

18. Dependency Aware Filter Pruning [PDF] 摘要

19. Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition [PDF] 摘要

20. CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement [PDF] 摘要

21. Multi-Head Attention with Joint Agent-Map Representation for Trajectory Prediction in Autonomous Driving [PDF] 摘要

22. Partly Supervised Multitask Learning [PDF] 摘要

23. Mimicry: Towards the Reproducibility of GAN Research [PDF] 摘要

24. Temporal Event Segmentation using Attention-based Perceptual Prediction Model for Continual Learning [PDF] 摘要

25. Iris segmentation techniques to recognize the behavior of a vigilant driver [PDF] 摘要

26. Data Augmentation via Mixed Class Interpolation using Cycle-Consistent Generative Adversarial Networks Applied to Cross-Domain Imagery [PDF] 摘要

27. Groupwise Multimodal Image Registration using Joint Total Variation [PDF] 摘要

28. High-Contrast Limited-Angle Reflection Tomography [PDF] 摘要

29. Stochastic Bottleneck: Rateless Auto-Encoder for Flexible Dimensionality Reduction [PDF] 摘要

30. Unsupervised Real-world Low-light Image Enhancement with Decoupled Networks [PDF] 摘要

31. Knee Injury Detection using MRI with Efficiently-Layered Network (ELNet) [PDF] 摘要

32. Unsupervised Pre-trained Models from Healthy ADLs Improve Parkinson's Disease Classification of Gait Patterns [PDF] 摘要

33. Multi-task pre-training of deep neural networks [PDF] 摘要

34. Enhancing Intrinsic Adversarial Robustness via Feature Pyramid Decoder [PDF] 摘要

35. Cross-media Structured Common Space for Multimedia Event Extraction [PDF] 摘要

36. A new design of a flying robot, with advanced computer vision techniques to perform self-maintenance of smart grids [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-05-07

发表于 2020-05-07 分类于 arxiv ， CL 42k 1:10

目录

1. Autoencoding Pixies: Amortised Variational Inference with Graph Convolutions for Functional Distributional Semantics [PDF] 摘要

2. PeTra: A Sparsely Supervised Memory Model for People Tracking [PDF] 摘要

3. What are the Goals of Distributional Semantics? [PDF] 摘要

4. Seeing the Forest and the Trees: Detection and Cross-Document Coreference Resolution of Militarized Interstate Disputes [PDF] 摘要

5. Multitask Models for Supervised Protests Detection in Texts [PDF] 摘要

6. Harvesting and Refining Question-Answer Pairs for Unsupervised QA [PDF] 摘要

7. Review of text style transfer based on deep learning [PDF] 摘要

8. TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking [PDF] 摘要

9. TAG : Type Auxiliary Guiding for Code Comment Generation [PDF] 摘要

10. Digraphie des langues ouest africaines : Latin2Ajami : un algorithme de translitteration automatique [PDF] 摘要

11. An Empirical Study of Multi-Task Learning on BERT for Biomedical Text Mining [PDF] 摘要

12. Unsupervised Neural Aspect Search with Related Terms Extraction [PDF] 摘要

13. Learning to Understand Child-directed and Adult-directed Speech [PDF] 摘要

14. Shape of synth to come: Why we should use synthetic data for English surface realization [PDF] 摘要

15. A Top-Down Neural Architecture towards Text-Level Parsing of Discourse Rhetorical Structure [PDF] 摘要

16. Building A User-Centric and Content-Driven Socialbot [PDF] 摘要

17. Moving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoders [PDF] 摘要

18. Crossing Variational Autoencoders for Answer Retrieval [PDF] 摘要

19. Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback [PDF] 摘要

20. The Cascade Transformer: an Application for Efficient Answer Sentence Selection [PDF] 摘要

21. Phonetic and Visual Priors for Decipherment of Informal Romanization [PDF] 摘要

22. MultiReQA: A Cross-Domain Evaluation for Retrieval Question Answering Models [PDF] 摘要

23. Efficient strategies for hierarchical text classification: External knowledge and auxiliary tasks [PDF] 摘要

24. Russian Natural Language Generation: Creation of a Language Modelling Dataset and Evaluation with Modern Neural Architectures [PDF] 摘要

25. Contextualizing Hate Speech Classifiers with Post-hoc Explanation [PDF] 摘要

26. Automated Personalized Feedback Improves Learning Gains in an Intelligent Tutoring System [PDF] 摘要

27. Graph-Embedding Empowered Entity Retrieval [PDF] 摘要

28. A Large-scale Industrial and Professional Occupation Dataset [PDF] 摘要

29. Learning Architectures from an Extended Search Space for Language Modeling [PDF] 摘要

30. Probing the Natural Language Inference Task with Automated Reasoning Tools [PDF] 摘要

31. ESG2Risk: A Deep Learning Framework from ESG News to Stock Volatility Prediction [PDF] 摘要

32. Cross-media Structured Common Space for Multimedia Event Extraction [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-05

发表于 2020-05-05 分类于 arxiv ， CV 116k 3:14

目录

1. Transforming and Projecting Images into Class-conditional Generative Networks [PDF] 摘要

2. How to Train Your Energy-Based Model for Regression [PDF] 摘要

3. Group Equivariant Generative Adversarial Networks [PDF] 摘要

4. Ego-motion and Surrounding Vehicle State Estimation Using a Monocular Camera [PDF] 摘要

5. VisualEchoes: Spatial Image Representation Learning through Echolocation [PDF] 摘要

6. MorphoCluster: Efficient Annotation of Plankton images by Clustering [PDF] 摘要

7. Can We Learn Heuristics For Graphical Model Inference Using Reinforcement Learning? [PDF] 摘要

8. On the Benefits of Models with Perceptually-Aligned Gradients [PDF] 摘要

9. CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotations [PDF] 摘要

10. Automated eye disease classification method from anterior eye image using anatomical structure focused image classification technique [PDF] 摘要

11. Correlating Edge, Pose with Parsing [PDF] 摘要

12. Monitoring COVID-19 social distancing with person detection and tracking via fine-tuned YOLO v3 and Deepsort techniques [PDF] 摘要

13. Anchors based method for fingertips position from a monocular RGB image using Deep Neural Network [PDF] 摘要

14. How to Train Your Dragon: Tamed Warping Network for Semantic Video Segmentation [PDF] 摘要

15. NTIRE 2020 Challenge on Image and Video Deblurring [PDF] 摘要

16. Visual Question Answering with Prior Class Semantics [PDF] 摘要

17. One-Shot Image Classification by Learning to Restore Prototypes [PDF] 摘要

18. AIM 2019 Challenge on Video Temporal Super-Resolution: Methods and Results [PDF] 摘要

19. Minor Privacy Protection Through Real-time Video Processing at the Edge [PDF] 摘要

20. Multi-focus Image Fusion: A Benchmark [PDF] 摘要

21. Deep Encoder-Decoder Neural Network for Fingerprint Image Denoising and Inpainting [PDF] 摘要

22. Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities [PDF] 摘要

23. Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences [PDF] 摘要

24. Using Artificial Intelligence to Analyze Fashion Trends [PDF] 摘要

25. Joint-SRVDNet: Joint Super Resolution and Vehicle Detection Network [PDF] 摘要

26. Quadtree Driven Lossy Event Compression [PDF] 摘要

27. Tensor optimal transport, distance between sets of measures and tensor scaling [PDF] 摘要

28. Multi-Modality Generative Adversarial Networks with Tumor Consistency Loss for Brain MR Image Synthesis [PDF] 摘要

29. SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction [PDF] 摘要

30. BeCAPTCHA-Mouse: Synthetic Mouse Trajectories and Improved Bot Detection [PDF] 摘要

31. Derivation of a Constant Velocity Motion Model for Visual Tracking [PDF] 摘要

32. DroTrack: High-speed Drone-based Object Tracking Under Uncertainty [PDF] 摘要

33. Projection Inpainting Using Partial Convolution for Metal Artifact Reduction [PDF] 摘要

34. CoMoGCN: Coherent Motion Aware Trajectory Prediction with Graph Representation [PDF] 摘要

35. Heterogeneous Knowledge Distillation using Information Flow Modeling [PDF] 摘要

36. Cross-View Image Retrieval -- Ground to Aerial Image Retrieval through Deep Learning [PDF] 摘要

37. PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data [PDF] 摘要

38. Jacks of All Trades, Masters Of None: Addressing Distributional Shift and Obtrusiveness via Transparent Patch Attacks [PDF] 摘要

39. Learning from Noisy Labels with Noise Modeling Network [PDF] 摘要

40. Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context [PDF] 摘要

41. Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring Expressions [PDF] 摘要

42. Pseudo-healthy synthesis with pathology disentanglement and adversarial learning [PDF] 摘要

43. Quantification of MagLIF morphology using the Mallat Scattering Transformation [PDF] 摘要

44. The Newspaper Navigator Dataset: Extracting And Analyzing Visual Content from 16 Million Historic Newspaper Pages in Chronicling America [PDF] 摘要

45. A Deep Convolutional Neural Network for COVID-19 Detection Using Chest X-Rays [PDF] 摘要

46. COVID-DA: Deep Domain Adaptation from Typical Pneumonia to COVID-19 [PDF] 摘要

47. An Adaptive Enhancement Based Hybrid CNN Model for Digital Dental X-ray Positions Classification [PDF] 摘要

48. A cascade network for Detecting COVID-19 using chest x-rays [PDF] 摘要

49. Spiking Neural Networks Hardware Implementations and Challenges: a Survey [PDF] 摘要

50. Stochastic Sparse Subspace Clustering [PDF] 摘要

51. Does Visual Self-Supervision Improve Learning of Speech Representations? [PDF] 摘要

52. A Comparative Study of Image Quality Assessment Models through Perceptual Optimization [PDF] 摘要

53. A Model-driven Deep Neural Network for Single Image Rain Removal [PDF] 摘要

54. Mutual Information Gradient Estimation for Representation Learning [PDF] 摘要

55. A Little Bit More: Bitplane-Wise Bit-Depth Recovery [PDF] 摘要

56. NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results [PDF] 摘要

57. Fusion of visible and infrared images via complex function [PDF] 摘要

58. Lupulus: A Flexible Hardware Accelerator for Neural Networks [PDF] 摘要

59. Explaining How Deep Neural Networks Forget by Deep Visualization [PDF] 摘要

60. A Concise yet Effective model for Non-Aligned Incomplete Multi-view and Missing Multi-label Learning [PDF] 摘要

61. Boundary-aware Context Neural Network for Medical Image Segmentation [PDF] 摘要

62. On the Convergence Rate of Projected Gradient Descent for a Back-Projection based Objective [PDF] 摘要

63. Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution [PDF] 摘要

64. Towards Occlusion-Aware Multifocal Displays [PDF] 摘要

65. Clue: Cross-modal Coherence Modeling for Caption Generation [PDF] 摘要

66. Towards Deep Learning Methods for Quality Assessment of Computer-Generated Imagery [PDF] 摘要

67. RMM: A Recursive Mental Model for Dialog Navigation [PDF] 摘要

68. Obtaining Faithful Interpretations from Compositional Neural Networks [PDF] 摘要

69. A Benchmark for Structured Procedural Knowledge Extraction from Cooking Videos [PDF] 摘要

70. Stochastic Neighbor Embedding of Multimodal Relational Data for Image-Text Simultaneous Visualization [PDF] 摘要

71. Probing Text Models for Common Ground with Visual Representations [PDF] 摘要

72. When Ensembling Smaller Models is More Efficient than Single Large Models [PDF] 摘要

73. RigNet: Neural Rigging for Articulated Characters [PDF] 摘要

74. Angle-based Search Space Shrinking for Neural Architecture Search [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-05-05

发表于 2020-05-05 分类于 arxiv ， CL 192k 5:20

目录

1. What is Learned in Visually Grounded Neural Syntax Acquisition [PDF] 摘要

2. Fast and Robust Unsupervised Contextual Biasing for Speech Recognition [PDF] 摘要

3. Evaluating Explanation Methods for Neural Machine Translation [PDF] 摘要

4. Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring Expressions [PDF] 摘要

5. A Tale of a Probe and a Parser [PDF] 摘要

6. Code and Named Entity Recognition in StackOverflow [PDF] 摘要

7. The Paradigm Discovery Problem [PDF] 摘要

8. From Arguments to Key Points: Towards Automatic Argument Summarization [PDF] 摘要

9. Reward Constrained Interactive Recommendation with Natural Language Feedback [PDF] 摘要

10. Compose Like Humans: Jointly Improving the Coherence and Novelty for Modern Chinese Poetry Generation [PDF] 摘要

11. What-if I ask you to explain: Explaining the effects of perturbations in procedural text [PDF] 摘要

12. To Test Machine Comprehension, Start by Defining Comprehension [PDF] 摘要

13. Towards A Sign Language Gloss Representation Of Modern Standard Arabic [PDF] 摘要

14. Using Context in Neural Machine Translation Training Objectives [PDF] 摘要

15. Introducing the VoicePrivacy Initiative [PDF] 摘要

16. The Sensitivity of Language Models and Humans to Winograd Schema Perturbations [PDF] 摘要

17. From SPMRL to NMRL: What Did We Learn (and Unlearn) in a Decade of Parsing Morphologically-Rich Languages (MRLs)? [PDF] 摘要

18. DoQA -- Accessing Domain-Specific FAQs via Conversational QA [PDF] 摘要

19. NLP in FinTech Applications: Past, Present and Future [PDF] 摘要

20. pyBART: Evidence-based Syntactic Transformations for IE [PDF] 摘要

21. Distributional Discrepancy: A Metric for Unconditional Text Generation [PDF] 摘要

22. WikiUMLS: Aligning UMLS to Wikipedia via Cross-lingual Neural Ranking [PDF] 摘要

23. Improving Adversarial Text Generation by Modeling the Distant Future [PDF] 摘要

24. A New Data Normalization Method to Improve Dialogue Generation by Minimizing Long Tail Effect [PDF] 摘要

25. Noise Pollution in Hospital Readmission Prediction: Long Document Classification with Reinforcement Learning [PDF] 摘要

26. Robust Encodings: A Framework for Combating Adversarial Typos [PDF] 摘要

27. Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering [PDF] 摘要

28. On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjectives and Verbs [PDF] 摘要

29. On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation [PDF] 摘要

30. Influence Paths for Characterizing Subject-Verb Number Agreement in LSTM Language Models [PDF] 摘要

31. Tailoring and Evaluating the Wikipedia for in-Domain Comparable Corpora Extraction [PDF] 摘要

32. Similarity Analysis of Contextual Word Representation Models [PDF] 摘要

33. Knowledge Graph-Augmented Abstractive Summarization with Semantic-Driven Cloze Reward [PDF] 摘要

34. Correcting the Autocorrect: Context-Aware Typographical Error Correction via Training Data Augmentation [PDF] 摘要

35. Out of the Echo Chamber: Detecting Countering Debate Speeches [PDF] 摘要

36. Let Me Choose: From Verbal Context to Font Selection [PDF] 摘要

37. Emergence of Syntax Needs Minimal Supervision [PDF] 摘要

38. Transformer-based End-to-End Question Generation [PDF] 摘要

39. Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence [PDF] 摘要

40. A Two-Stage Masked LM Method for Term Set Expansion [PDF] 摘要

41. A Position Aware Decay Weighted Network for Aspect based Sentiment Analysis [PDF] 摘要

42. An Accurate Model for Predicting the (Graded) Effect of Context in Word Similarity Based on Bert [PDF] 摘要

43. Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction [PDF] 摘要

44. How Does Selective Mechanism Improve Self-Attention Networks? [PDF] 摘要

45. Efficient Second-Order TreeCRF for Neural Dependency Parsing [PDF] 摘要

46. Unsupervised Morphological Paradigm Completion [PDF] 摘要

47. Towards Faithful Neural Table-to-Text Generation with Content-Matching Constraints [PDF] 摘要

48. Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation [PDF] 摘要

49. On the Inference Calibration of Neural Machine Translation [PDF] 摘要

50. Bootstrapping Techniques for Polysynthetic Morphological Analysis [PDF] 摘要

51. How Can We Accelerate Progress Towards Human-like Linguistic Generalization? [PDF] 摘要

52. Improving Non-autoregressive Neural Machine Translation with Monolingual Data [PDF] 摘要

53. Clue: Cross-modal Coherence Modeling for Caption Generation [PDF] 摘要

54. Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking [PDF] 摘要

55. Rationalizing Medical Relation Prediction from Corpus-level Statistics [PDF] 摘要

56. Improving Truthfulness of Headline Generation [PDF] 摘要

57. Single Model Ensemble using Pseudo-Tags and Distinct Vectors [PDF] 摘要

58. Predicting Performance for Natural Language Processing Tasks [PDF] 摘要

59. A language score based output selection method for multilingual speech recognition [PDF] 摘要

60. ENGINE: Energy-Based Inference Networks for Non-Autoregressive Machine Translation [PDF] 摘要

61. Sources of Transfer in Multilingual Named Entity Recognition [PDF] 摘要

62. Language Models as an Alternative Evaluator of Word Order Hypotheses: A Case Study in Japanese [PDF] 摘要

63. Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing [PDF] 摘要

64. DQI: Measuring Data Quality in NLP [PDF] 摘要

65. Social Biases in NLP Models as Barriers for Persons with Disabilities [PDF] 摘要

66. MultiQT: Multimodal Learning for Real-Time Question Tracking in Speech [PDF] 摘要

67. Teaching Machine Comprehension with Compositional Explanations [PDF] 摘要

68. Treebank Embedding Vectors for Out-of-domain Dependency Parsing [PDF] 摘要

69. A Simple Language Model for Task-Oriented Dialogue [PDF] 摘要

70. KinGDOM: Knowledge-Guided DOMain adaptation for sentiment analysis [PDF] 摘要

71. Measuring and Reducing Non-Multifact Reasoning in Multi-hop Question Answering [PDF] 摘要

72. Visually Grounded Continual Learning of Compositional Semantics [PDF] 摘要

73. Can BERT Reason? Logically Equivalent Probes for Evaluating the Inference Capabilities of Language Models [PDF] 摘要

74. ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning [PDF] 摘要

75. Exploring and Predicting Transferability across NLP Tasks [PDF] 摘要

76. BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QA [PDF] 摘要

77. Synthesizer: Rethinking Self-Attention in Transformer Models [PDF] 摘要

78. Hard-Coded Gaussian Attention for Neural Machine Translation [PDF] 摘要

79. ESPRIT: Explaining Solutions to Physical Reasoning Tasks [PDF] 摘要

80. RMM: A Recursive Mental Model for Dialog Navigation [PDF] 摘要

81. Obtaining Faithful Interpretations from Compositional Neural Networks [PDF] 摘要

82. Probing the Probing Paradigm: Does Probing Accuracy Entail Task Relevance? [PDF] 摘要

83. A Benchmark for Structured Procedural Knowledge Extraction from Cooking Videos [PDF] 摘要

84. AVA: an Automatic eValuation Approach to Question Answering Systems [PDF] 摘要

85. A Girl Has A Name: Detecting Authorship Obfuscation [PDF] 摘要

86. Expertise Style Transfer: A New Task Towards Better Communication between Experts and Laymen [PDF] 摘要

87. UnifiedQA: Crossing Format Boundaries With a Single QA System [PDF] 摘要

88. Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer [PDF] 摘要

89. DeFormer: Decomposing Pre-trained Transformers for Faster Question Answering [PDF] 摘要

90. Robust and Interpretable Grounding of Spatial References with Relation Networks [PDF] 摘要

91. Are Emojis Emotional? A Study to Understand the Association between Emojis and Emotions [PDF] 摘要

92. Design Challenges for Low-resource Cross-lingual Entity Linking [PDF] 摘要

93. Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering [PDF] 摘要

94. An Imitation Game for Learning Semantic Parsers from User Interaction [PDF] 摘要

95. Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models [PDF] 摘要

96. Opportunistic Decoding with Timely Correction for Simultaneous Translation [PDF] 摘要

97. Generating Derivational Morphology with BERT [PDF] 摘要

98. Contrastive Self-Supervised Learning for Commonsense Reasoning [PDF] 摘要

99. Benchmarking Multimodal Regex Synthesis with Complex Structures [PDF] 摘要

100. On Faithfulness and Factuality in Abstractive Summarization [PDF] 摘要

101. GenericsKB: A Knowledge Base of Generic Statements [PDF] 摘要

102. An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction [PDF] 摘要

103. Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates [PDF] 摘要

104. Scalable Multi-Hop Relational Reasoning for Knowledge-Aware Question Answering [PDF] 摘要

105. Syntactic Question Abstraction and Retrieval for Data-Scarce Semantic Parsing [PDF] 摘要

106. Spatial Dependency Parsing for 2D Document Understanding [PDF] 摘要

107. A Joint Framework for Inductive Representation Learning and Explainable Reasoning in Knowledge Graphs [PDF] 摘要

108. We Need to Talk About Random Splits [PDF] 摘要

109. Using Noisy Self-Reports to Predict Twitter User Demographics [PDF] 摘要

110. From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers [PDF] 摘要

111. KLEJ: Comprehensive Benchmark for Polish Language Understanding [PDF] 摘要

112. Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work? [PDF] 摘要

113. Predicting Declension Class from Form and Meaning [PDF] 摘要

114. Minimally Supervised Categorization of Text with Metadata [PDF] 摘要

115. Probing Text Models for Common Ground with Visual Representations [PDF] 摘要

116. Multi-Dimensional Gender Bias Classification [PDF] 摘要

117. A Controllable Model of Grounded Response Generation [PDF] 摘要

118. Learning an Unreferenced Metric for Online Dialogue Evaluation [PDF] 摘要

119. Multi-scale Transformer Language Models [PDF] 摘要

120. Evaluating Robustness to Input Perturbations for Neural Machine Translation [PDF] 摘要

121. Clinical Reading Comprehension: A Thorough Analysis of the emrQA Dataset [PDF] 摘要

122. Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition [PDF] 摘要

123. When BERT Plays the Lottery, All Tickets Are Winning [PDF] 摘要

124. POINTER: Constrained Text Generation via Insertion-based Generative Pre-training [PDF] 摘要

125. GoEmotions: A Dataset of Fine-Grained Emotions [PDF] 摘要

126. A Probabilistic Generative Model for Typographical Analysis of Early Modern Printing [PDF] 摘要

127. Does Visual Self-Supervision Improve Learning of Speech Representations? [PDF] 摘要

128. On Systematically Building a Controlled Natural Language for Functional Requirements [PDF] 摘要

129. Gender Gap in Natural Language Processing Research: Disparities in Authorship and Citations [PDF] 摘要

130. Extracting Entities and Topics from News and Connecting Criminal Records [PDF] 摘要

131. Understanding and Improving Information Transfer in Multi-Task Learning [PDF] 摘要

132. Quantifying Attention Flow in Transformers [PDF] 摘要

133. Examining Citations of Natural Language Processing Literature [PDF] 摘要

134. SEEK: Segmented Embedding of Knowledge Graphs [PDF] 摘要

135. Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge [PDF] 摘要

136. Stochastic Neighbor Embedding of Multimodal Relational Data for Image-Text Simultaneous Visualization [PDF] 摘要

137. Learning Collaborative Agents with Rule Guidance for Knowledge Graph Reasoning [PDF] 摘要

138. Low-Dimensional Hyperbolic Knowledge Graph Embeddings [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-04

发表于 2020-05-04 分类于 arxiv ， CV 54k 1:30

目录

1. An Efficient Integration of Disentangled Attended Expression and Identity FeaturesFor Facial Expression Transfer andSynthesis [PDF] 摘要

2. Computing the Testing Error without a Testing Set [PDF] 摘要

3. Investigating Class-level Difficulty Factors in Multi-label Classification Problems [PDF] 摘要

4. Aggregation and Finetuning for Clothes Landmark Detection [PDF] 摘要

5. MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud Downsampling [PDF] 摘要

6. A Comprehensive Study on Visual Explanations for Spatio-temporal Networks [PDF] 摘要

7. Generative Adversarial Data Programming [PDF] 摘要

8. M^3VSNet: Unsupervised Multi-metric Multi-view Stereo Network [PDF] 摘要

9. Survey on Reliable Deep Learning-Based Person Re-Identification Models: Are We There Yet? [PDF] 摘要

10. The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines [PDF] 摘要

11. Adversarial Synthesis of Human Pose from Text [PDF] 摘要

12. Diverse Visuo-Lingustic Question Answering (DVLQA) Challenge [PDF] 摘要

13. ACCL: Adversarial constrained-CNN loss for weakly supervised medical image segmentation [PDF] 摘要

14. PCA-SRGAN: Incremental Orthogonal Projection Discrimination for Face Super-resolution [PDF] 摘要

15. Multi-Camera Trajectory Forecasting: Pedestrian Trajectory Prediction in a Network of Cameras [PDF] 摘要

16. Recognizing American Sign Language Nonmanual Signal Grammar Errors in Continuous Videos [PDF] 摘要

17. Deepfake Forensics Using Recurrent Neural Networks [PDF] 摘要

18. Deeply Cascaded U-Net for Multi-Task Image Processing [PDF] 摘要

19. The AVA-Kinetics Localized Human Actions Video Dataset [PDF] 摘要

20. HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training [PDF] 摘要

21. Sequence Information Channel Concatenation for Improving Camera Trap Image Burst Classification [PDF] 摘要

22. Domain Siamese CNNs for Sparse Multispectral Disparity Estimation [PDF] 摘要

23. Importance Driven Continual Learning for Segmentation Across Domains [PDF] 摘要

24. Occlusion resistant learning of intuitive physics from videos [PDF] 摘要

25. CP-NAS: Child-Parent Neural Architecture Search for 1-bit CNNs [PDF] 摘要

26. HLVU : A New Challenge to Test Deep Understanding of Movies the Way Humans do [PDF] 摘要

27. A Naturalness Evaluation Database for Video Prediction Models [PDF] 摘要

28. On-board Deep-learning-based Unmanned Aerial Vehicle Fault Cause Detection and Identification [PDF] 摘要

29. Defocus Deblurring Using Dual-Pixel Data [PDF] 摘要

30. Distilling Spikes: Knowledge Distillation in Spiking Neural Networks [PDF] 摘要

31. Cross-modal Language Generation using Pivot Stabilization for Web-scale Language Coverage [PDF] 摘要

32. Conceptual Design of Human-Drone Communication in Collaborative Environments [PDF] 摘要

33. Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness [PDF] 摘要

34. Unsupervised Lesion Detection via Image Restoration with a Normative Prior [PDF] 摘要

阅读全文 »