【arxiv论文】 Computation and Language 2020-06-12

发表于 2020-06-12 分类于 arxiv ， CL 31k 51 分钟

目录

1. Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge [PDF] 摘要

2. Multi-hop Reading Comprehension across Documents with Path-based Graph Convolutional Network [PDF] 摘要

3. A Probabilistic Model with Commonsense Constraints for Pattern-based Temporal Fact Extraction [PDF] 摘要

4. CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP [PDF] 摘要

5. Provenance for Linguistic Corpora Through Nanopublications [PDF] 摘要

6. Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics [PDF] 摘要

7. Augmenting Data for Sarcasm Detection with Unlabeled Conversation Context [PDF] 摘要

8. Performance in the Courtroom: Automated Processing and Visualization of Appeal Court Decisions in France [PDF] 摘要

9. Discrete Latent Variable Representations for Low-Resource Text Classification [PDF] 摘要

10. A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages [PDF] 摘要

11. Emora STDM: A Versatile Framework for Innovative Dialogue System Development [PDF] 摘要

12. Towards Unified Dialogue System Evaluation: A Comprehensive Analysis of Current Evaluation Protocols [PDF] 摘要

13. Report from the NSF Future Directions Workshop, Toward User-Oriented Agents: Research Directions and Challenges [PDF] 摘要

14. Disentangled Non-Local Neural Networks [PDF] 摘要

15. VirTex: Learning Visual Representations from Textual Annotations [PDF] 摘要

16. Exploring Weaknesses of VQA Models through Attribution Driven Insights [PDF] 摘要

17. Deep Differential System Stability -- Learning advanced computations from examples [PDF] 摘要

18. Extracting and categorising the reactions to COVID-19 by the South African public -- A social media study [PDF] 摘要

19. Mental Workload and Language Production in Non-Native Speaker IPA Interaction [PDF] 摘要

20. See what I'm saying? Comparing Intelligent Personal Assistant use for Native and Non-Native Language Speakers [PDF] 摘要

21. Transparency in Language Generation: Levels of Automation [PDF] 摘要

22. XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System [PDF] 摘要

23. Large-Scale Adversarial Training for Vision-and-Language Representation Learning [PDF] 摘要

24. PeopleMap: Visualization Tool for Mapping Out Researchers using Natural Language Processing [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-11

发表于 2020-06-11 分类于 arxiv ， CV 136k 3:46

目录

1. MultiResolution Attention Extractor for Small Object Detection [PDF] 摘要

2. Simple and effective localized attribute representations for zero-shot learning [PDF] 摘要

3. Dataset Condensation with Gradient Matching [PDF] 摘要

4. Recent Advances in 3D Object and Hand Pose Estimation [PDF] 摘要

5. Separable Four Points Fundamental Matrix [PDF] 摘要

6. Deep Learning with Attention Mechanism for Predicting Driver Intention at Intersection [PDF] 摘要

7. DisCont: Self-Supervised Visual Attribute Disentanglement using Context Vectors [PDF] 摘要

8. Speech Fusion to Face: Bridging the Gap Between Human's Vocal Characteristics and Facial Imaging [PDF] 摘要

9. WasteNet: Waste Classification at the Edge for Smart Bins [PDF] 摘要

10. Geometry-Aware Segmentation of Remote Sensing Images via implicit height estimation [PDF] 摘要

11. Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation [PDF] 摘要

12. Embedding Task Knowledge into 3D Neural Networks via Self-supervised Learning [PDF] 摘要

13. Image Enhancement and Object Recognition for Night Vision Surveillance [PDF] 摘要

14. 3D Human Mesh Regression with Dense Correspondence [PDF] 摘要

15. Object Detection in the DCT Domain: is Luminance the Solution? [PDF] 摘要

16. Diagnosing Rarity in Human-Object Interaction Detection [PDF] 摘要

17. Estimating semantic structure for the VQA answer space [PDF] 摘要

18. Real-time single image depth perception in the wild with handheld devices [PDF] 摘要

19. Unique Faces Recognition in Videos [PDF] 摘要

20. Delta Descriptors: Change-Based Place Representation for Robust Visual Localization [PDF] 摘要

21. Rendering Natural Camera Bokeh Effect with Deep Learning [PDF] 摘要

22. TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model [PDF] 摘要

23. H3DNet: 3D Object Detection Using Hybrid Geometric Primitives [PDF] 摘要

24. IMUTube: Automatic extraction of virtual on-body accelerometry from video for human activity recognition [PDF] 摘要

25. 3D geometric moment invariants from the point of view of the classical invariant theory [PDF] 摘要

26. Agrupamento de Pixels para o Reconhecimento de Faces [PDF] 摘要

27. Scalable Backdoor Detection in Neural Networks [PDF] 摘要

28. A survey on deep hashing for image retrieval [PDF] 摘要

29. Deep Learning for Change Detection in Remote Sensing Images: Comprehensive Review and Meta-Analysis [PDF] 摘要

30. Condensing Two-stage Detection with Automatic Object Key Part Discovery [PDF] 摘要

31. CNN-Based Semantic Change Detection in Satellite Imagery [PDF] 摘要

32. Syn2Real Transfer Learning for Image Deraining using Gaussian Processes [PDF] 摘要

33. A gaze driven fast-forward method for first-person videos [PDF] 摘要

34. Tree Annotations in LiDAR Data Using Point Densities and Convolutional Neural Networks [PDF] 摘要

35. 3D Point Cloud Feature Explanations Using Gradient-Based Methods [PDF] 摘要

36. Dual-stream Maximum Self-attention Multi-instance Learning [PDF] 摘要

37. MVLidarNet: Real-Time Multi-Class Scene Understanding for Autonomous Driving Using Multiple Views [PDF] 摘要

38. Off-the-shelf sensor vs. experimental radar -- How much resolution is necessary in automotive radar classification? [PDF] 摘要

39. Standardised convolutional filtering for radiomics [PDF] 摘要

40. Dialog Policy Learning for Joint Clarification and Active Learning Queries [PDF] 摘要

41. D-VPnet: A Network for Real-time Dominant Vanishing Point Detection in Natural Scenes [PDF] 摘要

42. SAL++: Sign Agnostic Learning with Derivatives [PDF] 摘要

43. Open-Narrow-Synechiae Anterior Chamber Angle Classification in AS-OCT Sequences [PDF] 摘要

44. A Hybrid Framework for Matching Printing Design Files to Product Photos [PDF] 摘要

45. MeshWalker: Deep Mesh Understanding by Random Walks [PDF] 摘要

46. Towards Good Practices for Data Augmentation in GAN Training [PDF] 摘要

47. mEBAL: A Multimodal Database for Eye Blink Detection and Attention Level Estimation [PDF] 摘要

48. ComboNet: Combined 2D & 3D Architecture for Aorta Segmentation [PDF] 摘要

49. Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps [PDF] 摘要

50. Neural Network Activation Quantization with Bitwise Information Bottlenecks [PDF] 摘要

51. Multi-spectral Facial Landmark Detection [PDF] 摘要

52. Stereo RGB and Deeper LIDAR Based Network for 3D Object Detection [PDF] 摘要

53. A Note on Deepfake Detection with Low-Resources [PDF] 摘要

54. Breaking the Limits of Remote Sensing by Simulation and Deep Learning for Flood and Debris Flow Mapping [PDF] 摘要

55. Reconstruction and Quantification of 3D Iris Surface for Angle-Closure Glaucoma Detection in Anterior Segment OCT [PDF] 摘要

56. Physically constrained short-term vehicle trajectory forecasting with naive semantic maps [PDF] 摘要

57. Smooth Proxy-Anchor Loss for Noisy Metric Learning [PDF] 摘要

58. A Survey on Generative Adversarial Networks: Variants, Applications, and Training [PDF] 摘要

59. Over-crowdedness Alert! Forecasting the Future Crowd Distribution [PDF] 摘要

60. Roses Are Red, Violets Are Blue... but Should Vqa Expect Them To? [PDF] 摘要

61. GAP++: Learning to generate target-conditioned adversarial examples [PDF] 摘要

62. Towards an Intrinsic Definition of Robustness for a Classifier [PDF] 摘要

63. PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition [PDF] 摘要

64. SEKD: Self-Evolving Keypoint Detection and Description [PDF] 摘要

65. Detection of Makeup Presentation Attacks based on Deep Face Representations [PDF] 摘要

66. Learning Shared Filter Bases for Efficient ConvNets [PDF] 摘要

67. Single Image Deraining via Scale-space Invariant Attention Neural Network [PDF] 摘要

68. Can Synthetic Data Improve Object Detection Results for Remote Sensing Images? [PDF] 摘要

69. RGB-D-E: Event Camera Calibration for Fast 6-DOF Object Tracking [PDF] 摘要

70. Rethinking Classification Loss Designs for Person Re-identification with a Unified View [PDF] 摘要

71. Pixel-Wise Motion Deblurring of Thermal Videos [PDF] 摘要

72. A Self-supervised Approach for Adversarial Robustness [PDF] 摘要

73. What Matters in Unsupervised Optical Flow [PDF] 摘要

74. Reposing Humans by Warping 3D Features [PDF] 摘要

75. Probabilistic Semantic Mapping for Urban Autonomous Driving Applications [PDF] 摘要

76. Skinning a Parameterization of Three-Dimensional Space for Neural Network Cloth [PDF] 摘要

77. DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation [PDF] 摘要

78. Novel Perception Algorithmic Framework For Object Identification and Tracking In Autonomous Navigation [PDF] 摘要

79. A systematic review on the role of artificial intelligence in sonographic diagnosis of thyroid cancer: Past, present and future [PDF] 摘要

80. To Regularize or Not To Regularize? The Bias Variance Trade-off in Regularized AEs [PDF] 摘要

81. Applying Deep-Learning-Based Computer Vision to Wireless Communications: Methodologies, Opportunities, and Challenges [PDF] 摘要

82. Dual-level Semantic Transfer Deep Hashing for Efficient Social Image Retrieval [PDF] 摘要

83. Deep Learning-based Aerial Image Segmentation with Open Data for Disaster Impact Assessment [PDF] 摘要

84. Resolution-Enhanced MRI-Guided Navigation of Spinal Cellular Injection Robot [PDF] 摘要

85. Supervised Learning of Sparsity-Promoting Regularizers for Denoising [PDF] 摘要

86. A Deep Learning-Based Method for Automatic Segmentation of Proximal Femur from Quantitative Computed Tomography Images [PDF] 摘要

87. Can artificial intelligence (AI) be used to accurately detect tuberculosis (TB) from chest x-ray? A multiplatform evaluation of five AI products used for TB screening in a high TB-burden setting [PDF] 摘要

88. DcardNet: Diabetic Retinopathy Classification at Multiple Depths Based on Structural and Angiographic Optical Coherence Tomography [PDF] 摘要

89. Pruning neural networks without any data by iteratively conserving synaptic flow [PDF] 摘要

90. Neuroevolution in Deep Neural Networks: Current Trends and Future Challenges [PDF] 摘要

91. Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image [PDF] 摘要

92. A t-distribution based operator for enhancing \\ out of distribution robustness of neural network classifiers [PDF] 摘要

93. A Comparative Study on Early Detection of COVID-19 from Chest X-Ray Images [PDF] 摘要

94. UMLS-ChestNet: A deep convolutional neural network for radiological findings, differential diagnoses and localizations of COVID-19 in chest x-rays [PDF] 摘要

95. What takes the brain so long: Object recognition at the level of minimal images develops for up to seconds of presentation time [PDF] 摘要

96. A Review of Automatically Diagnosing COVID-19 based on Scanning Image [PDF] 摘要

97. Super-resolution Variational Auto-Encoders [PDF] 摘要

98. Automated Design Space Exploration for optimised Deployment of DNN on Arm Cortex-A CPUs [PDF] 摘要

99. Orientation Attentive Robot Grasp Synthesis [PDF] 摘要

100. High Tissue Contrast MRI Synthesis Using Multi-Stage Attention-GAN for Glioma Segmentation [PDF] 摘要

101. Deep learning to estimate the physical proportion of infected region of lung for COVID-19 pneumonia with CT image set [PDF] 摘要

102. Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT [PDF] 摘要

103. Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation [PDF] 摘要

104. Big GANs Are Watching You: Towards Unsupervised Object Segmentation with Off-the-Shelf Generative Models [PDF] 摘要

105. KiU-Net: Towards Accurate Segmentation of Biomedical Images using Over-complete Representations [PDF] 摘要

106. Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-06-11

发表于 2020-06-11 分类于 arxiv ， CL 47k 1:19

目录

1. Revisiting Few-sample BERT Fine-tuning [PDF] 摘要

2. ClarQ: A large-scale and diverse dataset for Clarification Question Generation [PDF] 摘要

3. Gender in Danger? Evaluating Speech Translation Technology on the MuST-SHE Corpus [PDF] 摘要

4. MC-BERT: Efficient Language Pre-Training via a Meta Controller [PDF] 摘要

5. Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network [PDF] 摘要

6. Position Masking for Language Models [PDF] 摘要

7. Data Augmentation for Training Dialog Models Robust to Speech Recognition Errors [PDF] 摘要

8. Understanding Points of Correspondence between Sentences for Abstractive Summarization [PDF] 摘要

9. Adversarial Training Based Multi-Source Unsupervised Domain Adaptation for Sentiment Analysis [PDF] 摘要

10. Predicting and Analyzing Law-Making in Kenya [PDF] 摘要

11. Modeling Label Semantics for Predicting Emotional Reactions [PDF] 摘要

12. Unsupervised Paraphrase Generation using Pre-trained Language Models [PDF] 摘要

13. Examination and Extension of Strategies for Improving Personalized Language Modeling via Interpolation [PDF] 摘要

14. Combination of abstractive and extractive approaches for summarization of long scientific texts [PDF] 摘要

15. Extensive Error Analysis and a Learning-Based Evaluation of Medical Entity Recognition Systems to Approximate User Experience [PDF] 摘要

16. Knowledge-Aided Open-Domain Question Answering [PDF] 摘要

17. Re-evaluating phoneme frequencies [PDF] 摘要

18. Learning to Recover from Multi-Modality Errors for Non-Autoregressive Neural Machine Translation [PDF] 摘要

19. ConfNet2Seq: Full Length Answer Generation from Spoken Questions [PDF] 摘要

20. Human brain activity for machine attention [PDF] 摘要

21. HausaMT v1.0: Towards English-Hausa Neural Machine Translation [PDF] 摘要

22. Universal Vector Neural Machine Translation With Effective Attention [PDF] 摘要

23. Embed2Detect: Temporally Clustered Embedded Words for Event Detection in Social Media [PDF] 摘要

24. Estimating semantic structure for the VQA answer space [PDF] 摘要

25. Learning Functions to Study the Benefit of Multitask Learning [PDF] 摘要

26. Improving Cross-Lingual Transfer Learning for End-to-End Speech Recognition with Speech Translation [PDF] 摘要

27. Dialog Policy Learning for Joint Clarification and Active Learning Queries [PDF] 摘要

28. Vocal markers from sustained phonation in Huntington's Disease [PDF] 摘要

29. Learning not to Discriminate: Task Agnostic Learning for Improving Monolingual and Code-switched Speech Recognition [PDF] 摘要

30. audino: A Modern Annotation Tool for Audio and Speech [PDF] 摘要

31. Graph-Aware Transformer: Is Attention All Graphs Need? [PDF] 摘要

32. Hand-crafted Attention is All You Need? A Study of Attention on Self-supervised Audio Transformer [PDF] 摘要

33. On the Effectiveness of Neural Text Generation based Data Augmentation for Recognition of Morphologically Rich Speech [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-10

发表于 2020-06-10 分类于 arxiv ， CV 58 1 分钟

---

注：中文为机器翻译结果！

【arxiv论文】 Computation and Language 2020-06-10

发表于 2020-06-10 分类于 arxiv ， CL 58 1 分钟

---

注：中文为机器翻译结果！

【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-09

发表于 2020-06-09 分类于 arxiv ， CV 148k 4:07

目录

1. Unsupervised Transfer Learning with Self-Supervised Remedy [PDF] 摘要

2. ResKD: Residual-Guided Knowledge Distillation [PDF] 摘要

3. Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior [PDF] 摘要

4. Unstructured Road Vanishing Point Detection Using the Convolutional Neural Network and Heatmap Regression [PDF] 摘要

5. Semantic Graph-enhanced Visual Network for Zero-shot Learning [PDF] 摘要

6. SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds [PDF] 摘要

7. Incorporating Image Gradients as Secondary Input Associated with Input Image to Improve the Performance of the CNN Model [PDF] 摘要

8. Person Re-identification in the 3D Space [PDF] 摘要

9. FibeR-CNN: Expanding Mask R-CNN to Improve Image-Based Fiber Analysis [PDF] 摘要

10. Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration [PDF] 摘要

11. More Information Supervised Probabilistic Deep Face Embedding Learning [PDF] 摘要

12. Action Recognition with Deep Multiple Aggregation Networks [PDF] 摘要

13. Deep hierarchical pooling design for cross-granularity action recognition [PDF] 摘要

14. Continual Representation Learning for Biometric Identification [PDF] 摘要

15. Novel Adaptive Binary Search Strategy-First Hybrid Pyramid- and Clustering-Based CNN Filter Pruning Method without Parameters Setting [PDF] 摘要

16. Passive Batch Injection Training Technique: Boosting Network Performance by Injecting Mini-Batches from a different Data Distribution [PDF] 摘要

17. Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection [PDF] 摘要

18. Semantics-Driven Unsupervised Learning for Monocular Depth and Ego-Motion Estimation [PDF] 摘要

19. Neural Sparse Representation for Image Restoration [PDF] 摘要

20. Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection [PDF] 摘要

21. Fast Synthetic LiDAR Rendering via Spherical UV Unwrapping of Equirectangular Z-Buffer Images [PDF] 摘要

22. Deep Neural Network Based Real-time Kiwi Fruit Flower Detection in an Orchard Environment [PDF] 摘要

23. Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels [PDF] 摘要

24. Ensemble Model with Batch Spectral Regularization and Data Blending for Cross-Domain Few-Shot Learning with Unlabeled Data [PDF] 摘要

25. Counterfactual VQA: A Cause-Effect Look at Language Bias [PDF] 摘要

26. Are We Hungry for 3D LiDAR Data for Semantic Segmentation? [PDF] 摘要

27. Text Detection and Recognition in the Wild: A Review [PDF] 摘要

28. How useful is Active Learning for Image-based Plant Phenotyping? [PDF] 摘要

29. AdaLAM: Revisiting Handcrafted Outlier Detection [PDF] 摘要

30. Efficient Poverty Mapping using Deep Reinforcement Learning [PDF] 摘要

31. Thoracic Disease Identification and Localization using Distance Learning and Region Verification [PDF] 摘要

32. Finger Texture Biometric Characteristic: a Survey [PDF] 摘要

33. Learning pose variations within shape population by constrained mixtures of factor analyzers [PDF] 摘要

34. Realistic text replacement with non-uniform style conditioning [PDF] 摘要

35. Decentralised Learning from Independent Multi-Domain Labels for Person Re-Identification [PDF] 摘要

36. Peer Collaborative Learning for Online Knowledge Distillation [PDF] 摘要

37. Learning Texture Transformer Network for Image Super-Resolution [PDF] 摘要

38. ADMP: An Adversarial Double Masks Based Pruning Framework For Unsupervised Cross-Domain Compression [PDF] 摘要

39. DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling [PDF] 摘要

40. Robust Learning Through Cross-Task Consistency [PDF] 摘要

41. Multi-view Contrastive Learning for Online Knowledge Distillation [PDF] 摘要

42. End-to-end Learning for Inter-Vehicle Distance and Relative Velocity Estimation in ADAS with a Monocular Camera [PDF] 摘要

43. CubifAE-3D: Monocular Camera Space Cubification on Autonomous Vehicles for Auto-Encoder based 3D Object Detection [PDF] 摘要

44. Siamese Keypoint Prediction Network for Visual Object Tracking [PDF] 摘要

45. NITS-VC System for VATEX Video Captioning Challenge 2020 [PDF] 摘要

46. Facial Expression Recognition using Deep Learning [PDF] 摘要

47. DeepRelativeFusion: Dense Monocular SLAM using Single-Image Relative Depth Prediction [PDF] 摘要

48. SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds [PDF] 摘要

49. SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation [PDF] 摘要

50. MeshSDF: Differentiable Iso-Surface Extraction [PDF] 摘要

51. Enhancing Facial Data Diversity with Style-based Face Aging [PDF] 摘要

52. Self-Supervised Dynamic Networks for Covariate Shift Robustness [PDF] 摘要

53. Self-supervising Fine-grained Region Similarities for Large-scale Image Localization [PDF] 摘要

54. A Robust Attentional Framework for License Plate Recognition in the Wild [PDF] 摘要

55. Ensemble Network for Ranking Images Based on Visual Appeal [PDF] 摘要

56. The Criminality From Face Illusion [PDF] 摘要

57. ARID: A New Dataset for Recognizing Action in the Dark [PDF] 摘要

58. Towards large-scale, automated, accurate detection of CCTV camera objects using computer vision. Applications and implications for privacy, safety, and cybersecurity. (Preprint) [PDF] 摘要

59. Instance segmentation of buildings using keypoints [PDF] 摘要

60. Building a Heterogeneous, Large Scale Morphable Face Model [PDF] 摘要

61. 3D Self-Supervised Methods for Medical Imaging [PDF] 摘要

62. UCLID-Net: Single View Reconstruction in Object Space [PDF] 摘要

63. An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation [PDF] 摘要

64. Extracting Cellular Location of Human Proteins Using Deep Learning [PDF] 摘要

65. Deep Mining External Imperfect Data for Chest X-ray Disease Screening [PDF] 摘要

66. No-Reference Image Quality Assessment via Feature Fusion and Multi-Task Learning [PDF] 摘要

67. MAGNet: Multi-Region Attention-Assisted Grounding of Natural Language Queries at Phrase Level [PDF] 摘要

68. Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completion [PDF] 摘要

69. GRNet: Gridding Residual Network for Dense Point Cloud Completion [PDF] 摘要

70. Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation [PDF] 摘要

71. Simple Primary Colour Editing for Consumer Product Images [PDF] 摘要

72. Unsupervised Abnormality Detection Using Heterogeneous Autonomous Systems [PDF] 摘要

73. WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos [PDF] 摘要

74. Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation [PDF] 摘要

75. Visual Transformers: Token-based Image Representation and Processing for Computer Vision [PDF] 摘要

76. AutoHAS: Differentiable Hyper-parameter and Architecture Search [PDF] 摘要

77. RIT-Eyes: Rendering of near-eye images for eye-tracking applications [PDF] 摘要

78. Knowledge transfer between bridges for drive-by monitoring using adversarial and multi-task learning [PDF] 摘要

79. Robust Face Verification via Disentangled Representations [PDF] 摘要

80. SparseFusion: Dynamic Human Avatar Modeling from Sparse RGBD Images [PDF] 摘要

81. Inception Augmentation Generative Adversarial Network [PDF] 摘要

82. Motion Prediction using Trajectory Sets and Self-Driving Domain Knowledge [PDF] 摘要

83. Biomechanics-informed Neural Networks for Myocardial Motion Tracking in MRI [PDF] 摘要

84. Neural Architecture Search without Training [PDF] 摘要

85. End-to-end learning for semiquantitative rating of COVID-19 severity on Chest X-rays [PDF] 摘要

86. On Universalized Adversarial and Invariant Perturbations [PDF] 摘要

87. Training Deep Spiking Neural Networks [PDF] 摘要

88. Cross-Domain Segmentation with Adversarial Loss and Covariate Shift for Biomedical Imaging [PDF] 摘要

89. Learning the Compositional Visual Coherence for Complementary Recommendations [PDF] 摘要

90. Photoacoustic Microscopy with Sparse Data Enabled by Convolutional Neural Networks for Fast Imaging [PDF] 摘要

91. Multi-step Estimation for Gradient-based Meta-learning [PDF] 摘要

92. EDropout: Energy-Based Dropout and Pruning of Deep Neural Networks [PDF] 摘要

93. Self-Representation Based Unsupervised Exemplar Selection in a Union of Subspaces [PDF] 摘要

94. Unsupervised Learning for Subterranean Junction Recognition Based on 2D Point Cloud [PDF] 摘要

95. A multi-channel framework for joint reconstruction of multi-contrast parallel MRI [PDF] 摘要

96. A Generic First-Order Algorithmic Framework for Bi-Level Programming Beyond Lower-Level Singleton [PDF] 摘要

97. A Comparative Analysis of E-Scooter and E-Bike Usage Patterns: Findings from the City of Austin, TX [PDF] 摘要

98. Neural Networks Out-of-Distribution Detection: Hyperparameter-Free Isotropic Maximization Loss, The Principle of Maximum Entropy, Cold Training, and Branched Inferences [PDF] 摘要

99. An Efficient $k$-modes Algorithm for Clustering Categorical Datasets [PDF] 摘要

100. Robust watermarking with double detector-discriminator approach [PDF] 摘要

101. Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement [PDF] 摘要

102. Applied Awareness: Test-Driven GUI Development using Computer Vision and Cryptography [PDF] 摘要

103. Texture Interpolation for Probing Visual Perception [PDF] 摘要

104. Evaluating the Disentanglement of Deep Generative Models through Manifold Topology [PDF] 摘要

105. Hierarchical Class-Based Curriculum Loss [PDF] 摘要

106. Equivariant Maps for Hierarchical Structures [PDF] 摘要

107. 3D Augmented Reality-Assisted CT-Guided Interventions: System Design and Preclinical Trial on an Abdominal Phantom using HoloLens 2 [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-06-09

发表于 2020-06-09 分类于 arxiv ， CL 62k 1:43

目录

1. What's the Difference Between Professional Human and Machine Translation? A Blind Multi-language Study on Domain-specific MT [PDF] 摘要

2. Modeling Discourse Structure for Document-level Neural Machine Translation [PDF] 摘要

3. CycleGT: Unsupervised Graph-to-Text and Text-to-Graph Generation via Cycle Training [PDF] 摘要

4. Misinformation has High Perplexity [PDF] 摘要

5. ColdGANs: Taming Language GANs with Cautious Sampling Strategies [PDF] 摘要

6. A Comprehensive Survey on Aspect Based Sentiment Analysis [PDF] 摘要

7. CS-Embed-francesita at SemEval-2020 Task 9: The effectiveness of code-switched word embeddings for sentiment analysis [PDF] 摘要

8. Towards an Argument Mining Pipeline Transforming Texts to Argument Graphs [PDF] 摘要

9. Combining word embeddings and convolutional neural networks to detect duplicated questions [PDF] 摘要

10. Tensors over Semirings for Latent-Variable Weighted Logic Programs [PDF] 摘要

11. Pre-training Polish Transformer-based Language Models at Scale [PDF] 摘要

12. BERT Loses Patience: Fast and Robust Inference with Early Exit [PDF] 摘要

13. Interactive Extractive Search over Biomedical Corpora [PDF] 摘要

14. Language Models as Fact Checkers? [PDF] 摘要

15. Growing Together: Modeling Human Language Learning With n-Best Multi-Checkpoint Machine Translation [PDF] 摘要

16. Semantic Loss Application to Entity Relation Recognition [PDF] 摘要

17. A Multitask Learning Approach for Diacritic Restoration [PDF] 摘要

18. Medical Concept Normalization in User Generated Texts by Learning Target Concept Embeddings [PDF] 摘要

19. Generative Adversarial Phonology: Modeling unsupervised phonetic and phonological learning with neural networks [PDF] 摘要

20. ValNorm: A New Word Embedding Intrinsic Evaluation Method Reveals Valence Biases are Consistent Across Languages and Over Decades [PDF] 摘要

21. A Cross-Task Analysis of Text Span Representations [PDF] 摘要

22. Challenges and Thrills of Legal Arguments [PDF] 摘要

23. Relation of the Relations: A New Paradigm of the Relation Extraction Problem [PDF] 摘要

24. Accelerating Natural Language Understanding in Task-Oriented Dialog [PDF] 摘要

25. UDPipe at EvaLatin 2020: Contextualized Embeddings and Treebank Embeddings [PDF] 摘要

26. Prague Dependency Treebank -- Consolidated 1.0 [PDF] 摘要

27. DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations [PDF] 摘要

28. DeBERTa: Decoding-enhanced BERT with Disentangled Attention [PDF] 摘要

29. Filtered Inner Product Projection for Multilingual Embedding Alignment [PDF] 摘要

30. MultiSpeech: Multi-Speaker Text to Speech with Transformer [PDF] 摘要

31. WaveNODE: A Continuous Normalizing Flow for Speech Synthesis [PDF] 摘要

32. FastSpeech 2: Fast and High-Quality End-to-End Text-to-Speech [PDF] 摘要

33. A non-causal FFTNet architecture for speech enhancement [PDF] 摘要

34. Characterizing Sociolinguistic Variation in the Competing Vaccination Communities [PDF] 摘要

35. Parametric Representation for Singing Voice Synthesis: a Comparative Evaluation [PDF] 摘要

36. Maximum Phase Modeling for Sparse Linear Prediction of Speech [PDF] 摘要

37. Analysis and Synthesis of Hypo and Hyperarticulated Speech [PDF] 摘要

38. Incorporating Pragmatic Reasoning Communication into Emergent Language [PDF] 摘要

39. Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases [PDF] 摘要

40. MAGNet: Multi-Region Attention-Assisted Grounding of Natural Language Queries at Phrase Level [PDF] 摘要

41. Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation [PDF] 摘要

42. BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-08

发表于 2020-06-08 分类于 arxiv ， CV 47k 1:18

目录

1. Novel Object Viewpoint Estimation through Reconstruction Alignment [PDF] 摘要

2. A Meta-Bayesian Model of Intentional Visual Search [PDF] 摘要

3. VALUE: Large Scale Voting-based Automatic Labelling for Urban Environments [PDF] 摘要

4. Segmentation of Surgical Instruments for Minimally-Invasive Robot-Assisted Procedures Using Generative Deep Neural Networks [PDF] 摘要

5. Learning Neural Light Transport [PDF] 摘要

6. Uncertainty-Aware CNNs for Depth Completion: Uncertainty from Beginning to End [PDF] 摘要

7. Explaining Autonomous Driving by Learning End-to-End Visual Attention [PDF] 摘要

8. MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction [PDF] 摘要

9. Multi-modal Feature Fusion with Feature Attention for VATEX Captioning Challenge 2020 [PDF] 摘要

10. Biometric Quality: Review and Application to Face Recognition with FaceQnet [PDF] 摘要

11. Real-time Human Activity Recognition Using Conditionally Parametrized Convolutions on Mobile and Wearable Devices [PDF] 摘要

12. TCDesc: Learning Topology Consistent Descriptors [PDF] 摘要

13. FP-Stereo: Hardware-Efficient Stereo Vision for Embedded Applications [PDF] 摘要

14. Content and Context Features for Scene Image Representation [PDF] 摘要

15. Content-Aware Inter-Scale Cost Aggregation for Stereo Matching [PDF] 摘要

16. Black-box Explanation of Object Detectors via Saliency Maps [PDF] 摘要

17. Egocentric Object Manipulation Graphs [PDF] 摘要

18. Scene Image Representation by Foreground, Background and Hybrid Features [PDF] 摘要

19. Pick-Object-Attack: Type-Specific Adversarial Attack for Object Detection [PDF] 摘要

20. MSDU-net: A Multi-Scale Dilated U-net for Blur Detection [PDF] 摘要

21. Unsupervised clustering of Roman pottery profiles from their SSAE representation [PDF] 摘要

22. SIDU: Similarity Difference and Uniqueness Method for Explainable AI [PDF] 摘要

23. Sponge Examples: Energy-Latency Attacks on Neural Networks [PDF] 摘要

24. Artificial Intelligence-based Clinical Decision Support for COVID-19 -- Where Art Thou? [PDF] 摘要

25. Acoustic Anomaly Detection for Machine Sounds based on Image Transfer Learning [PDF] 摘要

26. Detection of prostate cancer in whole-slide images through end-to-end training with image-level labels [PDF] 摘要

27. Structurally aware bidirectional unpaired image to image translation between CT and MR [PDF] 摘要

28. Learning to Rank Learning Curves [PDF] 摘要

29. Convolutional Neural Networks for Global Human Settlements Mapping from Sentinel-2 Satellite Imagery [PDF] 摘要

30. Discovering Parametric Activation Functions [PDF] 摘要

阅读全文 »