【arxiv论文】 Computation and Language 2020-03-23

发表于 2020-03-23 分类于 arxiv ， CL 15k 26 分钟

目录

1. FedNER: Medical Named Entity Recognition with Federated Learning [PDF] 摘要

2. Language Technology Programme for Icelandic 2019-2023 [PDF] 摘要

3. Parallel Intent and Slot Prediction using MLB Fusion [PDF] 摘要

4. TNT-KID: Transformer-based Neural Tagger for Keyword Identification [PDF] 摘要

5. NSURL-2019 Task 7: Named Entity Recognition (NER) in Farsi [PDF] 摘要

6. Techniques for Vocabulary Expansion in Hybrid Speech Recognition Systems [PDF] 摘要

7. Learning to Encode Position for Transformer with Continuous Dynamical Model [PDF] 摘要

8. Detecting Mismatch between Text Script and Voice-over Using Utterance Verification Based on Phoneme Recognition Ranking [PDF] 摘要

9. Automatic Identification of Types of Alterations in Historical Manuscripts [PDF] 摘要

10. The value of text for small business default prediction: A deep learning approach [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-20

发表于 2020-03-20 分类于 arxiv ， CV 177k 4:56

目录

1. GAN Compression: Efficient Architectures for Interactive Conditional GANs [PDF] 摘要

2. Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression [PDF] 摘要

3. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis [PDF] 摘要

4. Depth Estimation by Learning Triangulation and Densification of Sparse Points for Multi-view Stereo [PDF] 摘要

5. GIQA: Generated Image Quality Assessment [PDF] 摘要

6. Normalized and Geometry-Aware Self-Attention Network for Image Captioning [PDF] 摘要

7. Local Rotation Invariance in 3D CNNs [PDF] 摘要

8. Unique Geometry and Texture from Corresponding Image Patches [PDF] 摘要

9. Across Scales \& Across Dimensions: Temporal Super-Resolution using Deep Internal Learning [PDF] 摘要

10. Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation [PDF] 摘要

11. JAA-Net: Joint Facial Action Unit Detection and Face Alignment via Adaptive Attention [PDF] 摘要

12. DHOG: Deep Hierarchical Object Grouping [PDF] 摘要

13. Brain MRI-based 3D Convolutional Neural Networks for Classification of Schizophrenia and Controls [PDF] 摘要

14. Functional Data Analysis and Visualisation of Three-dimensional Surface Shape [PDF] 摘要

15. Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation [PDF] 摘要

16. Deep Learning for Automatic Tracking of Tongue Surface in Real-time Ultrasound Videos, Landmarks instead of Contours [PDF] 摘要

17. MagicEyes: A Large Scale Eye Gaze Estimation Dataset for Mixed Reality [PDF] 摘要

18. Deep Object Detection based Mitosis Analysis in Breast Cancer Histopathological Images [PDF] 摘要

19. Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction [PDF] 摘要

20. Pedestrian Detection: The Elephant In The Room [PDF] 摘要

21. Incremental Object Detection via Meta-Learning [PDF] 摘要

22. Teacher-Student chain for efficient semi-supervised histology image classification [PDF] 摘要

23. Deep Active Learning for Remote Sensing Object Detection [PDF] 摘要

24. High-Resolution Daytime Translation Without Domain Labels [PDF] 摘要

25. Child Face Age-Progression via Deep Feature Aging [PDF] 摘要

26. Self-Guided Adaptation: Progressive Representation Alignment for Domain Adaptive Object Detection [PDF] 摘要

27. Measuring and improving the quality of visual explanations [PDF] 摘要

28. Do CNNs Encode Data Augmentations? [PDF] 摘要

29. "Who is Driving around Me?" Unique Vehicle Instance Classification using Deep Neural Features [PDF] 摘要

30. ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection [PDF] 摘要

31. Personalized Taste and Cuisine Preference Modeling via Images [PDF] 摘要

32. A Review of Computational Approaches for Evaluation of Rehabilitation Exercises [PDF] 摘要

33. Dense Crowds Detection and Surveillance with Drones using Density Maps [PDF] 摘要

34. Salient Facial Features from Humans and Deep Neural Networks [PDF] 摘要

35. Shape retrieval of non-rigid 3d human models [PDF] 摘要

36. Exemplar Normalization for Learning Deep Representation [PDF] 摘要

37. A Question-Centric Model for Visual Question Answering in Medical Imaging [PDF] 摘要

38. FePh: An Annotated Facial Expression Dataset for the RWTH-PHOENIX-Weather 2014 Dataset [PDF] 摘要

39. A Compact Spectral Descriptor for Shape Deformations [PDF] 摘要

40. Adversarial Camouflage: Hiding Physical-World Attacks with Natural Styles [PDF] 摘要

41. Deep Neural Network Perception Models and Robust Autonomous Driving Systems [PDF] 摘要

42. Adaptive binarization based on fuzzy integrals [PDF] 摘要

43. SAM: The Sensitivity of Attribution Methods to Hyperparameters [PDF] 摘要

44. FineHand: Learning Hand Shapes for American Sign Language Recognition [PDF] 摘要

45. Hierarchical Modes Exploring in Generative Adversarial Networks [PDF] 摘要

46. Unique Class Group Based Multi-Label Balancing Optimizer for Action Unit Detection [PDF] 摘要

47. Longevity Associated Geometry Identified in Satellite Images: Sidewalks, Driveways and Hiking Trails [PDF] 摘要

48. Toward Enabling a Reliable Quality Monitoring System for Additive Manufacturing Process using Deep Convolutional Neural Networks [PDF] 摘要

49. Reduction of Surgical Risk Through the Evaluation of Medical Imaging Diagnostics [PDF] 摘要

50. IROF: a low resource evaluation metric for explanation methods [PDF] 摘要

51. On the Road with 16 Neurons: Mental Imagery with Bio-inspired Deep Neural Networks [PDF] 摘要

52. PLOP: Probabilistic poLynomial Objects trajectory Planning for autonomous driving [PDF] 摘要

53. Generative Multi-Stream Architecture For American Sign Language Recognition [PDF] 摘要

54. A CNN-based Patent Image Retrieval Method for Design Ideation [PDF] 摘要

55. Out-of-Distribution Detection in Multi-Label Datasets using Latent Space of $β$-VAE [PDF] 摘要

56. A Matlab Toolbox for Feature Importance Ranking [PDF] 摘要

57. Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes [PDF] 摘要

58. Fast Distance-based Anomaly Detection in Images Using an Inception-like Autoencoder [PDF] 摘要

59. Customized Video QoE Estimation with Algorithm-Agnostic Transfer Learning [PDF] 摘要

60. Dynamic Spatiotemporal Graph Neural Network with Tensor Network [PDF] 摘要

61. Giving Commands to a Self-driving Car: A Multimodal Reasoner for Visual Grounding [PDF] 摘要

62. Leveraging Frequency Analysis for Deep Fake Image Recognition [PDF] 摘要

63. Efficient and Robust Shape Correspondence via Sparsity-Enforced Quadratic Assignment [PDF] 摘要

64. LANCE: efficient low-precision quantized Winograd convolution for neural networks based on graphics processing units [PDF] 摘要

65. Detecting Deepfakes with Metric Learning [PDF] 摘要

66. Photo-Realistic Video Prediction on Natural Videos of Largely Changing Frames [PDF] 摘要

67. Unsupervised text line segmentation [PDF] 摘要

68. Foldover Features for Dynamic Object Behavior Description in Microscopic Videos [PDF] 摘要

69. Domain-Adaptive Few-Shot Learning [PDF] 摘要

70. PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions [PDF] 摘要

71. AQPDBJUT Dataset: Picture-Based PM2.5 Monitoring in the Campus of BJUT [PDF] 摘要

72. Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection [PDF] 摘要

73. Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering [PDF] 摘要

74. End-to-End Deep Diagnosis of X-ray Images [PDF] 摘要

75. Deep convolutional embedding for digitized painting clustering [PDF] 摘要

76. Curriculum DeepSDF [PDF] 摘要

77. High Accuracy Face Geometry Capture using a Smartphone Video [PDF] 摘要

78. CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries [PDF] 摘要

79. Quality Control of Neuron Reconstruction Based on Deep Learning [PDF] 摘要

80. Detecting Lane and Road Markings at A Distance with Perspective Transformer Layers [PDF] 摘要

81. Stereo Endoscopic Image Super-Resolution Using Disparity-Constrained Parallel Attention [PDF] 摘要

82. Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition [PDF] 摘要

83. SAPIEN: A SimulAted Part-based Interactive ENvironment [PDF] 摘要

84. Evaluating Salient Object Detection in Natural Images with Multiple Objects having Multi-level Saliency [PDF] 摘要

85. A Metric Learning Reality Check [PDF] 摘要

86. Reconstructing Sinus Anatomy from Endoscopic Video -- Towards a Radiation-free Approach for Quantitative Longitudinal Assessment [PDF] 摘要

87. Gaze-Sensing LEDs for Head Mounted Displays [PDF] 摘要

88. Self-Supervised Contextual Bandits in Computer Vision [PDF] 摘要

89. Visual link retrieval and knowledge discovery in painting datasets [PDF] 摘要

90. Semi-supervised few-shot learning for medical image segmentation [PDF] 摘要

91. Detecting Pancreatic Adenocarcinoma in Multi-phase CT Scans via Alignment Ensemble [PDF] 摘要

92. Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation [PDF] 摘要

93. Collaborative Distillation for Ultra-Resolution Universal Style Transfer [PDF] 摘要

94. STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos [PDF] 摘要

95. Volumetric parcellation of the right ventricle for regional geometric and functional assessment [PDF] 摘要

96. Oral-3D: Reconstructing the 3D Bone Structure of Oral Cavity from 2D Panoramic X-ray [PDF] 摘要

97. A Content Transformation Block For Image Style Transfer [PDF] 摘要

98. Adversarial Texture Optimization from RGB-D Scans [PDF] 摘要

99. Overinterpretation reveals image classification model pathologies [PDF] 摘要

100. Brain tumor segmentation with missing modalities via latent multi-source correlation representation [PDF] 摘要

101. DRST: Deep Residual Shearlet Transform for Densely Sampled Light Field Reconstruction [PDF] 摘要

102. Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives [PDF] 摘要

103. Addressing the Memory Bottleneck in AI Model Training [PDF] 摘要

104. RADIOGAN: Deep Convolutional Conditional Generative adversarial Network To Generate PET Images [PDF] 摘要

105. Backdooring and Poisoning Neural Networks with Image-Scaling Attacks [PDF] 摘要

106. HyNNA: Improved Performance for Neuromorphic Vision Sensor based Surveillance using Hybrid Neural Network Architecture [PDF] 摘要

107. Ensemble learning in CNN augmented with fully connected subnetworks [PDF] 摘要

108. Lifelong Learning with Searchable Extension Units [PDF] 摘要

109. Extremal Region Analysis based Deep Learning Framework for Detecting Defects [PDF] 摘要

110. Efficiently Calibrating Cable-Driven Surgical Robots With RGBD Sensing, Temporal Windowing, and Linear and Recurrent Neural Network Compensation [PDF] 摘要

111. MINT: Deep Network Compression via Mutual Information-based Neuron Trimming [PDF] 摘要

112. Two Tier Prediction of Stroke Using Artificial Neural Networks and Support Vector Machines [PDF] 摘要

113. Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-20

发表于 2020-03-20 分类于 arxiv ， CL 15k 25 分钟

目录

1. Utilizing Language Relatedness to improve Machine Translation: A Case Study on Languages of the Indian Subcontinent [PDF] 摘要

2. Beheshti-NER: Persian Named Entity Recognition Using BERT [PDF] 摘要

3. Boosting Factual Correctness of Abstractive Summarization with Knowledge Graph [PDF] 摘要

4. Diversity, Density, and Homogeneity: Quantitative Characteristic Metrics for Text Collections [PDF] 摘要

5. An Analysis on the Learning Rules of the Skip-Gram Model [PDF] 摘要

6. Normalized and Geometry-Aware Self-Attention Network for Image Captioning [PDF] 摘要

7. Deep Learning for Automatic Tracking of Tongue Surface in Real-time Ultrasound Videos, Landmarks instead of Contours [PDF] 摘要

8. Personalized Taste and Cuisine Preference Modeling via Images [PDF] 摘要

9. Giving Commands to a Self-driving Car: A Multimodal Reasoner for Visual Grounding [PDF] 摘要

10. QnAMaker: Data to Bot in 2 Minutes [PDF] 摘要

11. A Corpus of Adpositional Supersenses for Mandarin Chinese [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-19

发表于 2020-03-19 分类于 arxiv ， CL 12k 19 分钟

目录

1. X-Stance: A Multilingual Multi-Target Dataset for Stance Detection [PDF] 摘要

2. TTTTTackling WinoGrande Schemas [PDF] 摘要

3. Distant Supervision and Noisy Label Learning for Low Resource Named Entity Recognition: A Study on Hausa and Yorùbá [PDF] 摘要

4. Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training [PDF] 摘要

5. Pre-trained Models for Natural Language Processing: A Survey [PDF] 摘要

6. Gender Representation in Open Source Speech Resources [PDF] 摘要

7. Calibration of Pre-trained Transformers [PDF] 摘要

8. Anchor & Transform: Learning Sparse Representations of Discrete Objects [PDF] 摘要

9. Deliberation Model Based Two-Pass End-to-End Speech Recognition [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-18

发表于 2020-03-18 分类于 arxiv ， CL 30k 50 分钟

目录

1. Rethinking Batch Normalization in Transformers [PDF] 摘要

2. A Benchmarking Study of Embedding-based Entity Alignment for Knowledge Graphs [PDF] 摘要

3. PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry [PDF] 摘要

4. Adapting Deep Learning Methods for Mental Health Prediction on Social Media [PDF] 摘要

5. XPersona: Evaluating Multilingual Personalized Chatbot [PDF] 摘要

6. Multi-label natural language processing to identify diagnosis and procedure codes from MIMIC-III inpatient notes [PDF] 摘要

7. Recent Advances and Challenges in Task-oriented Dialog System [PDF] 摘要

8. Offensive Language Identification in Greek [PDF] 摘要

9. HELFI: a Hebrew-Greek-Finnish Parallel Bible Corpus with Cross-Lingual Morpheme Alignment [PDF] 摘要

10. A Label Proportions Estimation technique for Adversarial Domain Adaptation in Text Classification [PDF] 摘要

11. LAXARY: A Trustworthy Explainable Twitter Analysis Model for Post-Traumatic Stress Disorder Assessment [PDF] 摘要

12. Developing a Multilingual Annotated Corpus of Misogyny and Aggression [PDF] 摘要

13. Parallel sequence tagging for concept recognition [PDF] 摘要

14. A Formal Analysis of Multimodal Referring Strategies Under Common Ground [PDF] 摘要

15. Overview of the TREC 2019 deep learning track [PDF] 摘要

16. Multi-modal Dense Video Captioning [PDF] 摘要

17. Hybrid Autoregressive Transducer (hat) [PDF] 摘要

18. Who Wins the Game of Thrones? How Sentiments Improve the Prediction of Candidate Choice [PDF] 摘要

19. High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model [PDF] 摘要

20. Harnessing Explanations to Bridge AI and Humans [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-17

发表于 2020-03-17 分类于 arxiv ， CV 187k 5:12

目录

1. Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes [PDF] 摘要

2. Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks [PDF] 摘要

3. Complexity of Shapes Embedded in ${\mathbb Z^n}$ with a Bias Towards Squares [PDF] 摘要

4. Learning Shape Representations for Clothing Variations in Person Re-Identification [PDF] 摘要

5. G-LBM:Generative Low-dimensional Background Model Estimation from Video Sequences [PDF] 摘要

6. RSVQA: Visual Question Answering for Remote Sensing Data [PDF] 摘要

7. Resolution Adaptive Networks for Efficient Inference [PDF] 摘要

8. Domain Adaptive Ensemble Learning [PDF] 摘要

9. clDice -- a Topology-Preserving Loss Function for Tubular Structure Segmentation [PDF] 摘要

10. Context-Transformer: Tackling Object Confusion for Few-Shot Detection [PDF] 摘要

11. MVLoc: Multimodal Variational Geometry-Aware Learning for Visual Localization [PDF] 摘要

12. Towards Ground Truth Evaluation of Visual Explanations [PDF] 摘要

13. Neural Pose Transfer by Spatially Adaptive Instance Normalization [PDF] 摘要

14. A Rotation-Invariant Framework for Deep Point Cloud Analysis [PDF] 摘要

15. Joint COCO and Mapillary Workshop at ICCV 2019 Keypoint Detection Challenge Track Technical Report: Distribution-Aware Coordinate Representation for Human Pose Estimation [PDF] 摘要

16. FragNet: Writer Identification using Deep Fragment Networks [PDF] 摘要

17. Refinements in Motion and Appearance for Online Multi-Object Tracking [PDF] 摘要

18. GraphTCN: Spatio-Temporal Interaction Modeling for Human Trajectory Prediction [PDF] 摘要

19. Discriminative Feature and Dictionary Learning with Part-aware Model for Vehicle Re-identification [PDF] 摘要

20. Stochastic Frequency Masking to Improve Super-Resolution and Denoising Networks [PDF] 摘要

21. Minimal Solvers for Indoor UAV Positioning [PDF] 摘要

22. Synthesizing human-like sketches from natural images using a conditional convolutional decoder [PDF] 摘要

23. PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression [PDF] 摘要

24. LT-Net: Label Transfer by Learning Reversible Voxel-wise Correspondence for One-shot Medical Image Segmentation [PDF] 摘要

25. Adapting Object Detectors with Conditional Domain Normalization [PDF] 摘要

26. Self-Supervised Discovering of Causal Features: Towards Interpretable Reinforcement Learning [PDF] 摘要

27. On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial Location [PDF] 摘要

28. Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos [PDF] 摘要

29. Gated Texture CNN for Efficient and Configurable Image Denoising [PDF] 摘要

30. Extended Feature Pyramid Network for Small Object Detection [PDF] 摘要

31. Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution [PDF] 摘要

32. AVR: Attention based Salient Visual Relationship Detection [PDF] 摘要

33. Any-Shot Object Detection [PDF] 摘要

34. ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks [PDF] 摘要

35. Multi-Drone based Single Object Tracking with Agent Sharing Network [PDF] 摘要

36. House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation [PDF] 摘要

37. A CNN-Based Blind Denoising Method for Endoscopic Images [PDF] 摘要

38. TACO: Trash Annotations in Context for Litter Detection [PDF] 摘要

39. Vec2Face: Unveil Human Faces from their Blackbox Features in Face Recognition [PDF] 摘要

40. Frustratingly Simple Few-Shot Object Detection [PDF] 摘要

41. Camera Trace Erasing [PDF] 摘要

42. Scene Completenesss-Aware Lidar Depth Completion for Driving Scenario [PDF] 摘要

43. Hyperspectral-Multispectral Image Fusion with Weighted LASSO [PDF] 摘要

44. Self-Constructing Graph Convolutional Networks for Semantic Labeling [PDF] 摘要

45. Evaluation of Rounding Functions in Nearest-Neighbor Interpolation [PDF] 摘要

46. Night-time Semantic Segmentation with a Large Real Dataset [PDF] 摘要

47. Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes [PDF] 摘要

48. Multistage Curvilinear Coordinate Transform Based Document Image Dewarping using a Novel Quality Estimator [PDF] 摘要

49. Deep Affinity Net: Instance Segmentation via Affinity [PDF] 摘要

50. SF-Net: Single-Frame Supervision for Temporal Action Localization [PDF] 摘要

51. 3D-CariGAN: An End-to-End Solution to 3D Caricature Generation from Face Photos [PDF] 摘要

52. Energy-based Periodicity Mining with Deep Features for Action Repetition Counting in Unconstrained Videos [PDF] 摘要

53. FGSD: A Dataset for Fine-Grained Ship Detection in High Resolution Satellite Images [PDF] 摘要

54. VCNet: A Robust Approach to Blind Image Inpainting [PDF] 摘要

55. OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features [PDF] 摘要

56. StarNet: towards weakly supervised few-shot detection and explainable few-shot classification [PDF] 摘要

57. Performance Evaluation of Advanced Deep Learning Architectures for Offline Handwritten Character Recognition [PDF] 摘要

58. Learning Enriched Features for Real Image Restoration and Enhancement [PDF] 摘要

59. GMM-UNIT: Unsupervised Multi-Domain and Multi-Modal Image-to-Image Translation via Attribute Gaussian Mixture Modeling [PDF] 摘要

60. Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection [PDF] 摘要

61. DeepEMD: Few-Shot Image Classification with Differentiable Earth Mover's Distance and Structured Classifiers [PDF] 摘要

62. Siamese Box Adaptive Network for Visual Tracking [PDF] 摘要

63. Channel Pruning Guided by Classification Loss and Feature Importance [PDF] 摘要

64. MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps [PDF] 摘要

65. Learning 2D-3D Correspondences To Solve The Blind Perspective-n-Point Problem [PDF] 摘要

66. A Novel Learnable Gradient Descent Type Algorithm for Non-convex Non-smooth Inverse Problems [PDF] 摘要

67. Beyond without Forgetting: Multi-Task Learning for Classification with Disjoint Datasets [PDF] 摘要

68. Vision-Dialog Navigation by Exploring Cross-modal Memory [PDF] 摘要

69. A model of figure ground organization incorporating local and global cues [PDF] 摘要

70. NoiseRank: Unsupervised Label Noise Reduction with Dependence Models [PDF] 摘要

71. Class Conditional Alignment for Partial Domain Adaptation [PDF] 摘要

72. Emotions Don't Lie: A Deepfake Detection Method using Audio-Visual Affective Cues [PDF] 摘要

73. Identifying Individual Dogs in Social Media Images [PDF] 摘要

74. TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification [PDF] 摘要

75. Structured Domain Adaptation for Unsupervised Person Re-identification [PDF] 摘要

76. Fast Depth Estimation for View Synthesis [PDF] 摘要

77. Large-Scale Optimal Transport via Adversarial Training with Cycle-Consistency [PDF] 摘要

78. Non-Local Part-Aware Point Cloud Denoising [PDF] 摘要

79. Monocular Depth Estimation Based On Deep Learning: An Overview [PDF] 摘要

80. Medical Image Enhancement Using Histogram Processing and Feature Extraction for Cancer Classification [PDF] 摘要

81. Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition [PDF] 摘要

82. Collaborative Motion Prediction via Neural Motion Message Passing [PDF] 摘要

83. Image-to-image Neural Network for Addition and Subtraction of a Pair of Not Very Large Numbers [PDF] 摘要

84. From W-Net to CDGAN: Bi-temporal Change Detection via Deep Learning Techniques [PDF] 摘要

85. Counterfactual Samples Synthesizing for Robust Visual Question Answering [PDF] 摘要

86. Efficient Backbone Search for Scene Text Recognition [PDF] 摘要

87. Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation [PDF] 摘要

88. OccuSeg: Occupancy-aware 3D Instance Segmentation [PDF] 摘要

89. An End-to-End Geometric Deficiency Elimination Algorithm for 3D Meshes [PDF] 摘要

90. Learning Reinforced Agents with Counterfactual Simulation for Medical Automatic Diagnosis [PDF] 摘要

91. Instant recovery of shape from spectrum via latent space connections [PDF] 摘要

92. Symmetry Detection of Occluded Point Cloud Using Deep Learning [PDF] 摘要

93. Explainable Deep Classification Models for Domain Generalization [PDF] 摘要

94. Recurrent convolutional neural networks for mandible segmentation from computed tomography [PDF] 摘要

95. Self-supervised Single-view 3D Reconstruction via Semantic Consistency [PDF] 摘要

96. Inducing Optimal Attribute Representations for Conditional GANs [PDF] 摘要

97. GeoDA: a geometric framework for black-box adversarial attacks [PDF] 摘要

98. The GraphNet Zoo: A Plug-and-Play Framework for Deep Semi-Supervised Classification [PDF] 摘要

99. Mutual Information Maximization for Effective Lip Reading [PDF] 摘要

100. Learning Unbiased Representations via Mutual Information Backpropagation [PDF] 摘要

101. Active Depth Estimation: Stability Analysis and its Applications [PDF] 摘要

102. Anomalous Instance Detection in Deep Learning: A Survey [PDF] 摘要

103. Toward Adversarial Robustness via Semi-supervised Robust Training [PDF] 摘要

104. OmniTact: A Multi-Directional High Resolution Touch Sensor [PDF] 摘要

105. Output Diversified Initialization for Adversarial Attacks [PDF] 摘要

106. Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks [PDF] 摘要

107. Towards Privacy Protection by Generating Adversarial Identity Masks [PDF] 摘要

108. Experimenting with Convolutional Neural Network Architectures for the automatic characterization of Solitary Pulmonary Nodules' malignancy rating [PDF] 摘要

109. A proto-object based audiovisual saliency map [PDF] 摘要

110. Interactive Neural Style Transfer with Artists [PDF] 摘要

111. Investigating Generalization in Neural Networks under Optimally Evolved Training Perturbations [PDF] 摘要

112. Rapid Whole Slide Imaging via Learning-based Two-shot Virtual Autofocusing [PDF] 摘要

113. VarMixup: Exploiting the Latent Space for Robust Training and Inference [PDF] 摘要

114. Boundary Guidance Hierarchical Network for Real-Time Tongue Segmentation [PDF] 摘要

115. Leveraging Vision and Kinematics Data to Improve Realism of Biomechanic Soft-tissue Simulation for Robotic Surgery [PDF] 摘要

116. A Privacy-Preserving DNN Pruning and Mobile Acceleration Framework [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-17

发表于 2020-03-17 分类于 arxiv ， CL 24k 40 分钟

目录

1. Stanza: A Python Natural Language Processing Toolkit for Many Human Languages [PDF] 摘要

2. Key Phrase Classification in Complex Assignments [PDF] 摘要

3. CompLex --- A New Corpus for Lexical Complexity Predicition from Likert Scale Data [PDF] 摘要

4. TRANS-BLSTM: Transformer with Bidirectional LSTM for Language Understanding [PDF] 摘要

5. Synonymous Generalization in Sequence-to-Sequence Recurrent Networks [PDF] 摘要

6. Word Sense Disambiguation for 158 Languages using Word Embeddings Only [PDF] 摘要

7. Text Similarity Using Word Embeddings to Classify Misinformation [PDF] 摘要

8. LSCP: Enhanced Large Scale Colloquial Persian Language Understanding [PDF] 摘要

9. A Survey on Contextual Embeddings [PDF] 摘要

10. A Machine Learning Application for Raising WASH Awareness in the Times of Covid-19 Pandemic [PDF] 摘要

11. Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic models [PDF] 摘要

12. Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0 [PDF] 摘要

13. Counterfactual Samples Synthesizing for Robust Visual Question Answering [PDF] 摘要

14. Semantically-Enriched Search Engine for Geoportals: A Case Study with ArcGIS Online [PDF] 摘要

15. DAN: Dual-View Representation Learning for Adapting Stance Classifiers to New Domains [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-16

发表于 2020-03-16 更新于 2020-03-17 分类于 arxiv ， CV 55k 1:31

目录

1. Probabilistic Future Prediction for Video Scene Understanding [PDF] 摘要

2. Extending Maps with Semantic and Contextual Object Information for Robot Navigation: a Learning-Based Framework using Visual and Depth Cues [PDF] 摘要

3. Harmonizing Transferability and Discriminability for Adapting Object Detectors [PDF] 摘要

4. Automatic Lesion Detection System (ALDS) for Skin Cancer Classification Using SVM and Neural Classifiers [PDF] 摘要

5. Belief Propagation Reloaded: Learning BP-Layers for Labeling Problems [PDF] 摘要

6. Semantic Pyramid for Image Generation [PDF] 摘要

7. Pyramidal Edge-maps based Guided Thermal Super-resolution [PDF] 摘要

8. Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection [PDF] 摘要

9. Gimme Signals: Discriminative signal encoding for multimodal activity recognition [PDF] 摘要

10. PointINS: Point-based Instance Segmentation [PDF] 摘要

11. Is There Tradeoff between Spatial and Temporal in Video Super-Resolution? [PDF] 摘要

12. Partial Weight Adaptation for Robust DNN Inference [PDF] 摘要

13. Dual Temporal Memory Network for Efficient Video Object Segmentation [PDF] 摘要

14. BIHL:A Fast and High Performance Object Proposals based on Binarized HL Frequency [PDF] 摘要

15. A Spatial-Temporal Attentive Network with Spatial Continuity for Trajectory Prediction [PDF] 摘要

16. BigGAN-based Bayesian reconstruction of natural images from human brain activity [PDF] 摘要

17. Deep Domain-Adversarial Image Generation for Domain Generalisation [PDF] 摘要

18. Interaction Graphs for Object Importance Estimation in On-road Driving Videos [PDF] 摘要

19. Analyzing Visual Representations in Embodied Navigation Tasks [PDF] 摘要

20. LaserFlow: Efficient and Probabilistic Object Detection and Motion Forecasting [PDF] 摘要

21. Sparse Graphical Memory for Robust Planning [PDF] 摘要

22. Advanced Deep Learning Methodologies for Skin Cancer Classification in Prodromal Stages [PDF] 摘要

23. Human Activity Recognition using Multi-Head CNN followed by LSTM [PDF] 摘要

24. A Power-Efficient Binary-Weight Spiking Neural Network Architecture for Real-Time Object Classification [PDF] 摘要

25. What Information Does a ResNet Compress? [PDF] 摘要

26. Unsupervised Style and Content Separation by Minimizing Mutual Information for Speech Synthesis [PDF] 摘要

27. On the effectiveness of convolutional autoencoders on image-based personalized recommender systems [PDF] 摘要

28. Towards a Framework for Visual Intelligence in Service Robotics: Epistemic Requirements and Gap Analysis [PDF] 摘要

29. Random smooth gray value transformations for cross modality learning with gray value invariant networks [PDF] 摘要

30. LIBRE: The Multiple 3D LiDAR Dataset [PDF] 摘要

31. Action for Better Prediction [PDF] 摘要

32. Human Grasp Classification for Reactive Human-to-Robot Handovers [PDF] 摘要

33. Autoencoders [PDF] 摘要

34. LiDAR guided Small obstacle Segmentation [PDF] 摘要

35. W2S: A Joint Denoising and Super-Resolution Dataset [PDF] 摘要

阅读全文 »