【arxiv论文】 Computation and Language 2020-03-04

发表于 2020-03-04 更新于 2020-03-05 分类于 arxiv ， CL 20k 33 分钟

目录

1. Hybrid Generative-Retrieval Transformers for Dialogue Domain Adaptation [PDF] 摘要

2. Improving Uyghur ASR systems with decoders using morpheme-based language models [PDF] 摘要

3. Multi-Task Learning Network for Emotion Recognition in Conversation [PDF] 摘要

4. XGPT: Cross-modal Generative Pre-Training for Image Captioning [PDF] 摘要

5. Seshat: A tool for managing and verifying annotation campaigns of audio data [PDF] 摘要

6. Meta-Embeddings Based On Self-Attention [PDF] 摘要

7. CLUECorpus2020: A Large-scale Chinese Corpus for Pre-trainingLanguage Model [PDF] 摘要

8. Improving Candidate Generation for Low-resource Cross-lingual Entity Linking [PDF] 摘要

9. Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection [PDF] 摘要

10. Transfer Learning for Context-Aware Spoken Language Understanding [PDF] 摘要

11. Med7: a transferable clinical natural language processing model for electronic health records [PDF] 摘要

12. Understanding the Prediction Mechanism of Sentiments by XAI Visualization [PDF] 摘要

13. Hierarchical Context Enhanced Multi-Domain Dialogue System for Multi-domain Task Completion [PDF] 摘要

阅读全文 »

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

发表于 2020-03-03 更新于 2020-03-05 分类于 arxiv ， CV 189k 5:15

目录

1. Learn2Perturb: an End-to-end Feature Perturbation Learning to Improve Adversarial Robustness [PDF] 摘要

2. D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry [PDF] 摘要

3. Plug & Play Convolutional Regression Tracker for Video Object Detection [PDF] 摘要

4. DriverMHG: A Multi-Modal Dataset for Dynamic Recognition of Driver Micro Hand Gestures and a Real-Time Recognition Framework [PDF] 摘要

5. Always Look on the Bright Side of the Field: Merging Pose and Contextual Data to Estimate Orientation of Soccer Players [PDF] 摘要

6. Deep Meditations: Controlled navigation of latent space [PDF] 摘要

7. Learning Fast and Robust Target Models for Video Object Segmentation [PDF] 摘要

8. Learning to See: You Are What You See [PDF] 摘要

9. Revisiting Convolutional Neural Networks for Urban Flow Analytics [PDF] 摘要

10. Gated Fusion Network for Degraded Image Super Resolution [PDF] 摘要

11. Instance Separation Emerges from Inpainting [PDF] 摘要

12. 3D Object Detection From LiDAR Data Using Distance Depended Feature Extraction [PDF] 摘要

13. Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color Space [PDF] 摘要

14. The perceptual boost of visual attention is task-dependent in naturalistic settings [PDF] 摘要

15. Introducing Fuzzy Layers for Deep Learning [PDF] 摘要

16. Estimating a Null Model of Scientific Image Reuse to Support Research Integrity Investigations [PDF] 摘要

17. A Multi-view Perspective of Self-supervised Learning [PDF] 摘要

18. Predicting TUG score from gait characteristics based on video analysis and machine learning [PDF] 摘要

19. Few-shot Learning with Weakly-supervised Object Localization [PDF] 摘要

20. AlignSeg: Feature-Aligned Segmentation Networks [PDF] 摘要

21. Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation [PDF] 摘要

22. Exposing Backdoors in Robust Machine Learning Models [PDF] 摘要

23. Triangle-Net: Towards Robustness in Point Cloud Classification [PDF] 摘要

24. Deep Learning on Radar Centric 3D Object Detection [PDF] 摘要

25. Learning to Deblur and Generate High Frame Rate Video with an Event Camera [PDF] 摘要

26. FPGA Implementation of Minimum Mean Brightness Error Bi-Histogram Equalization [PDF] 摘要

27. A Machine Learning Framework for Data Ingestion in Document Images [PDF] 摘要

28. On Parameter Tuning in Meta-learning for Computer Vision [PDF] 摘要

29. Marine life through You Only Look Once's perspective [PDF] 摘要

30. Deep Variational Luenberger-type Observer for Stochastic Video Prediction [PDF] 摘要

31. CALVIS: chest, waist and pelvis circumference from 3D human body meshes as ground truth for deep learning [PDF] 摘要

32. CNN Hyperparameter tuning applied to Iris Liveness Detection [PDF] 摘要

33. An End-to-End Visual-Audio Attention Network for Emotion Recognition in User-Generated Videos [PDF] 摘要

34. Character Segmentation in Asian Collector's Seal Imprints: An Attempt to Retrieval Based on Ancient Character Typeface [PDF] 摘要

35. GSANet: Semantic Segmentation with Global and Selective Attention [PDF] 摘要

36. Verifying Deep Learning-based Decisions for Facial Expression Recognition [PDF] 摘要

37. CheXclusion: Fairness gaps in deep chest X-ray classifiers [PDF] 摘要

38. Realistic River Image Synthesis using Deep Generative Adversarial Networks [PDF] 摘要

39. SIP-SegNet: A Deep Convolutional Encoder-Decoder Network for Joint Semantic Segmentation and Extraction of Sclera, Iris and Pupil based on Periocular Region Suppression [PDF] 摘要

40. Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells [PDF] 摘要

41. Breast Cancer Histopathology Image Classification and Localization using Multiple Instance Learning [PDF] 摘要

42. MADAN: Multi-source Adversarial Domain Aggregation Network for Domain Adaptation [PDF] 摘要

43. Recognizing Handwritten Mathematical Expressions as LaTex Sequences Using a Multiscale Robust Neural Network [PDF] 摘要

44. Deepfakes for Medical Video De-Identification: Privacy Protection and Diagnostic Information Preservation [PDF] 摘要

45. Medicine Strip Identification using 2-D Cepstral Feature Extraction and Multiclass Classification Methods [PDF] 摘要

46. Vision based body gesture meta features for Affective Computing [PDF] 摘要

47. A Convolutional Baseline for Person Re-Identification Using Vision and Language Descriptions [PDF] 摘要

48. Firearm Detection and Segmentation Using an Ensemble of Semantic Neural Networks [PDF] 摘要

49. Task Augmentation by Rotating for Meta-Learning [PDF] 摘要

50. Hypernetwork approach to generating point clouds [PDF] 摘要

51. Real-Time target detection in maritime scenarios based on YOLOv3 model [PDF] 摘要

52. Preventing Clean Label Poisoning using Gaussian Mixture Loss [PDF] 摘要

53. Identity Recognition in Intelligent Cars with Behavioral Data and LSTM-ResNet Classifier [PDF] 摘要

54. Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry [PDF] 摘要

55. Learning Depth via Interaction [PDF] 摘要

56. Long Short-Term Sample Distillation [PDF] 摘要

57. Towards Unconstrained Palmprint Recognition on Consumer Devices: a Literature Review [PDF] 摘要

58. A-TVSNet: Aggregated Two-View Stereo Network for Multi-View Stereo Depth Estimation [PDF] 摘要

59. Learned Enrichment of Top-View Grid Maps Improves Object Detection [PDF] 摘要

60. Unbiased Mean Teacher for Cross Domain Object Detection [PDF] 摘要

61. GPU-Accelerated Mobile Multi-view Style Transfer [PDF] 摘要

62. Relational Deep Feature Learning for Heterogeneous Face Recognition [PDF] 摘要

63. Deep Image Spatial Transformation for Person Image Generation [PDF] 摘要

64. SketchGCN: Semantic Sketch Segmentation with Graph Convolutional Networks [PDF] 摘要

65. Global Context-Aware Progressive Aggregation Network for Salient Object Detection [PDF] 摘要

66. VAE/WGAN-Based Image Representation Learning For Pose-Preserving Seamless Identity Replacement In Facial Images [PDF] 摘要

67. A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Dataset [PDF] 摘要

68. Matching Neuromorphic Events and Color Images via Adversarial Learning [PDF] 摘要

69. Extremely Dense Point Correspondences using a Learned Feature Descriptor [PDF] 摘要

70. 3D Point Cloud Processing and Learning for Autonomous Driving [PDF] 摘要

71. Rethinking Fully Convolutional Networks for the Analysis of Photoluminescence Wafer Images [PDF] 摘要

72. Fast Lidar Clustering by Density and Connectivity [PDF] 摘要

73. The Sloop System for Individual Animal Identification with Deep Learning [PDF] 摘要

74. Soft-Root-Sign Activation Function [PDF] 摘要

75. ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection [PDF] 摘要

76. Deep Attention Aware Feature Learning for Person Re-Identification [PDF] 摘要

77. MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships [PDF] 摘要

78. PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling [PDF] 摘要

79. State-Aware Tracker for Real-Time Video Object Segmentation [PDF] 摘要

80. STC-Flow: Spatio-temporal Context-aware Optical Flow Estimation [PDF] 摘要

81. Deep Learning for Content-based Personalized Viewport Prediction of 360-Degree VR Videos [PDF] 摘要

82. Learning When and Where to Zoom with Deep Reinforcement Learning [PDF] 摘要

83. Towards Automatic Face-to-Face Translation [PDF] 摘要

84. PF-Net: Point Fractal Network for 3D Point Cloud Completion [PDF] 摘要

85. FMT:Fusing Multi-task Convolutional Neural Network for Person Search [PDF] 摘要

86. Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension [PDF] 摘要

87. Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only [PDF] 摘要

88. Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision [PDF] 摘要

89. Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning [PDF] 摘要

90. Joint Wasserstein Distribution Matching [PDF] 摘要

91. Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs [PDF] 摘要

92. Emotion Recognition System from Speech and Visual Information based on Convolutional Neural Networks [PDF] 摘要

93. Learning Cross-domain Generalizable Features by Representation Disentanglement [PDF] 摘要

94. Grounded and Controllable Image Completion by Incorporating Lexical Semantics [PDF] 摘要

95. Representations, Metrics and Statistics For Shape Analysis of Elastic Graphs [PDF] 摘要

96. Augmenting Visual Place Recognition with Structural Cues [PDF] 摘要

97. Reusing Discriminators for Encoding Towards Unsupervised Image-to-Image Translation [PDF] 摘要

98. Joint Face Completion and Super-resolution using Multi-scale Feature Relation Learning [PDF] 摘要

99. NAS-Count: Counting-by-Density with Neural Architecture Search [PDF] 摘要

100. Channel Equilibrium Networks for Learning Deep Representation [PDF] 摘要

101. Cross-Spectrum Dual-Subspace Pairing for RGB-infrared Cross-Modality Person Re-Identification [PDF] 摘要

102. Learning to Compare Relation: Semantic Alignment for Few-Shot Learning [PDF] 摘要

103. VideoSSL: Semi-Supervised Learning for Video Classification [PDF] 摘要

104. First Order Motion Model for Image Animation [PDF] 摘要

105. Robust 6D Object Pose Estimation by Learning RGB-D Features [PDF] 摘要

106. Augmented Cyclic Consistency Regularization for Unpaired Image-to-Image Translation [PDF] 摘要

107. HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection [PDF] 摘要

108. Attention-aware fusion RGB-D face recognition [PDF] 摘要

109. Towards Using Count-level Weak Supervision for Crowd Counting [PDF] 摘要

110. Self-supervised Representation Learning for Ultrasound Video [PDF] 摘要

111. Transferring Dense Pose to Proximal Animal Classes [PDF] 摘要

112. Bio-Inspired Modality Fusion for Active Speaker Detection [PDF] 摘要

113. Learning Nonparametric Human Mesh Reconstruction from a Single Image without Ground Truth Meshes [PDF] 摘要

114. Unlimited Resolution Image Generation with R2D2-GANs [PDF] 摘要

115. Constrained Nonnegative Matrix Factorization for Blind Hyperspectral Unmixing incorporating Endmember Independence [PDF] 摘要

116. Evaluating Temporal Queries Over Video Feeds [PDF] 摘要

117. Multi-View Learning for Vision-and-Language Navigation [PDF] 摘要

118. Addressing target shift in zero-shot learning using grouped adversarial learning [PDF] 摘要

119. Quantized Neural Network Inference with Precision Batching [PDF] 摘要

120. Convolutional Sparse Support Estimator Network (CSEN) From energy efficient support estimation to learning-aided Compressive Sensing [PDF] 摘要

121. MVP: Unified Motion and Visual Self-Supervised Learning for Large-Scale Robotic Navigation [PDF] 摘要

122. PSF--NET: A Non-parametric Point Spread Function Model for Ground Based Optical Telescopes [PDF] 摘要

123. 3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection [PDF] 摘要

124. Dimensionality reduction to maximize prediction generalization capability [PDF] 摘要

125. Environment-agnostic Multitask Learning for Natural Language Grounded Navigation [PDF] 摘要

126. Why is the Mahalanobis Distance Effective for Anomaly Detection? [PDF] 摘要

127. Unblind Your Apps: Predicting Natural-Language Labels for Mobile GUI Components by Deep Learning [PDF] 摘要

128. Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models [PDF] 摘要

129. An Evaluation of Knowledge Graph Embeddings for Autonomous Driving Data: Experience and Practice [PDF] 摘要

130. An estimation-based method to segment PET images [PDF] 摘要

131. Unsupervised Dictionary Learning for Anomaly Detection [PDF] 摘要

132. Image Hashing by Minimizing Independent Relaxed Wasserstein Distance [PDF] 摘要

133. Inexpensive surface electromyography sleeve with consistent electrode placement enables dexterous and stable prosthetic control through deep learning [PDF] 摘要

134. SeismiQB -- a novel framework for deep learning with seismic data [PDF] 摘要

阅读全文 »

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

发表于 2020-03-03 更新于 2020-03-05 分类于 arxiv ， CL 25k 41 分钟

目录

1. Gated Mechanism for Attention Based Multimodal Sentiment Analysis [PDF] 摘要

2. Identification of primary and collateral tracks in stuttered speech [PDF] 摘要

3. Multi-View Learning for Vision-and-Language Navigation [PDF] 摘要

4. PhoBERT: Pre-trained language models for Vietnamese [PDF] 摘要

5. Style Example-Guided Text Generation using Generative Adversarial Transformers [PDF] 摘要

6. Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation [PDF] 摘要

7. StructSum: Incorporating Latent and Explicit Sentence Dependencies for Single Document Summarization [PDF] 摘要

8. Clinical Text Summarization with Syntax-Based Negation and Semantic Concept Identification [PDF] 摘要

9. Voice trigger detection from LVCSR hypothesis lattices using bidirectional lattice recurrent neural networks [PDF] 摘要

10. Depth-Adaptive Graph Recurrent Network for Text Classification [PDF] 摘要

11. AraBERT: Transformer-based Model for Arabic Language Understanding [PDF] 摘要

12. The STEM-ECR Dataset: Grounding Scientific Entity References in STEM Scholarly Content to Authoritative Encyclopedic and Lexicographic Sources [PDF] 摘要

13. Pathological speech detection using x-vector embeddings [PDF] 摘要

14. Long Short-Term Sample Distillation [PDF] 摘要

15. Environment-agnostic Multitask Learning for Natural Language Grounded Navigation [PDF] 摘要

16. What Emotions Make One or Five Stars? Understanding Ratings of Online Product Reviews by Sentiment Analysis and XAI [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-02

发表于 2020-03-02 更新于 2020-03-05 分类于 arxiv ， CV 71k 1:59

目录

1. Applying Tensor Decomposition to image for Robustness against Adversarial Attack [PDF] 摘要

2. A Multi-Hypothesis Classification Approach to Color Constancy [PDF] 摘要

3. Sketch-to-Art: Synthesizing Stylized Art Images From Sketches [PDF] 摘要

4. Infrared and 3D skeleton feature fusion for RGB-D action recognition [PDF] 摘要

5. Indoor Scene Recognition in 3D [PDF] 摘要

6. Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples [PDF] 摘要

7. Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields [PDF] 摘要

8. KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations [PDF] 摘要

9. A Spatiotemporal Volumetric Interpolation Network for 4D Dynamic Medical Image [PDF] 摘要

10. Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data [PDF] 摘要

11. A U-Net Based Discriminator for Generative Adversarial Networks [PDF] 摘要

12. 4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras [PDF] 摘要

13. MINA: Convex Mixed-Integer Programming for Non-Rigid Shape Alignment [PDF] 摘要

14. SCALE-Net: Scalable Vehicle Trajectory Prediction Network under Random Number of Interacting Vehicles via Edge-enhanced Graph Convolutional Neural Network [PDF] 摘要

15. Exploring and Distilling Cross-Modal Information for Image Captioning [PDF] 摘要

16. Neural Inheritance Relation Guided One-Shot Layer Assignment Search [PDF] 摘要

17. MANet: Multimodal Attention Network based Point- View fusion for 3D Shape Recognition [PDF] 摘要

18. Hand-Priming in Object Localization for Assistive Egocentric Vision [PDF] 摘要

19. Automated classification of stems and leaves of potted plants based on point cloud data [PDF] 摘要

20. A Video Analysis Method on Wanfang Dataset via Deep Neural Network [PDF] 摘要

21. Detecting and Recovering Adversarial Examples: An Input Sensitivity Guided Method [PDF] 摘要

22. Utilizing Network Properties to Detect Erroneous Inputs [PDF] 摘要

23. DGST : Discriminator Guided Scene Text detector [PDF] 摘要

24. Detecting Patch Adversarial Attacks with Image Residuals [PDF] 摘要

25. Road Curb Detection and Localization with Monocular Forward-view Vehicle Camera [PDF] 摘要

26. Cross-modality Person re-identification with Shared-Specific Feature Transfer [PDF] 摘要

27. Improving Learning Effectiveness For Object Detection and Classification in Cluttered Backgrounds [PDF] 摘要

28. Target Detection, Tracking and Avoidance System for Low-cost UAVs using AI-Based Approaches [PDF] 摘要

29. TGGLines: A Robust Topological Graph Guided Line Segment Detector for Low Quality Binary Images [PDF] 摘要

30. MNN: A Universal and Efficient Inference Engine [PDF] 摘要

31. Learning in the Frequency Domain [PDF] 摘要

32. SilhoNet-Fisheye: Adaptation of A ROI Based Object Pose Estimation Network to Monocular Fisheye Images [PDF] 摘要

33. Brain-Inspired Model for Incremental Learning Using a Few Examples [PDF] 摘要

34. Affinity guided Geometric Semi-Supervised Metric Learning [PDF] 摘要

35. Joint 2D-3D Breast Cancer Classification [PDF] 摘要

36. Review: Noise and artifact reduction for MRI using deep learning [PDF] 摘要

37. Neural Network Segmentation of Interstitial Fibrosis, Tubular Atrophy, and Glomerulosclerosis in Renal Biopsies [PDF] 摘要

38. HOTCAKE: Higher Order Tucker Articulated Kernels for Deeper CNN Compression [PDF] 摘要

39. An Efficient Method of Training Small Models for Regression Problems with Knowledge Distillation [PDF] 摘要

40. Regional Registration of Whole Slide Image Stacks Containing Highly Deformed Artefacts [PDF] 摘要

41. Class-Specific Blind Deconvolutional Phase Retrieval Under a Generative Prior [PDF] 摘要

42. RSANet: Recurrent Slice-wise Attention Network for Multiple Sclerosis Lesion Segmentation [PDF] 摘要

43. LEEP: A New Measure to Evaluate Transferability of Learned Representations [PDF] 摘要

44. Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning? [PDF] 摘要

45. Provable Robust Learning Based on Transformation-Specific Smoothing [PDF] 摘要

46. NeurIPS 2019 Disentanglement Challenge: Improved Disentanglement through Learned Aggregation of Convolutional Feature Maps [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-02

发表于 2020-03-02 更新于 2020-03-05 分类于 arxiv ， CL 24k 41 分钟

目录

1. Do all Roads Lead to Rome? Understanding the Role of Initialization in Iterative Back-Translation [PDF] 摘要

2. Metaphoric Paraphrase Generation [PDF] 摘要

3. UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training [PDF] 摘要

4. Automatic Section Recognition in Obituaries [PDF] 摘要

5. Comparison of Speech Representations for Automatic Quality Estimation in Multi-Speaker Text-to-Speech Synthesis [PDF] 摘要

6. TextBrewer: An Open-Source Knowledge Distillation Toolkit for Natural Language Processing [PDF] 摘要

7. DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding [PDF] 摘要

8. Modeling Future Cost for Neural Machine Translation [PDF] 摘要

9. Robust Unsupervised Neural Machine Translation with Adversarial Training [PDF] 摘要

10. UKARA 1.0 Challenge Track 1: Automatic Short-Answer Scoring in Bahasa Indonesia [PDF] 摘要

11. Temporal Convolutional Attention-based Network For Sequence Modeling [PDF] 摘要

12. Optimizing Memory-Access Patterns for Deep Learning Accelerators [PDF] 摘要

13. RP-DNN: A Tweet level propagation context based deep neural networks for early rumor detection in Social Media [PDF] 摘要

14. A multi-layer approach to disinformation detection on Twitter [PDF] 摘要

15. Exploring and Distilling Cross-Modal Information for Image Captioning [PDF] 摘要

16. Learning Directly from Grammar Compressed Text [PDF] 摘要

17. Comment Ranking Diversification in Forum Discussions [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-02-28

发表于 2020-02-28 更新于 2020-03-05 分类于 arxiv ， CV 67k 1:51

目录

1. Measures to Evaluate Generative Adversarial Networks Based on Direct Analysis of Generated Images [PDF] 摘要

2. Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC [PDF] 摘要

3. Semantically-Guided Representation Learning for Self-Supervised Monocular Depth [PDF] 摘要

4. 2D Convolutional Neural Networks for 3D Digital Breast Tomosynthesis Classification [PDF] 摘要

5. Blurry Video Frame Interpolation [PDF] 摘要

6. The Mertens Unrolled Network (MU-Net): A High Dynamic Range Fusion Neural Network for Through the Windshield Driver Recognition [PDF] 摘要

7. ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images [PDF] 摘要

8. Learning Representations by Predicting Bags of Visual Words [PDF] 摘要

9. Meta-Transfer Learning for Zero-Shot Super-Resolution [PDF] 摘要

10. Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image [PDF] 摘要

11. Visual Commonsense R-CNN [PDF] 摘要

12. University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization [PDF] 摘要

13. Evolving Losses for Unsupervised Video Representation Learning [PDF] 摘要

14. Domain Decluttering: Simplifying Images to Mitigate Synthetic-Real Domain Shift and Improve Depth Estimation [PDF] 摘要

15. Deep Slow Motion Video Reconstruction with Hybrid Imaging System [PDF] 摘要

16. The Data Representativeness Criterion: Predicting the Performance of Supervised Classification Based on Data Set Similarity [PDF] 摘要

17. Action Quality Assessment using Siamese Network-Based Deep Metric Learning [PDF] 摘要

18. Reducing Geographic Performance Differential for Face Recognition [PDF] 摘要

19. XSepConv: Extremely Separated Convolution [PDF] 摘要

20. Attention-guided Chained Context Aggregation for Semantic Segmentation [PDF] 摘要

21. Multiple Discrimination and Pairwise CNN for View-based 3D Object Retrieval [PDF] 摘要

22. Unbiased Scene Graph Generation from Biased Training [PDF] 摘要

23. Features for Ground Texture Based Localization -- A Survey [PDF] 摘要

24. Weakly supervised discriminative feature learning with state information for person identification [PDF] 摘要

25. Auto-Encoding Twin-Bottleneck Hashing [PDF] 摘要

26. Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction [PDF] 摘要

27. Set-Constrained Viterbi for Set-Supervised Action Segmentation [PDF] 摘要

28. RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference [PDF] 摘要

29. Unshuffling Data for Improved Generalization [PDF] 摘要

30. Hierarchical Memory Decoding for Video Captioning [PDF] 摘要

31. Defense-PointNet: Protecting PointNet Against Adversarial Attacks [PDF] 摘要

32. GATCluster: Self-Supervised Gaussian-Attention Network for Image Clustering [PDF] 摘要

33. Towards Universal Representation Learning for Deep Face Recognition [PDF] 摘要

34. Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level Optimization [PDF] 摘要

35. Learning to Shade Hand-drawn Sketches [PDF] 摘要

36. On Leveraging Pretrained GANs for Limited-Data Generation [PDF] 摘要

37. Rethinking the Hyperparameters for Fine-tuning [PDF] 摘要

38. Hallucinative Topological Memory for Zero-Shot Visual Planning [PDF] 摘要

39. Coronary Wall Segmentation in CCTA Scans via a Hybrid Net with Contours Regularization [PDF] 摘要

40. Opportunities of a Machine Learning-based Decision Support System for Stroke Rehabilitation Assessment [PDF] 摘要

41. Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning [PDF] 摘要

42. Multi-source Domain Adaptation in the Deep Learning Era: A Systematic Survey [PDF] 摘要

43. Infinitely Wide Graph Convolutional Networks: Semi-supervised Learning via Gaussian Processes [PDF] 摘要

44. A Comprehensive Approach to Unsupervised Embedding Learning based on AND Algorithm [PDF] 摘要

45. Multi-Cycle-Consistent Adversarial Networks for CT Image Denoising [PDF] 摘要

46. Two-stage breast mass detection and segmentation system towards automated high-resolution full mammogram analysis [PDF] 摘要

47. Understanding and Enhancing Mixed Sample Data Augmentation [PDF] 摘要

48. Transductive Few-shot Learning with Meta-Learned Confidence [PDF] 摘要

49. Face Verification Using 60~GHz 802.11 waveforms [PDF] 摘要

50. Supervised Dimensionality Reduction and Visualization using Centroid-encoder [PDF] 摘要

51. Segmentation-based Method combined with Dynamic Programming for Brain Midline Delineation [PDF] 摘要

52. Max-Affine Spline Insights into Deep Generative Networks [PDF] 摘要

53. A Proto-Object Based Dynamic Visual Saliency Model with an FPGA Implementation [PDF] 摘要

54. Gradient Boosted Flows [PDF] 摘要

55. BBAND Index: A No-Reference Banding Artifact Predictor [PDF] 摘要

56. Kernel Bi-Linear Modeling for Reconstructing Data on Manifolds: The Dynamic-MRI Case [PDF] 摘要

57. Comparison of Multi-Class and Binary Classification Machine Learning Models in Identifying Strong Gravitational Lenses [PDF] 摘要

58. Analysis of diversity-accuracy tradeoff in image captioning [PDF] 摘要

59. Improving Robustness of Deep-Learning-Based Image Reconstruction [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-02-28

发表于 2020-02-28 更新于 2020-03-05 分类于 arxiv ， CL 19k 31 分钟

目录

1. Generating Followup Questions for Interpretable Multi-hop Question Answering [PDF] 摘要

2. Few-shot Natural Language Generation for Task-Oriented Dialog [PDF] 摘要

3. A Primer in BERTology: What we know about how BERT works [PDF] 摘要

4. Annotation of Emotion Carriers in Personal Narratives [PDF] 摘要

5. Improving cross-lingual model transfer by chunking [PDF] 摘要

6. Binarized PMI Matrix: Bridging Word Embeddings and Hyperbolic Spaces [PDF] 摘要

7. Integrating Boundary Assembling into a DNN Framework for Named Entity Recognition in Chinese Social Media Text [PDF] 摘要

8. CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset [PDF] 摘要

9. Analysis of diversity-accuracy tradeoff in image captioning [PDF] 摘要

10. Echo State Neural Machine Translation [PDF] 摘要

11. Universal Phone Recognition with a Multilingual Allophone System [PDF] 摘要

12. Train Large, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers [PDF] 摘要

13. Towards Zero-shot Learning for Automatic Phonemic Transcription [PDF] 摘要

14. SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech Translation [PDF] 摘要

15. Attacking Neural Text Detectors [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-02-27

发表于 2020-02-27 更新于 2020-03-05 分类于 arxiv ， CV 7.3k 12 分钟

目录

1. Graphcore C2 Card performance for image-based deep learning application: A Report [PDF] 摘要

2. Pedestrian Models for Autonomous Driving Part I: low level models, from sensing to tracking [PDF] 摘要

3. A Quadruplet Loss for Enforcing Semantically Coherent Embeddings in Multi-output Classification Problems [PDF] 摘要

4. Dynamic Graph Correlation Learning for Disease Diagnosis with Incomplete Labels [PDF] 摘要

5. Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution [PDF] 摘要

6. ARMA Nets: Expanding Receptive Field for Dense Prediction [PDF] 摘要

7. Automatically Searching for U-Net Image Translator Architecture [PDF] 摘要

8. Object Relational Graph with Teacher-Recommended Learning for Video Captioning [PDF] 摘要

9. CookGAN: Meal Image Synthesis from Ingredients [PDF] 摘要

10. Learning a Directional Soft Lane Affordance Model for Road Scenes Using Self-Supervision [PDF] 摘要

11. Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation Mapping [PDF] 摘要

12. Efficient Semantic Video Segmentation with Per-frame Inference [PDF] 摘要

13. Deform-GAN:An Unsupervised Learning Model for Deformable Registration [PDF] 摘要

14. Performance Evaluation of Deep Generative Models for Generating Hand-Written Character Images [PDF] 摘要

15. Disentangling Image Distortions in Deep Feature Space [PDF] 摘要

16. Force-Ultrasound Fusion:Bringing Spine Robotic-US to the Next "Level" [PDF] 摘要

17. Controllable Descendant Face Synthesis [PDF] 摘要

18. Adversarial Attack on Deep Product Quantization Network for Image Retrieval [PDF] 摘要

19. PuzzleNet: Scene Text Detection by Segment Context Graph Learning [PDF] 摘要

20. Unsupervised Temporal Video Segmentation as an Auxiliary Task for Predicting the Remaining Surgery Duration [PDF] 摘要

21. Rethinking the Route Towards Weakly Supervised Object Localization [PDF] 摘要

22. Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units [PDF] 摘要

23. Self-supervised Image Enhancement Network: Training with Low Light Images Only [PDF] 摘要

24. Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Data [PDF] 摘要

25. Adversarial Ranking Attack and Defense [PDF] 摘要

26. Generalized Product Quantization Network for Semi-supervised Hashing [PDF] 摘要

27. Learning Light Field Angular Super-Resolution via a Geometry-Aware Network [PDF] 摘要

28. Multi-Attribute Guided Painting Generation [PDF] 摘要

29. Back to the Future: Joint Aware Temporal Deep Learning 3D Human Pose Estimation [PDF] 摘要

30. Super-Resolving Commercial Satellite Imagery Using Realistic Training Data [PDF] 摘要

31. Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization [PDF] 摘要

32. Style Transfer for Light Field Photography [PDF] 摘要

33. Geometric Fusion via Joint Delay Embeddings [PDF] 摘要

34. Unsupervised Semantic Attribute Discovery and Control in Generative Models [PDF] 摘要

35. CLARA: Clinical Report Auto-completion [PDF] 摘要

36. Inceptive Event Time-Surfaces for Object Classification Using Neuromorphic Cameras [PDF] 摘要

37. Revisiting Ensembles in an Adversarial Context: Improving Natural Accuracy [PDF] 摘要

38. Region of Interest Identification for Brain Tumors in Magnetic Resonance Images [PDF] 摘要

39. Unpaired Image Super-Resolution using Pseudo-Supervision [PDF] 摘要

40. CheXpedition: Investigating Generalization Challenges for Translation of Chest X-Ray Algorithms to the Clinical Setting [PDF] 摘要

41. Invariance vs. Robustness of Neural Networks [PDF] 摘要

42. From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN) [PDF] 摘要

43. Deep Learning and Statistical Models for Time-Critical Pedestrian Behaviour Prediction [PDF] 摘要

44. End-to-End Models for the Analysis of System 1 and System 2 Interactions based on Eye-Tracking Data [PDF] 摘要

阅读全文 »