【arxiv论文】 Computation and Language 2020-03-16

发表于 2020-03-16 分类于 arxiv ， CL 15k 25 分钟

目录

1. Know thy corpus! Robust methods for digital curation of Web corpora [PDF] 摘要

2. Sentence Level Human Translation Quality Estimation with Attention-based Neural Networks [PDF] 摘要

3. Using word embeddings to improve the discriminability of co-occurrence text networks [PDF] 摘要

4. Review-guided Helpful Answer Identification in E-commerce [PDF] 摘要

5. WAC: A Corpus of Wikipedia Conversations for Online Abuse Detection [PDF] 摘要

6. MixPoet: Diverse Poetry Generation via Learning Controllable Mixed Latent Space [PDF] 摘要

7. Local Contextual Attention with Hierarchical Structure for Dialogue Act Recognition [PDF] 摘要

8. Efficient Rule Learning with Template Saturation for Knowledge Graph Completion [PDF] 摘要

9. Heterogeneous Relational Reasoning in Knowledge Graphs with Reinforcement Learning [PDF] 摘要

10. CRWIZ: A Framework for Crowdsourcing Real-Time Wizard-of-Oz Dialogues [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-13

发表于 2020-03-13 分类于 arxiv ， CV 59k 1:39

目录

1. Cascade EF-GAN: Progressive Facial Expression Editing with Local Focuses [PDF] 摘要

2. SASL: Saliency-Adaptive Sparsity Learning for Neural Network Acceleration [PDF] 摘要

3. Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\leftrightarrow$Preserving Image Content [PDF] 摘要

4. End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds [PDF] 摘要

5. CPS: Class-level 6D Pose and Shape Estimation From Monocular Images [PDF] 摘要

6. Top-1 Solution of Multi-Moments in Time Challenge 2019 [PDF] 摘要

7. Cross-modal Multi-task Learning for Graphic Recognition of Caricature Face [PDF] 摘要

8. SynCGAN: Using learnable class specific priors to generate synthetic data for improving classifier performance on cytological images [PDF] 摘要

9. EDC3: Ensemble of Deep-Classifiers using Class-specific Copula functions to Improve Semantic Image Segmentation [PDF] 摘要

10. Deformation Flow Based Two-Stream Network for Lip Reading [PDF] 摘要

11. Fairness by Learning Orthogonal Disentangled Representations [PDF] 摘要

12. Low-Rank and Total Variation Regularization and Its Application to Image Recovery [PDF] 摘要

13. Skeleton Based Action Recognition using a Stacked Denoising Autoencoder with Constraints of Privileged Information [PDF] 摘要

14. ARAE: Adversarially Robust Training of Autoencoders Improves Novelty Detection [PDF] 摘要

15. Conditional Convolutions for Instance Segmentation [PDF] 摘要

16. Open Source Computer Vision-based Layer-wise 3D Printing Analysis [PDF] 摘要

17. Towards High-Fidelity 3D Face Reconstruction from In-the-Wild Images Using Graph Convolutional Networks [PDF] 摘要

18. Highly Efficient Salient Object Detection with 100K Parameters [PDF] 摘要

19. Understanding Crowd Flow Movements Using Active-Langevin Model [PDF] 摘要

20. Beyond the Camera: Neural Networks in World Coordinates [PDF] 摘要

21. Arbitrary-Oriented Object Detection with Circular Smooth Label [PDF] 摘要

22. Learning to Segment 3D Point Clouds in 2D Image Space [PDF] 摘要

23. Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting [PDF] 摘要

24. ZSTAD: Zero-Shot Temporal Activity Detection [PDF] 摘要

25. Extended Batch Normalization [PDF] 摘要

26. SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates [PDF] 摘要

27. Memory-efficient Learning for Large-scale Computational Imaging [PDF] 摘要

28. Frequency-Tuned Universal Adversarial Attacks [PDF] 摘要

29. VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutions [PDF] 摘要

30. Softmax Splatting for Video Frame Interpolation [PDF] 摘要

31. Confidence Guided Stereo 3D Object Detection with Split Depth Estimation [PDF] 摘要

32. Unified Image and Video Saliency Modeling [PDF] 摘要

33. Deep Vectorization of Technical Drawings [PDF] 摘要

34. Optimal HDR and Depth from Dual Cameras [PDF] 摘要

35. Truncated Inference for Latent Variable Optimization Problems: Application to Robust Estimation and Learning [PDF] 摘要

36. Explaining Away Attacks Against Neural Networks [PDF] 摘要

37. Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection [PDF] 摘要

38. AirSim Drone Racing Lab [PDF] 摘要

39. DeepURL: Deep Pose Estimation Framework for Underwater Relative Localization [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-13

发表于 2020-03-13 分类于 arxiv ， CL 13k 22 分钟

目录

1. KGvec2go -- Knowledge Graph Embeddings as a Service [PDF] 摘要

2. It Means More if It Sounds Good: Yet Another Hypotheses Concerning the Evolution of Polysemous Words [PDF] 摘要

3. Sentiment Analysis with Contextual Embeddings and Self-Attention [PDF] 摘要

4. Learning word-referent mappings and concepts from raw inputs [PDF] 摘要

5. Semantic Holism and Word Representations in Artificial Neural Networks [PDF] 摘要

6. Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking [PDF] 摘要

7. A Precisely Xtreme-Multi Channel Hybrid Approach For Roman Urdu Sentiment Analysis [PDF] 摘要

8. Investigating the influence Brexit had on Financial Markets, in particular the GBP/EUR exchange rate [PDF] 摘要

9. Regular Intersection Emptiness of Graph Problems: Finding a Needle in a Haystack of Graphs with the Help of Automata [PDF] 摘要

10. Expressiveness and machine processability of Knowledge Organization Systems (KOS): An analysis of concepts and relations [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-12

发表于 2020-03-12 分类于 arxiv ， CV 57k 1:35

目录

1. Rethinking Image Mixture for Unsupervised Visual Representation Learning [PDF] 摘要

2. Bi-Directional Attention for Joint Instance and Semantic Segmentation in Point Clouds [PDF] 摘要

3. How Powerful Are Randomly Initialized Pointcloud Set Functions? [PDF] 摘要

4. xCos: An Explainable Cosine Metric for Face Verification Task [PDF] 摘要

5. Plant Disease Detection from Images [PDF] 摘要

6. Training-Set Distillation for Real-Time UAV Object Tracking [PDF] 摘要

7. Semi-Local 3D Lane Detection and Uncertainty Estimation [PDF] 摘要

8. GID-Net: Detecting Human-Object Interaction with Global and Instance Dependency [PDF] 摘要

9. Channel Interaction Networks for Fine-Grained Image Categorization [PDF] 摘要

10. Keyfilter-Aware Real-Time UAV Object Tracking [PDF] 摘要

11. A Fourier Domain Feature Approach for Human Activity Recognition & Fall Detection [PDF] 摘要

12. Improving Convolutional Neural Networks Via Conservative Field Regularisation and Integration [PDF] 摘要

13. Equalization Loss for Long-Tailed Object Recognition [PDF] 摘要

14. Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning [PDF] 摘要

15. Regularized Adaptation for Stable and Efficient Continuous-Level Learning [PDF] 摘要

16. CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing [PDF] 摘要

17. Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networks [PDF] 摘要

18. Uncertainty depth estimation with gated images for 3D reconstruction [PDF] 摘要

19. PONAS: Progressive One-shot Neural Architecture Search for Very Efficient Deployment [PDF] 摘要

20. Learning-Based Human Segmentation and Velocity Estimation Using Automatic Labeled LiDAR Sequence for Training [PDF] 摘要

21. SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image Classification [PDF] 摘要

22. Visual Grounding in Video for Unsupervised Word Translation [PDF] 摘要

23. Cloth in the Wind: A Case Study of Physical Measurement through Simulation [PDF] 摘要

24. Rapid AI Development Cycle for the Coronavirus (COVID-19) Pandemic: Initial Results for Automated Detection & Patient Monitoring using Deep Learning CT Image Analysis [PDF] 摘要

25. SuperMix: Supervising the Mixing Data Augmentation [PDF] 摘要

26. Learning Video Object Segmentation from Unlabeled Videos [PDF] 摘要

27. PL${}_{1}$P -- Point-line Minimal Problems under Partial Visibility in Three Views [PDF] 摘要

28. Using an ensemble color space model to tackle adversarial examples [PDF] 摘要

29. LC-GAN: Image-to-image Translation Based on Generative Adversarial Network for Endoscopic Images [PDF] 摘要

30. Tidying Deep Saliency Prediction Architectures [PDF] 摘要

31. HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation [PDF] 摘要

32. Learning Diverse Fashion Collocation by Neural Graph Filtering [PDF] 摘要

33. Learning Predictive Representations for Deformable Objects Using Contrastive Estimation [PDF] 摘要

34. Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric graphs [PDF] 摘要

35. Early Response Assessment in Lung Cancer Patients using Spatio-temporal CBCT Images [PDF] 摘要

36. ENSEI: Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving Visual Recognition [PDF] 摘要

37. A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU [PDF] 摘要

38. FlowFusion: Dynamic Dense RGB-D SLAM Based on Optical Flow [PDF] 摘要

39. Multi-level Context Gating of Embedded Collective Knowledge for Medical Image Segmentation [PDF] 摘要

40. Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods [PDF] 摘要

41. SAFE: Similarity-Aware Multi-Modal Fake News Detection [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-12

发表于 2020-03-12 分类于 arxiv ， CL 46k 1:17

目录

1. Brazilian Lyrics-Based Music Genre Classification Using a BLSTM Network [PDF] 摘要

2. Capturing document context inside sentence-level neural machine translation models with self-training [PDF] 摘要

3. Vector symbolic architectures for context-free grammars [PDF] 摘要

4. A Benchmark for Systematic Generalization in Grounded Language Understanding [PDF] 摘要

5. TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages [PDF] 摘要

6. Toward Interpretability of Dual-Encoder Models for Dialogue Response Suggestions [PDF] 摘要

7. GASP! Generating Abstracts of Scientific Papers from Abstracts of Cited Papers [PDF] 摘要

8. Masking Orchestration: Multi-task Pretraining for Multi-role Dialogue Representation Learning [PDF] 摘要

9. Learning to mirror speaking styles incrementally [PDF] 摘要

10. Multi-task Learning with Multi-head Attention for Multi-choice Reading Comprehension [PDF] 摘要

11. Unsupervised and Interpretable Domain Adaptation to Rapidly Filter Social Web Data for Emergency Services [PDF] 摘要

12. ScopeIt: Scoping Task Relevant Sentences in Documents [PDF] 摘要

13. A Financial Service Chatbot based on Deep Bidirectional Transformers [PDF] 摘要

14. Investigating an approach for low resource language dataset creation, curation and classification: Setswana and Sepedi [PDF] 摘要

15. Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT [PDF] 摘要

16. Understanding the Downstream Instability of Word Embeddings [PDF] 摘要

17. SAFE: Similarity-Aware Multi-Modal Fake News Detection [PDF] 摘要

18. Improving Reliability of Latent Dirichlet Allocation by Assessing Its Stability Using Clustering Techniques on Replicated Runs [PDF] 摘要

19. Fake News Detection with Different Models [PDF] 摘要

20. Mask & Focus: Conversation Modelling by Learning Concepts [PDF] 摘要

21. A Computational Investigation on Denominalization [PDF] 摘要

22. Transformer++ [PDF] 摘要

23. Localized Flood DetectionWith Minimal Labeled Social Media Data Using Transfer Learning [PDF] 摘要

24. A Comparative Study of Sequence Classification Models for Privacy Policy Coverage Analysis [PDF] 摘要

25. A Dataset Independent Set of Baselines for Relation Prediction in Argument Mining [PDF] 摘要

26. Aspect Term Extraction using Graph-based Semi-Supervised Learning [PDF] 摘要

27. KryptoOracle: A Real-Time Cryptocurrency Price Prediction Platform Using Twitter Sentiments [PDF] 摘要

28. Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning [PDF] 摘要

29. Visual Grounding in Video for Unsupervised Word Translation [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-11

发表于 2020-03-11 更新于 2020-03-12 分类于 arxiv ， CV 80k 2:14

目录

1. Unpaired Image-to-Image Translation using Adversarial Consistency Loss [PDF] 摘要

2. Image Restoration for Under-Display Camera [PDF] 摘要

3. PANDA: A Gigapixel-level Human-centric Video Dataset [PDF] 摘要

4. Hierarchical Human Parsing with Typed Part-Relation Reasoning [PDF] 摘要

5. SAD: Saliency-based Defenses Against Adversarial Examples [PDF] 摘要

6. Dam Burst: A region-merging-based image segmentation method [PDF] 摘要

7. Off-Road Drivable Area Extraction Using 3D LiDAR Data [PDF] 摘要

8. Multi-Task Recurrent Neural Network for Surgical Gesture Recognition and Progress Prediction [PDF] 摘要

9. AP-MTL: Attention Pruned Multi-task Learning Model for Real-time Instrument Detection and Segmentation in Robot-assisted Surgery [PDF] 摘要

10. Rainy screens: Collecting rainy datasets, indoors [PDF] 摘要

11. Restore from Restored: Single Image Denoising with Pseudo Clean Image [PDF] 摘要

12. Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization [PDF] 摘要

13. Deep Blind Video Super-resolution [PDF] 摘要

14. Deep Hough Transform for Semantic Line Detection [PDF] 摘要

15. Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class [PDF] 摘要

16. Incremental Few-Shot Object Detection [PDF] 摘要

17. Lung Infection Quantification of COVID-19 in CT Images with Deep Learning [PDF] 摘要

18. HeatNet: Bridging the Day-Night Domain Gap in Semantic Segmentation with Thermal Images [PDF] 摘要

19. PnP-Net: A hybrid Perspective-n-Point Network [PDF] 摘要

20. Hierarchical Neural Architecture Search for Single Image Super-Resolution [PDF] 摘要

21. Convolutional Occupancy Networks [PDF] 摘要

22. Label-Driven Reconstruction for Domain Adaptation in Semantic Segmentation [PDF] 摘要

23. The Virtual Tailor: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style [PDF] 摘要

24. DymSLAM:4D Dynamic Scene Reconstruction Based on Geometrical Motion Segmentation [PDF] 摘要

25. Channel Pruning via Optimal Thresholding [PDF] 摘要

26. 3D Quasi-Recurrent Neural Network for Hyperspectral Image Denoising [PDF] 摘要

27. PBRnet: Pyramidal Bounding Box Refinement to Improve Object Localization Accuracy [PDF] 摘要

28. Implementation of Deep Neural Networks to Classify EEG Signals using Gramian Angular Summation Field for Epilepsy Diagnosis [PDF] 摘要

29. FOAL: Fast Online Adaptive Learning for Cardiac Motion Estimation [PDF] 摘要

30. Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion [PDF] 摘要

31. Deep learning approach for breast cancer diagnosis [PDF] 摘要

32. Tracking Road Users using Constraint Programming [PDF] 摘要

33. Single-view 2D CNNs with Fully Automatic Non-nodule Categorization for False Positive Reduction in Pulmonary Nodule Detection [PDF] 摘要

34. SDVTracker: Real-Time Multi-Sensor Association and Tracking for Self-Driving Vehicles [PDF] 摘要

35. Multi-Scale Superpatch Matching using Dual Superpixel Descriptors [PDF] 摘要

36. Texture Superpixel Clustering from Patch-based Nearest Neighbor Matching [PDF] 摘要

37. FusionLane: Multi-Sensor Fusion for Lane Marking Semantic Segmentation Using Deep Neural Networks [PDF] 摘要

38. A New Meta-Baseline for Few-Shot Learning [PDF] 摘要

39. Category-wise Attack: Transferable Adversarial Examples for Anchor Free Object Detection [PDF] 摘要

40. Crossmodal learning for audio-visual speech event localization [PDF] 摘要

41. Video Caption Dataset for Describing Human Actions in Japanese [PDF] 摘要

42. Weighted Encoding Based Image Interpolation With Nonlocal Linear Regression Model [PDF] 摘要

43. Reconstruction of 3D flight trajectories from ad-hoc camera networks [PDF] 摘要

44. Computer Aided Diagnosis for Spitzoid lesions classification using Artificial Intelligence techniques [PDF] 摘要

45. TorchIO: a Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning [PDF] 摘要

46. Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog [PDF] 摘要

47. Enabling Viewpoint Learning through Dynamic Label Generation [PDF] 摘要

48. DIBS: Diversity inducing Information Bottleneck in Model Ensembles [PDF] 摘要

49. Spine intervertebral disc labeling using a fully convolutional redundant counting model [PDF] 摘要

50. Automatic segmentation of spinal multiple sclerosis lesions: How to generalize across MRI contrasts? [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-03-11

发表于 2020-03-11 更新于 2020-03-12 分类于 arxiv ， CL 20k 33 分钟

目录

1. Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity [PDF] 摘要

2. Video Caption Dataset for Describing Human Actions in Japanese [PDF] 摘要

3. Undersensitivity in Neural Reading Comprehension [PDF] 摘要

4. Efficient Intent Detection with Dual Sentence Encoders [PDF] 摘要

5. Learning to Respond with Stickers: A Framework of Unifying Multi-Modality in Multi-Turn Dialog [PDF] 摘要

6. A Framework for Evaluation of Machine Reading Comprehension Gold Standards [PDF] 摘要

7. Combining Pretrained High-Resource Embeddings and Subword Representations for Low-Resource Languages [PDF] 摘要

8. GenNet : Reading Comprehension with Multiple Choice Questions using Generation and Selection model [PDF] 摘要

9. ReZero is All You Need: Fast Convergence at Large Depth [PDF] 摘要

10. On the coexistence of competing languages [PDF] 摘要

11. Neuro-symbolic Architectures for Context Understanding [PDF] 摘要

12. Ecological Semantics: Programming Environments for Situated Language Understanding [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-03-10

发表于 2020-03-10 更新于 2020-03-12 分类于 arxiv ， CV 157k 4:22

目录

1. Multi-modal Self-Supervision from Generalized Data Transformations [PDF] 摘要

2. Improved Baselines with Momentum Contrastive Learning [PDF] 摘要

3. Knowledge distillation via adaptive instance normalization [PDF] 摘要

4. Restore from Restored: Video Restoration with Pseudo Clean Video [PDF] 摘要

5. Cascaded Human-Object Interaction Recognition [PDF] 摘要

6. SOIC: Semantic Online Initialization and Calibration for LiDAR and Camera [PDF] 摘要

7. Motion-Attentive Transition for Zero-Shot Video Object Segmentation [PDF] 摘要

8. Hierarchical Kinematic Human Mesh Recovery [PDF] 摘要

9. Semantic Object Prediction and Spatial Sound Super-Resolution with Binaural Sounds [PDF] 摘要

10. Domain Adversarial Training for Infrared-colour Person Re-Identification [PDF] 摘要

11. BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye View [PDF] 摘要

12. Embedding Propagation: Smoother Manifold for Few-Shot Classification [PDF] 摘要

13. Accurate Temporal Action Proposal Generation with Relation-Aware Pyramid Network [PDF] 摘要

14. iFAN: Image-Instance Full Alignment Networks for Adaptive Object Detection [PDF] 摘要

15. The Utility of Feature Reuse: Transfer Learning in Data-Starved Regimes [PDF] 摘要

16. Hazard Detection in Supermarkets using Deep Learning on the Edge [PDF] 摘要

17. A Strong Baseline for Fashion Retrieval with Person Re-Identification Models [PDF] 摘要

18. Searching Central Difference Convolutional Networks for Face Anti-Spoofing [PDF] 摘要

19. When Person Re-identification Meets Changing Clothes [PDF] 摘要

20. On the Texture Bias for Few-Shot CNN Segmentation [PDF] 摘要

21. Transformation-based Adversarial Video Prediction on Large-Scale Data [PDF] 摘要

22. Learning Delicate Local Representations for Multi-Person Pose Estimation [PDF] 摘要

23. Dense Dilated Convolutions Merging Network for Land Cover Classification [PDF] 摘要

24. Context-Aware Domain Adaptation in Semantic Segmentation [PDF] 摘要

25. Pseudo-Convolutional Policy Gradient for Sequence-to-Sequence Lip-Reading [PDF] 摘要

26. Cross-View Tracking for Multi-Human 3D Pose Estimation at over 100 FPS [PDF] 摘要

27. BiDet: An Efficient Binarized Object Detector [PDF] 摘要

28. Cross-Modal Food Retrieval: Learning a Joint Embedding of Food Images and Recipes with Semantic Consistency and Attention Mechanism [PDF] 摘要

29. Pacemaker: Intermediate Teacher Knowledge Distillation For On-The-Fly Convolutional Neural Network [PDF] 摘要

30. MCMC Guided CNN Training and Segmentation for Pancreas Extraction [PDF] 摘要

31. Deconfounded Image Captioning: A Causal Retrospect [PDF] 摘要

32. ROSE: Real One-Stage Effort to Detect the Fingerprint Singular Point Based on Multi-scale Spatial Attention [PDF] 摘要

33. FarSee-Net: Real-Time Semantic Segmentation by Efficient Multi-scale Context Aggregation and Feature Space Super-resolution [PDF] 摘要

34. Faster ILOD: Incremental Learning for Object Detectors based on Faster RCNN [PDF] 摘要

35. An Empirical Evaluation on Robustness and Uncertainty of Regularization Methods [PDF] 摘要

36. FoCL: Feature-Oriented Continual Learning for Generative Models [PDF] 摘要

37. A Tracking System For Baseball Game Reconstruction [PDF] 摘要

38. Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment [PDF] 摘要

39. Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches [PDF] 摘要

40. No Surprises: Training Robust Lung Nodule Detection for Low-Dose CT Scans by Augmenting with Adversarial Attacks [PDF] 摘要

41. PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models [PDF] 摘要

42. Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation [PDF] 摘要

43. DADA: Differentiable Automatic Data Augmentation [PDF] 摘要

44. Rectifying Pseudo Label Learning via Uncertainty Estimation for Domain Adaptive Semantic Segmentation [PDF] 摘要

45. IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval [PDF] 摘要

46. Pixel-In-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild [PDF] 摘要

47. A Benchmark for Temporal Color Constancy [PDF] 摘要

48. Monocular 3D Object Detection in Cylindrical Images from Fisheye Cameras [PDF] 摘要

49. Domain-Specific Image Super-Resolution with Progressive Adversarial Network [PDF] 摘要

50. Better Captioning with Sequence-Level Exploration [PDF] 摘要

51. A Multi-scale CNN-CRF Framework for Environmental Microorganism Image Segmentation [PDF] 摘要

52. Object-Oriented Video Captioning with Temporal Graph and Prior Knowledge Building [PDF] 摘要

53. Meta3D: Single-View 3D Object Reconstruction from Shape Priors in Memory [PDF] 摘要

54. Trajectory Grouping with Curvature Regularization for Tubular Structure Tracking [PDF] 摘要

55. Adaptive Semantic-Visual Tree for Hierarchical Embeddings [PDF] 摘要

56. Transferring Cross-domain Knowledge for Video Sign Language Recognition [PDF] 摘要

57. Unifying Specialist Image Embedding into Universal Image Embedding [PDF] 摘要

58. Adaptive Offline Quintuplet Loss for Image-Text Matching [PDF] 摘要

59. SalsaNext: Fast Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving [PDF] 摘要

60. Inferring Spatial Uncertainty in Object Detection [PDF] 摘要

61. AlphaNet: An Attention Guided Deep Network for Automatic Image Matting [PDF] 摘要

62. DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images [PDF] 摘要

63. Generative Low-bitwidth Data Free Quantization [PDF] 摘要

64. StyleGAN2 Distillation for Feed-forward Image Manipulation [PDF] 摘要

65. CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection [PDF] 摘要

66. Crowd Counting via Hierarchical Scale Recalibration Network [PDF] 摘要

67. TTPP: Temporal Transformer with Progressive Prediction for Efficient Action Anticipation [PDF] 摘要

68. MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision [PDF] 摘要

69. Distilling portable Generative Adversarial Networks for Image Translation [PDF] 摘要

70. Cross-modal Learning for Multi-modal Video Categorization [PDF] 摘要

71. Weight mechanism adding a constant in concatenation of series connect [PDF] 摘要

72. MatchingGAN: Matching-based Few-shot Image Generation [PDF] 摘要

73. Semantic Change Pattern Analysis [PDF] 摘要

74. Super Resolution Using Segmentation-Prior Self-Attention Generative Adversarial Network [PDF] 摘要

75. ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions [PDF] 摘要

76. PoseNet3D: Unsupervised 3D Human Shape and Pose Estimation [PDF] 摘要

77. Semi-Supervised StyleGAN for Disentanglement Learning [PDF] 摘要

78. Scalable Uncertainty for Computer Vision with Functional Variational Inference [PDF] 摘要

79. Manifold Regularization for Adversarial Robustness [PDF] 摘要

80. Deep Inverse Feature Learning: A Representation Learning of Error [PDF] 摘要

81. How to Train Your Super-Net: An Analysis of Training Heuristics in Weight-Sharing NAS [PDF] 摘要

82. MLography: An Automated Quantitative Metallography Model for Impurities Anomaly Detection using Novel Data Mining and Deep Learning Approach [PDF] 摘要

83. Toward Cross-Domain Speech Recognition with End-to-End Models [PDF] 摘要

84. Hybrid calibration procedure for fringe projection profilometry based on stereo-vision and polynomial fitting [PDF] 摘要

85. Learned Spectral Computed Tomography [PDF] 摘要

86. $Π-$nets: Deep Polynomial Neural Networks [PDF] 摘要

87. Deep Learning Guided Undersampling Mask Design for MR Image Reconstruction [PDF] 摘要

88. DFVS: Deep Flow Guided Scene Agnostic Image Based Visual Servoing [PDF] 摘要

89. Online Self-Supervised Learning for Object Picking: Detecting Optimum Grasping Position using a Metric Learning Approach [PDF] 摘要

90. AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks [PDF] 摘要

91. Explaining Knowledge Distillation by Quantifying the Knowledge [PDF] 摘要

92. Diffusion State Distances: Multitemporal Analysis, Fast Algorithms, and Applications to Biological Networks [PDF] 摘要

93. STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Image [PDF] 摘要

94. Novel Radiomic Feature for Survival Prediction of Lung Cancer Patients using Low-Dose CBCT Images [PDF] 摘要

95. Robust, Occlusion-aware Pose Estimation for Objects Grasped by Adaptive Hands [PDF] 摘要

96. SuPer Deep: A Surgical Perception Framework for Robotic Tissue Manipulation using Deep Learning for Feature Extraction [PDF] 摘要

97. Endoscopy disease detection challenge 2020 [PDF] 摘要

阅读全文 »