【arxiv论文】 Computation and Language 2020-12-21

发表于 2020-12-21 分类于 arxiv ， CL 34k 57 分钟

目录

1. Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training [PDF] 摘要

2. HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection [PDF] 摘要

3. An Empirical Study of Using Pre-trained BERT Models for Vietnamese Relation Extraction Task at VLSP 2020 [PDF] 摘要

4. Understood in Translation, Transformers for Domain Understanding [PDF] 摘要

5. ReINTEL Challenge 2020: A Multimodal Ensemble Model for Detecting Unreliable Information on Vietnamese SNS [PDF] 摘要

6. A Benchmark Arabic Dataset for Commonsense Explanation [PDF] 摘要

7. AdvExpander: Generating Natural Language Adversarial Examples by Expanding Text [PDF] 摘要

8. Deep Open Intent Classification with Adaptive Decision Boundary [PDF] 摘要

9. Regularized Attentive Capsule Network for Overlapped Relation Extraction [PDF] 摘要

10. Technical Progress Analysis Using a Dynamic Topic Model for Technical Terms to Revise Patent Classification Codes [PDF] 摘要

11. Mention Extraction and Linking for SQL Query Generation [PDF] 摘要

12. Attention-Based LSTM Network for COVID-19 Clinical Trial Parsing [PDF] 摘要

13. Leveraging Event Specific and Chunk Span features to Extract COVID Events from tweets [PDF] 摘要

14. Exploring Fluent Query Reformulations with Text-to-Text Transformers and Reinforcement Learning [PDF] 摘要

15. NeurST: Neural Speech Translation Toolkit [PDF] 摘要

16. Can Transformers Reason About Effects of Actions? [PDF] 摘要

17. Named Entity Recognition in the Legal Domain using a Pointer Generator Network [PDF] 摘要

18. Trying Bilinear Pooling in Video-QA [PDF] 摘要

19. Should I visit this place? Inclusion and Exclusion Phrase Mining from Reviews [PDF] 摘要

20. On Modality Bias in the TVQA Dataset [PDF] 摘要

21. End-to-End Speaker Diarization as Post-Processing [PDF] 摘要

22. Predicting Decisions in Language Based Persuasion Games [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-12-18

发表于 2020-12-18 分类于 arxiv ， CV 122k 3:23

目录

1. Reconstructing Hand-Object Interactions in the Wild [PDF] 摘要

2. Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image [PDF] 摘要

3. Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image [PDF] 摘要

4. Human Mesh Recovery from Multiple Shots [PDF] 摘要

5. $\mathbb{X}$Resolution Correspondence Networks [PDF] 摘要

6. Taming Transformers for High-Resolution Image Synthesis [PDF] 摘要

7. Transformer Interpretability Beyond Attention Visualization [PDF] 摘要

8. SceneFormer: Indoor Scene Generation with Transformers [PDF] 摘要

9. Neural Radiance Flow for 4D View Synthesis and Video Processing [PDF] 摘要

10. End-to-end Deep Object Tracking with Circular Loss Function for Rotated Bounding Box [PDF] 摘要

11. End-to-End Human Pose and Mesh Reconstruction with Transformers [PDF] 摘要

12. Interpretable Image Clustering via Diffeomorphism-Aware K-Means [PDF] 摘要

13. AutoCaption: Image Captioning with Neural Architecture Search [PDF] 摘要

14. Robust Image Captioning [PDF] 摘要

15. Efficient CNN-LSTM based Image Captioning using Neural Network Compression [PDF] 摘要

16. RainNet: A Large-Scale Dataset for Spatial Precipitation Downscaling [PDF] 摘要

17. PCT: Point Cloud Transformer [PDF] 摘要

18. Multi-Modal Depth Estimation Using Convolutional Neural Networks [PDF] 摘要

19. A fully pipelined FPGA accelerator for scale invariant feature transform keypoint descriptor matching, [PDF] 摘要

20. Firearm Detection via Convolutional Neural Networks: Comparing a Semantic Segmentation Model Against End-to-End Solutions [PDF] 摘要

21. Detection and Prediction of Nutrient Deficiency Stress using Longitudinal Aerial Imagery [PDF] 摘要

22. Trajectory saliency detection using consistency-oriented latent codes from a recurrent auto-encoder [PDF] 摘要

23. Incremental Learning from Low-labelled Stream Data in Open-Set Video Face Recognition [PDF] 摘要

24. Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN [PDF] 摘要

25. Embodied Visual Active Learning for Semantic Segmentation [PDF] 摘要

26. A Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks [PDF] 摘要

27. Exploiting Learnable Joint Groups for Hand Pose Estimation [PDF] 摘要

28. CT Film Recovery via Disentangling Geometric Deformation and Illumination Variation: Simulated Datasets and Deep Models [PDF] 摘要

29. Learning to Share: A Multitasking Genetic Programming Approach to Image Feature Learning [PDF] 摘要

30. FG-Net: Fast Large-Scale LiDAR Point CloudsUnderstanding Network Leveraging CorrelatedFeature Mining and Geometric-Aware Modelling [PDF] 摘要

31. Multi-shot Temporal Event Localization: a Benchmark [PDF] 摘要

32. PanoNet3D: Combining Semantic and Geometric Understanding for LiDARPoint Cloud Detection [PDF] 摘要

33. Computation-Efficient Knowledge Distillation via Uncertainty-Aware Mixup [PDF] 摘要

34. Temporal LiDAR Frame Prediction for Autonomous Driving [PDF] 摘要

35. LIGHTEN: Learning Interactions with Graph and Hierarchical TEmporal Networks for HOI in videos [PDF] 摘要

36. Zoom-to-Inpaint: Image Inpainting with High Frequency Details [PDF] 摘要

37. Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation [PDF] 摘要

38. Efficient Golf Ball Detection and Tracking Based on Convolutional Neural Networks and Kalman Filter [PDF] 摘要

39. Event Camera Calibration of Per-pixel Biased Contrast Threshold [PDF] 摘要

40. Unlabeled Data Guided Semi-supervised Histopathology Image Segmentation [PDF] 摘要

41. Semi-Global Shape-aware Network [PDF] 摘要

42. Learning to Recover 3D Scene Shape from a Single Image [PDF] 摘要

43. Roof-GAN: Learning to Generate Roof Geometry and Relations for Residential Houses [PDF] 摘要

44. Unsupervised Learning of Local Discriminative Representation for Medical Images [PDF] 摘要

45. Polyblur: Removing mild blur by polynomial reblurring [PDF] 摘要

46. Learning to Recognize Patch-Wise Consistency for Deepfake Detection [PDF] 摘要

47. Self-Supervised Sketch-to-Image Synthesis [PDF] 摘要

48. Projected Distribution Loss for Image Enhancement [PDF] 摘要

49. Sparse Signal Models for Data Augmentation in Deep Learning ATR [PDF] 摘要

50. ISD: Self-Supervised Learning by Iterative Similarity Distillation [PDF] 摘要

51. Neural Pruning via Growing Regularization [PDF] 摘要

52. S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds [PDF] 摘要

53. uBAM: Unsupervised Behavior Analysis and Magnification using Deep Learning [PDF] 摘要

54. Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation [PDF] 摘要

55. On Episodes, Prototypical Networks, and Few-shot Learning [PDF] 摘要

56. Learning Cross-Domain Correspondence for Control with Dynamics Cycle-Consistency [PDF] 摘要

57. Deep Learning Techniques for Super-Resolution in Video Games [PDF] 摘要

58. Describing the Structural Phenotype of the Glaucomatous Optic Nerve Head Using Artificial Intelligence [PDF] 摘要

59. Image-Based Jet Analysis [PDF] 摘要

60. Combating Mode Collapse in GAN training: An Empirical Analysis using Hessian Eigenvalues [PDF] 摘要

61. Kernelized Classification in Deep Networks [PDF] 摘要

62. Learned Block-based Hybrid Image Compression [PDF] 摘要

63. A new semi-supervised self-training method for lung cancer prediction [PDF] 摘要

64. Joint Search of Data Augmentation Policies and Network Architectures [PDF] 摘要

65. A Contrast Synthesized Thalamic Nuclei Segmentation Scheme using Convolutional Neural Networks [PDF] 摘要

66. On the Limitations of Denoising Strategies as Adversarial Defenses [PDF] 摘要

67. Clique: Spatiotemporal Object Re-identification at the City Scale [PDF] 摘要

68. Simultaneous View and Feature Selection for Collaborative Multi-Robot Recognition [PDF] 摘要

69. StarcNet: Machine Learning for Star Cluster Identification [PDF] 摘要

70. Spatial Context-Aware Self-Attention Model For Multi-Organ Segmentation [PDF] 摘要

71. Reduction in the complexity of 1D 1H-NMR spectra by the use of Frequency to Information Transformation [PDF] 摘要

72. Transfer Learning Through Weighted Loss Function and Group Normalization for Vessel Segmentation from Retinal Images [PDF] 摘要

73. MELINDA: A Multimodal Dataset for Biomedical Experiment Method Classification [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-12-18

发表于 2020-12-18 分类于 arxiv ， CL 32k 53 分钟

目录

1. Continual Lifelong Learning in Natural Language Processing: A Survey [PDF] 摘要

2. BERT Goes Shopping: Comparing Distributional Models for Product Representations [PDF] 摘要

3. MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering [PDF] 摘要

4. Benchmarking Automatic Detection of Psycholinguistic Characteristics for Better Human-Computer Interaction [PDF] 摘要

5. Hate Speech detection in the Bengali language: A dataset and its baseline evaluation [PDF] 摘要

6. Ultra-Fast, Low-Storage, Highly Effective Coarse-grained Selection in Retrieval-based Chatbot by Using Deep Semantic Hashing [PDF] 摘要

7. ReferentialGym: A Nomenclature and Framework for Language Emergence & Grounding in (Visual) Referential Games [PDF] 摘要

8. cif-based collaborative decoding for end-to-end contextual speech recognition [PDF] 摘要

9. Unsupervised Learning of Discourse Structures using a Tree Autoencoder [PDF] 摘要

10. Interactive Question Clarification in Dialogue via Reinforcement Learning [PDF] 摘要

11. InSRL: A Multi-view Learning Framework Fusing Multiple Information Sources for Distantly-supervised Relation Extraction [PDF] 摘要

12. Assessing COVID-19 Impacts on College Students via Automated Processing of Free-form Text [PDF] 摘要

13. Literature Retrieval for Precision Medicine with Neural Matching and Faceted Summarization [PDF] 摘要

14. Do You Do Yoga? Understanding Twitter Users' Types and Motivations using Social and Textual Information [PDF] 摘要

15. MELINDA: A Multimodal Dataset for Biomedical Experiment Method Classification [PDF] 摘要

16. SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning [PDF] 摘要

17. The effectiveness of unsupervised subword modeling with autoregressive and cross-lingual phone-aware networks [PDF] 摘要

18. The voice of COVID-19: Acoustic correlates of infection [PDF] 摘要

19. MASKER: Masked Keyword Regularization for Reliable Text Classification [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-12-17

发表于 2020-12-17 更新于 2020-12-18 分类于 arxiv ， CV 106k 2:57

目录

1. Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts [PDF] 摘要

2. Point Transformer [PDF] 摘要

3. Learning Continuous Image Representation with Local Implicit Image Function [PDF] 摘要

4. DECOR-GAN: 3D Shape Detailization by Conditional Refinement [PDF] 摘要

5. Joint Generative and Contrastive Learning for Unsupervised Person Re-identification [PDF] 摘要

6. Towards Recognizing New Semantic Concepts in New Visual Domains [PDF] 摘要

7. Improved StyleGAN Embedding: Where are the Good Latents? [PDF] 摘要

8. CompositeTasking: Understanding Images by Spatial Composition of Tasks [PDF] 摘要

9. AdjointBackMap: Reconstructing Effective Decision Hypersurfaces from CNN Layers Using Adjoint Operators [PDF] 摘要

10. I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting [PDF] 摘要

11. Sketch Generation with Drawing Process Guided by Vector Flow and Grayscale [PDF] 摘要

12. C2F-FWN: Coarse-to-Fine Flow Warping Network for Spatial-Temporal Consistent Motion Transfer [PDF] 摘要

13. SimuGAN: Unsupervised forward modeling and optimal design of a LIDAR Camera [PDF] 摘要

14. Deep Reinforcement Learning of Graph Matching [PDF] 摘要

15. SAfE: Self-Attention Based Unsupervised Road Safety Classification in Hazardous Environments [PDF] 摘要

16. Copyspace: Where to Write on Images? [PDF] 摘要

17. FuseVis: Interpreting neural networks for image fusion using per-pixel saliency visualization [PDF] 摘要

18. Unsupervised Image Segmentation using Mutual Mean-Teaching [PDF] 摘要

19. Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera [PDF] 摘要

20. Temporal Graph Modeling for Skeleton-based Action Recognition [PDF] 摘要

21. Latent Space Conditioning on Generative Adversarial Networks [PDF] 摘要

22. Analysing the Direction of Emotional Influence in Nonverbal Dyadic Communication: A Facial-Expression Study [PDF] 摘要

23. Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices [PDF] 摘要

24. Difficulty in estimating visual information from randomly sampled images [PDF] 摘要

25. Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification [PDF] 摘要

26. Event-based Motion Segmentation with Spatio-Temporal Graph Cuts [PDF] 摘要

27. Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models [PDF] 摘要

28. SID-NISM: A Self-supervised Low-light Image Enhancement Framework [PDF] 摘要

29. Two-Stage Copy-Move Forgery Detection with Self Deep Matching and Proposal SuperGlue [PDF] 摘要

30. Domain Adaptive Object Detection via Feature Separation and Alignment [PDF] 摘要

31. StrokeGAN: Reducing Mode Collapse in Chinese Font Generation via Stroke Encoding [PDF] 摘要

32. Training an Emotion Detection Classifier using Frames from a Mobile Therapeutic Game for Children with Developmental Disorders [PDF] 摘要

33. A Closer Look at the Robustness of Vision-and-Language Pre-trained Models [PDF] 摘要

34. Automated system to measure Tandem Gait to assess executive functions in children [PDF] 摘要

35. Enabling Collaborative Video Sensing at the Edge through Convolutional Sharing [PDF] 摘要

36. Does the dataset meet your expectations? Explaining sample representation in image data [PDF] 摘要

37. A grid-point detection method based on U-net for a structured light system [PDF] 摘要

38. Spectral band selection for vegetation properties retrieval using Gaussian processes regression [PDF] 摘要

39. Sparsity-driven Digital Terrain Model Extraction [PDF] 摘要

40. Post-Hurricane Damage Assessment Using Satellite Imagery and Geolocation Features [PDF] 摘要

41. Pose Error Reduction for Focus Enhancement in Thermal Synthetic Aperture Visualization [PDF] 摘要

42. FoggySight: A Scheme for Facial Lookup Privacy [PDF] 摘要

43. Attentional Local Contrast Networks for Infrared Small Target Detection [PDF] 摘要

44. Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection [PDF] 摘要

45. End-to-end Generative Floor-plan and Layout with Attributes and Relation Graph [PDF] 摘要

46. Exploration of Whether Skylight Polarization Patterns Contain Three-dimensional Attitude Information [PDF] 摘要

47. Personal Mental Health Navigator: Harnessing the Power of Data, Personal Models, and Health Cybernetics to Promote Psychological Well-being [PDF] 摘要

48. TEMImageNet and AtomSegNet Deep Learning Training Library and Models for High-Precision Atom Segmentation, Localization, Denoising, and Super-resolution Processing of Atom-Resolution Scanning TEM Images [PDF] 摘要

49. Evaluation of deep learning-based myocardial infarction quantification using Segment CMR software [PDF] 摘要

50. PGMAN: An Unsupervised Generative Multi-adversarial Network for Pan-sharpening [PDF] 摘要

51. A Differential Model of the Complex Cell [PDF] 摘要

52. Learning-Based Algorithms for Vessel Tracking: A Review [PDF] 摘要

53. Secret Key Agreement with Physical Unclonable Functions: An Optimality Summary [PDF] 摘要

54. Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces [PDF] 摘要

55. Learning to Run with Potential-Based Reward Shaping and Demonstrations from Video Data [PDF] 摘要

56. Cross-Cohort Generalizability of Deep and Conventional Machine Learning for MRI-based Diagnosis and Prediction of Alzheimer's Disease [PDF] 摘要

57. Learning-Based Quality Assessment for Image Super-Resolution [PDF] 摘要

58. Responsible Disclosure of Generative Models Using Scalable Fingerprinting [PDF] 摘要

59. Wasserstein Contrastive Representation Distillation [PDF] 摘要

60. Mitigating bias in calibration error estimation [PDF] 摘要

61. CUDA-Optimized real-time rendering of a Foveated Visual System [PDF] 摘要

62. An anatomically-informed 3D CNN for brain aneurysm classification with weak labels [PDF] 摘要

63. Jet tagging in the Lund plane with graph networks [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-12-17

发表于 2020-12-17 更新于 2020-12-18 分类于 arxiv ， CL 33k 55 分钟

目录

1. LIREx: Augmenting Language Inference with Relevant Explanation [PDF] 摘要

2. Building and Using Personal Knowledge Graph to Improve Suicidal Ideation Detection on Social Media [PDF] 摘要

3. Exploring Thematic Coherence in Fake News [PDF] 摘要

4. You Are What You Tweet: Profiling Users by Past Tweets to Improve Hate Speech Detection [PDF] 摘要

5. Show or Tell? Demonstration is More Robust to Changes in Shared Perception than Explanation [PDF] 摘要

6. Using Meta-Knowledge Mined from Identifiers to Improve Intent Recognition in Neuro-Symbolic Algorithms [PDF] 摘要

7. Discovering New Intents with Deep Aligned Clustering [PDF] 摘要

8. No Budget? Don't Flex! Cost Consideration when Planning to Adopt NLP for Your Business [PDF] 摘要

9. R$^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching [PDF] 摘要

10. Multilingual Evidence Retrieval and Fact Verification to Combat Global Disinformation: The Power of Polyglotism [PDF] 摘要

11. Learning from the Best: Rationalizing Prediction by Adversarial Information Calibration [PDF] 摘要

12. Multi-type Disentanglement without Adversarial Training [PDF] 摘要

13. A Lightweight Neural Model for Biomedical Entity Linking [PDF] 摘要

14. Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference [PDF] 摘要

15. Focusing More on Conflicts with Mis-Predictions Helps Language Pre-Training [PDF] 摘要

16. Building domain specific lexicon based on TikTok comment dataset [PDF] 摘要

17. Improving Multilingual Neural Machine Translation For Low-Resource Languages: French-, English- Vietnamese [PDF] 摘要

18. DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition [PDF] 摘要

19. Pre-Training Transformers as Energy-Based Cloze Models [PDF] 摘要

20. Exploring Transfer Learning For End-to-End Spoken Language Understanding [PDF] 摘要

21. A Closer Look at the Robustness of Vision-and-Language Pre-trained Models [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-12-16

发表于 2020-12-16 分类于 arxiv ， CV 95k 2:39

目录

1. FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation [PDF] 摘要

2. GTA: Global Temporal Attention for Video Action Understanding [PDF] 摘要

3. Object-based attention for spatio-temporal reasoning: Outperforming neuro-symbolic models with flexible distributed architectures [PDF] 摘要

4. Object-Centric Neural Scene Rendering [PDF] 摘要

5. NAPA: Neural Art Human Pose Amplifier [PDF] 摘要

6. Geometric Surface Image Prediction for Image Recognition Enhancement [PDF] 摘要

7. Detecting Invisible People [PDF] 摘要

8. SPOC learner's final grade prediction based on a novel sampling batch normalization embedded neural network method [PDF] 摘要

9. FINED: Fast Inference Network for Edge Detection [PDF] 摘要

10. mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets [PDF] 摘要

11. Practical Auto-Calibration for Spatial Scene-Understanding from Crowdsourced Dashcamera Videos [PDF] 摘要

12. Improved Image Matting via Real-time User Clicks and Uncertainty Estimation [PDF] 摘要

13. Robots Understanding Contextual Information in Human-Centered Environments using Weakly Supervised Mask Data Distillation [PDF] 摘要

14. Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation [PDF] 摘要

15. Artificial Dummies for Urban Dataset Augmentation [PDF] 摘要

16. FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Monocular Depth Completion [PDF] 摘要

17. HeadGAN: Video-and-Audio-Driven Talking Head Synthesis [PDF] 摘要

18. Geometry Enhancements from Visual Content: Going Beyond Ground Truth [PDF] 摘要

19. Robust Factorization Methods Using a Gaussian/Uniform Mixture Model [PDF] 摘要

20. Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses [PDF] 摘要

21. Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment [PDF] 摘要

22. Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation [PDF] 摘要

23. FMODetect: Robust Detection and Trajectory Estimation of Fast Moving Objects [PDF] 摘要

24. Unsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection [PDF] 摘要

25. Seeing Behind Objects for 3D Multi-Object Tracking in RGB-D Sequences [PDF] 摘要

26. Representing Ambiguity in Registration Problems with Conditional Invertible Neural Networks [PDF] 摘要

27. docExtractor: An off-the-shelf historical document element extraction [PDF] 摘要

28. Research on All-content Text Recognition Method for Financial Ticket Image [PDF] 摘要

29. Dilated-Scale-Aware Attention ConvNet For Multi-Class Object Counting [PDF] 摘要

30. NeuralQAAD: An Efficient Differentiable Framework for High Resolution Point Cloud Compression [PDF] 摘要

31. Deep Layout of Custom-size Furniture through Multiple-domain Learning [PDF] 摘要

32. Class-incremental Learning with Rectified Feature-Graph Preservation [PDF] 摘要

33. KOALAnet: Blind Super-Resolution using Kernel-Oriented Adaptive Local Adjustment [PDF] 摘要

34. Fast 3D Image Moments [PDF] 摘要

35. Towards Improving Spatiotemporal Action Recognition in Videos [PDF] 摘要

36. FAWA: Fast Adversarial Watermark Attack on Optical Character Recognition (OCR) Systems [PDF] 摘要

37. Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data Augmentation [PDF] 摘要

38. Image Inpainting Guided by Coherence Priors of Semantics and Textures [PDF] 摘要

39. Teach me to segment with mixed supervision: Confident students become masters [PDF] 摘要

40. Semantic-Guided Representation Enhancement for Self-supervised Monocular Trained Depth Estimation [PDF] 摘要

41. NUTA: Non-uniform Temporal Aggregation for Action Recognition [PDF] 摘要

42. Classification of Smoking and Calling using Deep Learning [PDF] 摘要

43. DeepGamble: Towards unlocking real-time player intelligence using multi-layer instance segmentation and attribute detection [PDF] 摘要

44. FaceDet3D: Facial Expressions with 3D Geometric Detail Prediction [PDF] 摘要

45. FasteNet: A Fast Railway Fastener Detector [PDF] 摘要

46. Automatic Vertebra Localization and Identification in CT by Spine Rectification and Anatomically-constrained Optimization [PDF] 摘要

47. Robust One Shot Audio to Video Generation [PDF] 摘要

48. Exploring Vicinal Risk Minimization for Lightweight Out-of-Distribution Detection [PDF] 摘要

49. Masksembles for Uncertainty Estimation [PDF] 摘要

50. Do not repeat these mistakes -- a critical appraisal of applications of explainable artificial intelligence for image based COVID-19 detection [PDF] 摘要

51. Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methods [PDF] 摘要

52. Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution [PDF] 摘要

53. CosSGD: Nonlinear Quantization for Communication-efficient Federated Learning [PDF] 摘要

54. Frozen-to-Paraffin: Categorization of Histological Frozen Sections by the Aid of Paraffin Sections and Generative Adversarial Networks [PDF] 摘要

55. Hypothesis Disparity Regularized Mutual Information Maximization [PDF] 摘要

56. Iterative label cleaning for transductive and semi-supervised few-shot learning [PDF] 摘要

57. Towards broader generalization of deep learning methods for multiple sclerosis lesion segmentation [PDF] 摘要

58. When Physical Unclonable Function Meets Biometrics [PDF] 摘要

59. Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-12-16

发表于 2020-12-16 分类于 arxiv ， CL 34k 57 分钟

目录

1. Nested Named Entity Recognition with Partially-Observed TreeCRFs [PDF] 摘要

2. Multi-Aspect Sentiment Analysis with Latent Sentiment-Aspect Attribution [PDF] 摘要

3. Modeling Homophone Noise for Robust Neural Machine Translation [PDF] 摘要

4. Keyword-Guided Neural Conversational Model [PDF] 摘要

5. CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts [PDF] 摘要

6. Enhance Multimodal Transformer With External Label And In-Domain Pretrain: Hateful Meme Challenge Winning Solution [PDF] 摘要

7. Efficient Clustering from Distributions over Topics [PDF] 摘要

8. Learning to Check Contract Inconsistencies [PDF] 摘要

9. A Response Retrieval Approach for Dialogue Using a Multi-Attentive Transformer [PDF] 摘要

10. Writing Polishment with Simile: Task, Dataset and A Neural Approach [PDF] 摘要

11. Enriched Annotations for Tumor Attribute Classification from Pathology Reports with Limited Labeled Data [PDF] 摘要

12. Traditional IR rivals neural models on the MS~MARCO Document Ranking Leaderboard [PDF] 摘要

13. Primer AI's Systems for Acronym Identification and Disambiguation [PDF] 摘要

14. Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision [PDF] 摘要

15. Model Choices Influence Attributive Word Associations: A Semi-supervised Analysis of Static Word Embeddings [PDF] 摘要

16. Object-based attention for spatio-temporal reasoning: Outperforming neuro-symbolic models with flexible distributed architectures [PDF] 摘要

17. Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks [PDF] 摘要

18. QUARC: Quaternion Multi-Modal Fusion Architecture For Hate Speech Classification [PDF] 摘要

19. *-CFQ: Analyzing the Scalability of Machine Learning on a Compositional Task [PDF] 摘要

20. Generation of complex database queries and API calls from natural language utterances [PDF] 摘要

21. Relation-Aware Neighborhood Matching Model for Entity Alignment [PDF] 摘要

22. A review of on-device fully neural end-to-end automatic speech recognition algorithms [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-12-15

发表于 2020-12-15 分类于 arxiv ， CV 197k 5:28

目录

1. Real-Time High-Resolution Background Matting [PDF] 摘要

2. img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimation [PDF] 摘要

3. PePScenes: A Novel Dataset and Baseline for Pedestrian Action Prediction in 3D [PDF] 摘要

4. Digital rock reconstruction with user-defined properties using conditional generative adversarial networks [PDF] 摘要

5. Improving Panoptic Segmentation at All Scales [PDF] 摘要

6. High-resolution global irrigation prediction with Sentinel-2 30m data [PDF] 摘要

7. Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection [PDF] 摘要

8. Deep Neural Networks for COVID-19 Detection and Diagnosis using Images and Acoustic-based Techniques: A Recent Review [PDF] 摘要

9. ProLab: perceptually uniform projective colour coordinate system [PDF] 摘要

10. Decoupled Self Attention for Accurate One Stage Object Detection [PDF] 摘要

11. Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective [PDF] 摘要

12. WDNet: Watermark-Decomposition Network for Visible Watermark Removal [PDF] 摘要

13. Agglomerative Clustering of Handwritten Numerals to Determine Similarity of Different Languages [PDF] 摘要

14. FlowMOT: 3D Multi-Object Tracking by Scene Flow Association [PDF] 摘要

15. Temporal Relational Modeling with Self-Supervision for Action Segmentation [PDF] 摘要

16. Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates [PDF] 摘要

17. Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds [PDF] 摘要

18. Deep Learning for Material recognition: most recent advances and open challenges [PDF] 摘要

19. Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU [PDF] 摘要

20. Aggregative Self-Supervised Feature Learning [PDF] 摘要

21. Learned Video Codec with Enriched Reconstruction for CLIC P-frame Coding [PDF] 摘要

22. Pyramid-Focus-Augmentation: Medical Image Segmentation with Step-Wise Focus [PDF] 摘要

23. DSM Refinement with Deep Encoder-Decoder Networks [PDF] 摘要

24. One-Shot Learning with Triplet Loss for Vegetation Classification Tasks [PDF] 摘要

25. HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation [PDF] 摘要

26. The Open Brands Dataset: Unified brand detection and recognition at scale [PDF] 摘要

27. Articulated Shape Matching Using Laplacian Eigenfunctions and Unsupervised Point Registration [PDF] 摘要

28. Intrinsic Image Captioning Evaluation [PDF] 摘要

29. Combining Similarity and Adversarial Learning to Generate Visual Explanation: Application to Medical Image Classification [PDF] 摘要

30. Morphology on categorical distributions [PDF] 摘要

31. Multi Modal Adaptive Normalization for Audio to Video Generation [PDF] 摘要

32. Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer [PDF] 摘要

33. Learning Category-level Shape Saliency via Deep Implicit Surface Networks [PDF] 摘要

34. Semantic Layout Manipulation with High-Resolution Sparse Attention [PDF] 摘要

35. Information-Theoretic Segmentation by Inpainting Error Maximization [PDF] 摘要

36. TDAF: Top-Down Attention Framework for Vision Tasks [PDF] 摘要

37. Deep Optimized Priors for 3D Shape Modeling and Reconstruction [PDF] 摘要

38. INSPIRE: Intensity and Spatial Information-Based Deformable Image Registration [PDF] 摘要

39. Knowledge-Routed Visual Question Reasoning: Challenges for Deep Representation Embedding [PDF] 摘要

40. Meticulous Object Segmentation [PDF] 摘要

41. Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation [PDF] 摘要

42. MSAF: Multimodal Split Attention Fusion [PDF] 摘要

43. FSOCO: The Formula Student Objects in Context Dataset [PDF] 摘要

44. Location-aware Single Image Reflection Removal [PDF] 摘要

45. Iterative Knowledge Exchange Between Deep Learning and Space-Time Spectral Clustering for Unsupervised Segmentation in Videos [PDF] 摘要

46. DFR: Deep Feature Reconstruction for Unsupervised Anomaly Segmentation [PDF] 摘要

47. Learning Heatmap-Style Jigsaw Puzzles Provides Good Pretraining for 2D Human Pose Estimation [PDF] 摘要

48. MSVD-Turkish: A Comprehensive Multimodal Dataset for Integrated Vision and Language Research in Turkish [PDF] 摘要

49. EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search [PDF] 摘要

50. Robust Real-Time Pedestrian Detection on Embedded Devices [PDF] 摘要

51. Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network [PDF] 摘要

52. PoNA: Pose-guided Non-local Attention for Human Pose Transfer [PDF] 摘要

53. One-Shot Object Localization in Medical Images based on Relative Position Regression [PDF] 摘要

54. Semi-supervised Segmentation via Uncertainty Rectified Pyramid Consistency and Its Application to Gross Target Volume of Nasopharyngeal Carcinoma [PDF] 摘要

55. Uncertainty Estimation in Deep Neural Networks for Point Cloud Segmentation in Factory Planning [PDF] 摘要

56. Efficient Human Pose Estimation by Learning Deeply Aggregated Representations [PDF] 摘要

57. Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal [PDF] 摘要

58. Effective multi-view registration of point sets based on student's t mixture model [PDF] 摘要

59. Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation [PDF] 摘要

60. Contrastive Learning for Label-Efficient Semantic Segmentation [PDF] 摘要

61. GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation [PDF] 摘要

62. MVFNet: Multi-View Fusion Network for Efficient Video Recognition [PDF] 摘要

63. Spontaneous Emotion Recognition from Facial Thermal Images [PDF] 摘要

64. Fully-Automated Liver Tumor Localization and Characterization from Multi-Phase MR Volumes Using Key-Slice ROI Parsing: A Physician-Inspired Approach [PDF] 摘要

65. Using Computer Vision to Automate Hand Detection and Tracking of Surgeon Movements in Videos of Open Surgery [PDF] 摘要

66. MiniVLM: A Smaller and Faster Vision-Language Model [PDF] 摘要

67. Human Pose Transfer by Adaptive Hierarchical Deformation [PDF] 摘要

68. Assessing The Importance Of Colours For CNNs In Object Recognition [PDF] 摘要

69. PAIRS AutoGeo: an Automated Machine Learning Framework for Massive Geospatial Data [PDF] 摘要

70. AMINN: Autoencoder-based Multiple Instance Neural Network for Outcome Prediction of Multifocal Liver Metastases [PDF] 摘要

71. Spectral Unmixing With Multinomial Mixture Kernel and Wasserstein Generative Adversarial Loss [PDF] 摘要

72. LiveChess2FEN: a Framework for Classifying Chess Pieces based on CNNs [PDF] 摘要

73. Multi-Scale Cascading Network with Compact Feature Learning for RGB-Infrared Person Re-Identification [PDF] 摘要

74. High Order Local Directional Pattern Based Pyramidal Multi-structure for Robust Face Recognition [PDF] 摘要

75. Alpha-Refine: Boosting Tracking Performance by Precise Bounding Box Estimation [PDF] 摘要

76. Fine-grained Classification via Categorical Memory Networks [PDF] 摘要

77. DETR for Pedestrian Detection [PDF] 摘要

78. Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces [PDF] 摘要

79. An Overview of Depth Cameras and Range Scanners Based on Time-of-Flight Technologies [PDF] 摘要

80. Fusion of Range and Stereo Data for High-Resolution Scene-Modeling [PDF] 摘要

81. Anomaly detection through latent space restoration using vector-quantized variational autoencoders [PDF] 摘要

82. Periocular in the Wild Embedding Learning with Cross-Modal Consistent Knowledge Distillation [PDF] 摘要

83. Computer Vision and Normalizing Flow Based Defect Detection [PDF] 摘要

84. Multimodal In-bed Pose and Shape Estimation under the Blankets [PDF] 摘要

85. PoP-Net: Pose over Parts Network for Multi-Person 3D Pose Estimation from a Depth Image [PDF] 摘要

86. Mask Guided Matting via Progressive Refinement Network [PDF] 摘要

87. Teacher-Student Asynchronous Learning with Multi-Source Consistency for Facial Landmark Detection [PDF] 摘要

88. D$^2$IM-Net: Learning Detail Disentangled Implicit Fields from Single Images [PDF] 摘要

89. Street-view Panoramic Video Synthesis from a Single Satellite Image [PDF] 摘要

90. Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes [PDF] 摘要

91. Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints [PDF] 摘要

92. Biomechanical modelling of brain atrophy through deep learning [PDF] 摘要

93. Movie Summarization via Sparse Graph Construction [PDF] 摘要

94. Phase Retrieval with Holography and Untrained Priors: Tackling the Challenges of Low-Photon Nanoscale Imaging [PDF] 摘要

95. Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction [PDF] 摘要

96. IPN-V2 and OCTA-500: Methodology and Dataset for Retinal Image Segmentation [PDF] 摘要

97. Accurate Cell Segmentation in Digital Pathology Images via Attention Enforced Networks [PDF] 摘要

98. Multi-Domain Multi-Task Rehearsal for Lifelong Learning [PDF] 摘要

99. D-LEMA: Deep Learning Ensembles from Multiple Annotations -- Application to Skin Lesion Segmentation [PDF] 摘要

100. Pseudo Shots: Few-Shot Learning with Auxiliary Data [PDF] 摘要

101. Learning Contextual Causality from Time-consecutive Images [PDF] 摘要

102. Robust Segmentation of Optic Disc and Cup from Fundus Images Using Deep Neural Networks [PDF] 摘要

103. Leaking Sensitive Financial Accounting Data in Plain Sight using Deep Autoencoder Neural Networks [PDF] 摘要

104. CHS-Net: A Deep learning approach for hierarchical segmentation of COVID-19 infected CT images [PDF] 摘要

105. LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT [PDF] 摘要

106. Learn-Prune-Share for Lifelong Learning [PDF] 摘要

107. Attentional Biased Stochastic Gradient for Imbalanced Classification [PDF] 摘要

108. The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models [PDF] 摘要

109. Interactive Radiotherapy Target Delineation with 3D-Fused Context Propagation [PDF] 摘要

110. Delay Differential Neural Networks [PDF] 摘要

111. Knowledge Capture and Replay for Continual Learning [PDF] 摘要

112. Generative Adversarial Networks for Automatic Polyp Segmentation [PDF] 摘要

113. HI-Net: Hyperdense Inception 3D UNet for Brain Tumor Segmentation [PDF] 摘要

114. Sampling Training Data for Continual Learning Between Robots and the Cloud [PDF] 摘要

115. Learning Consistent Deep Generative Models from Sparse Data via Prediction Constraints [PDF] 摘要

阅读全文 »