【arxiv论文】 Computation and Language 2020-10-07

发表于 2020-10-07 更新于 2020-10-08 分类于 arxiv ， CL 151k 4:12

目录

1. Keep CALM and Explore: Language Models for Action Generation in Text-based Games [PDF] 摘要

2. COD3S: Diverse Generation with Discrete Semantic Signatures [PDF] 摘要

3. LOGAN: Local Group Bias Detection by Clustering [PDF] 摘要

4. A Novel Challenge Set for Hebrew Morphological Disambiguation and Diacritics Restoration [PDF] 摘要

5. Robustness and Reliability of Gender Bias Assessment in WordEmbeddings: The Role of Base Pairs [PDF] 摘要

6. Semantic Evaluation for Text-to-SQL with Distilled Test Suites [PDF] 摘要

7. PRover: Proof Generation for Interpretable Reasoning over Rules [PDF] 摘要

8. QADiscourse -- Discourse Relations as QA Pairs: Representation, Crowdsourcing and Baselines [PDF] 摘要

9. Intrinsic Probing through Dimension Selection [PDF] 摘要

10. Swiss Parliaments Corpus, an Automatically Aligned Swiss German Speech to Standard German Text Corpus [PDF] 摘要

11. Learning to Ignore: Long Document Coreference with Bounded Memory Neural Networks [PDF] 摘要

12. Textual Supervision for Visually Grounded Spoken Language Understanding [PDF] 摘要

13. Tackling the Low-resource Challenge for Canonical Segmentation [PDF] 摘要

14. COSMIC: COmmonSense knowledge for eMotion Identification in Conversations [PDF] 摘要

15. An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks [PDF] 摘要

16. A Multi-Task Incremental Learning Framework with Category Name Embedding for Aspect-Category Sentiment Analysis [PDF] 摘要

17. Stepwise Extractive Summarization and Planning with Structured Transformers [PDF] 摘要

18. Towards Coalgebras in Stylometry [PDF] 摘要

19. Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation [PDF] 摘要

20. Aspect Sentiment Classification with Aspect-Specific Opinion Spans [PDF] 摘要

21. Analyzing Individual Neurons in Pre-trained Language Models [PDF] 摘要

22. SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling [PDF] 摘要

23. BERT Knows Punta Cana is not just beautiful, it's gorgeous: Ranking Scalar Adjectives with Contextualised Representations [PDF] 摘要

24. Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder [PDF] 摘要

25. Incorporating Behavioral Hypotheses for Query Generation [PDF] 摘要

26. Automatic Metaphor Interpretation Using Word Embeddings [PDF] 摘要

27. Detecting Attackable Sentences in Arguments [PDF] 摘要

28. Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysis [PDF] 摘要

29. Extracting Implicitly Asserted Propositions in Argumentation [PDF] 摘要

30. If beam search is the answer, what was the question? [PDF] 摘要

31. Context Modeling with Evidence Filter for Multiple Choice Question Answering [PDF] 摘要

32. On the Sub-Layer Functionalities of Transformer Decoder [PDF] 摘要

33. On the Sparsity of Neural Machine Translation Models [PDF] 摘要

34. Neural Speech Synthesis for Estonian [PDF] 摘要

35. On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers [PDF] 摘要

36. Position-Aware Tagging for Aspect Sentiment Triplet Extraction [PDF] 摘要

37. DaNetQA: a yes/no Question Answering Dataset for the Russian Language [PDF] 摘要

38. Converting the Point of View of Messages Spoken to Virtual Assistants [PDF] 摘要

39. Embedding Words in Non-Vector Space with Unsupervised Graph Learning [PDF] 摘要

40. Semantically Driven Sentence Fusion: Modeling and Evaluation [PDF] 摘要

41. Scene Graph Modification Based on Natural Language Commands [PDF] 摘要

42. CoRefi: A Crowd Sourcing Suite for Coreference Annotation [PDF] 摘要

43. Dissecting Span Identification Tasks with Performance Prediction [PDF] 摘要

44. Knowing What You Know: Calibrating Dialogue Belief State Distributions via Ensembles [PDF] 摘要

45. Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start [PDF] 摘要

46. The Multilingual Amazon Reviews Corpus [PDF] 摘要

47. Does the Objective Matter? Comparing Training Objectives for Pronoun Resolution [PDF] 摘要

48. StyleDGPT: Stylized Response Generation with Pre-trained Language Models [PDF] 摘要

49. SupMMD: A Sentence Importance Model for Extractive Summarization using Maximum Mean Discrepancy [PDF] 摘要

50. Cross-Lingual Text Classification with Minimal Resources by Transferring a Sparse Teacher [PDF] 摘要

51. LEGAL-BERT: The Muppets straight out of Law School [PDF] 摘要

52. PolicyQA: A Reading Comprehension Dataset for Privacy Policies [PDF] 摘要

53. Data Rejuvenation: Exploiting Inactive Training Examples for Neural Machine Translation [PDF] 摘要

54. Please Mind the Root: Decoding Arborescences for Dependency Parsing [PDF] 摘要

55. Do Explicit Alignments Robustly Improve Multilingual Encoders? [PDF] 摘要

56. An Empirical Study of Tokenization Strategies for Various Korean NLP Tasks [PDF] 摘要

57. Multi-task Learning for Multilingual Neural Machine Translation [PDF] 摘要

58. Investigating African-American Vernacular English in Transformer-Based Text Generation [PDF] 摘要

59. Efficient Meta Lifelong-Learning with Limited Memory [PDF] 摘要

60. GRUEN for Evaluating Linguistic Quality of Generated Text [PDF] 摘要

61. Joint Turn and Dialogue level User Satisfaction Estimation on Multi-Domain Conversations [PDF] 摘要

62. Help! Need Advice on Identifying Advice [PDF] 摘要

63. Dynamic Semantic Matching and Aggregation Network for Few-shot Intent Detection [PDF] 摘要

64. Pretrained Language Model Embryology: The Birth of ALBERT [PDF] 摘要

65. Iterative Domain-Repaired Back-Translation [PDF] 摘要

66. Are Words Commensurate with Actions? Quantifying Commitment to a Cause from Online Public Messaging [PDF] 摘要

67. On the Branching Bias of Syntax Extracted from Pre-trained Language Models [PDF] 摘要

68. Multi-Fact Correction in Abstractive Text Summarization [PDF] 摘要

69. Modeling Preconditions in Text with a Crowd-sourced Dataset [PDF] 摘要

70. UNQOVERing Stereotyping Biases via Underspecified Questions [PDF] 摘要

71. On the Role of Supervision in Unsupervised Constituency Parsing [PDF] 摘要

72. Efficient Inference For Neural Machine Translation [PDF] 摘要

73. Efficient One-Pass End-to-End Entity Linking for Questions [PDF] 摘要

74. Adversarial Grammatical Error Correction [PDF] 摘要

75. Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning [PDF] 摘要

76. Guiding Attention for Self-Supervised Learning with Transformers [PDF] 摘要

77. Plan Optimization to Bilingual Dictionary Induction for Low-Resource Language Families [PDF] 摘要

78. A Generalized Constraint Approach to Bilingual Dictionary Induction for Low-Resource Language Families [PDF] 摘要

79. Mixup-Transfomer: Dynamic Data Augmentation for NLP Tasks [PDF] 摘要

80. Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning [PDF] 摘要

81. Fine-Grained Grounding for Multimodal Speech Recognition [PDF] 摘要

82. Improving Neural Topic Models using Knowledge Distillation [PDF] 摘要

83. Investigating representations of verb bias in neural language models [PDF] 摘要

84. Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning [PDF] 摘要

85. Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages [PDF] 摘要

86. Inference Strategies for Machine Translation with Conditional Masking [PDF] 摘要

87. We Don't Speak the Same Language: Interpreting Polarization through Machine Translation [PDF] 摘要

88. CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation [PDF] 摘要

89. InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective [PDF] 摘要

90. SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup [PDF] 摘要

91. Sentiment Analysis for Reinforcement Learning [PDF] 摘要

92. KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation [PDF] 摘要

93. Conversational Document Prediction to Assist Customer Care Agents [PDF] 摘要

94. PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation [PDF] 摘要

95. Semi-Supervised Speech-Language Joint Pre-Training for Spoken Language Understanding [PDF] 摘要

96. Effects of Naturalistic Variation in Goal-Oriented Dialog [PDF] 摘要

97. An Ensemble Approach to Automatic Structuring of Radiology Reports [PDF] 摘要

98. MedFilter: Extracting Task-relevant Utterances from Medical Dialogue through Integration of Discourse Structure and Ontological Knowledge [PDF] 摘要

99. Acrostic Poem Generation [PDF] 摘要

100. Learning to Generalize for Sequential Decision Making [PDF] 摘要

101. Joint Semantics and Data-Driven Path Representation for Knowledge Graph Inference [PDF] 摘要

102. Finding the Evidence: Localization-aware Answer Prediction for Text Visual Question Answering [PDF] 摘要

103. Unsupervised Hierarchical Concept Learning [PDF] 摘要

104. A Unified Deep Learning Framework for Short-Duration Speaker Verification in Adverse Environments [PDF] 摘要

105. Learning Visual-Semantic Embeddings for Reporting Abnormal Findings on Chest X-rays [PDF] 摘要

106. Identifying Spurious Correlations for Robust Text Classification [PDF] 摘要

107. The Sequence-to-Sequence Baseline for the Voice Conversion Challenge 2020: Cascading ASR and TTS [PDF] 摘要

108. ERFit: Entropic Regression Fit Matlab Package, for Data-Driven System Identification of Underlying Dynamic Equations [PDF] 摘要

阅读全文 »

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

发表于 2020-10-06 分类于 arxiv ， CV 49k 1:21

目录

1. Mind the Pad -- CNNs can Develop Blind Spots [PDF] 摘要

2. Ego-Motion Alignment from Face Detections for Collaborative Augmented Reality [PDF] 摘要

3. TrueImage: A Machine Learning Algorithm to Improve the Quality of Telehealth Photos [PDF] 摘要

4. Non-anchor-based vehicle detection for traffic surveillance using bounding ellipses [PDF] 摘要

5. Probabilistic 3D surface reconstruction from sparse MRI information [PDF] 摘要

6. BalaGAN: Image Translation Between Imbalanced Domains via Cross-Modal Transfer [PDF] 摘要

7. A Novel Actor Dual-Critic Model for Remote Sensing Image Captioning [PDF] 摘要

8. EqCo: Equivalent Rules for Self-supervised Contrastive Learning [PDF] 摘要

9. Automatic label correction based on CCESD [PDF] 摘要

10. Best Buddies Registration for Point Clouds [PDF] 摘要

11. Semantics through Time: Semi-supervised Segmentation of Aerial Videos with Iterative Label Propagation [PDF] 摘要

12. Joint Scene and Object Tracking for Cost-Effective Augmented Reality Assisted Patient Positioning in Radiation Therapy [PDF] 摘要

13. Joint Pruning & Quantization for Extremely Sparse Neural Networks [PDF] 摘要

14. MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Maps [PDF] 摘要

15. Monocular Rotational Odometry with Incremental Rotation Averaging and Loop Closure [PDF] 摘要

16. AE-Netv2: Optimization of Image Fusion Efficiency and Network Architecture [PDF] 摘要

17. Depth-wise layering of 3d images using dense depth maps: a threshold based approach [PDF] 摘要

18. Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance [PDF] 摘要

19. Painting Outside as Inside: Edge Guided Image Outpainting via Bidirectional Rearrangement with Step-By-Step Learning [PDF] 摘要

20. Long-tailed Recognition by Routing Diverse Distribution-Aware Experts [PDF] 摘要

21. MetaPhys: Unsupervised Few-Shot Adaptation for Non-Contact Physiological Measurement [PDF] 摘要

22. A Review of Vegetation Encroachment Detection in Power Transmission Lines using Optical Sensing Satellite Imagery [PDF] 摘要

23. Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratch [PDF] 摘要

24. Attention Guided Semantic Relationship Parsing for Visual Question Answering [PDF] 摘要

25. MetaDetect: Uncertainty Quantification and Prediction Quality Estimates for Object Detection [PDF] 摘要

26. Generating Gameplay-Relevant Art Assets with Transfer Learning [PDF] 摘要

27. Learning Complete 3D Morphable Face Models from Images and Videos [PDF] 摘要

28. Multi-Resolution Fusion and Multi-scale Input Priors Based Crowd Counting [PDF] 摘要

29. Supporting large-scale image recognition with out-of-domain samples [PDF] 摘要

30. Unknown Presentation Attack Detection against Rational Attackers [PDF] 摘要

31. The FaceChannelS: Strike of the Sequences for the AffWild 2 Challenge [PDF] 摘要

32. Holistic static and animated 3D scene generation from diverse text descriptions [PDF] 摘要

33. Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting [PDF] 摘要

34. A Study for Universal Adversarial Attacks on Texture Recognition [PDF] 摘要

35. A New Mask R-CNN Based Method for Improved Landslide Detection [PDF] 摘要

36. Generalized Two-Dimensional Quaternion Principal Component Analysis with Weighting for Color Image Recognition [PDF] 摘要

37. MDReg-Net: Multi-resolution diffeomorphic image registration using fully convolutional networks with deep self-supervision [PDF] 摘要

38. LEGAN: Disentangled Manipulation of Directional Lighting and Facial Expressions by Leveraging Human Perceptual Judgements [PDF] 摘要

39. 3D Orientation Field Transform [PDF] 摘要

40. MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network [PDF] 摘要

41. Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments [PDF] 摘要

42. Adversarial and Natural Perturbations for General Robustness [PDF] 摘要

43. Actionet: An Interactive End-To-End Platform For Task-Based Data Collection And Augmentation In 3D Environment [PDF] 摘要

44. A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition [PDF] 摘要

45. End-to-End Training of CNN Ensembles for Person Re-Identification [PDF] 摘要

46. Gaussian Vector: An Efficient Solution for Facial Landmark Detection [PDF] 摘要

47. A simulation environment for drone cinematography [PDF] 摘要

48. Bounding Boxes Are All We Need: Street View Image Classification via Context Encoding of Detected Buildings [PDF] 摘要

49. Deep Convolutional Neural Network Based Facial Expression Recognition in the Wild [PDF] 摘要

50. Unsupervised Shadow Removal Using Target Consistency Generative Adversarial Network [PDF] 摘要

51. Generating the Cloud Motion Winds Field from Satellite Cloud Imagery Using Deep Learning Approach [PDF] 摘要

52. TCLNet: Learning to Locate Typhoon Center Using Deep Neural Network [PDF] 摘要

53. UCP: Uniform Channel Pruning for Deep Convolutional Neural Networks Compression and Acceleration [PDF] 摘要

54. 3D-Aided Data Augmentation for Robust Face Understanding [PDF] 摘要

55. Consensus Clustering with Unsupervised Representation Learning [PDF] 摘要

56. Nonconvex Regularization for Network Slimming:Compressing CNNs Even More [PDF] 摘要

57. A Deep Genetic Programming based Methodology for Art Media Classification Robust to Adversarial Perturbations [PDF] 摘要

58. Stuttering Speech Disfluency Prediction using Explainable Attribution Vectors of Facial Muscle Movements [PDF] 摘要

59. Video Saliency Detection with Domain Adaption using Hierarchical Gradient Reversal Layers [PDF] 摘要

60. Artificial Intelligence Enabled Traffic Monitoring System [PDF] 摘要

61. Leveraging Tacit Information Embedded in CNN Layers for Visual Tracking [PDF] 摘要

62. Background Adaptive Faster R-CNN for Semi-Supervised Convolutional Object Detection of Threats in X-Ray Images [PDF] 摘要

63. Semantic MapNet: Building Allocentric SemanticMaps and Representations from Egocentric Views [PDF] 摘要

64. Adaptive Neural Layer for Globally Filtered Segmentation [PDF] 摘要

65. Machine learning approach to force reconstruction in photoelastic materials [PDF] 摘要

66. MM-Hand: 3D-Aware Multi-Modal Guided Hand Generative Network for 3D Hand Pose Synthesis [PDF] 摘要

67. Semantics-Guided Clustering with Deep Progressive Learning for Semi-Supervised Person Re-identification [PDF] 摘要

68. Medical Imaging and Computational Image Analysis in COVID-19 Diagnosis: A Review [PDF] 摘要

69. i-DenseNets [PDF] 摘要

70. Automatic Deep Learning System for COVID-19 Infection Quantification in chest CT [PDF] 摘要

71. Machine Learning and Computer Vision Techniques to Predict Thermal Properties of Particulate Composites [PDF] 摘要

72. A Comparative Study of Existing and New Deep Learning Methods for Detecting Knee Injuries using the MRNet Dataset [PDF] 摘要

73. Unsupervised Region-based Anomaly Detection in Brain MRI with Adversarial Image Inpainting [PDF] 摘要

74. Test-time Unsupervised Domain Adaptation [PDF] 摘要

75. Quantifying Statistical Significance of Neural Network Representation-Driven Hypotheses by Selective Inference [PDF] 摘要

76. DCT-SNN: Using DCT to Distribute Spatial Information over Time for Learning Low-Latency Spiking Neural Networks [PDF] 摘要

77. Towards Generalized and Distributed Privacy-Preserving Representation Learning [PDF] 摘要

78. Photon-Driven Neural Path Guiding [PDF] 摘要

79. OLALA: Object-Level Active Learning Based Layout Annotation [PDF] 摘要

80. Learning Manifold Implicitly via Explicit Heat-Kernel Learning [PDF] 摘要

81. Lipschitz Bounded Equilibrium Networks [PDF] 摘要

82. Surface Agnostic Metrics for Cortical Volume Segmentation and Regression [PDF] 摘要

83. KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation [PDF] 摘要

84. AFN: Attentional Feedback Network based 3D Terrain Super-Resolution [PDF] 摘要

85. AIFNet: Automatic Vascular Function Estimation for Perfusion Analysis Using Deep Learning [PDF] 摘要

86. Collaborative Tracking and Capture of Aerial Object using UAVs [PDF] 摘要

87. Facial gesture interfaces for expression and communication [PDF] 摘要

88. Towards Cross-modality Medical Image Segmentation with Online Mutual Knowledge Distillation [PDF] 摘要

89. Async-RED: A Provably Convergent Asynchronous Block Parallel Stochastic Method using Deep Denoising Priors [PDF] 摘要

90. autoTICI: Automatic Brain Tissue Reperfusion Scoring on 2D DSA Images of Acute Ischemic Stroke Patients [PDF] 摘要

91. Unsupervised Monocular Depth Estimation for Night-time Images using Adversarial Domain Feature Adaptation [PDF] 摘要

92. COVID-19 Classification of X-ray Images Using Deep Neural Networks [PDF] 摘要

93. WeMix: How to Better Utilize Data Augmentation [PDF] 摘要

94. CorrAttack: Black-box Adversarial Attack with Structured Search [PDF] 摘要

95. Deep Expectation-Maximization for Semi-Supervised Lung Cancer Screening [PDF] 摘要

阅读全文 »

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

发表于 2020-10-06 分类于 arxiv ， CL 132k 3:39

目录

1. Self-training Improves Pre-training for Natural Language Understanding [PDF] 摘要

2. Pareto Probing: Trading Off Accuracy for Complexity [PDF] 摘要

3. Assessing the Helpfulness of Learning Materials with Inference-Based Learner-Like Agent [PDF] 摘要

4. Speakers Fill Lexical Semantic Gaps with Context [PDF] 摘要

5. A Streaming Approach For Efficient Batched Beam Search [PDF] 摘要

6. Knowledge Association with Hyperbolic Knowledge Graph Embeddings [PDF] 摘要

7. Viable Threat on News Reading: Generating Biased News Using Natural Language Models [PDF] 摘要

8. PublishInCovid19 at WNUT 2020 Shared Task-1: Entity Recognition in Wet Lab Protocols using Structured Learning Ensemble and Contextualised Embeddings [PDF] 摘要

9. Lifelong Language Knowledge Distillation [PDF] 摘要

10. Explaining The Efficacy of Counterfactually-Augmented Data [PDF] 摘要

11. Gauravarora@HASOC-Dravidian-CodeMix-FIRE2020: Pre-training ULMFiT on Synthetically Generated Code-Mixed Data for Hate Speech Detection [PDF] 摘要

12. The Grammar of Emergent Languages [PDF] 摘要

13. Modulated Fusion using Transformer for Linguistic-Acoustic Emotion Recognition [PDF] 摘要

14. A Fully Hyperbolic Neural Model for Hierarchical Multi-Class Classification [PDF] 摘要

15. Zero-Shot Clinical Acronym Expansion with a Hierarchical Metadata-Based Latent Variable Model [PDF] 摘要

16. Gender prediction using limited Twitter Data [PDF] 摘要

17. Assessing Robustness of Text Classification through Maximal Safe Radius Computation [PDF] 摘要

18. X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset [PDF] 摘要

19. Learning from Context or Names? An Empirical Study on Neural Relation Extraction [PDF] 摘要

20. Exploiting Unsupervised Data for Emotion Recognition in Conversations [PDF] 摘要

21. Dynamic Anticipation and Completion for Multi-Hop Reasoning over Sparse Knowledge Graph [PDF] 摘要

22. Exploring Semantic Capacity of Terms [PDF] 摘要

23. PUM at SemEval-2020 Task 12: Aggregation of Transformer-based models' features for offensive language recognition [PDF] 摘要

24. Regularizing Dialogue Generation by Imitating Implicit Scenarios [PDF] 摘要

25. A Pilot Study of Text-to-SQL Semantic Parsing for Vietnamese [PDF] 摘要

26. "LazImpa": Lazy and Impatient neural agents learn to communicate efficiently [PDF] 摘要

27. Linguistic Profiling of a Neural Language Model [PDF] 摘要

28. Discern: Discourse-Aware Entailment Reasoning Network for Conversational Machine Reading [PDF] 摘要

29. On the Frailty of Universal POS Tags for Neural UD Parsers [PDF] 摘要

30. GenAug: Data Augmentation for Finetuning Text Generators [PDF] 摘要

31. Pruning Redundant Mappings in Transformer Models via Spectral-Normalized Identity Prior [PDF] 摘要

32. Corpora Evaluation and System Bias Detection in Multi-document Summarization [PDF] 摘要

33. Unsupervised Reference-Free Summary Quality Evaluation via Contrastive Learning [PDF] 摘要

34. Improving AMR Parsing with Sequence-to-Sequence Pre-training [PDF] 摘要

35. Second-Order NLP Adversarial Examples [PDF] 摘要

36. On the Effects of Knowledge-Augmented Data in Word Embeddings [PDF] 摘要

37. Effective Unsupervised Domain Adaptation with Adversarially Trained Language Models [PDF] 摘要

38. Transformer-Based Neural Text Generation with Syntactic Guidance [PDF] 摘要

39. MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning [PDF] 摘要

40. STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation [PDF] 摘要

41. Reading Comprehension as Natural Language Inference: A Semantic Analysis [PDF] 摘要

42. On Losses for Modern Language Models [PDF] 摘要

43. DLGNet-Task: An End-to-end Neural Network Framework for Modeling Multi-turn Multi-domain Task-Oriented Dialogue [PDF] 摘要

44. Weakly-supervised Fine-grained Event Recognition on Social Media Texts for Disaster Management [PDF] 摘要

45. Optimal Neural Program Synthesis from Multimodal Specifications [PDF] 摘要

46. Local Additivity Based Data Augmentation for Semi-supervised NER [PDF] 摘要

47. Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization [PDF] 摘要

48. Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation [PDF] 摘要

49. Generating Dialogue Responses from a Semantic Latent Space [PDF] 摘要

50. Inquisitive Question Generation for High Level Text Comprehension [PDF] 摘要

51. An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels [PDF] 摘要

52. Meta Sequence Learning and Its Applications [PDF] 摘要

53. When in Doubt, Ask: Generating Answerable and Unanswerable Questions, Unsupervised [PDF] 摘要

54. Adversarial Attack and Defense of Structured Prediction Models [PDF] 摘要

55. Reverse Operation based Data Augmentation for Solving Math Word Problems [PDF] 摘要

56. Leveraging Multilingual News Websites for Building a Kurdish Parallel Corpus [PDF] 摘要

57. A Survey of Unsupervised Dependency Parsing [PDF] 摘要

58. A Multi-task Learning Framework for Opinion Triplet Extraction [PDF] 摘要

59. Multi-turn Response Selection using Dialogue Dependency Relations [PDF] 摘要

60. Explaining Deep Neural Networks [PDF] 摘要

61. Dialogue Generation on Infrequent Sentence Functions via Structured Meta-Learning [PDF] 摘要

62. Paragraph-Level Commonsense Transformers with Recurrent Memory [PDF] 摘要

63. Knowledge-Enhanced Personalized Review Generation with Capsule Graph Neural Network [PDF] 摘要

64. Tell Me How to Ask Again: Question Data Augmentation with Controllable Rewriting in Continuous Space [PDF] 摘要

65. Sentence Constituent-Aware Aspect-Category Sentiment Analysis with Graph Attention Networks [PDF] 摘要

66. MIME: MIMicking Emotions for Empathetic Response Generation [PDF] 摘要

67. GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems [PDF] 摘要

68. Aspect-Based Sentiment Analysis in Education Domain [PDF] 摘要

69. Semantic Role Labeling Guided Multi-turn Dialogue ReWriter [PDF] 摘要

70. A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples [PDF] 摘要

71. Personality Trait Detection Using Bagged SVM over BERT Word Embedding Ensembles [PDF] 摘要

72. Unsupervised Cross-lingual Image Captioning [PDF] 摘要

73. Towards Interpretable Reasoning over Paragraph Effects in Situation [PDF] 摘要

74. Partially-Aligned Data-to-Text Generation with Distant Supervision [PDF] 摘要

75. Multilevel Text Alignment with Cross-Document Attention [PDF] 摘要

76. Mining Knowledge for Natural Language Inference from Wikipedia Categories [PDF] 摘要

77. AI pptX: Robust Continuous Learning for Document Generation with AI Insights [PDF] 摘要

78. Multi-domain Clinical Natural Language Processing with MedCAT: the Medical Concept Annotation Toolkit [PDF] 摘要

79. Automatic Extraction of Rules Governing Morphological Agreement [PDF] 摘要

80. Cost-effective Selection of Pretraining Data: A Case Study of Pretraining BERT on Social Media [PDF] 摘要

81. Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems [PDF] 摘要

82. A Spherical Hidden Markov Model for Semantics-Rich Human Mobility Modeling [PDF] 摘要

83. Improving Device Directedness Classification of Utterances with Semantic Lexical Features [PDF] 摘要

84. PMI-Masking: Principled masking of correlated spans [PDF] 摘要

85. Multi-microphone Complex Spectral Mapping for Utterance-wise and Continuous Speaker Separation [PDF] 摘要

86. Deep Just-In-Time Inconsistency Detection Between Comments and Source Code [PDF] 摘要

87. Holistic static and animated 3D scene generation from diverse text descriptions [PDF] 摘要

88. NLP Service APIs and Models for Efficient Registration of New Clients [PDF] 摘要

89. Reproducible Science with \LaTeX [PDF] 摘要

90. SumGNN: Multi-typed Drug Interaction Prediction via Efficient Knowledge Graph Summarization [PDF] 摘要

91. Code to Comment "Translation": Data, Metrics, Baselining & Evaluation [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-10-05

发表于 2020-10-05 分类于 arxiv ， CV 98k 2:44

目录

1. Embedded Systems and Computer Vision Techniques utilized in Spray Painting Robots: A Review [PDF] 摘要

2. Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation [PDF] 摘要

3. AIM 2020 Challenge on Image Extreme Inpainting [PDF] 摘要

4. Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks [PDF] 摘要

5. Efficient Colon Cancer Grading with Graph Neural Networks [PDF] 摘要

6. Pre-Training by Completing Point Clouds [PDF] 摘要

7. Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus [PDF] 摘要

8. Homography Estimation with Convolutional Neural Networks Under Conditions of Variance [PDF] 摘要

9. Hard Negative Mixing for Contrastive Learning [PDF] 摘要

10. DecAug: Augmenting HOI Detection via Decomposition [PDF] 摘要

11. DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection [PDF] 摘要

12. RDCNet: Instance segmentation with a minimalist recurrent residual network [PDF] 摘要

13. Uncertainty driven probabilistic voxel selection for image registration [PDF] 摘要

14. Group Equivariant Stand-Alone Self-Attention For Vision [PDF] 摘要

15. Taking Modality-free Human Identification as Zero-shot Learning [PDF] 摘要

16. RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval [PDF] 摘要

17. DOTS: Decoupling Operation and Topology in Differentiable Architecture Search [PDF] 摘要

18. MGD-GAN: Text-to-Pedestrian generation through Multi-Grained Discrimination [PDF] 摘要

19. Image-based underwater 3D reconstruction for Cultural Heritage: from image collection to 3D. Critical steps and considerations [PDF] 摘要

20. Multiple Infrared Small Targets Detection based on Hierarchical Maximal Entropy Random Walk [PDF] 摘要

21. Self-Play Reinforcement Learning for Fast Image Retargeting [PDF] 摘要

22. OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets [PDF] 摘要

23. Remote Sensing Image Scene Classification with Self-Supervised Paradigm under Limited Labeled Samples [PDF] 摘要

24. Rotated Ring, Radial and Depth Wise Separable Radial Convolutions [PDF] 摘要

25. Weight and Gradient Centralization in Deep Neural Networks [PDF] 摘要

26. CAPTION: Correction by Analyses, POS-Tagging and Interpretation of Objects using only Nouns [PDF] 摘要

27. Discriminative and Generative Models for Anatomical Shape Analysison Point Clouds with Deep Neural Networks [PDF] 摘要

28. Deep4Air: A Novel Deep Learning Framework for Airport Airside Surveillance [PDF] 摘要

29. PrognoseNet: A Generative Probabilistic Framework for Multimodal Position Prediction given Context Information [PDF] 摘要

30. Block-wise Image Transformation with Secret Key for Adversarially Robust Defense [PDF] 摘要

31. Online Knowledge Distillation via Multi-branch Diversity Enhancement [PDF] 摘要

32. A Parallel Down-Up Fusion Network for Salient Object Detection in Optical Remote Sensing Images [PDF] 摘要

33. Deep Learning for Earth Image Segmentation based on Imperfect Polyline Labels with Annotation Errors [PDF] 摘要

34. Contrastive Learning of Medical Visual Representations from Paired Images and Text [PDF] 摘要

35. Smart-Inspect: Micro Scale Localization and Classification of Smartphone Glass Defects for Industrial Automation [PDF] 摘要

36. Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer [PDF] 摘要

37. LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion [PDF] 摘要

38. Using ROC and Unlabeled Data for Increasing Low-Shot Transfer Learning Classification Accuracy [PDF] 摘要

39. Deep Reinforcement Learning with Mixed Convolutional Network [PDF] 摘要

40. Binary Neural Networks for Memory-Efficient and Effective Visual Place Recognition in Changing Environments [PDF] 摘要

41. Learned Dual-View Reflection Removal [PDF] 摘要

42. Active Learning for Bayesian 3D Hand Pose Estimation [PDF] 摘要

43. Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation [PDF] 摘要

44. Multiscale Detection of Cancerous Tissue in High Resolution Slide Scans [PDF] 摘要

45. StreamSoNG: A Soft Streaming Classification Approach [PDF] 摘要

46. Efficient Image Super-Resolution Using Pixel Attention [PDF] 摘要

47. Attention-Based Clustering: Learning a Kernel from Context [PDF] 摘要

48. Encoded Prior Sliced Wasserstein AutoEncoder for learning latent manifold representations [PDF] 摘要

49. Understanding the Predictability of Gesture Parameters from Speech and their Perceptual Importance [PDF] 摘要

50. An Empirical Study of DNNs Robustification Inefficacy in Protecting Visual Recommenders [PDF] 摘要

51. A Deep-Unfolded Reference-Based RPCA Network For Video Foreground-Background Separation [PDF] 摘要

52. Tubular Shape Aware Data Generation for Semantic Segmentation in Medical Imaging [PDF] 摘要

53. Weight Encode Reconstruction Network for Computed Tomography in a Semi-Case-Wise and Learning-Based Way [PDF] 摘要

54. Morphological segmentation of hyperspectral images [PDF] 摘要

55. Continuous close-range 3D object pose estimation [PDF] 摘要

56. Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds [PDF] 摘要

57. Explainable Online Validation of Machine Learning Models for Practical Applications [PDF] 摘要

58. Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning [PDF] 摘要

59. Cell Complex Neural Networks [PDF] 摘要

60. BCNN: A Binary CNN with All Matrix Ops Quantized to 1 Bit Precision [PDF] 摘要

61. Implicit Rank-Minimizing Autoencoder [PDF] 摘要

62. VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models [PDF] 摘要

63. Tabular GANs for uneven distribution [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-10-05

发表于 2020-10-05 分类于 arxiv ， CL 44k 1:13

目录

1. Cross-Lingual Transfer Learning for Complex Word Identification [PDF] 摘要

2. Multi-Modal Open-Domain Dialogue [PDF] 摘要

3. HUMAN: Hierarchical Universal Modular ANnotator [PDF] 摘要

4. Syntax Representation in Word Embeddings and Neural Networks -- A Survey [PDF] 摘要

5. Long-Tail Zero and Few-Shot Learning via Contrastive Pretraining on and for Small Data [PDF] 摘要

6. LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention [PDF] 摘要

7. Unsupervised Text Style Transfer with Padded Masked Language Models [PDF] 摘要

8. TeRo: A Time-aware Knowledge Graph Embedding via Temporal Rotation [PDF] 摘要

9. MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale [PDF] 摘要

10. Continual Learning for Natural Language Generation in Task-oriented Dialog Systems [PDF] 摘要

11. Autoregressive Entity Retrieval [PDF] 摘要

12. SST-BERT at SemEval-2020 Task 1: Semantic Shift Tracing by Clustering in BERT-based Embedding Spaces [PDF] 摘要

13. Which *BERT? A Survey Organizing Contextualized Encoders [PDF] 摘要

14. MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models [PDF] 摘要

15. JAKET: Joint Pre-training of Knowledge Graph and Language Understanding [PDF] 摘要

16. An Empirical Investigation Towards Efficient Multi-Domain Language Model Pre-training [PDF] 摘要

17. Enhancing Fine-grained Sentiment Classification Exploiting Local Context Embedding [PDF] 摘要

18. Enriching Word Embeddings with Temporal and Spatial Information [PDF] 摘要

19. STIL -- Simultaneous Slot Filling, Translation, Intent Classification, and Language Identification: Initial Results using mBART on MultiATIS++ [PDF] 摘要

20. A Survey of the State of Explainable AI for Natural Language Processing [PDF] 摘要

21. Nearest Neighbor Machine Translation [PDF] 摘要

22. How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds [PDF] 摘要

23. Beyond The Text: Analysis of Privacy Statements through Syntactic and Semantic Role Labeling [PDF] 摘要

24. Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding [PDF] 摘要

25. Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers [PDF] 摘要

26. Predicting User Engagement Status for Online Evaluation of Intelligent Assistants [PDF] 摘要

27. Discontinuous Constituent Parsing as Sequence Labeling [PDF] 摘要

28. Building Large Lexicalized Ontologies from Text: a Use Case in Automatic Indexing of Biotechnology Patents [PDF] 摘要

29. Contrastive Learning of Medical Visual Representations from Paired Images and Text [PDF] 摘要

30. Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer [PDF] 摘要

31. Evaluating a Generative Adversarial Framework for Information Retrieval [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-10-02

发表于 2020-10-02 分类于 arxiv ， CV 72k 2:01

目录

1. DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization [PDF] 摘要

2. A Multi-modal Machine Learning Approach and Toolkit to Automate Recognition of Early Stages of Dementia among British Sign Language Users [PDF] 摘要

3. Neural encoding with visual attention [PDF] 摘要

4. Linguistic Structure Guided Context Modeling for Referring Image Segmentation [PDF] 摘要

5. Referring Image Segmentation via Cross-Modal Progressive Comprehension [PDF] 摘要

6. Few-Shot Classification By Few-Iteration Meta-Learning [PDF] 摘要

7. An Ultra Lightweight CNN for Low Resource Circuit Component Recognition [PDF] 摘要

8. Mini-DDSM: Mammography-based Automatic Age Estimation [PDF] 摘要

9. From Handcrafted to Deep Features for Pedestrian Detection: A Survey [PDF] 摘要

10. X-Fields: Implicit Neural View-, Light- and Time-Image Interpolation [PDF] 摘要

11. DeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation [PDF] 摘要

12. Answer-Driven Visual State Estimator for Goal-Oriented Visual Dialogue [PDF] 摘要

13. Meta-Consolidation for Continual Learning [PDF] 摘要

14. Can You Trust Your Pose? Confidence Estimation in Visual Localization [PDF] 摘要

15. Training general representations for remote sensing using in-domain knowledge [PDF] 摘要

16. Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector [PDF] 摘要

17. Open-Set Hypothesis Transfer with Semantic Consistency [PDF] 摘要

18. Cost-Sensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images [PDF] 摘要

19. Action Units Recognition with Pairwise Deep Architecture [PDF] 摘要

20. RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation [PDF] 摘要

21. CariMe: Unpaired Caricature Generation with Multiple Exaggerations [PDF] 摘要

22. MLRSNet: A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene Understanding [PDF] 摘要

23. Quantum Annealing Approaches to the Phase-Unwrapping Problem in Synthetic-Aperture Radar Imaging [PDF] 摘要

24. Multi-label Classification of Common Bengali Handwritten Graphemes: Dataset and Challenge [PDF] 摘要

25. Deformable Kernel Convolutional Network for Video Extreme Super-Resolution [PDF] 摘要

26. Self-Guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs [PDF] 摘要

27. MaterialGAN: Reflectance Capture using a Generative SVBRDF Model [PDF] 摘要

28. The Importance of Balanced Data Sets: Analyzing a Vehicle Trajectory Prediction Model based on Neural Networks and Distributed Representations [PDF] 摘要

29. GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization [PDF] 摘要

30. Depth Estimation from Monocular Images and Sparse Radar Data [PDF] 摘要

31. DOT: Dynamic Object Tracking for Visual SLAM [PDF] 摘要

32. Utilizing Transfer Learning and a Customized Loss Function for Optic Disc Segmentation from Retinal Images [PDF] 摘要

33. ISAAQ -- Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attention [PDF] 摘要

34. Dynamic Facial Asset and Rig Generation from a Single Scan [PDF] 摘要

35. Understanding the Role of Adversarial Regularization in Supervised Learning [PDF] 摘要

36. Why Adversarial Interaction Creates Non-Homogeneous Patterns: A Pseudo-Reaction-Diffusion Model for Turing Instability [PDF] 摘要

37. Ray-based classification framework for high-dimensional data [PDF] 摘要

38. Physical Exercise Recommendation and Success Prediction Using Interconnected Recurrent Neural Networks [PDF] 摘要

39. Bag of Tricks for Adversarial Training [PDF] 摘要

40. GraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for Identifying COVID-19 on Chest X-rays [PDF] 摘要

41. Improving spatial domain based image formation through compressed sensing [PDF] 摘要

42. Deep Group-wise Variational Diffeomorphic Image Registration [PDF] 摘要

43. DEEPMIR: A DEEP convolutional neural network for differential detection of cerebral Microbleeds and IRon deposits in MRI [PDF] 摘要

44. Sampling possible reconstructions of undersampled acquisitions in MR imaging [PDF] 摘要

45. RG-Flow: A hierarchical and explainable flow model based on renormalization group and sparse prior [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-10-02

发表于 2020-10-02 分类于 arxiv ， CL 43k 1:11

目录

1. Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking [PDF] 摘要

2. Understanding tables with intermediate pre-training [PDF] 摘要

3. ISAAQ -- Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attention [PDF] 摘要

4. LiveQA: A Question Answering Dataset over Sports Live [PDF] 摘要

5. Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary [PDF] 摘要

6. Evaluating Multilingual BERT for Estonian [PDF] 摘要

7. A Survey on Explainability in Machine Reading Comprehension [PDF] 摘要

8. Citation Sentiment Changes Analysis [PDF] 摘要

9. How LSTM Encodes Syntax: Exploring Context Vectors and Semi-Quantization on Natural Text [PDF] 摘要

10. Detecting White Supremacist Hate Speech using Domain Specific Word Embedding with Deep Learning and BERT [PDF] 摘要

11. "Did you really mean what you said?" : Sarcasm Detection in Hindi-English Code-Mixed Data using Bilingual Word Embeddings [PDF] 摘要

12. CoLAKE: Contextualized Language and Knowledge Embedding [PDF] 摘要

13. Phonemer at WNUT-2020 Task 2: Sequence Classification Using COVID Twitter BERT and Bagging Ensemble Technique based on Plurality Voting [PDF] 摘要

14. Joint Persian Word Segmentation Correction and Zero-Width Non-Joiner Recognition Using BERT [PDF] 摘要

15. WeChat Neural Machine Translation Systems for WMT20 [PDF] 摘要

16. Improving Vietnamese Named Entity Recognition from Speech Using Word Capitalization and Punctuation Recovery Models [PDF] 摘要

17. A Compare Aggregate Transformer for Understanding Document-grounded Dialogue [PDF] 摘要

18. Examining the rhetorical capacities of neural language models [PDF] 摘要

19. Learning from Mistakes: Combining Ontologies via Self-Training for Dialogue Generation [PDF] 摘要

20. CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models [PDF] 摘要

21. Interactive Re-Fitting as a Technique for Improving Word Embeddings [PDF] 摘要

22. Multi-document Summarization with Maximal Marginal Relevance-guided Reinforcement Learning [PDF] 摘要

23. AbuseAnalyzer: Abuse Detection, Severity and Target Prediction for Gab Posts [PDF] 摘要

24. Linguistic Structure Guided Context Modeling for Referring Image Segmentation [PDF] 摘要

25. Referring Image Segmentation via Cross-Modal Progressive Comprehension [PDF] 摘要

26. AMUSED: An Annotation Framework of Multi-modal Social Media Data [PDF] 摘要

27. A survey on natural language processing (nlp) and applications in insurance [PDF] 摘要

28. RRF102: Meeting the TREC-COVID Challenge with a 100+ Runs Ensemble [PDF] 摘要

29. Dual Attention Model for Citation Recommendation [PDF] 摘要

30. Multi-label Classification of Common Bengali Handwritten Graphemes: Dataset and Challenge [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-09-30

发表于 2020-09-30 分类于 arxiv ， CV 88k 2:26

目录

1. Uncertainty Sets for Image Classifiers using Conformal Prediction [PDF] 摘要

2. Robust Detection of Objects under Periodic Motion with Gaussian Process Filtering [PDF] 摘要

3. Multi-View Consistency Loss for Improved Single-Image 3D Reconstruction of Clothed People [PDF] 摘要

4. A Survey on Deep Learning Techniques for Video Anomaly Detection [PDF] 摘要

5. Score-level Multi Cue Fusion for Sign Language Recognition [PDF] 摘要

6. Asymmetric Loss For Multi-Label Classification [PDF] 摘要

7. CoKe: Localized Contrastive Learning for Robust Keypoint Detection [PDF] 摘要

8. Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection [PDF] 摘要

9. Attentional Feature Fusion [PDF] 摘要

10. Fast Gravitational Approach for Rigid Point Set Registration with Ordinary Differential Equations [PDF] 摘要

11. Improving Interpretability for Computer-aided Diagnosis tools on Whole Slide Imaging with Multiple Instance Learning and Gradient-based Explanations [PDF] 摘要

12. MARA-Net: Single Image Deraining Network with Multi-level connection and Adaptive Regional Attention [PDF] 摘要

13. A Prototype-Based Generalized Zero-Shot Learning Framework for Hand Gesture Recognition [PDF] 摘要

14. Beneficial Perturbation Network for designing general adaptive artificial intelligence systems [PDF] 摘要

15. One-Shot learning based classification for segregation of plastic waste [PDF] 摘要

16. MS-RANAS: Multi-Scale Resource-Aware Neural Architecture Search [PDF] 摘要

17. A Comparative Study of Deep Learning Loss Functions for Multi-Label Remote Sensing Image Classification [PDF] 摘要

18. Weakly-supervised Salient Instance Detection [PDF] 摘要

19. Multi-term and Multi-task Affect Analysis in the Wild [PDF] 摘要

20. Where is the Model Looking At?--Concentrate and Explain the Network Attention [PDF] 摘要

21. Neural Alignment for Face De-pixelization [PDF] 摘要

22. imdpGAN: Generating Private and Specific Data with Generative Adversarial Networks [PDF] 摘要

23. SIR: Similar Image Retrieval for Product Search in E-Commerce [PDF] 摘要

24. TinyGAN: Distilling BigGAN for Conditional Image Generation [PDF] 摘要

25. An Image Processing Pipeline for Automated Packaging Structure Recognition [PDF] 摘要

26. BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model [PDF] 摘要

27. A comparison of classical and variational autoencoders for anomaly detection [PDF] 摘要

28. Micro-Facial Expression Recognition in Video Based on Optimal Convolutional Neural Network (MFEOCNN) Algorithm [PDF] 摘要

29. Knowledge Fusion Transformers for Video Action Recognition [PDF] 摘要

30. Geometric Loss for Deep Multiple Sclerosis lesion Segmentation [PDF] 摘要

31. SwiftFace: Real-Time Face Detection [PDF] 摘要

32. MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization [PDF] 摘要

33. Graph-based methods for analyzing orchard tree structure using noisy point cloud data [PDF] 摘要

34. A Flow Base Bi-path Network for Cross-scene Video Crowd Understanding in Aerial View [PDF] 摘要

35. A Comprehensive Review for MRF and CRF Approaches in Pathology Image Analysis [PDF] 摘要

36. Deep discriminant analysis for task-dependent compact network search [PDF] 摘要

37. Learn like a Pathologist: Curriculum Learning by Annotator Agreement for Histopathology Image Classification [PDF] 摘要

38. Detecting soccer balls with reduced neural networks: a comparison of multiple architectures under constrained hardware scenarios [PDF] 摘要

39. VIVO: Surpassing Human Performance in Novel Object Captioning with Visual Vocabulary Pre-Training [PDF] 摘要

40. Cross-Task Representation Learning for Anatomical Landmark Detection [PDF] 摘要

41. Fully Automated Left Atrium Segmentation from Anatomical Cine Long-axis MRI Sequences using Deep Convolutional Neural Network with Unscented Kalman Filter [PDF] 摘要

42. A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection [PDF] 摘要

43. Deep Evolution for Facial Emotion Recognition [PDF] 摘要

44. Learning to Compress Videos without Computing Motion [PDF] 摘要

45. Deep Image Reconstruction using Unregistered Measurements without Groundtruth [PDF] 摘要

46. Tackling unsupervised multi-source domain adaptation with optimism and consistency [PDF] 摘要

47. Machine Learning for Semi-Automated Meteorite Recovery [PDF] 摘要

48. Loop-box: Multi-Agent Direct SLAM Triggered by Single Loop Closure for Large-Scale Mapping [PDF] 摘要

49. Self-grouping Convolutional Neural Networks [PDF] 摘要

50. Learned Fine-Tuner for Incongruous Few-Shot Learning [PDF] 摘要

51. Cranial Implant Design via Virtual Craniectomy with Shape Priors [PDF] 摘要

52. Mathematical derivation for Vora-Value based filter design method: Gradient and Hessian [PDF] 摘要

53. Breaking the Memory Wall for AI Chip with a New Dimension [PDF] 摘要

54. MPG-Net: Multi-Prediction Guided Network for Segmentation of Retinal Layers in OCT Images [PDF] 摘要

55. Multi-focus Image Fusion for Visual Sensor Networks [PDF] 摘要

56. Fully Automatic Intervertebral Disc Segmentation Using Multimodal 3D U-Net [PDF] 摘要

阅读全文 »