【arxiv论文】 Computation and Language 2020-05-04

发表于 2020-05-04 分类于 arxiv ， CL 106k 2:57

目录

1. Why Overfitting Isn't Always Bad: Retrofitting Cross-Lingual Word Embeddings to Dictionaries [PDF] 摘要

2. HipoRank: Incorporating Hierarchical and Positional Information into Graph-based Unsupervised Long Document Extractive Summarization [PDF] 摘要

3. SciREX: A Challenge Dataset for Document-Level Information Extraction [PDF] 摘要

4. Structured Tuning for Semantic Role Labeling [PDF] 摘要

5. ASSET: A Dataset for Tuning and Evaluation of Sentence Simplification Models with Multiple Rewriting Transformations [PDF] 摘要

6. Knowledge Base Inference for Regular Expression Queries [PDF] 摘要

7. MedType: Improving Medical Entity Linking with Semantic Type Prediction [PDF] 摘要

8. Style Variation as a Vantage Point for Code-Switching [PDF] 摘要

9. USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation [PDF] 摘要

10. Defense of Word-level Adversarial Attacks via Random Substitution Encoding [PDF] 摘要

11. Topological Sort for Sentence Ordering [PDF] 摘要

12. Identifying Necessary Elements for BERT's Multilinguality [PDF] 摘要

13. Will-They-Won't-They: A Very Large Dataset for Stance Detection on Twitter [PDF] 摘要

14. Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research [PDF] 摘要

15. Multilingual Unsupervised Sentence Simplification [PDF] 摘要

16. XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning [PDF] 摘要

17. CDL: Curriculum Dual Learning for Emotion-Controllable Response Generation [PDF] 摘要

18. Can Multilingual Language Models Transfer to an Unseen Dialect? A Case Study on North African Arabizi [PDF] 摘要

19. Self-supervised Knowledge Triplet Learning for Zero-shot Question Answering [PDF] 摘要

20. Mind the Trade-off: Debiasing NLU Models without Degrading the In-distribution Performance [PDF] 摘要

21. Language (Re)modelling: Towards Embodied Language Understanding [PDF] 摘要

22. Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation [PDF] 摘要

23. Hitachi at SemEval-2020 Task 12: Offensive Language Identification with Noisy Labels using Statistical Sampling and Post-Processing [PDF] 摘要

24. Facilitating Access to Multilingual COVID-19 Information via Neural Machine Translation [PDF] 摘要

25. Unsupervised Transfer of Semantic Role Models from Verbal to Nominal Domain [PDF] 摘要

26. Towards Controllable Biases in Language Generation [PDF] 摘要

27. Low Resource Multi-Task Sequence Tagging -- Revisiting Dynamic Conditional Random Fields [PDF] 摘要

28. AdapterFusion: Non-Destructive Task Composition for Transfer Learning [PDF] 摘要

29. Cross-modal Language Generation using Pivot Stabilization for Web-scale Language Coverage [PDF] 摘要

30. TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions [PDF] 摘要

31. Biomedical Entity Representations with Synonym Marginalization [PDF] 摘要

32. Multi-head Monotonic Chunkwise Attention For Online Speech Recognition [PDF] 摘要

33. KPQA: A Metric for Generative Question Answering Using Word Weights [PDF] 摘要

34. Evaluating Neural Machine Comprehension Model Robustness to Noisy Inputs and Adversarial Attacks [PDF] 摘要

35. Cross-Linguistic Syntactic Evaluation of Word Prediction Models [PDF] 摘要

36. Sparse, Dense, and Attentional Representations for Text Retrieval [PDF] 摘要

37. Selecting Informative Contexts Improves Language Model Finetuning [PDF] 摘要

38. Universal Adversarial Attacks with Natural Triggers for Text Classification [PDF] 摘要

39. Information Seeking in the Spirit of Learning: a Dataset for Conversational Curiosity [PDF] 摘要

40. Cross-lingual Entity Alignment for Knowledge Graphs with Incidental Supervision from Free Text [PDF] 摘要

41. Recurrent Neural Network Language Models Always Learn English-Like Relative Clause Attachment [PDF] 摘要

42. Attend to Medical Ontologies: Content Selection for Clinical Abstractive Summarization [PDF] 摘要

43. Recurrent Interaction Network for Jointly Extracting Entities and Classifying Relations [PDF] 摘要

44. Why and when should you pool? Analyzing Pooling in Recurrent Architectures [PDF] 摘要

45. Neural Entity Summarization with Joint Encoding and Weak Supervision [PDF] 摘要

46. Interpretable Entity Representations through Large-Scale Typing [PDF] 摘要

47. Contextual Text Style Transfer [PDF] 摘要

48. Structure-Tags Improve Text Classification for Scholarly Document Quality Prediction [PDF] 摘要

49. Revisiting Memory-Efficient Incremental Coreference Resolution [PDF] 摘要

50. Learning to Faithfully Rationalize by Construction [PDF] 摘要

51. On the Spontaneous Emergence of Discrete and Compositional Signals [PDF] 摘要

52. Linguistic Typology Features from Text: Inferring the Sparse Features of World Atlas of Language Structures [PDF] 摘要

53. Revisiting Unsupervised Relation Extraction [PDF] 摘要

54. AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languages [PDF] 摘要

55. Aspect-Controlled Neural Argument Generation [PDF] 摘要

56. Attribution Analysis of Grammatical Dependencies in LSTMs [PDF] 摘要

57. MAD-X: An Adapter-based Framework for Multi-task Cross-lingual Transfer [PDF] 摘要

58. UiO-UvA at SemEval-2020 Task 1: Contextualised Embeddings for Lexical Semantic Change Detection [PDF] 摘要

59. Context based Text-generation using LSTM networks [PDF] 摘要

60. Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering [PDF] 摘要

61. Generating Persona-Consistent Dialogue Responses Using Deep Reinforcement Learning [PDF] 摘要

62. Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society [PDF] 摘要

63. Representations of Syntax [MASK] Useful: Effects of Constituency and Dependency Structure in Recursive LSTMs [PDF] 摘要

64. Partially-Typed NER Datasets Integration: Connecting Practice to Theory [PDF] 摘要

65. Automatic Discourse Segmentation: Review and Perspectives [PDF] 摘要

66. HLVU : A New Challenge to Test Deep Understanding of Movies the Way Humans do [PDF] 摘要

67. Bipartite Flat-Graph Network for Nested Named Entity Recognition [PDF] 摘要

68. Diverse Visuo-Lingustic Question Answering (DVLQA) Challenge [PDF] 摘要

69. TransOMCS: From Linguistic Graphs to Commonsense Knowledge [PDF] 摘要

70. HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training [PDF] 摘要

71. On the Merging of Domain-Specific Heterogeneous Ontologies using Wordnet and Web Pattern-based Queries [PDF] 摘要

72. Unsupervised Learning of KB Queries in Task Oriented Dialogs [PDF] 摘要

73. Learning to Rank Intents in Voice Assistants [PDF] 摘要

74. An Early Study on Intelligent Analysis of Speech under COVID-19: Severity, Sleep Quality, Fatigue, and Anxiety [PDF] 摘要

75. Method for Customizable Automated Tagging: Addressing the Problem of Over-tagging and Under-tagging Text Documents [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-05-01

发表于 2020-05-01 分类于 arxiv ， CV 69k 1:54

目录

1. Consistent Video Depth Estimation [PDF] 摘要

2. SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation [PDF] 摘要

3. Improving Vision-and-Language Navigation with Image-Text Pairs from the Web [PDF] 摘要

4. Improving Semantic Segmentation via Self-Training [PDF] 摘要

5. Polarization Human Shape and Pose Dataset [PDF] 摘要

6. PreCNet: Next Frame Video Prediction Based on Predictive Coding [PDF] 摘要

7. Polygonal Building Segmentation by Frame Field Learning [PDF] 摘要

8. Progressive Transformers for End-to-End Sign Language Production [PDF] 摘要

9. A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion [PDF] 摘要

10. IROS 2019 Lifelong Robotic Vision Challenge -- Lifelong Object Recognition Report [PDF] 摘要

11. Pedestrian Path, Pose and Intention Prediction through Gaussian Process Dynamical Models and Pedestrian Activity Recognition [PDF] 摘要

12. Inability of spatial transformations of CNN feature maps to support invariant recognition [PDF] 摘要

13. SS3D: Single Shot 3D Object Detector [PDF] 摘要

14. Attentive Weakly Supervised land cover mapping for object-based satellite image time series data with spatial interpretation [PDF] 摘要

15. DIABLO: Dictionary-based Attention Block for Deep Metric Learning [PDF] 摘要

16. The 4th AI City Challenge [PDF] 摘要

17. Dynamic Language Binding in Relational Visual Reasoning [PDF] 摘要

18. Bilateral Attention Network for RGB-D Salient Object Detection [PDF] 摘要

19. Feedback U-net for Cell Image Segmentation [PDF] 摘要

20. APB2Face: Audio-guided face reenactment with auxiliary pose and blink signals [PDF] 摘要

21. A Multi-scale Optimization Learning Framework for Diffeomorphic Deformable Registration [PDF] 摘要

22. Salient Object Detection Combining a Self-attention Module and a Feature Pyramid Network [PDF] 摘要

23. MobileDets: Searching for Object Detection Architectures for Mobile Accelerators [PDF] 摘要

24. Rethinking Class-Discrimination Based CNN Channel Pruning [PDF] 摘要

25. Detecting Deep-Fake Videos from Appearance and Behavior [PDF] 摘要

26. Teaching Cameras to Feel: Estimating Tactile Physical Properties of Surfaces From Images [PDF] 摘要

27. CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization [PDF] 摘要

28. Generative Adversarial Networks in Digital Pathology: A Survey on Trends and Future Potential [PDF] 摘要

29. MuSe 2020 -- The First International Multimodal Sentiment Analysis in Real-life Media Challenge and Workshop [PDF] 摘要

30. Multiresolution and Multimodal Speech Recognition with Transformers [PDF] 摘要

31. RAIN: Robust and Accurate Classification Networks with Randomization and Enhancement [PDF] 摘要

32. Multi-task Learning with Crowdsourced Features Improves Skin Lesion Diagnosis [PDF] 摘要

33. Multi-View Spectral Clustering Tailored Tensor Low-Rank Representation [PDF] 摘要

34. Towards Embodied Scene Description [PDF] 摘要

35. EXACT: A collaboration toolset for algorithm-aided annotation of almost everything [PDF] 摘要

36. Out-of-the-box channel pruned networks [PDF] 摘要

37. TRP: Trained Rank Pruning for Efficient Deep Neural Networks [PDF] 摘要

38. Physarum Powered Differentiable Linear Programming Layers and Applications [PDF] 摘要

39. Bias-corrected estimator for intrinsic dimension and differential entropy--a visual multiscale approach [PDF] 摘要

40. Interactive Video Stylization Using Few-Shot Patch-Based Training [PDF] 摘要

41. Pragmatic Issue-Sensitive Image Captioning [PDF] 摘要

42. UAV and Machine Learning Based Refinement of a Satellite-Driven Vegetation Index for Precision Agriculture [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-05-01

发表于 2020-05-01 分类于 arxiv ， CL 146k 4:03

目录

1. Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO [PDF] 摘要

2. WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context [PDF] 摘要

3. Imitation Attacks and Defenses for Black-box Machine Translation Systems [PDF] 摘要

4. When does data augmentation help generalization in NLP? [PDF] 摘要

5. TLDR: Extreme Summarization of Scientific Documents [PDF] 摘要

6. Lexical Semantic Recognition [PDF] 摘要

7. Few-Shot Natural Language Generation by Rewriting Templates [PDF] 摘要

8. Word Rotator's Distance: Decomposing Vectors Gives Better Representations [PDF] 摘要

9. On the Evaluation of Contextual Embeddings for Zero-Shot Cross-Lingual Transfer Learning [PDF] 摘要

10. A Matter of Framing: The Impact of Linguistic Formalism on Probing Results [PDF] 摘要

11. SegaBERT: Pre-training of Segment-aware BERT for Language Understanding [PDF] 摘要

12. How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking [PDF] 摘要

13. Explicit Representation of the Translation Space: Automatic Paraphrasing for Machine Translation Evaluation [PDF] 摘要

14. Control, Generate, Augment: A Scalable Framework for Multi-Attribute Text Generation [PDF] 摘要

15. Paraphrasing vs Coreferring: Two Sides of the Same Coin [PDF] 摘要

16. Investigating Transferability in Pretrained Language Models [PDF] 摘要

17. Fact or Fiction: Verifying Scientific Claims [PDF] 摘要

18. PlotMachines: Outline-Conditioned Generation with Dynamic Plot State Tracking [PDF] 摘要

19. Use of Machine Translation to Obtain Labeled Datasets for Resource-Constrained Languages [PDF] 摘要

20. Mutlitask Learning for Cross-Lingual Transfer of Semantic Dependencies [PDF] 摘要

21. Natural Language Premise Selection: Finding Supporting Statements for Mathematical Text [PDF] 摘要

22. A Call for More Rigor in Unsupervised Cross-lingual Learning [PDF] 摘要

23. Language Model Prior for Low-Resource Neural Machine Translation [PDF] 摘要

24. Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation [PDF] 摘要

25. Bridging linguistic typology and multilingual machine translation with multi-view language representations [PDF] 摘要

26. Tired of Topic Models? Clusters of Pretrained Word Embeddings Make for Fast and Good Topics too! [PDF] 摘要

27. Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation [PDF] 摘要

28. You are right. I am ALARMED -- But by Climate Change Counter Movement [PDF] 摘要

29. Modelling Suspense in Short Stories as Uncertainty Reduction over Neural Representation [PDF] 摘要

30. MLSUM: The Multilingual Summarization Corpus [PDF] 摘要

31. Analyzing the Surprising Variability in Word Embedding Stability Across Languages [PDF] 摘要

32. Multi-Domain Spoken Language Understanding Using Domain- and Task-Aware Parameterization [PDF] 摘要

33. Mind Your Inflections! Improving NLP for Non-Standard English with Base-Inflection Encoding [PDF] 摘要

34. TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task [PDF] 摘要

35. Enriched Pre-trained Transformers for Joint Slot Filling and Intent Detection [PDF] 摘要

36. The role of context in neural pitch accent detection in English [PDF] 摘要

37. Do Neural Models Learn Systematicity of Monotonicity Inference in Natural Language? [PDF] 摘要

38. Accurate Word Alignment Induction from Neural Machine Translation [PDF] 摘要

39. Vocabulary Adaptation for Distant Domain Adaptation in Neural Machine Translation [PDF] 摘要

40. Knowledge Graph Empowered Entity Description Generation [PDF] 摘要

41. STARC: Structured Annotations for Reading Comprehension [PDF] 摘要

42. Character-Level Translation with Self-attention [PDF] 摘要

43. Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT [PDF] 摘要

44. Semantic Triple Encoder for Fast Open-Set Link Prediction [PDF] 摘要

45. Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation [PDF] 摘要

46. Self-Supervised and Controlled Multi-Document Opinion Summarization [PDF] 摘要

47. Named Entity Recognition without Labelled Data: A Weak Supervision Approach [PDF] 摘要

48. Towards Unsupervised Language Understanding and Generation by Joint Dual Learning [PDF] 摘要

49. A Span-based Linearization for Constituent Trees [PDF] 摘要

50. Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders [PDF] 摘要

51. AMPERSAND: Argument Mining for PERSuAsive oNline Discussions [PDF] 摘要

52. End-to-End Neural Word Alignment Outperforms GIZA++ [PDF] 摘要

53. NUBIA: NeUral Based Interchangeability Assessor for Text Generation [PDF] 摘要

54. Capsule-Transformer for Neural Machine Translation [PDF] 摘要

55. Robust Question Answering Through Sub-part Alignment [PDF] 摘要

56. CohEval: Benchmarking Coherence Models [PDF] 摘要

57. Modular Representation Underlies Systematic Generalization in Neural Natural Language Inference Models [PDF] 摘要

58. Universal Dependencies according to BERT: both more specific and more general [PDF] 摘要

59. Unsupervised Injection of Knowledge into Dialogue Generation via Language Models [PDF] 摘要

60. Can Your Context-Aware MT System Pass the DiP Benchmark Tests? : Evaluation Benchmarks for Discourse Phenomena in Machine Translation [PDF] 摘要

61. Look at the First Sentence: Position Bias in Question Answering [PDF] 摘要

62. Pretraining on Non-linguistic Structure as a Tool for Analyzing Learning Bias in Language Models [PDF] 摘要

63. EnsembleGAN: Adversarial Learning for Retrieval-Generation Ensemble Model on Short-Text Conversation [PDF] 摘要

64. Improved Natural Language Generation via Loss Truncation [PDF] 摘要

65. Logic2Text: High-Fidelity Natural Language Generation from Logical Forms [PDF] 摘要

66. Exploring Contextualized Neural Language Models for Temporal Dependency Parsing [PDF] 摘要

67. memeBot: Towards Automatic Image Meme Generation [PDF] 摘要

68. Boosting Naturalness of Language in Task-oriented Dialogues via Adversarial Training [PDF] 摘要

69. Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing [PDF] 摘要

70. RikiNet: Reading Wikipedia Pages for Natural Question Answering [PDF] 摘要

71. User-Guided Aspect Classification for Domain-Specific Texts [PDF] 摘要

72. Indirect Identification of Psychosocial Risks from Natural Language [PDF] 摘要

73. Filtering before Iteratively Referring for Knowledge-Grounded Response Selection in Retrieval-Based Chatbots [PDF] 摘要

74. WT5?! Training Text-to-Text Models to Explain their Predictions [PDF] 摘要

75. TextAT: Adversarial Training for Natural Language Understanding with Token-Level Perturbation [PDF] 摘要

76. Text Segmentation by Cross Segment Attention [PDF] 摘要

77. Hierarchical Encoders for Modeling and Interpreting Screenplays [PDF] 摘要

78. Stay Hungry, Stay Focused: Generating Informative and Specific Questions in Information-Seeking Conversations [PDF] 摘要

79. Simulated Multiple Reference Training Improves Low-Resource Machine Translation [PDF] 摘要

80. Exploiting Sentence Order in Document Alignment [PDF] 摘要

81. A Focused Study to Compare Arabic Pre-training Models on Newswire IE Tasks [PDF] 摘要

82. Bilingual Text Extraction as Reading Comprehension [PDF] 摘要

83. A Supervised Word Alignment Method based on Cross-Language Span Prediction using Multilingual BERT [PDF] 摘要

84. Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition [PDF] 摘要

85. Asking without Telling: Exploring Latent Ontologies in Contextual Representations [PDF] 摘要

86. Posterior Calibrated Training on Sentence Classification Tasks [PDF] 摘要

87. "The Boating Store Had Its Best Sail Ever": Pronunciation-attentive Contextualized Pun Recognition [PDF] 摘要

88. A Large-Scale Semi-Supervised Dataset for Offensive Language Identification [PDF] 摘要

89. Pragmatic Issue-Sensitive Image Captioning [PDF] 摘要

90. What Happens To BERT Embeddings During Fine-tuning? [PDF] 摘要

91. Distantly-Supervised Neural Relation Extraction with Side Information using BERT [PDF] 摘要

92. A Benchmark Dataset of Check-worthy Factual Claims [PDF] 摘要

93. Improving Vision-and-Language Navigation with Image-Text Pairs from the Web [PDF] 摘要

94. Learning to Ask Screening Questions for Job Postings [PDF] 摘要

95. Few-Shot Learning for Abstractive Multi-Document Opinion Summarization [PDF] 摘要

96. Progressive Transformers for End-to-End Sign Language Production [PDF] 摘要

97. MuSe 2020 -- The First International Multimodal Sentiment Analysis in Real-life Media Challenge and Workshop [PDF] 摘要

98. Knowledge Graph Embeddings and Explainable AI [PDF] 摘要

99. Preventing Posterior Collapse with Levenshtein Variational Autoencoder [PDF] 摘要

100. Counterfactual Off-Policy Training for Neural Response Generation [PDF] 摘要

101. Zero-shot Neural Retrieval via Domain-targeted Synthetic Query Generation [PDF] 摘要

102. The Effect of Natural Distribution Shift on Question Answering Models [PDF] 摘要

103. Neural Speech Separation Using Spatially Distributed Microphones [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-30

发表于 2020-04-30 分类于 arxiv ， CV 52k 1:27

目录

1. VGGSound: A Large-scale Audio-Visual Dataset [PDF] 摘要

2. Editing in Style: Uncovering the Local Semantics of GANs [PDF] 摘要

3. Smart Attendance System Usign CNN [PDF] 摘要

4. Tensor train rank minimization with nonlocal self-similarity for tensor completion [PDF] 摘要

5. Action Sequence Predictions of Vehicles in Urban Environments using Map and Social Context [PDF] 摘要

6. Image Captioning through Image Transformer [PDF] 摘要

7. Deepfake Video Forensics based on Transfer Learning [PDF] 摘要

8. Assessing Car Damage using Mask R-CNN [PDF] 摘要

9. Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Review [PDF] 摘要

10. Minimal Rolling Shutter Absolute Pose with Unknown Focal Length and Radial Distortion [PDF] 摘要

11. Single-Side Domain Generalization for Face Anti-Spoofing [PDF] 摘要

12. Counting of Grapevine Berries in Images via Semantic Segmentation using Convolutional Neural Networks [PDF] 摘要

13. Retinal vessel segmentation by probing adaptive to lighting variations [PDF] 摘要

14. Motion Guided 3D Pose Estimation from Videos [PDF] 摘要

15. Skeleton Focused Human Activity Recognition in RGB Video [PDF] 摘要

16. Effective Human Activity Recognition Based on Small Datasets [PDF] 摘要

17. Deep Transfer Learning For Plant Center Localization [PDF] 摘要

18. Video Contents Understanding using Deep Neural Networks [PDF] 摘要

19. Deflating Dataset Bias Using Synthetic Data Augmentation [PDF] 摘要

20. Less is More: Sample Selection and Label Conditioning Improve Skin Lesion Segmentation [PDF] 摘要

21. Boosting Deep Open World Recognition by Clustering [PDF] 摘要

22. Pyramid Attention Networks for Image Restoration [PDF] 摘要

23. CMRNet++: Map and Camera Agnostic Monocular Visual Localization in LiDAR Maps [PDF] 摘要

24. Cross-modal Speaker Verification and Recognition: A Multilingual Perspective [PDF] 摘要

25. Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTube [PDF] 摘要

26. Seeing voices and hearing voices: learning discriminative embeddings using cross-modal self-supervision [PDF] 摘要

27. A Wearable Social Interaction Aid for Children with Autism [PDF] 摘要

28. A Fast 3D CNN for Hyperspectral Image Classification [PDF] 摘要

29. Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Scans [PDF] 摘要

30. Informative Scene Decomposition for Crowd Analysis, Comparison and Simulation Guidance [PDF] 摘要

31. DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data [PDF] 摘要

32. Image Morphing with Perceptual Constraints and STN Alignment [PDF] 摘要

33. The International Workshop on Osteoarthritis Imaging Knee MRI Segmentation Challenge: A Multi-Institute Evaluation and Analysis Framework on a Standardized Dataset [PDF] 摘要

34. Span-based Localizing Network for Natural Language Video Localization [PDF] 摘要

35. An Auto-Encoder Strategy for Adaptive Image Segmentation [PDF] 摘要

36. Unmanned Aerial Systems for Wildland and Forest Fires: Sensing, Perception, Cooperation and Assistance [PDF] 摘要

37. Histogram-based Auto Segmentation: A Novel Approach to Segmenting Integrated Circuit Structures from SEM Images [PDF] 摘要

38. Character-level Japanese Text Generation with Attention Mechanism for Chest Radiography Diagnosis [PDF] 摘要

39. Minority Reports Defense: Defending Against Adversarial Patches [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-29

发表于 2020-04-29 分类于 arxiv ， CV 84k 2:19

目录

1. Style-transfer GANs for bridging the domain gap in synthetic pose estimator training [PDF] 摘要

2. A novel Region of Interest Extraction Layer for Instance Segmentation [PDF] 摘要

3. Event-based Robotic Grasping Detection with Neuromorphic Vision Sensor and Event-Stream Dataset [PDF] 摘要

4. Colon Shape Estimation Method for Colonoscope Tracking using Recurrent Neural Networks [PDF] 摘要

5. Data Augmentation Imbalance For Imbalanced Attribute Classification [PDF] 摘要

6. Exploring Self-attention for Image Recognition [PDF] 摘要

7. Do We Need Fully Connected Output Layers in Convolutional Networks? [PDF] 摘要

8. Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation [PDF] 摘要

9. Multivariate Confidence Calibration for Object Detection [PDF] 摘要

10. Attention Prior for Real Image Restoration [PDF] 摘要

11. Identity Enhanced Residual Image Denoising [PDF] 摘要

12. Small-Task Incremental Learning [PDF] 摘要

13. DiVA: Diverse Visual Feature Aggregation forDeep Metric Learning [PDF] 摘要

14. Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction [PDF] 摘要

15. Real-Time Apple Detection System Using Embedded Systems With Hardware Accelerators: An Edge AI Application [PDF] 摘要

16. Multi-Scale Boosted Dehazing Network with Dense Feature Fusion [PDF] 摘要

17. Revisiting Multi-Task Learning in the Deep Learning Era [PDF] 摘要

18. 3D Solid Spherical Bispectrum CNNs for Biomedical Texture Analysis [PDF] 摘要

19. Gradient-Induced Co-Saliency Detection [PDF] 摘要

20. Learning Feature Descriptors using Camera Pose Supervision [PDF] 摘要

21. SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing [PDF] 摘要

22. Neural Hair Rendering [PDF] 摘要

23. VD-BERT: A Unified Vision and Dialog Transformer with BERT [PDF] 摘要

24. Trainable Activation Function Supported CNN in Image Classification [PDF] 摘要

25. Deep Auto-Encoders with Sequential Learning for Multimodal Dimensional Emotion Recognition [PDF] 摘要

26. Inferring Temporal Compositions of Actions Using Probabilistic Automata [PDF] 摘要

27. Graph2Plan: Learning Floorplan Generation from Layout Graphs [PDF] 摘要

28. Multi-Task Image-Based Dietary Assessment for Food Recognition and Portion Size Estimation [PDF] 摘要

29. A Disentangling Invertible Interpretation Network for Explaining Latent Representations [PDF] 摘要

30. Compact retail shelf segmentation for mobile deployment [PDF] 摘要

31. Self-Supervised Attention Learning for Depth and Ego-motion Estimation [PDF] 摘要

32. The Problem of Fragmented Occlusion in Object Detection [PDF] 摘要

33. A generic and efficient convolutional neural network accelerator using HLS for a system on chip design [PDF] 摘要

34. A Novel Attention-based Aggregation Function to Combine Vision and Language [PDF] 摘要

35. GIMP-ML: Python Plugins for using Computer Vision Models in GIMP [PDF] 摘要

36. Residual Channel Attention Generative Adversarial Network for Image Super-Resolution and Noise Reduction [PDF] 摘要

37. Visual Grounding of Learned Physical Models [PDF] 摘要

38. Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels [PDF] 摘要

39. TRAKO: Efficient Transmission of Tractography Data for Visualization [PDF] 摘要

40. Hybrid Attention for Automatic Segmentation of Whole Fetal Head in Prenatal Ultrasound Volumes [PDF] 摘要

41. Addressing Artificial Intelligence Bias in Retinal Disease Diagnostics [PDF] 摘要

42. FU-net: Multi-class Image Segmentation Using Feedback Weighted U-net [PDF] 摘要

43. DRU-net: An Efficient Deep Convolutional Neural Network for Medical Image Segmentation [PDF] 摘要

44. Identification of Cervical Pathology using Adversarial Neural Networks [PDF] 摘要

45. The Immersion of Directed Multi-graphs in Embedding Fields. Generalisations [PDF] 摘要

46. SSIM-Based CTU-Level Joint Optimal Bit Allocation and Rate Distortion Optimization [PDF] 摘要

47. Transferable Active Grasping and Real Embodied Dataset [PDF] 摘要

48. Attacks on Image Encryption Schemes for Privacy-Preserving Deep Neural Networks [PDF] 摘要

49. A scoping review of transfer learning research on medical image analysis using ImageNet [PDF] 摘要

50. LSHR-Net: a hardware-friendly solution for high-resolution computational imaging using a mixed-weights neural network [PDF] 摘要

51. Clustering via torque balance with mass and distance [PDF] 摘要

52. Harnessing adversarial examples with a surprisingly simple defense [PDF] 摘要

53. ML-driven Malware that Targets AV Safety [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-28

发表于 2020-04-28 分类于 arxiv ， CV 161k 4:29

目录

1. MakeItTalk: Speaker-Aware Talking Head Animation [PDF] 摘要

2. CoReNet: Coherent 3D scene reconstruction from a single RGB image [PDF] 摘要

3. Audio-Visual Instance Discrimination with Cross-Modal Agreement [PDF] 摘要

4. Improvement in Land Cover and Crop Classification based on Temporal Features Learning from Sentinel-2 Data Using Recurrent-Convolutional Neural Network (R-CNN) [PDF] 摘要

5. AI-Driven CT-based quantification, staging and short-term outcome prediction of COVID-19 pneumonia [PDF] 摘要

6. A Deep Attentive Convolutional Neural Network for Automatic Cortical Plate Segmentation in Fetal MRI [PDF] 摘要

7. Detecting and Tracking Communal Bird Roosts in Weather Radar Data [PDF] 摘要

8. Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder [PDF] 摘要

9. Per-pixel Classification Rebar Exposures in Bridge Eye-inspection [PDF] 摘要

10. Adversarial Fooling Beyond "Flipping the Label" [PDF] 摘要

11. A Skip-connected Multi-column Network for Isolated Handwritten Bangla Character and Digit recognition [PDF] 摘要

12. Semantic Neighborhood-Aware Deep Facial Expression Recognition [PDF] 摘要

13. Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training [PDF] 摘要

14. GraftNet: An Engineering Implementation of CNN for Fine-grained Multi-label Task [PDF] 摘要

15. On indirect assessment of heart rate in video [PDF] 摘要

16. In-Vehicle Object Detection in the Wild for Driverless Vehicles [PDF] 摘要

17. Remote Photoplethysmography: Rarely Considered Factors [PDF] 摘要

18. Distance Guided Channel Weighting for Semantic Segmentation [PDF] 摘要

19. Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos [PDF] 摘要

20. 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection [PDF] 摘要

21. CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents [PDF] 摘要

22. Preliminary Forensics Analysis of DeepFake Images [PDF] 摘要

23. Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios [PDF] 摘要

24. Maximum Density Divergence for Domain Adaptation [PDF] 摘要

25. Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latency [PDF] 摘要

26. VTGNet: A Vision-based Trajectory Generation Network for Autonomous Vehicles in Urban Environments [PDF] 摘要

27. Difficulty Translation in Histopathology Images [PDF] 摘要

28. Fully Embedding Fast Convolutional Networks on Pixel Processor Arrays [PDF] 摘要

29. Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes [PDF] 摘要

30. On the Limits to Multi-Modal Popularity Prediction on Instagram -- A New Robust, Efficient and Explainable Baseline [PDF] 摘要

31. Designing a physically-feasible colour filter to make a camera more colorimetric [PDF] 摘要

32. One-Shot Identity-Preserving Portrait Reenactment [PDF] 摘要

33. All you need is a second look: Towards Tighter Arbitrary shape text detection [PDF] 摘要

34. Stitcher: Feedback-driven Data Provider for Object Detection [PDF] 摘要

35. Disentangled Image Generation Through Structured Noise Injection [PDF] 摘要

36. Hyperspectral image classification based on multi-scale residual network with attention mechanism [PDF] 摘要

37. Evaluation Metrics for Conditional Image Generation [PDF] 摘要

38. When CNNs Meet Random RNNs: Towards Multi-Level Analysis for RGB-D Object and Scene Recognition [PDF] 摘要

39. Climate Adaptation: Reliably Predicting from Imbalanced Satellite Data [PDF] 摘要

40. Transfer learning for leveraging computer vision in infrastructure maintenance [PDF] 摘要

41. A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging [PDF] 摘要

42. AutoHR: A Strong End-to-end Baseline for Remote Heart Rate Measurement with Neural Searching [PDF] 摘要

43. Stomach 3D Reconstruction Based on Virtual Chromoendoscopic Image Generation [PDF] 摘要

44. Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset [PDF] 摘要

45. Learning to Autofocus [PDF] 摘要

46. TPNet: Trajectory Proposal Network for Motion Prediction [PDF] 摘要

47. Joint Inference of States, Robot Knowledge, and Human (False-)Beliefs [PDF] 摘要

48. Congestion-aware Evacuation Routing using Augmented Reality Devices [PDF] 摘要

49. Detective: An Attentive Recurrent Model for Sparse Object Detection [PDF] 摘要

50. EfficientPose: Scalable single-person pose estimation [PDF] 摘要

51. Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection [PDF] 摘要

52. Revisiting Sequence-to-Sequence Video Object Segmentation with Multi-Task Loss and Skip-Memory [PDF] 摘要

53. CNN based Road User Detection using the 3D Radar Cube [PDF] 摘要

54. Offline Signature Verification on Real-World Documents [PDF] 摘要

55. How to read faces without looking at them [PDF] 摘要

56. Clustering by Constructing Hyper-Planes [PDF] 摘要

57. Deep Multimodal Neural Architecture Search [PDF] 摘要

58. CS-AF: A Cost-sensitive Multi-classifier Active Fusion Framework for Skin Lesion Classification [PDF] 摘要

59. Deep convolutional neural networks for face and iris presentation attack detection: Survey and case study [PDF] 摘要

60. StRDAN: Synthetic-to-Real Domain Adaptation Network for Vehicle Re-Identification [PDF] 摘要

61. Deepfakes Detection with Automatic Face Weighting [PDF] 摘要

62. Neural Head Reenactment with Latent Pose Descriptors [PDF] 摘要

63. Extending and Analyzing Self-Supervised Learning Across Domains [PDF] 摘要

64. DALES: A Large-scale Aerial LiDAR Data Set for Semantic Segmentation [PDF] 摘要

65. DriftNet: Aggressive Driving Behavior Classification using 3D EfficientNet Architecture [PDF] 摘要

66. Leveraging Planar Regularities for Point Line Visual-Inertial Odometry [PDF] 摘要

67. Eigenfeatures: Discrimination of X-ray images of epoxy resins using singular value decomposition of deep learning features [PDF] 摘要

68. Defining Benchmarks for Continual Few-Shot Learning [PDF] 摘要

69. Extreme Consistency: Overcoming Annotation Scarcity and Domain Shifts [PDF] 摘要

70. On the safety of vulnerable road users by cyclist orientation detection using Deep Learning [PDF] 摘要

71. Towards causal generative scene models via competition of experts [PDF] 摘要

72. Control Design of Autonomous Drone Using Deep Learning Based Image Understanding Techniques [PDF] 摘要

73. A Light CNN for detecting COVID-19 from CT scans of the chest [PDF] 摘要

74. A Critic Evaluation of Methods for COVID-19 Automatic Detection from X-Ray Images [PDF] 摘要

75. Quantifying Graft Detachment after Descemet's Membrane Endothelial Keratoplasty with Deep Convolutional Neural Networks [PDF] 摘要

76. A Cascaded Learning Strategy for Robust COVID-19 Pneumonia Chest X-Ray Screening [PDF] 摘要

77. Boosting Connectivity in Retinal Vessel Segmentation via a Recursive Semantics-Guided Network [PDF] 摘要

78. EAO-SLAM: Monocular Semi-Dense Object SLAM Based on Ensemble Data Association [PDF] 摘要

79. Reconstructing normal section profiles of 3D revolving structures via pose-unconstrained multi-line structured-light vision [PDF] 摘要

80. OR-UNet: an Optimized Robust Residual U-Net for Instrument Segmentation in Endoscopic Images [PDF] 摘要

81. Continuous hand-eye calibration using 3D points [PDF] 摘要

82. Improving Endoscopic Decision Support Systems by Translating Between Imaging Modalities [PDF] 摘要

83. Robust Screening of COVID-19 from Chest X-ray via Discriminative Cost-Sensitive Learning [PDF] 摘要

84. Towards Efficient COVID-19 CT Annotation: A Benchmark for Lung and Infection Segmentation [PDF] 摘要

85. Towards Accurate and Robust Domain Adaptation under Noisy Environments [PDF] 摘要

86. Cross-Domain Structure Preserving Projection for Heterogeneous Domain Adaptation [PDF] 摘要

87. Towards Feature Space Adversarial Attack [PDF] 摘要

88. Joint Liver Lesion Segmentation and Classification via Transfer Learning [PDF] 摘要

89. DeepSeg: Deep Neural Network Framework for Automatic Brain Tumor Segmentation using Magnetic Resonance FLAIR Images [PDF] 摘要

90. Development of a High Fidelity Simulator for Generalised Photometric Based Space Object Classification using Machine Learning [PDF] 摘要

91. Deep DIH : Statistically Inferred Reconstruction of Digital In-Line Holography by Deep Learning [PDF] 摘要

92. Explainable Deep CNNs for MRI-Based Diagnosis of Alzheimer's Disease [PDF] 摘要

93. A Survey on Domain Knowledge Powered Deep Learning for Medical Image Analysis [PDF] 摘要

94. POCOVID-Net: Automatic Detection of COVID-19 From a New Lung Ultrasound Imaging Dataset (POCUS) [PDF] 摘要

95. SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System [PDF] 摘要

96. GPO: Global Plane Optimization for Fast and Accurate Monocular SLAM Initialization [PDF] 摘要

97. Self-supervised Learning of Visual Speech Features with Audiovisual Speech Enhancement [PDF] 摘要

98. Spectral Data Augmentation Techniques to quantify Lung Pathology from CT-images [PDF] 摘要

99. DeepMerge: Classifying High-redshift Merging Galaxies with Deep Neural Networks [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-04-28

发表于 2020-04-28 分类于 arxiv ， CL 85k 2:22

目录

1. DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference [PDF] 摘要

2. Natural language processing for achieving sustainable development: the case of neural labelling to enhance community profiling [PDF] 摘要

3. SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations [PDF] 摘要

4. Intelligent Translation Memory Matching and Retrieval with Sentence Encoders [PDF] 摘要

5. DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking [PDF] 摘要

6. Synonyms and Antonyms: Embedded Conflict [PDF] 摘要

7. LightPAFF: A Two-Stage Distillation Framework for Pre-training and Fine-tuning [PDF] 摘要

8. ColBERT: Using BERT Sentence Embedding for Humor Detection [PDF] 摘要

9. The Gutenberg Dialogue Dataset [PDF] 摘要

10. Augmenting Transformers with KNN-Based Composite Memory for Dialogue [PDF] 摘要

11. Screenplay Summarization Using Latent Narrative Structure [PDF] 摘要

12. BLEU Neighbors: A Reference-less Approach to Automatic Evaluation [PDF] 摘要

13. Semantic Graphs for Generating Deep Questions [PDF] 摘要

14. Lexically Constrained Neural Machine Translation with Levenshtein Transformer [PDF] 摘要

15. Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting [PDF] 摘要

16. On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification [PDF] 摘要

17. Neural Machine Translation with Monte-Carlo Tree Search [PDF] 摘要

18. Assessing Discourse Relations in Language Generationfrom Pre-trained Language Models [PDF] 摘要

19. PTPARL-D: Annotated Corpus of 44 years of Portuguese Parliament debates [PDF] 摘要

20. Experiments with LVT and FRE for Transformer model [PDF] 摘要

21. Semi-Supervised Neural System for Tagging, Parsing and Lematization [PDF] 摘要

22. Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language [PDF] 摘要

23. Towards Multimodal Response Generation with Exemplar Augmentation and Curriculum Optimization [PDF] 摘要

24. Masking as an Efficient Alternative to Finetuning for Pretrained Language Models [PDF] 摘要

25. Heterogeneous Graph Neural Networks for Extractive Document Summarization [PDF] 摘要

26. GLUECoS : An Evaluation Benchmark for Code-Switched NLP [PDF] 摘要

27. Multi-Domain Dialogue Acts and Response Co-Generation [PDF] 摘要

28. Relational Graph Attention Network for Aspect-based Sentiment Analysis [PDF] 摘要

29. Is Your Classifier Actually Biased? Measuring Fairness under Uncertainty with Bernstein Bounds [PDF] 摘要

30. Endowing Empathetic Conversational Models with Personas [PDF] 摘要

31. MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization [PDF] 摘要

32. Dual Learning for Semi-Supervised Natural Language Understanding [PDF] 摘要

33. Show, Describe and Conclude: On Exploiting the Structure Information of Chest X-Ray Reports [PDF] 摘要

34. Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias [PDF] 摘要

35. Hierarchical Multi Task Learning with Subword Contextual Embeddings for Languages with Rich Morphology [PDF] 摘要

36. MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification [PDF] 摘要

37. MCQA: Multimodal Co-attention Based Network for Question Answering [PDF] 摘要

38. Quantifying the Contextualization of Word Representations with Semantic Class Probing [PDF] 摘要

39. QURATOR: Innovative Technologies for Content and Data Curation [PDF] 摘要

40. Towards Discourse Parsing-inspired Semantic Storytelling [PDF] 摘要

41. Learning to Update Natural Language Comments Based on Code Changes [PDF] 摘要

42. How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence [PDF] 摘要

43. A Rigourous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land? [PDF] 摘要

44. All Word Embeddings from One Embedding [PDF] 摘要

45. A Heterogeneous Graph with Factual, Temporal and Logical Knowledge for Question Answering Over Dynamic Contexts [PDF] 摘要

46. When do Word Embeddings Accurately Reflect Surveys on our Beliefs About People? [PDF] 摘要

47. Contextualized Representations Using Textual Encyclopedic Knowledge [PDF] 摘要

48. Syntactic Data Augmentation Increases Robustness to Inference Heuristics [PDF] 摘要

49. Collecting Entailment Data for Pretraining: New Protocols and Negative Results [PDF] 摘要

50. The Inception Team at NSURL-2019 Task 8: Semantic Question Similarity in Arabic [PDF] 摘要

51. Practical Comparable Data Collection for Low-Resource Languages via Images [PDF] 摘要

52. ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT [PDF] 摘要

53. "Unsex me here": Revisiting Sexism Detection Using Psychological Scales and Adversarial Samples [PDF] 摘要

54. A Batch Normalized Inference Network Keeps the KL Vanishing Away [PDF] 摘要

55. Detecting fake news for the new coronavirus by reasoning on the Covid-19 ontology [PDF] 摘要

56. Methods for Computing Legal Document Similarity: A Comparative Study [PDF] 摘要

57. Beyond 512 Tokens: Siamese Multi-depth Transformer-based Hierarchical Encoder for Document Matching [PDF] 摘要

58. Jointly Trained Transformers models for Spoken Language Translation [PDF] 摘要

59. Deep Multimodal Neural Architecture Search [PDF] 摘要

60. Self-supervised Learning of Visual Speech Features with Audiovisual Speech Enhancement [PDF] 摘要

61. Question Answering over Curated and Open Web Sources [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-04-27

发表于 2020-04-27 分类于 arxiv ， CV 82k 2:17

目录

1. Revisiting Modulated Convolutions for Visual Counting and Beyond [PDF] 摘要

2. Learning Gaussian Maps for Dense Object Detection [PDF] 摘要

3. DFUC2020: Analysis Towards Diabetic Foot Ulcer Detection [PDF] 摘要

4. Deep learning for smart fish farming: applications, opportunities and challenges [PDF] 摘要

5. Analysis of Social Media Data using Multimodal Deep Learning for Disaster Response [PDF] 摘要

6. Detecting Unsigned Physical Road Incidents from Driver-View Images [PDF] 摘要

7. Facial Expression Recognition with Deep Learning [PDF] 摘要

8. 3D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Training [PDF] 摘要

9. Decoupling Global and Local Representations from/for Image Generation [PDF] 摘要

10. Domain Adaptive Transfer Attack (DATA)-based Segmentation Networks for Building Extraction from Aerial Images [PDF] 摘要

11. Deep Interleaved Network for Image Super-Resolution With Asymmetric Co-Attention [PDF] 摘要

12. Applications of the Streaming Networks [PDF] 摘要

13. Deep Face Forgery Detection [PDF] 摘要

14. Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Study [PDF] 摘要

15. DPDist : Comparing Point Clouds Using Deep Point Cloud Distance [PDF] 摘要

16. Quantization of Deep Neural Networks for Accumulator-constrained Processors [PDF] 摘要

17. GAPS: Generator for Automatic Polynomial Solvers [PDF] 摘要

18. Ultra Fast Structure-aware Deep Lane Detection [PDF] 摘要

19. PipeNet: Selective Modal Pipeline of Fusion Network for Multi-Modal Face Anti-Spoofing [PDF] 摘要

20. A Two-Stage Multiple Instance Learning Framework for the Detection of Breast Cancer in Mammograms [PDF] 摘要

21. Learning Decision Ensemble using a Graph Neural Network for Comorbidity Aware Chest Radiograph Screening [PDF] 摘要

22. A Systematic Search over Deep Convolutional Neural Network Architectures for Screening Chest Radiographs [PDF] 摘要

23. Understanding when spatial transformer networks do not support invariance, and what to do about it [PDF] 摘要

24. Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning [PDF] 摘要

25. Any Motion Detector: Learning Class-agnostic Scene Dynamics from a Sequence of LiDAR Point Clouds [PDF] 摘要

26. A Survey on Visual Sentiment Analysis [PDF] 摘要

27. Dynamic Sampling for Deep Metric Learning [PDF] 摘要

28. Low-latency hand gesture recognition with a low resolution thermal imager [PDF] 摘要

29. Vision based hardware-software real-time control system for autonomous landing of an UAV [PDF] 摘要

30. Deep 3D Portrait from a Single Image [PDF] 摘要

31. Deep Global Registration [PDF] 摘要

32. Systematic Evaluation of Backdoor Data Poisoning Attacks on Image Classifiers [PDF] 摘要

33. What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentation [PDF] 摘要

34. Mining self-similarity: Label super-resolution with epitomic representations [PDF] 摘要

35. Roof material classification from aerial imagery [PDF] 摘要

36. Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Surveillance Videos [PDF] 摘要

37. YOLO and K-Means Based 3D Object Detection Method on Image and Point Cloud [PDF] 摘要

38. Debiasing Skin Lesion Datasets and Models? Not So Fast [PDF] 摘要

39. Style Your Face Morph and Improve Your Face Morphing Attack Detector [PDF] 摘要

40. Conditional Variational Image Deraining [PDF] 摘要

41. Optic disc and fovea localisation in ultra-widefield scanning laser ophthalmoscope images captured in multiple modalities [PDF] 摘要

42. Automated diagnosis of COVID-19 with limited posteroanterior chest X-ray images using fine-tuned deep neural networks [PDF] 摘要

43. YCB-M: A Multi-Camera RGB-D Dataset for Object Recognition and 6DoF Pose Estimation [PDF] 摘要

44. Convolution-Weight-Distribution Assumption: Rethinking the Criteria of Channel Pruning [PDF] 摘要

45. A Review of an Old Dilemma: Demosaicking First, or Denoising First? [PDF] 摘要

46. Deep Feature-preserving Normal Estimation for Point Cloud Filtering [PDF] 摘要

47. Dropout as an Implicit Gating Mechanism For Continual Learning [PDF] 摘要

48. Automatic low-bit hybrid quantization of neural networks through meta learning [PDF] 摘要

49. Adversarial Machine Learning: An Interpretation Perspective [PDF] 摘要

50. Pill Identification using a Mobile Phone App for Assessing Medication Adherence and Post-Market Drug Surveillance [PDF] 摘要

51. Upgrading the Newsroom: An Automated Image Selection System for News Articles [PDF] 摘要

52. Device-based Image Matching with Similarity Learning by Convolutional Neural Networks that Exploit the Underlying Camera Sensor Pattern Noise [PDF] 摘要

53. LRTD: Long-Range Temporal Dependency based Active Learning for Surgical Workflow Recognition [PDF] 摘要

阅读全文 »