【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-18

发表于 2020-06-18 分类于 arxiv ， CV 90k 2:30

目录

1. Learning to Detect 3D Reflection Symmetry for Single-View Reconstruction [PDF] 摘要

2. LSD-C: Linearly Separable Deep Clusters [PDF] 摘要

3. Semantic Visual Navigation by Watching YouTube Videos [PDF] 摘要

4. Fast Object Classification and Meaningful Data Representation of Segmented Lidar Instances [PDF] 摘要

5. Deeply Learned Spectral Total Variation Decomposition [PDF] 摘要

6. Noise or Signal: The Role of Image Backgrounds in Object Recognition [PDF] 摘要

7. WhoAmI: An Automatic Tool for Visual Recognition of Tiger and Leopard Individuals in the Wild [PDF] 摘要

8. When We First Met: Visual-Inertial Person Localization for Co-Robot Rendezvous [PDF] 摘要

9. Contrastive Learning for Weakly Supervised Phrase Grounding [PDF] 摘要

10. FISHING Net: Future Inference of Semantic Heatmaps In Grids [PDF] 摘要

11. Vision-Aided Dynamic Blockage Prediction for 6G Wireless Communication Networks [PDF] 摘要

12. Let's face it: Probabilistic multi-modal interlocutor-aware generation of facial gestures in dyadic settings [PDF] 摘要

13. Quantification of groundnut leaf defects using image processing algorithms [PDF] 摘要

14. Unsupervised Learning of Visual Features by Contrasting Cluster Assignments [PDF] 摘要

15. Using Wavelets and Spectral Methods to Study Patterns in Image-Classification Datasets [PDF] 摘要

16. Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues [PDF] 摘要

17. Shallow Feature Based Dense Attention Network for Crowd Counting [PDF] 摘要

18. Burst Photography for Learning to Enhance Extremely Dark Images [PDF] 摘要

19. Sketch-Guided Scenery Image Outpainting [PDF] 摘要

20. Self-supervised Knowledge Distillation for Few-shot Learning [PDF] 摘要

21. Mitosis Detection Under Limited Annotation: A Joint Learning Approach [PDF] 摘要

22. Maximum Roaming Multi-Task Learning [PDF] 摘要

23. Evaluation of 3D CNN Semantic Mapping for Rover Navigation [PDF] 摘要

24. Probabilistic orientation estimation with matrix Fisher distributions [PDF] 摘要

25. LRPD: Long Range 3D Pedestrian Detection Leveraging Specific Strengths of LiDAR and RGB [PDF] 摘要

26. Adversarial Defense by Latent Style Transformations [PDF] 摘要

27. 3D Shape Reconstruction from Free-Hand Sketches [PDF] 摘要

28. A Real-time Action Representation with Temporal Encoding and Deep Compression [PDF] 摘要

29. Revealing the Invisible with Model and Data Shrinking for Composite-database Micro-expression Recognition [PDF] 摘要

30. MetaSDF: Meta-learning Signed Distance Functions [PDF] 摘要

31. Implicit Neural Representations with Periodic Activation Functions [PDF] 摘要

32. Self-Supervised Representation Learning for Visual Anomaly Detection [PDF] 摘要

33. Learning Visual Commonsense for Robust Scene Graph Generation [PDF] 摘要

34. Multi-Subspace Neural Network for Image Recognition [PDF] 摘要

35. Learning Sparse Masks for Efficient Image Super-Resolution [PDF] 摘要

36. Cross-Correlated Attention Networks for Person Re-Identification [PDF] 摘要

37. Mining Label Distribution Drift in Unsupervised Domain Adaptation [PDF] 摘要

38. Explanation-based Weakly-supervised Learning of Visual Relations with Graph Networks [PDF] 摘要

39. Visual Chirality [PDF] 摘要

40. A generalizable saliency map-based interpretation of model outcome [PDF] 摘要

41. On the Inference of Soft Biometrics from Typing Patterns Collected in a Multi-device Environment [PDF] 摘要

42. Intriguing generalization and simplicity of adversarially trained neural networks [PDF] 摘要

43. Big Self-Supervised Models are Strong Semi-Supervised Learners [PDF] 摘要

44. Universal Lower-Bounds on Classification Error under Adversarial Attacks and Random Corruption [PDF] 摘要

45. Multilevel Image Thresholding Using a Fully Informed Cuckoo Search Algorithm [PDF] 摘要

46. High-Fidelity Generative Image Compression [PDF] 摘要

47. Universally Quantized Neural Compression [PDF] 摘要

48. CoSE: Compositional Stroke Embeddings [PDF] 摘要

49. Learning Colour Representations of Search Queries [PDF] 摘要

50. Intelligent Protection & Classification of Transients in Two-Core Symmetric Phase Angle Regulating Transformers [PDF] 摘要

51. Optimizing Grouped Convolutions on Edge Devices [PDF] 摘要

52. Neural Anisotropy Directions [PDF] 摘要

53. StatAssist & GradBoost: A Study on Optimal INT8 Quantization-aware Training from Scratch [PDF] 摘要

54. Visor: Privacy-Preserving Video Analytics as a Cloud Service [PDF] 摘要

55. On sparse connectivity, adversarial robustness, and a novel model of the artificial neuron [PDF] 摘要

56. Interpretable multimodal fusion networks reveal mechanisms of brain cognition [PDF] 摘要

57. Noise2Inpaint: Learning Referenceless Denoising by Inpainting Unrolling [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-06-18

发表于 2020-06-18 分类于 arxiv ， CL 29k 49 分钟

目录

1. On the Learnability of Concepts: With Applications to Comparing Word Embedding Algorithms [PDF] 摘要

2. Fine-grained Sentiment Controlled Text Generation [PDF] 摘要

3. An Exploratory Study of Argumentative Writing by Young Students: A Transformer-based Approach [PDF] 摘要

4. Improving unsupervised neural aspect extraction for online discussions using out-of-domain classification [PDF] 摘要

5. A Tweet-based Dataset for Company-Level Stock Return Prediction [PDF] 摘要

6. Automatically Ranked Russian Paraphrase Corpus for Text Generation [PDF] 摘要

7. Exploiting Review Neighbors for Contextualized Helpfulness Prediction [PDF] 摘要

8. Iterative Edit-Based Unsupervised Sentence Simplification [PDF] 摘要

9. Building Low-Resource NER Models Using Non-Speaker Annotation [PDF] 摘要

10. Canonicalizing Open Knowledge Bases with Multi-Layered Meta-Graph Neural Network [PDF] 摘要

11. Modeling subjective assessments of guilt in newspaper crime narratives [PDF] 摘要

12. Cross-lingual Retrieval for Iterative Self-Supervised Training [PDF] 摘要

13. EPIE Dataset: A Corpus For Possible Idiomatic Expressions [PDF] 摘要

14. Selective Question Answering under Domain Shift [PDF] 摘要

15. The Role of Verb Semantics in Hungarian Verb-Object Order [PDF] 摘要

16. Conversational Neuro-Symbolic Commonsense Reasoning [PDF] 摘要

17. A novel sentence embedding based topic detection method for micro-blog [PDF] 摘要

18. Contrastive Learning for Weakly Supervised Phrase Grounding [PDF] 摘要

19. De-Anonymizing Text by Fingerprinting Language Generation [PDF] 摘要

20. CO-Search: COVID-19 Information Retrieval with Semantic Search, Question Answering, and Abstractive Summarization [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-06-17

发表于 2020-06-17 分类于 arxiv ， CL 37k 1:02

目录

1. Ranking Transfer Languages with Pragmatically-Motivated Features for Multilingual Sentiment Analysis [PDF] 摘要

2. Communicative need modulates competition in language change [PDF] 摘要

3. Modeling Graph Structure via Relative Position for Better Text Generation from Knowledge Graphs [PDF] 摘要

4. Weakly-supervised Domain Adaption for Aspect Extraction via Multi-level Interaction Transfer [PDF] 摘要

5. FFR v1.1: Fon-French Neural Machine Translation [PDF] 摘要

6. A Hybrid Natural Language Generation System Integrating Rules and Deep Learning Algorithms [PDF] 摘要

7. Results of the seventh edition of the BioASQ Challenge [PDF] 摘要

8. CUHK at SemEval-2020 Task 4: CommonSense Explanation, Reasoning and Prediction with Multi-task Learning [PDF] 摘要

9. How to Probe Sentence Embeddings in Low-Resource Languages: On Structural Design Choices for Probing Task Evaluation [PDF] 摘要

10. PERL: Pivot-based Domain Adaptation for Pre-trained Deep Contextualized Embedding Models [PDF] 摘要

11. The SPPD System for Schema Guided Dialogue State Tracking Challenge [PDF] 摘要

12. Manipulating emotions for ground truth emotion analysis [PDF] 摘要

13. Causal Knowledge Extraction from Scholarly Papers in Social Sciences [PDF] 摘要

14. Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation [PDF] 摘要

15. End-to-End Code Switching Language Models for Automatic Speech Recognition [PDF] 摘要

16. On the use of human reference data for evaluating automatic image descriptions [PDF] 摘要

17. Automatic Validation of Textual Attribute Values in E-commerce Catalog by Learning with Limited Labeled Data [PDF] 摘要

18. DynE: Dynamic Ensemble Decoding for Multi-Document Summarization [PDF] 摘要

19. To Pretrain or Not to Pretrain: Examining the Benefits of Pretraining on Resource Rich Tasks [PDF] 摘要

20. "Notic My Speech" -- Blending Speech Patterns With Multimedia [PDF] 摘要

21. On the Computational Power of Transformers and Its Implications in Sequence Modeling [PDF] 摘要

22. Modelling High-Level Mathematical Reasoning in Mechanised Declarative Proofs [PDF] 摘要

23. Towards Automated Assessment of Stuttering and Stuttering Therapy [PDF] 摘要

24. AVLnet: Learning Audio-Visual Language Representations from Instructional Videos [PDF] 摘要

25. Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based VisualQuestion Answering [PDF] 摘要

26. Generative Semantic Hashing Enhanced via Boltzmann Machines [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-16

发表于 2020-06-16 分类于 arxiv ， CV 177k 4:56

目录

1. Coherent Reconstruction of Multiple Humans from a Single Image [PDF] 摘要

2. Now that I can see, I can improve: Enabling data-driven finetuning of CNNs on the edge [PDF] 摘要

3. Visibility Guided NMS: Efficient Boosting of Amodal Object Detection in Crowded Traffic Scenes [PDF] 摘要

4. Go-CaRD -- Generic, Optical Car Part Recognition and Detection: Collection, Insights, and Applications [PDF] 摘要

5. Towards Incorporating Contextual Knowledge into the Prediction of Driving Behavior [PDF] 摘要

6. 3D-ZeF: A 3D Zebrafish Tracking Benchmark Dataset [PDF] 摘要

7. SD-RSIC: Summarization Driven Deep Remote Sensing Image Captioning [PDF] 摘要

8. Pixel Invisibility: Detecting Objects Invisible in Color Images [PDF] 摘要

9. Generating Master Faces for Use in Performing Wolf Attacks on Face Recognition Systems [PDF] 摘要

10. Tamil Vowel Recognition With Augmented MNIST-like Data Set [PDF] 摘要

11. CoDeNet: Algorithm-hardware Co-design for Deformable Convolution [PDF] 摘要

12. ORD: Object Relationship Discovery for Visual Dialogue Generation [PDF] 摘要

13. On the Preservation of Spatio-temporal Information in Machine Learning Applications [PDF] 摘要

14. Mitigating Gender Bias in Captioning Systems [PDF] 摘要

15. Deep-CAPTCHA: a deep learning based CAPTCHA solver for vulnerability assessment [PDF] 摘要

16. AMENet: Attentive Maps Encoder Network for Trajectory Prediction [PDF] 摘要

17. Dermatologist vs Neural Network [PDF] 摘要

18. Learn to cycle: Time-consistent feature discovery for action recognition [PDF] 摘要

19. AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks [PDF] 摘要

20. Infinite Feature Selection: A Graph-based Feature Filtering Approach [PDF] 摘要

21. Binary DAD-Net: Binarized Driveable Area Detection Network for Autonomous Driving [PDF] 摘要

22. Neural gradients are lognormally distributed: understanding sparse and quantized training [PDF] 摘要

23. Filter design for small target detection on infrared imagery using normalized-cross-correlation layer [PDF] 摘要

24. Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion [PDF] 摘要

25. Classifying degraded images over various levels of degradation [PDF] 摘要

26. Anomalous Motion Detection on Highway Using Deep Learning [PDF] 摘要

27. Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction [PDF] 摘要

28. Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution [PDF] 摘要

29. RasterNet: Modeling Free-Flow Speed using LiDAR and Overhead Imagery [PDF] 摘要

30. BatVision with GCC-PHAT Features for Better Sound to Vision Predictions [PDF] 摘要

31. Road Mapping in Low Data Environments with OpenStreetMap [PDF] 摘要

32. Emergent Properties of Foveated Perceptual Systems [PDF] 摘要

33. GradAug: A New Regularization Method for Deep Neural Networks [PDF] 摘要

34. ShapeFlow: Learnable Deformations Among 3D Shapes [PDF] 摘要

35. Geodesic-HOF: 3D Reconstruction Without Cutting Corners [PDF] 摘要

36. Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization [PDF] 摘要

37. Meta Approach to Data Augmentation Optimization [PDF] 摘要

38. Team RUC_AIM3 Technical Report at Activitynet 2020 Task 2: Exploring Sequential Events Detection for Dense Video Captioning [PDF] 摘要

39. Optical Music Recognition: State of the Art and Major Challenges [PDF] 摘要

40. FenceMask: A Data Augmentation Approach for Pre-extracted Image Features [PDF] 摘要

41. Explicitly Modeled Attention Maps for Image Classification [PDF] 摘要

42. Cityscapes 3D: Dataset and Benchmark for 9 DoF Vehicle Detection [PDF] 摘要

43. An adversarial learning algorithm for mitigating gender bias in face recognition [PDF] 摘要

44. A Generalized Asymmetric Dual-front Model for Active Contours and Image Segmentation [PDF] 摘要

45. Multi-Miner: Object-Adaptive Region Mining for Weakly-Supervised Semantic Segmentation [PDF] 摘要

46. On Saliency Maps and Adversarial Robustness [PDF] 摘要

47. PCAAE: Principal Component Analysis Autoencoder for organising the latent space of generative networks [PDF] 摘要

48. Few-shot Object Detection on Remote Sensing Images [PDF] 摘要

49. Working with scale: 2nd place solution to Product Detection in Densely Packed Scenes [Technical Report] [PDF] 摘要

50. Adaptively Meshed Video Stabilization [PDF] 摘要

51. Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates [PDF] 摘要

52. 2D Image Relighting with Image-to-Image Translation [PDF] 摘要

53. Disentanglement for Discriminative Visual Recognition [PDF] 摘要

54. ReLGAN: Generalization of Consistency for GAN with Disjoint Constraints and Relative Learning of Generative Processes for Multiple Transformation Learning [PDF] 摘要

55. Relative Pose Estimation for Stereo Rolling Shutter Cameras [PDF] 摘要

56. Geometry-Aware Instance Segmentation with Disparity Maps [PDF] 摘要

57. Hyper RPCA: Joint Maximum Correntropy Criterion and Laplacian Scale Mixture Modeling On-the-Fly for Moving Object Detection [PDF] 摘要

58. Generative 3D Part Assembly via Dynamic Graph Learning [PDF] 摘要

59. PrimA6D: Rotational Primitive Reconstruction for Enhanced and Robust 6D Pose Estimation [PDF] 摘要

60. Cascaded deep monocular 3D human pose estimation with evolutionary training data [PDF] 摘要

61. Domain Adaptation and Image Classification via Deep Conditional Adaptation Network [PDF] 摘要

62. Recurrent Distillation based Crowd Counting [PDF] 摘要

63. 3D Reconstruction of Novel Object Shapes from Single Images [PDF] 摘要

64. Exploiting the ConvLSTM: Human Action Recognition using Raw Depth Video-Based Recurrent Neural Networks [PDF] 摘要

65. 3DFCNN: Real-Time Action Recognition using 3D Deep Neural Networks with Raw Depth Information [PDF] 摘要

66. Split-Merge Pooling [PDF] 摘要

67. V2E: From video frames to realistic DVS event camera streams [PDF] 摘要

68. Sensorless Freehand 3D Ultrasound Reconstruction via Deep Contextual Learning [PDF] 摘要

69. Uncertainty-aware Score Distribution Learning for Action Quality Assessment [PDF] 摘要

70. Convolutional Generation of Textured 3D Meshes [PDF] 摘要

71. DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms [PDF] 摘要

72. Equivariant Neural Rendering [PDF] 摘要

73. DTG-Net: Differentiated Teachers Guided Self-Supervised Video Action Recognition [PDF] 摘要

74. HRDNet: High-resolution Detection Network for Small Objects [PDF] 摘要

75. Faces à la Carte: Text-to-Face Generation via Attribute Disentanglement [PDF] 摘要

76. Dynamic gesture retrieval: searching videos by human pose sequence [PDF] 摘要

77. NoPeopleAllowed: The Three-Step Approach to Weakly Supervised Semantic Segmentation [PDF] 摘要

78. Attribute-aware Identity-hard Triplet Loss for Video-based Person Re-identification [PDF] 摘要

79. Semantic-driven Colorization [PDF] 摘要

80. Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation [PDF] 摘要

81. Mitigating Face Recognition Bias via Group Adaptive Classifier [PDF] 摘要

82. Unbiased Auxiliary Classifier GANs with MINE [PDF] 摘要

83. Accurate Anchor Free Tracking [PDF] 摘要

84. GAN Memory with No Forgetting [PDF] 摘要

85. FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction [PDF] 摘要

86. CBR-Net: Cascade Boundary Refinement Network for Action Detection: Submission to ActivityNet Challenge 2020 (Task 1) [PDF] 摘要

87. Self-Supervised Discovery of Anatomical Shape Landmarks [PDF] 摘要

88. Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E) [PDF] 摘要

89. Weakly-supervised Any-shot Object Detection [PDF] 摘要

90. Multi-Modal Fingerprint Presentation Attack Detection: Evaluation On A New Dataset [PDF] 摘要

91. OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfold [PDF] 摘要

92. Multispectral Biometrics System Framework: Application to Presentation Attack Detection [PDF] 摘要

93. Early Blindness Detection Based on Retinal Images Using Ensemble Learning [PDF] 摘要

94. Learning-to-Learn Personalised Human Activity Recognition Models [PDF] 摘要

95. Defending against GAN-based Deepfake Attacks via Transformation-aware Adversarial Faces [PDF] 摘要

96. The DeepFake Detection Challenge Dataset [PDF] 摘要

97. Spectral DiffuserCam: lensless snapshot hyperspectral imaging with a spectral filter array [PDF] 摘要

98. Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction [PDF] 摘要

99. Efficient Black-Box Adversarial Attack Guided by the Distribution of Adversarial Perturbations [PDF] 摘要

100. Improved Conditional Flow Models for Molecule to Image Synthesis [PDF] 摘要

101. The Limit of the Batch Size [PDF] 摘要

102. APQ: Joint Search for Network Architecture, Pruning and Quantization Policy [PDF] 摘要

103. Deep learning mediated single time-point image-based prediction of embryo developmental outcome at the cleavage stage [PDF] 摘要

104. A Dataset and Benchmarks for Multimedia Social Analysis [PDF] 摘要

105. Differentiable Neural Architecture Transformation for Reproducible Architecture Improvement [PDF] 摘要

106. Slowing Down the Weight Norm Increase in Momentum-based Optimizers [PDF] 摘要

107. Dissimilarity Mixture Autoencoder for Deep Clustering [PDF] 摘要

108. Emotion Recognition in Audio and Video Using Deep Neural Networks [PDF] 摘要

109. Generalized Adversarially Learned Inference [PDF] 摘要

110. CompressNet: Generative Compression at Extremely Low Bitrates [PDF] 摘要

111. Leveraging Multimodal Behavioral Analytics for Automated Job Interview Performance Assessment and Feedback [PDF] 摘要

112. Continual General Chunking Problem and SyncMap [PDF] 摘要

113. Structural Autoencoders Improve Representations for Generation and Transfer [PDF] 摘要

114. DeeperGCN: All You Need to Train Deeper GCNs [PDF] 摘要

115. Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning [PDF] 摘要

116. RoadNet-RT: High Throughput CNN Architecture and SoC Design for Real-Time Road Segmentation [PDF] 摘要

117. Adversarial Self-Supervised Contrastive Learning [PDF] 摘要

118. Sparse Separable Nonnegative Matrix Factorization [PDF] 摘要

119. Rethinking the Value of Labels for Improving Class-Imbalanced Learning [PDF] 摘要

120. TURB-Rot. A large database of 3d and 2d snapshots from turbulent rotating flows [PDF] 摘要

121. BI-MAML: Balanced Incremental Approach for Meta Learning [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-06-16

发表于 2020-06-16 分类于 arxiv ， CL 64k 1:46

目录

1. Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech [PDF] 摘要

2. Wat zei je? Detecting Out-of-Distribution Translations with Variational Transformers [PDF] 摘要

3. Subjective Question Answering: Deciphering the inner workings of Transformers in the realm of subjectivity [PDF] 摘要

4. Graph-Stega: Semantic Controllable Steganographic Text Generation Guided by Knowledge Graph [PDF] 摘要

5. DeepVar: An End-to-End Deep Learning Approach for Genomic Variant Recognition in Biomedical Literature [PDF] 摘要

6. Open-Domain Question Answering with Pre-Constructed Question Spaces [PDF] 摘要

7. Affective Conditioning on Hierarchical Networks applied to Depression Detection from Transcribed Clinical Interviews [PDF] 摘要

8. A Dataset and Benchmarks for Multimedia Social Analysis [PDF] 摘要

9. StackOverflow vs Kaggle: A Study of Developer Discussions About Data Science [PDF] 摘要

10. An Augmented Translation Technique for low Resource language pair: Sanskrit to Hindi translation [PDF] 摘要

11. Probing Neural Dialog Models for Conversational Understanding [PDF] 摘要

12. ETHOS: an Online Hate Speech Detection Dataset [PDF] 摘要

13. Fine-grained Human Evaluation of Transformer and Recurrent Approaches to Neural Machine Translation for English-to-Chinese [PDF] 摘要

14. On the Multi-Property Extraction and Beyond [PDF] 摘要

15. Extracting N-ary Cross-sentence Relations using Constrained Subsequence Kernel [PDF] 摘要

16. Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder [PDF] 摘要

17. FinBERT: A Pretrained Language Model for Financial Communications [PDF] 摘要

18. FinEst BERT and CroSloEngual BERT: less is more in multilingual models [PDF] 摘要

19. Vietnamese Word Segmentation with SVM: Ambiguity Reduction and Suffix Capture [PDF] 摘要

20. Through the Twitter Glass: Detecting Questions in Micro-Text [PDF] 摘要

21. Transferring Monolingual Model to Low-Resource Language: The Case of Tigrinya [PDF] 摘要

22. Words ranking and Hirsch index for identifying the core of the hapaxes in political texts [PDF] 摘要

23. GIPFA: Generating IPA Pronunciation from Audio [PDF] 摘要

24. Do Dogs have Whiskers? A New Knowledge Base of hasPart Relations [PDF] 摘要

25. A Generative Model for Joint Natural Language Understanding and Generation [PDF] 摘要

26. Measuring Forecasting Skill from Text [PDF] 摘要

27. Evaluating a Multi-sense Definition Generation Model for Multiple Languages [PDF] 摘要

28. Regularized Forward-Backward Decoder for Attention Models [PDF] 摘要

29. SD-RSIC: Summarization Driven Deep Remote Sensing Image Captioning [PDF] 摘要

30. EPIC: An Epidemics Corpus Of Over 20 Million Relevant Tweets [PDF] 摘要

31. Tamil Vowel Recognition With Augmented MNIST-like Data Set [PDF] 摘要

32. Exploration of End-to-End ASR for OpenSTT -- Russian Open Speech-to-Text Dataset [PDF] 摘要

33. Relational reasoning and generalization using non-symbolic neural networks [PDF] 摘要

34. UWSpeech: Speech to Speech Translation for Unwritten Languages [PDF] 摘要

35. Leveraging Multimodal Behavioral Analytics for Automated Job Interview Performance Assessment and Feedback [PDF] 摘要

36. Examining the Role of Mood Patterns in Predicting Self-Reported Depressive symptoms [PDF] 摘要

37. Continual General Chunking Problem and SyncMap [PDF] 摘要

38. Pot, kettle: Nonliteral titles aren't (natural) science [PDF] 摘要

39. SE-MelGAN -- Speaker Agnostic Rapid Speech Enhancement [PDF] 摘要

40. Mining Implicit Relevance Feedback from User Behavior forWeb Question Answering [PDF] 摘要

41. Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Search [PDF] 摘要

42. A Multifunction Printer CUI for the Blind [PDF] 摘要

43. Understanding Unintended Memorization in Federated Learning [PDF] 摘要

44. How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-15

发表于 2020-06-15 分类于 arxiv ， CV 79k 2:12

目录

1. Robust Baggage Detection and Classification Based on Local Tri-directional Pattern [PDF] 摘要

2. GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learning [PDF] 摘要

3. Multiple-Vehicle Tracking in the Highway Using Appearance Model and Visual Object Tracking [PDF] 摘要

4. Pitfalls of the Gram Loss for Neural Texture Synthesis in Light of Deep Feature Histograms [PDF] 摘要

5. Local-Area-Learning Network: Meaningful Local Areas for Efficient Point Cloud Analysis [PDF] 摘要

6. Branch-Cooperative OSNet for Person Re-Identification [PDF] 摘要

7. Video Understanding as Machine Translation [PDF] 摘要

8. ESAD: Endoscopic Surgeon Action Detection Dataset [PDF] 摘要

9. Are we done with ImageNet? [PDF] 摘要

10. Attribute analysis with synthetic dataset for person re-identification [PDF] 摘要

11. Knowledge Distillation Meets Self-Supervision [PDF] 摘要

12. A Face Preprocessing Approach for Improved DeepFake Detection [PDF] 摘要

13. Unmasking the Inductive Biases of Unsupervised Object Representations for Video Sequences [PDF] 摘要

14. Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks [PDF] 摘要

15. Background Modeling via Uncertainty Estimation for Weakly-supervised Action Localization [PDF] 摘要

16. Quantum Robust Fitting [PDF] 摘要

17. Towards Robust Pattern Recognition: A Review [PDF] 摘要

18. Multi Layer Neural Networks as Replacement for Pooling Operations [PDF] 摘要

19. The eyes know it: FakeET -- An Eye-tracking Database to Understand Deepfake Perception [PDF] 摘要

20. Does Unsupervised Architecture Representation Learning Help Neural Architecture Search? [PDF] 摘要

21. Iterate & Cluster: Iterative Semi-Supervised Action Recognition [PDF] 摘要

22. SemifreddoNets: Partially Frozen Neural Networks for Efficient Computer Vision Systems [PDF] 摘要

23. Rethinking Pre-training and Self-training [PDF] 摘要

24. Feudal Steering: Hierarchical Learning for Steering Angle Prediction [PDF] 摘要

25. SegNBDT: Visual Decision Rules for Segmentation [PDF] 摘要

26. On Improving the Generalization of Face Recognition in the Presence of Occlusions [PDF] 摘要

27. On Improving Temporal Consistency for Online Face Liveness Detection [PDF] 摘要

28. PRGFlow: Benchmarking SWAP-Aware Unified Deep Visual Inertial Odometry [PDF] 摘要

29. An Unsupervised Information-Theoretic Perceptual Quality Metric [PDF] 摘要

30. Deep Convolutional Likelihood Particle Filter for Visual Tracking [PDF] 摘要

31. Gaze estimation problem tackled through synthetic images [PDF] 摘要

32. Training Generative Adversarial Networks with Limited Data [PDF] 摘要

33. Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis [PDF] 摘要

34. CPR: Classifier-Projection Regularization for Continual Learning [PDF] 摘要

35. FedGAN: Federated Generative AdversarialNetworks for Distributed Data [PDF] 摘要

36. Sparse and Continuous Attention Mechanisms [PDF] 摘要

37. HMIC: Hierarchical Medical Image Classification, A Deep Learning Approach [PDF] 摘要

38. Move-to-Data: A new Continual Learning approach with Deep CNNs, Application for image-class recognition [PDF] 摘要

39. Non-Negative Bregman Divergence Minimization for Deep Direct Density Ratio Estimation [PDF] 摘要

40. Early Detection of Retinopathy of Prematurity (ROP) in Retinal Fundus Images Via Convolutional Neural Networks [PDF] 摘要

41. LSSL: Longitudinal Self-Supervised Learning [PDF] 摘要

42. Potential Field Guided Actor-Critic Reinforcement Learning [PDF] 摘要

43. Online Sequential Extreme Learning Machines: Features Combined From Hundreds of Midlayers [PDF] 摘要

44. Reintroducing Straight-Through Estimators as Principled Methods for Stochastic Binary Networks [PDF] 摘要

45. Combining the band-limited parameterization and Semi-Lagrangian Runge--Kutta integration for efficient PDE-constrained LDDMM [PDF] 摘要

46. Automated Identification of Thoracic Pathology from Chest Radiographs with Enhanced Training Pipeline [PDF] 摘要

47. Multigrid-in-Channels Architectures for Wide Convolutional Neural Networks [PDF] 摘要

48. One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers [PDF] 摘要

49. Data Driven Prediction Architecture for Autonomous Driving and its Application on Apollo Platform [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-06-15

发表于 2020-06-15 分类于 arxiv ， CL 21k 35 分钟

目录

1. Information Extraction of Clinical Trial Eligibility CriteriaYitong [PDF] 摘要

2. Low-resource Languages: A Review of Past Work and Future Challenges [PDF] 摘要

3. SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020) [PDF] 摘要

4. Speaker Sensitive Response Evaluation Model [PDF] 摘要

5. Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System [PDF] 摘要

6. Comparing Natural Language Processing Techniques for Alzheimer's Dementia Prediction in Spontaneous Speech [PDF] 摘要

7. Dutch General Public Reaction on Governmental COVID-19 Measures and Announcements in Twitter Data [PDF] 摘要

8. Sparse and Continuous Attention Mechanisms [PDF] 摘要

9. NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processing [PDF] 摘要

10. Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL [PDF] 摘要

11. Learning Effective Representations for Person-Job Fit by Feature Fusion [PDF] 摘要

12. Improving GAN Training with Probability Ratio Clipping and Sample Reweighting [PDF] 摘要

13. High-Precision Extraction of Emerging Concepts from Scientific Literature [PDF] 摘要

14. FastPitch: Parallel Text-to-speech with Pitch Prediction [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-06-12

发表于 2020-06-12 分类于 arxiv ， CV 102k 2:50

目录

1. Understanding Human Hands in Contact at Internet Scale [PDF] 摘要

2. Disentangled Non-Local Neural Networks [PDF] 摘要

3. VirTex: Learning Visual Representations from Textual Annotations [PDF] 摘要

4. Quasi-Dense Instance Similarity Learning [PDF] 摘要

5. Robust Multi-object Matching via Iterative Reweighting of the Graph Connection Laplacian [PDF] 摘要

6. Exploring Weaknesses of VQA Models through Attribution Driven Insights [PDF] 摘要

7. Privacy-Preserving Visual Feature Descriptors through Adversarial Affine Subspace Embedding [PDF] 摘要

8. SLIC-UAV: A Method for monitoring recovery in tropical restoration projects through identification of signature species using UAVs [PDF] 摘要

9. MatchGAN: A Self-Supervised Semi-Supervised Conditional Generative Adversarial Network [PDF] 摘要

10. Improving Deep Metric Learning with Virtual Classes and Examples Mining [PDF] 摘要

11. What makes instance discrimination good for transfer learning? [PDF] 摘要

12. Spectral Image Segmentation with Global Appearance Modeling [PDF] 摘要

13. Transferring and Regularizing Prediction for Semantic Segmentation [PDF] 摘要

14. Learning a Unified Sample Weighting Network for Object Detection [PDF] 摘要

15. Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation [PDF] 摘要

16. Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification [PDF] 摘要

17. Rethinking the Truly Unsupervised Image-to-Image Translation [PDF] 摘要

18. Protecting Against Image Translation Deepfakes by Leaking Universal Perturbations from Black-Box Neural Networks [PDF] 摘要

19. Minimum Potential Energy of Point Cloud for Robust Global Registration [PDF] 摘要

20. Morphing Attack Detection -- Database, Evaluation Platform and Benchmarking [PDF] 摘要

21. Convolutional neural networks compression with low rank and sparse tensor decompositions [PDF] 摘要

22. CoMIR: Contrastive Multimodal Image Representation for Registration [PDF] 摘要

23. A Deep Learning Framework for Recognizing both Static and Dynamic Gestures [PDF] 摘要

24. Hypernetwork-Based Augmentation [PDF] 摘要

25. RTEX: A novel methodology for Ranking, Tagging, and Explanatory diagnostic captioning of radiography exams [PDF] 摘要

26. Fast Coherent Point Drift [PDF] 摘要

27. Privacy-Aware Activity Classification from First Person Office Videos [PDF] 摘要

28. CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks [PDF] 摘要

29. Fall Detector Adapted to Nursing Home Needs through an Optical-Flow based CNN [PDF] 摘要

30. An Edge Information and Mask Shrinking Based Image Inpainting Approach [PDF] 摘要

31. Large-Scale Adversarial Training for Vision-and-Language Representation Learning [PDF] 摘要

32. JIT-Masker: Efficient Online Distillation for Background Matting [PDF] 摘要

33. Telling Left from Right: Learning Spatial Correspondence between Sight and Sound [PDF] 摘要

34. MOMS with Events: Multi-Object Motion Segmentation With Monocular Event Cameras [PDF] 摘要

35. Image Deconvolution via Noise-Tolerant Self-Supervised Inversion [PDF] 摘要

36. Kalman Filter Based Multiple Person Head Tracking [PDF] 摘要

37. Dance Revolution: Long Sequence Dance Generation with Music via Curriculum Learning [PDF] 摘要

38. Continual Learning for Affective Computing [PDF] 摘要

39. Autonomous Driving with Deep Learning: A Survey of State-of-Art Technologies [PDF] 摘要

40. DivNoising: Diversity Denoising with Fully Convolutional Variational Autoencoders [PDF] 摘要

41. Joint Training of Variational Auto-Encoder and Latent Energy-Based Model [PDF] 摘要

42. Map3D: Registration Based Multi-Object Tracking on 3D Serial Whole Slide Images [PDF] 摘要

43. Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features [PDF] 摘要

44. Revisiting visual-inertial structure from motion for odometry and SLAM initialization [PDF] 摘要

45. Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty [PDF] 摘要

46. Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning [PDF] 摘要

47. Interpretable Visualizations with Differentiating Embedding Networks [PDF] 摘要

48. Real-Time Video Inference on Edge Devices via Adaptive Model Streaming [PDF] 摘要

49. Diagnosis and Analysis of Celiac Disease and Environmental Enteropathy on Biopsy Images using Deep Learning Approaches [PDF] 摘要

50. A Primer on Large Intelligent Surface (LIS) for Wireless Sensing in an Industrial Setting [PDF] 摘要

51. MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles [PDF] 摘要

52. Fully-automated deep learning slice-based muscle estimation from CT images for sarcopenia assessment [PDF] 摘要

53. Interpreting CNN for Low Complexity Learned Sub-pixel Motion Compensation in Video Coding [PDF] 摘要

54. TensorFlow with user friendly Graphical Framework for object detection API [PDF] 摘要

55. Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors [PDF] 摘要

56. DSU-net: Dense SegU-net for automatic head-and-neck tumor segmentation in MR images [PDF] 摘要

57. W-net: Simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network [PDF] 摘要

58. Unsupervised Learning of 3D Point Set Registration [PDF] 摘要

59. COVID-19-CT-CXR: a freely accessible and weakly labeled chest X-ray and CT image collection on COVID-19 from biomedical literature [PDF] 摘要

60. Enabling Nonlinear Manifold Projection Reduced-Order Models by Extending Convolutional Neural Networks to Unstructured Data [PDF] 摘要

61. Deterministic Gaussian Averaged Neural Networks [PDF] 摘要

62. Disease Detection from Lung X-ray Images based on Hybrid Deep Learning [PDF] 摘要

阅读全文 »