【arxiv论文】 Computation and Language 2020-11-17

发表于 2020-11-17 分类于 arxiv ， CL 71k 1:58

目录

1. Learning from Task Descriptions [PDF] 摘要

2. A Dataset for Tracking Entities in Open Domain Procedural Text [PDF] 摘要

3. Tweet Sentiment Quantification: An Experimental Re-Evaluation [PDF] 摘要

4. Answer Identification in Collaborative Organizational Group Chat [PDF] 摘要

5. Analyzing Sustainability Reports Using Natural Language Processing [PDF] 摘要

6. Topic-Centric Unsupervised Multi-Document Summarization of Scientific and News Articles [PDF] 摘要

7. JNLP Team: Deep Learning for Legal Processing in COLIEE 2020 [PDF] 摘要

8. Hierarchical Transformer for Task Oriented Dialog Systems [PDF] 摘要

9. "What is on your mind?" Automated Scoring of Mindreading in Childhood and Early Adolescence [PDF] 摘要

10. Comparative Probing of Lexical Semantics Theories for Cognitive Plausibility and Technological Usefulness [PDF] 摘要

11. The Person Index Challenge: Extraction of Persons from Messy, Short Texts [PDF] 摘要

12. Datasets and Models for Authorship Attribution on Italian Personal Writings [PDF] 摘要

13. Learning from similarity and information extraction from structured documents [PDF] 摘要

14. Performance of Transfer Learning Model vs. Traditional Neural Network in Low System Resource Environment [PDF] 摘要

15. An Empirical Investigation of Contextualized Number Prediction [PDF] 摘要

16. Explicitly Modeling Syntax in Language Model improves Generalization [PDF] 摘要

17. Pre-training Text-to-Text Transformers for Concept-centric Common Sense [PDF] 摘要

18. Score Combination for Improved Parallel Corpus Filtering for Low Resource Conditions [PDF] 摘要

19. Text Information Aggregation with Centrality Attention [PDF] 摘要

20. Evaluating Sentence Segmentation and Word Tokenization Systems on Estonian Web Texts [PDF] 摘要

21. WikiAsp: A Dataset for Multi-domain Aspect-based Summarization [PDF] 摘要

22. Deep Shallow Fusion for RNN-T Personalization [PDF] 摘要

23. Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases [PDF] 摘要

24. Reinforced Medical Report Generation with X-Linear Attention and Repetition Penalty [PDF] 摘要

25. IIT_kgp at FinCausal 2020, Shared Task 1: Causality Detection using Sentence Embeddings in Financial Reports [PDF] 摘要

26. ArraMon: A Joint Navigation-Assembly Instruction Interpretation Task in Dynamic Environments [PDF] 摘要

27. DORB: Dynamically Optimizing Multiple Rewards with Bandits [PDF] 摘要

28. The Challenge of Diacritics in Yoruba Embeddings [PDF] 摘要

29. Morphologically Aware Word-Level Translation [PDF] 摘要

30. Target Guided Emotion Aware Chat Machine [PDF] 摘要

31. Iterative Self-Learning for Enhanced Back-Translation in Low Resource Neural Machine Translation [PDF] 摘要

32. Lessons from Computational Modelling of Reference Production in Mandarin and English [PDF] 摘要

33. Words are the Window to the Soul: Language-based User Representations for Fake News Detection [PDF] 摘要

34. Conditioned Natural Language Generation using only Unconditioned Language Model: An Exploration [PDF] 摘要

35. Meaningful Answer Generation of E-Commerce Question-Answering [PDF] 摘要

36. Sentiment Analysis for Sinhala Language using Deep Learning Techniques [PDF] 摘要

37. DebateSum: A large-scale argument mining and summarization dataset [PDF] 摘要

38. CL-IMS @ DIACR-Ita: Volente o Nolente: BERT does not outperform SGNS on Semantic Change Detection [PDF] 摘要

39. Utilizing Bidirectional Encoder Representations from Transformers for Answer Selection [PDF] 摘要

40. Language Models not just for Pre-training: Fast Online Neural Noisy Channel Modeling [PDF] 摘要

41. IIRC: A Dataset of Incomplete Information Reading Comprehension Questions [PDF] 摘要

42. Zero-shot Learning for Relation Extraction [PDF] 摘要

43. Streaming Attention-Based Models with Augmented Memory for End-to-End Speech Recognition [PDF] 摘要

44. The Teacher-Student Chatroom Corpus [PDF] 摘要

45. Sampling Approach Matters: Active Learning for Robotic Language Acquisition [PDF] 摘要

46. Text Mining to Identify and Extract Novel Disease Treatments From Unstructured Datasets [PDF] 摘要

47. hyper-sinh: An Accurate and Reliable Function from Shallow to Deep Learning in TensorFlow and Keras [PDF] 摘要

48. Deep multi-modal networks for book genre classification based on its cover [PDF] 摘要

49. Generating Negative Commonsense Knowledge [PDF] 摘要

50. Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-11-16

发表于 2020-11-16 分类于 arxiv ， CV 37k 1:02

目录

1. Using Graph Neural Networks to Reconstruct Ancient Documents [PDF] 摘要

2. A Study of Domain Generalization on Ultrasound-based Multi-Class Segmentation of Arteries, Veins, Ligaments, and Nerves Using Transfer Learning [PDF] 摘要

3. NightVision: Generating Nighttime Satellite Imagery from Infra-Red Observations [PDF] 摘要

4. Multi-layered tensor networks for image classification [PDF] 摘要

5. Transformer-Encoder Detector Module: Using Context to Improve Robustness to Adversarial Attacks on Object Detection [PDF] 摘要

6. Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis [PDF] 摘要

7. A Study of Image Pre-processing for Faster Object Recognition [PDF] 摘要

8. Image Animation with Perturbed Masks [PDF] 摘要

9. Discriminative Feature Representation with Spatio-temporal Cues for Vehicle Re-identification [PDF] 摘要

10. Transductive Zero-Shot Learning using Cross-Modal CycleGAN [PDF] 摘要

11. LULC classification by semantic segmentation of satellite images using FastFCN [PDF] 摘要

12. SHAD3S: : A model to Sketch, Shade and Shadow [PDF] 摘要

13. Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints [PDF] 摘要

14. Adaptive Future Frame Prediction with Ensemble Network [PDF] 摘要

15. Fast and Scalable Earth Texture Synthesis using Spatially Assembled Generative Adversarial Neural Networks [PDF] 摘要

16. Lightweight Single-Image Super-Resolution Network with Attentive Auxiliary Feature Learning [PDF] 摘要

17. Filter Pre-Pruning for Improved Fine-tuning of Quantized Deep Neural Networks [PDF] 摘要

18. Structured Attention Graphs for Understanding Deep Image Classifications [PDF] 摘要

19. Local Anomaly Detection in Videos using Object-Centric Adversarial Learning [PDF] 摘要

20. Adversarial Robustness Against Image Color Transformation within Parametric Filter Space [PDF] 摘要

21. Trajectory Prediction in Autonomous Driving with a Lane Heading Auxiliary Loss [PDF] 摘要

22. Empirical Performance Analysis of Conventional Deep Learning Models for Recognition of Objects in 2-D Images [PDF] 摘要

23. Automatic segmentation with detection of local segmentation failures in cardiac MRI [PDF] 摘要

24. Monitoring and Diagnosability of Perception Systems [PDF] 摘要

25. Relative Drone -- Ground Vehicle Localization using LiDAR and Fisheye Cameras through Direct and Indirect Observations [PDF] 摘要

26. Metastatic Cancer Image Classification Based On Deep Learning Method [PDF] 摘要

27. SALAD: Self-Assessment Learning for Action Detection [PDF] 摘要

28. LEAN: graph-based pruning for convolutional neural networks by extracting longest chains [PDF] 摘要

29. REPAC: Reliable estimation of phase-amplitude coupling in brain networks [PDF] 摘要

30. Unified Multi-Modal Landmark Tracking for Tightly Coupled Lidar-Visual-Inertial Odometry [PDF] 摘要

31. FastTrack: an open-source software for tracking varying numbers of deformable objects [PDF] 摘要

32. Learning Object Manipulation Skills via Approximate State Estimation from Real Videos [PDF] 摘要

33. Diffusion models for Handwriting Generation [PDF] 摘要

34. Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation [PDF] 摘要

35. Disassemblable Fieldwork CT Scanner Using a 3D-printed Calibration Phantom [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-11-12

发表于 2020-11-12 分类于 arxiv ， CV 21k 36 分钟

目录

1. GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts [PDF] 摘要

2. LittleYOLO-SPP: A Delicate Real-Time Vehicle Detection Algorithm [PDF] 摘要

3. Age Gap Reducer-GAN for Recognizing Age-Separated Faces [PDF] 摘要

4. Transferred Fusion Learning using Skipped Networks [PDF] 摘要

5. DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs [PDF] 摘要

6. Where to drive: free space detection with one fisheye camera [PDF] 摘要

7. Dynamic Plane Convolutional Occupancy Networks [PDF] 摘要

8. Learned Equivariant Rendering without Transformation Supervision [PDF] 摘要

9. Finding Relevant Flood Images on Twitter using Content-based Filters [PDF] 摘要

10. Survey on 3D face reconstruction from uncalibrated images [PDF] 摘要

11. DeepSim: Semantic similarity metrics for learned image registration [PDF] 摘要

12. A CNN-based Feature Space for Semi-supervised Incremental Learning in Assisted Living Applications [PDF] 摘要

13. Learning from THEODORE: A Synthetic Omnidirectional Top-View Indoor Dataset for Deep Transfer Learning [PDF] 摘要

14. Invariant Deep Compressible Covariance Pooling for Aerial Scene Categorization [PDF] 摘要

15. Noise Conscious Training of Non Local Neural Network powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising [PDF] 摘要

16. Zero-Pair Image to Image Translation using Domain Conditional Normalization [PDF] 摘要

17. FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification [PDF] 摘要

18. A Hybrid Approach for 6DoF Pose Estimation [PDF] 摘要

19. Progressive Spatio-Temporal Graph Convolutional Network for Skeleton-Based Human Action Recognition [PDF] 摘要

20. Skeleton-based Relational Reasoning for Group Activity Analysis [PDF] 摘要

21. Semi-supervised Sparse Representation with Graph Regularization for Image Classification [PDF] 摘要

22. Self-supervised Segmentation via Background Inpainting [PDF] 摘要

23. Scribble-Supervised Semantic Segmentation by Random Walk on Neural Representation and Self-Supervision on Neural Eigenspa [PDF] 摘要

24. Intentonomy: a Dataset and Study towards Human Intent Understanding [PDF] 摘要

25. End-to-End Chinese Landscape Painting Creation Using Generative Adversarial Networks [PDF] 摘要

26. Optimized Loss Functions for Object detection and Application on Nighttime Vehicle Detection [PDF] 摘要

27. Automatic Open-World Reliability Assessment [PDF] 摘要

28. Unsupervised Learning of Dense Visual Representations [PDF] 摘要

29. ForestNet: Classifying Drivers of Deforestation in Indonesia using Deep Learning on Satellite Imagery [PDF] 摘要

30. A Self-supervised Learning System for Object Detection in Videos Using Random Walks on Graphs [PDF] 摘要

31. Fast & Slow Learning: Incorporating Synthetic Gradients in Neural Memory Controllers [PDF] 摘要

32. Debugging Tests for Model Explanations [PDF] 摘要

33. Using GANs to Synthesise Minimum Training Data for Deepfake Generation [PDF] 摘要

34. Collaborative Augmented Reality on Smartphones via Life-long City-scale Maps [PDF] 摘要

35. Selective Spatio-Temporal Aggregation Based Pose Refinement System: Towards Understanding Human Activities in Real-World Videos [PDF] 摘要

36. Vulnerability of the Neural Networks Against Adversarial Examples: A Survey [PDF] 摘要

37. Transformers for One-Shot Visual Imitation [PDF] 摘要

38. FAT: Training Neural Networks for Reliable Inference Under Hardware Faults [PDF] 摘要

39. Distorted image restoration using stacked adversarial network [PDF] 摘要

40. Classification of COVID-19 in Chest CT Images using Convolutional Support Vector Machines [PDF] 摘要

41. EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labels [PDF] 摘要

42. Skin disease diagnosis with deep learning: a review [PDF] 摘要

43. Adversarial images for the primate brain [PDF] 摘要

44. Invertible CNN-Based Super Resolution with Downsampling Awareness [PDF] 摘要

45. An ensemble-based approach by fine-tuning the deep transfer learning models to classify pneumonia from chest X-ray images [PDF] 摘要

46. A Unified Framework for Compressive Video Recovery from Coded Exposure Techniques [PDF] 摘要

47. Dense U-net for super-resolution with shuffle pooling layer [PDF] 摘要

48. Do You See What I See? Coordinating Multiple Aerial Cameras for Robot Cinematography [PDF] 摘要

49. Self-Supervised Out-of-Distribution Detection in Brain CT Scans [PDF] 摘要

50. Glioma Classification Using Multimodal Radiology and Histology Data [PDF] 摘要

51. Deep Learning Derived Histopathology Image Score for Increasing Phase 3 Clinical Trial Probability of Success [PDF] 摘要

阅读全文 »

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

发表于 2020-11-11 分类于 arxiv ， CV 95k 2:38

目录

1. Learning to Communicate and Correct Pose Errors [PDF] 摘要

2. Perception Improvement for Free: Exploring Imperceptible Black-box Adversarial Attacks on Image Classification [PDF] 摘要

3. Classification of Polarimetric SAR Images Using Compact Convolutional Neural Networks [PDF] 摘要

4. Temporal Stochastic Softmax for 3D CNNs: An Application in Facial Expression Recognition [PDF] 摘要

5. Pixel precise unsupervised detection of viral particle proliferation in cellular imaging data [PDF] 摘要

6. A Multi-Plant Disease Diagnosis Method using Convolutional Neural Network [PDF] 摘要

7. Multi-modal, multi-task, multi-attention (M3) deep learning detection of reticular pseudodrusen: 1 towards automated and accessible classification of age-related macular degeneration [PDF] 摘要

8. Multi-pooled Inception features for no-reference image quality assessment [PDF] 摘要

9. On-Device Language Identification of Text in Images using Diacritic Characters [PDF] 摘要

10. MP-ResNet: Multi-path Residual Network for the Semantic segmentation of High-Resolution PolSAR Images [PDF] 摘要

11. Decoupled Appearance and Motion Learning for Efficient Anomaly Detection in Surveillance Video [PDF] 摘要

12. Human-centric Spatio-Temporal Video Grounding With Visual Transformers [PDF] 摘要

13. Point Cloud Registration Based on Consistency Evaluation of Rigid Transformation in Parameter Space [PDF] 摘要

14. Residual Pose: A Decoupled Approach for Depth-based 3D Human Pose Estimation [PDF] 摘要

15. Deep Multimodal Fusion by Channel Exchanging [PDF] 摘要

16. Joint Super-Resolution and Rectification for Solar Cell Inspection [PDF] 摘要

17. Removing Brightness Bias in Rectified Gradients [PDF] 摘要

18. AIM 2020 Challenge on Learned Image Signal Processing Pipeline [PDF] 摘要

19. SelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environments [PDF] 摘要

20. Conceptual Compression via Deep Structure and Texture Synthesis [PDF] 摘要

21. Detecting Human-Object Interaction with Mixed Supervision [PDF] 摘要

22. Unsupervised Contrastive Photo-to-Caricature Translation based on Auto-distortion [PDF] 摘要

23. Multi-modal Fusion for Single-Stage Continuous Gesture Recognition [PDF] 摘要

24. Simple means Faster: Real-Time Human Motion Forecasting in Monocular First Person Videos on CPU [PDF] 摘要

25. Stage-wise Channel Pruning for Model Compression [PDF] 摘要

26. CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection [PDF] 摘要

27. A low latency ASR-free end to end spoken language understanding system [PDF] 摘要

28. STCNet: Spatio-Temporal Cross Network for Industrial Smoke Detection [PDF] 摘要

29. On Efficient and Robust Metrics for RANSAC Hypotheses and 3D Rigid Registration [PDF] 摘要

30. Understanding the hand-gestures using Convolutional Neural Networks and Generative Adversial Networks [PDF] 摘要

31. Social-STAGE: Spatio-Temporal Multi-Modal Future Trajectory Forecast [PDF] 摘要

32. Ellipse Detection and Localization with Applications to Knots in Sawn Lumber Images [PDF] 摘要

33. CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection [PDF] 摘要

34. Kinematics-Guided Reinforcement Learning for Object-Aware 3D Ego-Pose Estimation [PDF] 摘要

35. After All, Only The Last Neuron Matters: Comparing Multi-modal Fusion Functions for Scene Graph Generation [PDF] 摘要

36. Predicting Landsat Reflectance with Deep Generative Fusion [PDF] 摘要

37. MUSE: Illustrating Textual Attributes by Portrait Generation [PDF] 摘要

38. Learning to Infer Semantic Parameters for 3D Shape Editing [PDF] 摘要

39. Similarity-Based Clustering for Enhancing Image Classification Architectures [PDF] 摘要

40. Ontology-driven Event Type Classification in Images [PDF] 摘要

41. Explainable COVID-19 Detection Using Chest CT Scans and Deep Learning [PDF] 摘要

42. An Attack on InstaHide: Is Private Learning Possible with Instance Encoding? [PDF] 摘要

43. EPSR: Edge Profile Super resolution [PDF] 摘要

44. OpenKinoAI: An Open Source Framework for Intelligent Cinematography and Editing of Live Performances [PDF] 摘要

45. Pristine annotations-based multi-modal trained artificial intelligence solution to triage chest X-ray for COVID-19 [PDF] 摘要

46. Bridging the Performance Gap between FGSM and PGD Adversarial Training [PDF] 摘要

47. Principles of Stochastic Computing: Fundamental Concepts and Applications [PDF] 摘要

48. Classification of optics-free images with deep neural networks [PDF] 摘要

49. A Soft Computing Approach for Selecting and Combining Spectral Bands [PDF] 摘要

50. Noise2Stack: Improving Image Restoration by Learning from Volumetric Data [PDF] 摘要

51. Deep correction of breathing-related artifacts in MR-thermometry [PDF] 摘要

52. Tattoo tomography: Freehand 3D photoacoustic image reconstruction with an optical pattern [PDF] 摘要

53. AIM 2020 Challenge on Rendering Realistic Bokeh [PDF] 摘要

54. Towards a Better Global Loss Landscape of GANs [PDF] 摘要

55. The Virtual Goniometer: A new method for measuring angles on 3D models of fragmentary bone and lithics [PDF] 摘要

56. Learnings from Frontier Development Lab and SpaceML -- AI Accelerators for NASA and ESA [PDF] 摘要

57. Deep Reinforcement Learning for Navigation in AAA Video Games [PDF] 摘要

58. Predicting the Future is like Completing a Painting! [PDF] 摘要

阅读全文 »

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

发表于 2020-11-11 分类于 arxiv ， CL 37k 1:02

目录

1. DoLFIn: Distributions over Latent Features for Interpretability [PDF] 摘要

2. Neural Machine Translation for Extremely Low-Resource African Languages: A Case Study on Bambara [PDF] 摘要

3. Towards Interpretable Natural Language Understanding with Explanations as Latent Variables [PDF] 摘要

4. Medical Knowledge-enriched Textual Entailment Framework [PDF] 摘要

5. Towards Preemptive Detection of Depression and Anxiety in Twitter [PDF] 摘要

6. On the State of Social Media Data for Mental Health Research [PDF] 摘要

7. UmBERTo-MTSA @ AcCompl-It: Improving Complexity and Acceptability Prediction with Multi-task Learning on Self-Supervised Annotations [PDF] 摘要

8. Multi-Task Sequence Prediction For Tunisian Arabizi Multi-Level Annotation [PDF] 摘要

9. Does Social Support Expressed in Post Titles Elicit Comments in Online Substance Use Recovery Forums? [PDF] 摘要

10. Translating Similar Languages: Role of Mutual Intelligibility in Multilingual Transformers [PDF] 摘要

11. To What Degree Can Language Borders Be Blurred In BERT-based Multilingual Spoken Language Understanding? [PDF] 摘要

12. When Do You Need Billions of Words of Pretraining Data? [PDF] 摘要

13. On the Usefulness of Self-Attention for Automatic Speech Recognition with Transformers [PDF] 摘要

14. Determining Question-Answer Plausibility in Crowdsourced Datasets Using Multi-Task Learning [PDF] 摘要

15. A Transfer Learning Approach for Dialogue Act Classification of GitHub Issue Comments [PDF] 摘要

16. Natural Language Inference in Context -- Investigating Contextual Reasoning over Long Texts [PDF] 摘要

17. Simultaneous Speech-to-Speech Translation System with Neural Incremental ASR, MT, and TTS [PDF] 摘要

18. Multi-document Summarization via Deep Learning Techniques: A Survey [PDF] 摘要

19. Language Through a Prism: A Spectral Approach for Multiscale Language Representations [PDF] 摘要

20. EstBERT: A Pretrained Language-Specific BERT for Estonian [PDF] 摘要

21. An Analysis of Dataset Overlap on Winograd-Style Tasks [PDF] 摘要

22. Adversarial Semantic Collisions [PDF] 摘要

23. CLAR: A Cross-Lingual Argument Regularizer for Semantic Role Labeling [PDF] 摘要

24. Biomedical Information Extraction for Disease Gene Prioritization [PDF] 摘要

25. Generalized LSTM-based End-to-End Text-Independent Speaker Verification [PDF] 摘要

26. Pretraining Strategies, Waveform Model Choice, and Acoustic Configurations for Multi-Speaker End-to-End Speech Synthesis [PDF] 摘要

27. Personalized Query Rewriting in Conversational AI Agents [PDF] 摘要

28. Speaker De-identification System using Autoencodersand Adversarial Training [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-11-10

发表于 2020-11-10 分类于 arxiv ， CV 154k 4:17

目录

1. Find it if You Can: End-to-End Adversarial Erasing for Weakly-Supervised Semantic Segmentation [PDF] 摘要

2. Fast Fourier Intrinsic Network [PDF] 摘要

3. Masked Face Image Classification with Sparse Representation based on Majority Voting Mechanism [PDF] 摘要

4. MinkLoc3D: Point Cloud Based Large-Scale Place Recognition [PDF] 摘要

5. Fast Hybrid Cascade for Voxel-based 3D Object Classification [PDF] 摘要

6. DynaVSR: Dynamic Adaptive Blind Video Super-Resolution [PDF] 摘要

7. Deep Transfer Learning for Automated Diagnosis of Skin Lesions from Photographs [PDF] 摘要

8. Neural Architecture Search with an Efficient Multiobjective Evolutionary Framework [PDF] 摘要

9. TTVOS: Lightweight Video Object Segmentation with Adaptive Template Attention Module and Temporal Consistency Loss [PDF] 摘要

10. FACEGAN: Facial Attribute Controllable rEenactment GAN [PDF] 摘要

11. SeasonDepth: Cross-Season Monocular Depth Prediction Dataset and Benchmark under Multiple Environments [PDF] 摘要

12. EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes [PDF] 摘要

13. MAGNeto: An Efficient Deep Learning Method for the Extractive Tags Summarization Problem [PDF] 摘要

14. EfficientPose -- An efficient, accurate and scalable end-to-end 6D multi object pose estimation approach [PDF] 摘要

15. Learning the Best Pooling Strategy for Visual Semantic Embedding [PDF] 摘要

16. Sketch-Inspector: a Deep Mixture Model for High-Quality Sketch Generation of Cats [PDF] 摘要

17. Closing the Generalization Gap in One-Shot Object Detection [PDF] 摘要

18. Unified Quality Assessment of In-the-Wild Videos with Mixed Datasets Training [PDF] 摘要

19. Robust Visual Tracking via Statistical Positive Sample Generation and Gradient Aware Learning [PDF] 摘要

20. Improved Soccer Action Spotting using both Audio and Video Streams [PDF] 摘要

21. Real-time object detection method based on improved YOLOv4-tiny [PDF] 摘要

22. Dual ResGCN for Balanced Scene GraphGeneration [PDF] 摘要

23. End-to-end Lane Shape Prediction with Transformers [PDF] 摘要

24. An improved helmet detection method for YOLOv3 on an unbalanced dataset [PDF] 摘要

25. Detecting Outliers with Foreign Patch Interpolation [PDF] 摘要

26. Two-Stream Appearance Transfer Network for Person Image Generation [PDF] 摘要

27. Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications [PDF] 摘要

28. Localising In Complex Scenes Using Balanced Adversarial Adaptation [PDF] 摘要

29. Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks [PDF] 摘要

30. Image Clustering using an Augmented Generative Adversarial Network and Information Maximization [PDF] 摘要

31. An HVS-Oriented Saliency Map Prediction Modeling [PDF] 摘要

32. AI on the Bog: Monitoring and Evaluating Cranberry Crop Risk [PDF] 摘要

33. Analysis of Dimensional Influence of Convolutional Neural Networks for Histopathological Cancer Classification [PDF] 摘要

34. Performance Analysis of Optimizers for Plant Disease Classification with Convolutional Neural Networks [PDF] 摘要

35. Predictive Analysis of Diabetic Retinopathy with Transfer Learning [PDF] 摘要

36. Adaptive Linear Span Network for Object Skeleton Detection [PDF] 摘要

37. The quantization error in a Self-Organizing Map as a contrast and colour specific indicator of single-pixel change in large random patterns [PDF] 摘要

38. FlowCaps: Optical Flow Estimation with Capsule Networks For Action Recognition [PDF] 摘要

39. Right on Time: Multi-Temporal Convolutions for Human Action Recognition in Videos [PDF] 摘要

40. PointTransformer for Shape Classification and Retrieval of 3D and ALS Roof PointClouds [PDF] 摘要

41. Integrating Human Gaze into Attention for Egocentric Activity Recognition [PDF] 摘要

42. Faster object tracking pipeline for real time tracking [PDF] 摘要

43. Channel Pruning Guided by Spatial and Channel Attention for DNNs in Intelligent Edge Computing [PDF] 摘要

44. Latent Neural Differential Equations for Video Generation [PDF] 摘要

45. Deep traffic light detection by overlaying synthetic context on arbitrary natural images [PDF] 摘要

46. On the spatial attention in Spatio-Temporal Graph Convolutional Networks for skeleton-based human action recognition [PDF] 摘要

47. Towards Resolving the Challenge of Long-tail Distribution in UAV Images for Object Detection [PDF] 摘要

48. Sim-to-Real Transfer for Vision-and-Language Navigation [PDF] 摘要

49. Symmetric Parallax Attention for Stereo Image Super-Resolution [PDF] 摘要

50. Deep Learning Analysis and Age Prediction from Shoeprints [PDF] 摘要

51. Rapid Pose Label Generation through Sparse Representation of Unknown Objects [PDF] 摘要

52. Text-to-Image Generation Grounded by Fine-Grained User Attention [PDF] 摘要

53. A Multi-stream Convolutional Neural Network for Micro-expression Recognition Using Optical Flow and EVM [PDF] 摘要

54. A Strong Baseline for Crowd Counting and Unsupervised People Localization [PDF] 摘要

55. Coarse- and Fine-grained Attention Network with Background-aware Loss for Crowd Density Map Estimation [PDF] 摘要

56. DeepCFL: Deep Contextual Features Learning from a Single Image [PDF] 摘要

57. Blind Motion Deblurring through SinGAN Architecture [PDF] 摘要

58. TB-Net: A Three-Stream Boundary-Aware Network for Fine-Grained Pavement Disease Segmentation [PDF] 摘要

59. Depthwise Multiception Convolution for Reducing Network Parameters without Sacrificing Accuracy [PDF] 摘要

60. Domain-Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing [PDF] 摘要

61. Identifying Mislabeled Images in Supervised Learning Utilizing Autoencoder [PDF] 摘要

62. ROBIN: a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariants [PDF] 摘要

63. Augmented Equivariant Attention Networks for Electron Microscopy Image Super-Resolution [PDF] 摘要

64. Efficient Robust Watermarking Based on Quaternion Singular Value Decomposition and Coefficient Pair Selection [PDF] 摘要

65. A Weakly Supervised Convolutional Network for Change Segmentation and Classification [PDF] 摘要

66. Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze [PDF] 摘要

67. MPRNet: Multi-Path Residual Network for Lightweight Image Super Resolution [PDF] 摘要

68. Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts [PDF] 摘要

69. Learning to Localize in New Environments from Synthetic Training Data [PDF] 摘要

70. Towards a quantitative assessment of neurodegeneration in Alzheimer's disease [PDF] 摘要

71. A Poisson multi-Bernoulli mixture filter for coexisting point and extended targets [PDF] 摘要

72. An Empirical Study of Visual Features for DNN based Audio-Visual Speech Enhancement in Multi-talker Environments [PDF] 摘要

73. CapWAP: Captioning with a Purpose [PDF] 摘要

74. PAMS: Quantized Super-Resolution via Parameterized Max Scale [PDF] 摘要

75. Geometric Structure Aided Visual Inertial Localization [PDF] 摘要

76. Fine Perceptive GANs for Brain MR Image Super-Resolution in Wavelet Domain [PDF] 摘要

77. Kimera-Multi: a System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping [PDF] 摘要

78. Long Range Arena: A Benchmark for Efficient Transformers [PDF] 摘要

79. Real-time Surgical Environment Enhancement for Robot-Assisted Minimally Invasive Surgery Based on Super-Resolution [PDF] 摘要

80. Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments [PDF] 摘要

81. Cross-Modal Self-Attention Distillation for Prostate Cancer Segmentation [PDF] 摘要

82. Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles [PDF] 摘要

83. Autonomous Intruder Detection Using a ROS-Based Multi-Robot System Equipped with 2D-LiDAR Sensors [PDF] 摘要

84. Multiscale Point Cloud Geometry Compression [PDF] 摘要

85. Grading the Severity of Arteriolosclerosis from Retinal Arterio-venous Crossing Patterns [PDF] 摘要

86. Robustness and Diversity Seeking Data-Free Knowledge Distillation [PDF] 摘要

87. Interventional Domain Adaptation [PDF] 摘要

88. Data--driven Image Restoration with Option--driven Learning for Big and Small Astronomical Image Datasets [PDF] 摘要

89. Deeply-Supervised Density Regression for Automatic Cell Counting in Microscopy Images [PDF] 摘要

90. Strawberry Detection Using a Heterogeneous Multi-Processor Platform [PDF] 摘要

91. Motion Prediction on Self-driving Cars: A Review [PDF] 摘要

92. Unmasking Communication Partners: A Low-Cost AI Solution for Digitally Removing Head-Mounted Displays in VR-Based Telepresence [PDF] 摘要

93. HDR Imaging with Quanta Image Sensors: Theoretical Limits and Optimal Reconstruction [PDF] 摘要

94. Chest X-ray Image Phase Features for Improved Diagnosis of COVID-19 Using Convolutional Neural Network [PDF] 摘要

阅读全文 »

【arxiv论文】 Computation and Language 2020-11-10

发表于 2020-11-10 分类于 arxiv ， CL 77k 2:08

目录

1. Scaling Hidden Markov Language Models [PDF] 摘要

2. Action State Update Approach to Dialogue Management [PDF] 摘要

3. Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze [PDF] 摘要

4. Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts [PDF] 摘要

5. Automated Discovery of Mathematical Definitions in Text with Deep Neural Networks [PDF] 摘要

6. Auxiliary Sequence Labeling Tasks for Disfluency Detection [PDF] 摘要

7. VisBERT: Hidden-State Visualizations for Transformers [PDF] 摘要

8. Synonym Knowledge Enhanced Reader for Chinese Idiom Reading Comprehension [PDF] 摘要

9. Hierarchical Multitask Learning Approach for BERT [PDF] 摘要

10. Bangla Text Classification using Transformers [PDF] 摘要

11. Catch the "Tails" of BERT [PDF] 摘要

12. Low-Resource Adaptation of Neural NLP Models [PDF] 摘要

13. Character-level Representations Improve DRS-based Semantic Parsing Even in the Age of BERT [PDF] 摘要

14. BERT-JAM: Boosting BERT-Enhanced Neural Machine Translation with Joint Attention [PDF] 摘要

15. CapWAP: Captioning with a Purpose [PDF] 摘要

16. AI Stories: An Interactive Narrative System for Children [PDF] 摘要

17. Pointing to Subwords for Generating Function Names in Source Code [PDF] 摘要

18. Efficient End-to-End Speech Recognition Using Performers in Conformers [PDF] 摘要

19. Text Classification through Glyph-aware Disentangled Character Embedding and Semantic Sub-character Augmentation [PDF] 摘要

20. Chapter Captor: Text Segmentation in Novels [PDF] 摘要

21. "What Do You Mean by That?" A Parser-Independent Interactive Approach for Enhancing Text-to-SQL [PDF] 摘要

22. CxGBERT: BERT meets Construction Grammar [PDF] 摘要

23. The UCF Podcast Summarization System at TREC 2020 [PDF] 摘要

24. What time is it? Temporal Analysis of Novels [PDF] 摘要

25. Metrics also Disagree in the Low Scoring Range: Revisiting Summarization Evaluation Metrics [PDF] 摘要

26. Exploring End-to-End Differentiable Natural Logic Modeling [PDF] 摘要

27. Stochastic Attention Head Removal: A Simple and Effective Method for Improving Automatic Speech Recognition with Transformers [PDF] 摘要

28. Adapting a Language Model for Controlled Affective Text Generation [PDF] 摘要

29. A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systems [PDF] 摘要

30. Detecting Emerging Symptoms of COVID-19 using Context-based Twitter Embeddings [PDF] 摘要

31. On the Practical Ability of Recurrent Neural Networks to Recognize Hierarchical Languages [PDF] 摘要

32. Denoising Relation Extraction from Document-level Distant Supervision [PDF] 摘要

33. Best Practices for Data-Efficient Modeling in NLG:How to Train Production-Ready Neural Models with Less Data [PDF] 摘要

34. Explainable Automated Fact-Checking: A Survey [PDF] 摘要

35. Knowledge-driven Self-supervision for Zero-shot Commonsense Question Answering [PDF] 摘要

36. Rethinking the Value of Transformer Components [PDF] 摘要

37. PairRE: Knowledge Graph Embeddings via Paired Relation Vectors [PDF] 摘要

38. AlphaMWE: Construction of Multilingual Parallel Corpora with MWE Annotations [PDF] 摘要

39. Know What You Don't Need: Single-Shot Meta-Pruning for Attention Heads [PDF] 摘要

40. NLP-CIC @ PRELEARN: Mastering prerequisites relations, from handcrafted features to embeddings [PDF] 摘要

41. NLP-CIC @ DIACR-Ita: POS and Neighbor Based Distributional Models for Lexical Semantic Change in Diachronic Italian Corpora [PDF] 摘要

42. Naturalization of Text by the Insertion of Pauses and Filler Words [PDF] 摘要

43. Acoustics Based Intent Recognition Using Discovered Phonetic Units for Low Resource Languages [PDF] 摘要

44. Hostility Detection Dataset in Hindi [PDF] 摘要

45. Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesis [PDF] 摘要

46. Artificial Intelligence Decision Support for Medical Triage [PDF] 摘要

47. Mask Proxy Loss for Text-Independent Speaker Recognition [PDF] 摘要

48. Knowledge Distillation for Singing Voice Detection [PDF] 摘要

49. Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition [PDF] 摘要

50. Long Range Arena: A Benchmark for Efficient Transformers [PDF] 摘要

51. DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion [PDF] 摘要

52. Learning to Model and Ignore Dataset Bias with Mixed Capacity Ensembles [PDF] 摘要

53. Sim-to-Real Transfer for Vision-and-Language Navigation [PDF] 摘要

54. Template Controllable keywords-to-text Generation [PDF] 摘要

阅读全文 »

【arxiv论文】 Computer Vision and Pattern Recognition 2020-11-09

发表于 2020-11-09 分类于 arxiv ， CV 50k 1:23

目录

1. Large-scale multilingual audio visual dubbing [PDF] 摘要

2. Deep Cross-modal Proxy Hashing [PDF] 摘要

3. Illumination Normalization by Partially Impossible Encoder-Decoder Cost Function [PDF] 摘要

4. Disentangling 3D Prototypical Networks For Few-Shot Concept Learning [PDF] 摘要

5. Domain Adaptive Person Re-Identification via Coupling Optimization [PDF] 摘要

6. Self Supervised Learning for Object Localisation in 3D Tomographic Images [PDF] 摘要

7. Towards Efficient Scene Understanding via Squeeze Reasoning [PDF] 摘要

8. Learning to Orient Surfaces by Self-supervised Spherical CNNs [PDF] 摘要

9. Event-VPR: End-to-End Weakly Supervised Network Architecture for Event-based Visual Place Recognition [PDF] 摘要

10. "What's This?" -- Learning to Segment Unknown Objects from Manipulation Sequences [PDF] 摘要

11. Hi-UCD: A Large-scale Dataset for Urban Semantic Change Detection in Remote Sensing Imagery [PDF] 摘要

12. Channel Pruning via Multi-Criteria based on Weight Dependency [PDF] 摘要

13. Efficient image retrieval using multi neural hash codes and bloom filters [PDF] 摘要

14. Learning a Geometric Representation for Data-Efficient Depth Estimation via Gradient Field and Contrastive Loss [PDF] 摘要

15. ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras [PDF] 摘要

16. GHFP: Gradually Hard Filter Pruning [PDF] 摘要

17. Confusable Learning for Large-class Few-Shot Classification [PDF] 摘要

18. Affinity LCFCN: Learning to Segment Fish with Weak Supervision [PDF] 摘要

19. Ellipse Loss for Scene-Compliant Motion Prediction [PDF] 摘要

20. Uncertainty-Aware Vehicle Orientation Estimation for Joint Detection-Prediction Models [PDF] 摘要

21. Learning Rolling Shutter Correction from Real Data without Camera Motion Assumption [PDF] 摘要

22. Can Human Sex Be Learned Using Only 2D Body Keypoint Estimations? [PDF] 摘要

23. Smart Time-Multiplexing of Quads Solves the Multicamera Interference Problem [PDF] 摘要

24. End-to-end Deep Learning Methods for Automated Damage Detection in Extreme Events at Various Scales [PDF] 摘要

25. Towards Keypoint Guided Self-Supervised Depth Estimation [PDF] 摘要

26. A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNs [PDF] 摘要

27. A Tree-structure Convolutional Neural Network for Temporal Features Exaction on Sensor-based Multi-resident Activity Recognition [PDF] 摘要

28. A Comprehensive Comparison of Multi-Dimensional Image Denoising Methods [PDF] 摘要

29. Noise2Sim -- Similarity-based Self-Learning for Image Denoising [PDF] 摘要

30. Intra-Domain Task-Adaptive Transfer Learning to Determine Acute Ischemic Stroke Onset Time [PDF] 摘要

31. Learning to Respond with Your Favorite Stickers: A Framework of Unifying Multi-Modality and User Preference in Multi-Turn Dialog [PDF] 摘要

32. Deep coastal sea elements forecasting using U-Net based models [PDF] 摘要

33. Modular Primitives for High-Performance Differentiable Rendering [PDF] 摘要

34. Task-relevant Representation Learning for Networked Robotic Perception [PDF] 摘要

35. Automatic Head and Neck Tumor Segmentation in PET/CT with Scale Attention Network [PDF] 摘要

36. MorphEyes: Variable Baseline Stereo For Quadrotor Navigation [PDF] 摘要

37. Identifying and interpreting tuning dimensions in deep networks [PDF] 摘要

阅读全文 »