Papers
Wed 6 Apr 2022
190 papers
- Demonstrate Once, Imitate Immediately (DOME): Learning Visual Servoing for One-Shot Imitation LearningOffline RL and imitation learning from data → Robot manipulation imitation learning
- Learning to Adapt Clinical Sequences with Residual Mixture of ExpertsMixture-of-experts → Medical and biomedical MoE
- The Swiss Army Knife for Image-to-Image Translation: Multi-Task Diffusion ModelsDiffusion models → Medical imaging and segmentation
- Classification of Buildings' Potential for Seismic Damage by Means of Artificial Intelligence Techniques
- Machine Learning-Based GPS Multipath Detection Method Using Dual Antennas
- Machine learning identification of organic compounds using visible light
- Domain Specific Fine-tuning of Denoising Sequence-to-Sequence Models for Natural Language Summarization
- The TalkMoves Dataset: K-12 Mathematics Lesson Transcripts Annotated for Teacher and Student Discursive Moves
- GlacierNet2: A Hybrid Multi-Model Learning Architecture for Alpine Glacier Mapping
- Stochastic Multi-armed Bandits with Non-stationary Rewards Generated by a Linear Dynamical System
- Forecasting Cryptocurrency Returns from Sentiment Signals: An Analysis of BERT Classifiers and Weak Supervision
- Domain Adversarial Graph Convolutional Network Based on RSSI and Crowdsensing for Indoor Localization
- IMLE-Net: An Interpretable Multi-level Multi-channel Model for ECG Classification
- Structure-aware Protein Self-supervised Learning
- GPSAF: A Generalized Probabilistic Surrogate-Assisted Framework for Constrained Single- and Multi-objective Optimization
- Mitosis domain generalization in histopathology images -- The MIDOG challenge
- Drivers' attention detection: a systematic literature review
- Successes and critical failures of neural networks in capturing human-like speech recognition
- PlutoNet: An Efficient Polyp Segmentation Network with Modified Partial Decoder and Decoder Consistency Training
- RF Signal Transformation and Classification using Deep Neural Networks
- Emotional Speech Recognition with Pre-trained Deep Visual Models
- Deep transfer learning for system identification using long short-term memory neural networks
- A novel nonconvex, smooth-at-origin penalty for statistical learning
- AutoCOR: Autonomous Condylar Offset Ratio Calculator on TKA-Postoperative Lateral Knee X-ray
- BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis
- UIGR: Unified Interactive Garment Retrieval
- AUV-Net: Learning Aligned UV Maps for Texture Transfer and Synthesis
- Hierarchical Self-supervised Representation Learning for Movie Understanding
- Data Justice Stories: A Repository of Case Studies
- Advancing Data Justice Research and Practice: An Integrated Literature Review
- Knowledge Infused Decoding
- Audio-Visual Person-of-Interest DeepFake Detection
- Instance Segmentation of Unlabeled Modalities via Cyclic Segmentation GAN
- Graph Neural Networks Designed for Different Graph Types: A Survey
- OSCARS: An Outlier-Sensitive Content-Based Radiography Retrieval System
- Urdu Morphology, Orthography and Lexicon Extraction
- ByT5 model for massively multilingual grapheme-to-phoneme conversion
- The Self-Optimal-Transport Feature Transform
- The 2021 Urdu Fake News Detection Task using Supervised Machine Learning and Feature Combinations
- Late multimodal fusion for image and audio music transcription
- Abusive and Threatening Language Detection in Urdu using Supervised Machine Learning and Feature Combinations
- Standardized feature extraction from pairwise conflicts applied to the train rescheduling problem
- Thermal to Visible Image Synthesis under Atmospheric Turbulence
- Perceive, Represent, Generate: Translating Multimodal Information to Robotic Motion Trajectories
- Fusing finetuned models for better pretraining
- FFC-SE: Fast Fourier Convolution for Speech Enhancement
- SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesis
- DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors
- Hierarchical Annotation for Building A Suite of Clinical Natural Language Processing Tasks: Progress Note Understanding
- VALUE: Understanding Dialect Disparity in NLU
- Statistical Model Criticism of Variational Auto-Encoders
- Federated Learning for Distributed Spectrum Sensing in NextG Communication Networks
- Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment
- The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems
- Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency
- EfficientCellSeg: Efficient Volumetric Cell Segmentation Using Context Aware Pseudocoloring
- Analysis of Different Losses for Deep Learning Image Colorization
- A neural network-supported two-stage algorithm for lightweight dereverberation on hearing devices
- Multi-Scale Memory-Based Video Deblurring
- Follow My Eye: Using Gaze to Supervise Computer-Aided Diagnosis
- Temporal Alignment Networks for Long-term Video
- Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation
- LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification
- Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection
- SMU-Net: Style matching U-Net for brain tumor segmentation with missing modalities
- Simple and Effective Synthesis of Indoor 3D Scenes
- LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity
- Video Demoireing with Relation-Based Temporal Consistency
- Inducing Positive Perspectives with Text Reframing
- Koopman-based spectral clustering of directed and time-evolving graphs
- Guaranteed Bounds for Posterior Inference in Universal Probabilistic Programming
- Marrying Fairness and Explainability in Supervised Learning
- "The Pedestrian next to the Lamppost" Adaptive Object Graphs for Better Instantaneous Mapping
- Intervertebral Disc Labeling With Learning Shape Information, A Look Once Approach
- S-R2F2U-Net: A single-stage model for teeth segmentation
- Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
- An Empirical Study of End-to-End Temporal Action Detection
- Beam Search: Faster and Monotonic
- Paying More Attention to Self-attention: Improving Pre-trained Language Models via Attention Guiding
- A survey on recently proposed activation functions for Deep Learning
- Question Generation for Reading Comprehension Assessment by Modeling How and What to Ask
- Knowledge Base Index Compression via Dimensionality and Precision Reduction
- EMMT: A simultaneous eye-tracking, 4-electrode EEG and audio corpus for multi-modal reading and translation scenarios
- Efficient Bayesian Network Structure Learning via Parameterized Local Search on Topological Orderings
- End-to-End Instance Edge Detection
- Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks
- DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors
- A Cognitive Framework for Delegation Between Error-Prone AI and Human Agents
- Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attacks
- PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations
- ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound
- Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis
- Influence of Color Spaces for Deep Learning Image Colorization
- KNN-Diffusion: Image Generation via Large-Scale Retrieval
- Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training
- Open-Source Tools for Behavioral Video Analysis: Setup, Methods, and Development
- CCAT-NET: A Novel Transformer Based Semi-supervised Framework for Covid-19 Lung Lesion Segmentation
- High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize
- An Empirical Study of Remote Sensing Pretraining
- ShowFace: Coordinated Face Inpainting with Memory-Disentangled Refinement Networks
All 190
- Language Resources and Technologies for Non-Scheduled and Endangered Indian Languages
- drsphelps at SemEval-2022 Task 2: Learning idiom representations using BERTRAM
- Aggression in Hindi and English Speech: Acoustic Correlates and Automatic Identification
- An Algebraic Approach to Learning and Grounding
- BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation
- Expression-preserving face frontalization improves visually assisted speech processing
- Federated Self-supervised Speech Representations: Are We There Yet?
- Dimensionality Expansion of Load Monitoring Time Series and Transfer Learning for EMS
- Implicit Motion-Compensated Network for Unsupervised Video Object Segmentation
- Global Readiness of Language Technology for Healthcare: What would it Take to Combat the Next Pandemic?
- GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasets
- 3D face reconstruction with dense landmarks
- Detail-recovery Image Deraining via Dual Sample-augmented Contrastive Learning
- Data-Centric Green AI: An Exploratory Empirical Study
- BFRnet: A deep learning-based MR background field removal method for QSM of the brain containing significant pathological susceptibility sources
- Risk budget portfolios with convex Non-negative Matrix Factorization
- Universal Representations: A Unified Look at Multiple Task and Domain Learning
- Neural Network-augmented Kalman Filtering for Robust Online Speech Dereverberation in Noisy Reverberant Environments
- Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network
- Adversarial Learning to Reason in an Arbitrary Logic
- Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck
- Georeferencing of Photovoltaic Modules from Aerial Infrared Videos using Structure-from-Motion
- Match-Prompt: Improving Multi-task Generalization Ability for Neural Text Matching via Prompt Learning
- Annotation-Scheme Reconstruction for "Fake News" and Japanese Fake News Dataset
- A New Dataset for Topic-Based Paragraph Classification in Genocide-Related Court Transcripts
- Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings
- Fundamental limits to learning closed-form mathematical models from data
- Aesthetic Text Logo Synthesis via Content-aware Layout Inferring
- VNIbCReg: VICReg with Neighboring-Invariance and better-Covariance Evaluated on Non-stationary Seismic Signal Time Series
- Customizable End-to-end Optimization of Online Neural Network-supported Dereverberation for Hearing Devices
- MM-SEAL: A Large-scale Video Dataset of Multi-person Multi-grained Spatio-temporally Action Localization
- SecureBERT: A Domain-Specific Language Model for Cybersecurity
- Domain-Agnostic Prior for Transfer Semantic Segmentation
- Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations
- PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model
- Random Features Model with General Convex Regularization: A Fine Grained Analysis with Precise Asymptotic Learning Curves
- Rolling Colors: Adversarial Laser Exploits against Traffic Light Recognition
- Faster-TAD: Towards Temporal Action Detection with Proposal Generation and Classification in a Unified Network
- Disentangling the Computational Complexity of Network Untangling
- Towards An End-to-End Framework for Flow-Guided Video Inpainting
- Accelerating Backward Aggregation in GCN Training with Execution Path Preparing on GPUs
- CAIPI in Practice: Towards Explainable Interactive Medical Image Classification
- Yunshan Cup 2020: Overview of the Part-of-Speech Tagging Task for Low-resourced Languages
- CHIEF: Clustering with Higher-order Motifs in Big Networks
- Using Synthetic Data for Conversational Response Generation in Low-resource Settings
- Spatio-Temporal Dynamic Graph Relation Learning for Urban Metro Flow Prediction
- Failure Identification from Unstable Log Data using Deep Learning
- Federated Reinforcement Learning with Environment Heterogeneity
- DAGAM: Data Augmentation with Generation And Modification
- DeFTA: A Plug-and-Play Decentralized Replacement for FedAvg
- Super-resolved multi-temporal segmentation with deep permutation-invariant networks
- IterVM: Iterative Vision Modeling Module for Scene Text Recognition
- A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning
- Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020
- There Are a Thousand Hamlets in a Thousand People's Eyes: Enhancing Knowledge-grounded Dialogue with Personal Memory
- Attention-based CNN-LSTM and XGBoost hybrid model for stock prediction
- Towards Robust Adaptive Object Detection under Noisy Annotations
- Data-Driven Approach for Log Instruction Quality Assessment
- Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification
- Efficient Test-Time Model Adaptation without Forgetting
- Face recognition in a transformed domain
- Consensual Aggregation on Random Projected High-dimensional Features for Regression
- Distributed Transition Systems with Tags for Privacy Analysis
- Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency
- Fine-Grained Predicates Learning for Scene Graph Generation
- Nonlinear gradient mappings and stochastic optimization: A general framework with applications to heavy-tail noise
- Contextual Attention Mechanism, SRGAN Based Inpainting System for Eliminating Interruptions from Images
- Learning to Anticipate Future with Dynamic Context Removal
- SqueezeNeRF: Further factorized FastNeRF for memory-efficient inference
- PAGP: A physics-assisted Gaussian process framework with active learning for forward and inverse problems of partial differential equations
- Banana Sub-Family Classification and Quality Prediction using Computer Vision
- FocalClick: Towards Practical Interactive Image Segmentation
- Detecting key Soccer match events to create highlights using Computer Vision
- Greedier is Better: Selecting Multiple Neighbors per Iteration for Sparse Subspace Clustering
- Optimal Sublinear Sampling of Spanning Trees and Determinantal Point Processes via Average-Case Entropic Independence
- Gait Recognition in the Wild with Dense 3D Representations and A Benchmark
- FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons
- Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension
- DouZero+: Improving DouDizhu AI by Opponent Modeling and Coach-guided Learning
- MixFormer: Mixing Features across Windows and Dimensions
- RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection
- Continuous LWE is as Hard as LWE & Applications to Learning Gaussian Mixtures
- C3KG: A Chinese Commonsense Conversation Knowledge Graph
- Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentation
- Modeling Motion with Multi-Modal Features for Text-Based Video Segmentation
- Quick Starting Dialog Systems with Paraphrase Generation
- Improving Zero-Shot Event Extraction via Sentence Simplification
- Prosodic Alignment for off-screen automatic dubbing
- Emphasis on the Minimization of False Negatives or False Positives in Binary Classification
- Simple and Effective Unsupervised Speech Synthesis