Papers
Tue 6 Apr 2021
186 papers
- Data-Driven Simulation of Ride-Hailing Services using Imitation and Reinforcement LearningOffline RL and imitation learning from data → Imitation and offline RL for driving
- A non-asymptotic approach for model selection via penalization in high-dimensional mixture of experts modelsMixture-of-experts → MoE theory and gating functions
- Noise Estimation for Generative Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Teacher-Student Adversarial Depth Hallucination to Improve Face RecognitionKnowledge distillation → General knowledge distillation methods
- NU-Wave: A Diffusion Probabilistic Model for Neural Audio UpsamplingDiffusion models → Audio, speech and music
- A Decade of Research for Image Compression In Multimedia Laboratory
- Profitability Analysis in Stock Investment Using an LSTM-Based Deep Learning Model
- Zeus: Efficiently Localizing Actions in Videos using Reinforcement Learning
- Confidence-Optimal Random Embeddings
- Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation
- One-shot learning for solution operators of partial differential equations
- An approach utilizing negation of extended-dimensional vector of disposing mass for ordinal evidences combination in a fuzzy environment
- Design and implementation of an environment for Learning to Run a Power Network (L2RPN)
- Progressive extension of reinforcement learning action dimension for asymmetric assembly tasks
- Towards a Rigorous Evaluation of Explainability for Multivariate Time Series
- TB-Net: A Tailored, Self-Attention Deep Convolutional Neural Network Design for Detection of Tuberculosis Cases from Chest X-ray Images
- IndoFashion : Apparel Classification for Indian Ethnic Clothes
- Ecole: A Library for Learning Inside MILP Solvers
- Low-Regret Active learning
- Towards Measuring Fairness in AI: the Casual Conversations Dataset
- Time-Multiplexed Coded Aperture Imaging: Learned Coded Aperture and Pixel Exposures for Compressive Imaging Systems
- Learning to Rank Microphones for Distant Speech Recognition
- On the Applicability of Synthetic Data for Face Recognition
- C2CL: Contact to Contactless Fingerprint Matching
- Sparse Partial Least Squares for Coarse Noisy Graph Alignment
- First arrival picking using U-net with Lovasz loss and nearest point picking method
- VERB: Visualizing and Interpreting Bias Mitigation Techniques for Word Representations
- A fully automated end-to-end process for fluorescence microscopy images of yeast cells: From segmentation to detection and classification
- NeuMIP: Multi-Resolution Neural Materials
- Safe-by-Repair: A Convex Optimization Approach for Repairing Unsafe Two-Level Lattice Neural Network Controllers
- Localization of Autonomous Vehicles: Proof of Concept for A Computer Vision Approach
- Autoencoder-based Representation Learning from Heterogeneous Multivariate Time Series Data of Mechatronic Systems
- A New Dimension in Testimony: Relighting Video with Reflectance Field Exemplars
- The Power of Subsampling in Submodular Maximization
- Variable selection with missing data in both covariates and outcomes: Imputation and machine learning
- Robust Semantic Interpretability: Revisiting Concept Activation Vectors
- Lidar-Monocular Surface Reconstruction Using Line Segments
- Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Models
- Efficient transfer learning for NLP with ELECTRA
- Machine Learning-Driven Virtual Bidding with Electricity Market Efficiency Analysis
- Heuristics2Annotate: Efficient Annotation of Large-Scale Marathon Dataset For Bounding Box Regression
- Communication-Efficient Agnostic Federated Averaging
- Proof of the Theory-to-Practice Gap in Deep Learning via Sampling Complexity bounds for Neural Network Approximation Spaces
- InverseForm: A Loss Function for Structured Boundary-Aware Segmentation
- Approximate Robust NMPC using Reinforcement Learning
- Conditional physics informed neural networks
- Neural Network-based Control for Multi-Agent Systems from Spatio-Temporal Specifications
- Visual Vibration Tomography: Estimating Interior Material Properties from Monocular Video
- Creativity and Machine Learning: A Survey
- Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictions
- The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions
- deepregression: a Flexible Neural Network Framework for Semi-Structured Deep Distributional Regression
- Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge
- Adversarial Robustness under Long-Tailed Distribution
- ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement
- Localizing Visual Sounds the Hard Way
- A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting
- Strumming to the Beat: Audio-Conditioned Contrastive Video Textures
- A New Parallel Adaptive Clustering and its Application to Streaming Data
- Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations
- Test-Time Adaptation for Super-Resolution: You Only Need to Overfit on a Few More Images
- Model-data-driven constitutive responses: application to a multiscale computational framework
- gradSim: Differentiable simulation for system identification and visuomotor control
- Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
- Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation
- Local Metrics for Multi-Object Tracking
- Uncertainty-aware Joint Salient Object and Camouflaged Object Detection
- How to Accelerate Capsule Convolutions in Capsule Networks
- Are GAN generated images easy to detect? A critical analysis of the state-of-the-art
- MirrorNeRF: One-shot Neural Portrait Radiance Field from Multi-mirror Catadioptric Imaging
- Automatic Large Scale Detection of Red Palm Weevil Infestation using Aerial and Street View Images
- Accelerated Gradient Tracking over Time-varying Graphs for Decentralized Optimization
- Future of work: ethics
- Attentional Graph Neural Network for Parking-slot Detection
- Speaker embeddings by modeling channel-wise correlations
- Proof Complexity of Symbolic QBF Reasoning
- Structured Citation Trend Prediction Using Graph Neural Networks
- Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model
- Physics-Informed Neural Nets for Control of Dynamical Systems
- Fourier Image Transformer
- Deep learning for prediction of complex geology ahead of drilling
- White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Tasks
- Data-driven Design of Context-aware Monitors for Hazard Prediction in Artificial Pancreas Systems
- EasyCall corpus: a dysarthric speech dataset
- Instantaneous Stereo Depth Estimation of Real-World Stimuli with a Neuromorphic Stereo-Vision Setup
- Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision
- Optimal Transport-based Adaptation in Dysarthric Speech Tasks
- DCANet: Dense Context-Aware Network for Semantic Segmentation
- End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning
- Vote from the Center: 6 DoF Pose Estimation in RGB-D Images by Radial Keypoint Voting
- LT-LM: a novel non-autoregressive language model for single-shot lattice rescoring
- Searching Efficient Model-guided Deep Network for Image Denoising
- AI4D -- African Language Program
- A Bayesian approach to modeling topic-metadata relationships
- Deep Animation Video Interpolation in the Wild
- RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applications
- Nonlinear Model Based Guidance with Deep Learning Based Target Trajectory Prediction Against Aerial Agile Attack Patterns
- Weakly supervised segmentation with cross-modality equivariant constraints
- SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation
- OodGAN: Generative Adversarial Network for Out-of-Domain Data Generation
All 186
- Speaker Diarization using Two-pass Leave-One-Out Gaussian PLDA Clustering of DNN Embeddings
- A Novel Approach for Semiconductor Etching Process with Inductive Biases
- A Review of Formal Methods applied to Machine Learning
- Contrastive Explanations for Explaining Model Adaptations
- A Latent space solver for PDE generalization
- CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing
- Few-Shot Transformation of Common Actions into Time and Space
- mSHINE: A Multiple-meta-paths Simultaneous Learning Framework for Heterogeneous Information Network Embedding
- Fine-Grained Fashion Similarity Prediction by Attribute-Specific Embedding Learning
- The Duo of Artificial Intelligence and Big Data for Industry 4.0: Review of Applications, Techniques, Challenges, and Future Research Directions
- Variational Transformer Networks for Layout Generation
- MPC-based Reinforcement Learning for Economic Problems with Application to Battery Storage
- Using Voice and Biofeedback to Predict User Engagement during Product Feedback Interviews
- Learning to Estimate Hidden Motions with Global Motion Aggregation
- ProsoBeast Prosody Annotation Tool
- Ensemble deep learning: A review
- Weakly Supervised Video Salient Object Detection
- Generalization of GANs and overparameterized models under Lipschitz continuity
- Learning Spatial Context with Graph Neural Network for Multi-Person Pose Grouping
- Scene Graph Embeddings Using Relative Similarity Supervision
- Leverage Score Sampling for Complete Mode Coverage in Generative Adversarial Networks
- The Fragility of Noise Estimation in Kalman Filter: Optimization Can Handle Model-Misspecification
- Classification with Runge-Kutta networks and feature space augmentation
- Neural Feature Search for RGB-Infrared Person Re-Identification
- Backdoor Attack in the Physical World
- Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization
- Robust Adversarial Classification via Abstaining
- Pyramid U-Net for Retinal Vessel Segmentation
- Brain Tumors Classification for MR images based on Attention Guided Deep Learning Model
- Visual Alignment Constraint for Continuous Sign Language Recognition
- Self-Supervised Learning based CT Denoising using Pseudo-CT Image Pairs
- Multiple instance active learning for object detection
- Objects are Different: Flexible Monocular 3D Object Detection
- Efficient Video Compression via Content-Adaptive Super-Resolution
- A hybrid ensemble method with negative correlation learning for regression
- SERRANT: a syntactic classifier for English Grammatical Error Types
- MuSLCAT: Multi-Scale Multi-Level Convolutional Attention Transformer for Discriminative Music Modeling on Raw Waveforms
- ODE Transformer: An Ordinary Differential Equation-Inspired Model for Neural Machine Translation
- Balancing Predictive Relevance of Ligand Biochemical Activities
- Binary Neural Network for Speaker Verification
- Exploration of Hardware Acceleration Methods for an XNOR Traffic Signs Classifier
- Hyperspectral and LiDAR data classification based on linear self-attention
- Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression
- Change Detection from SAR Images Based on Deformable Residual Convolutional Neural Networks
- Shapley Explanation Networks
- On the Optimality of Batch Policy Optimization Algorithms
- Contrastive Syn-to-Real Generalization
- Preferential Structures for Comparative Probabilistic Reasoning
- Text-guided Legal Knowledge Graph Reasoning
- Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning
- A novel activity pattern generation incorporating deep learning for transport demand models
- Spatio-Temporal Graph Convolutional Networks for Road Network Inundation Status Prediction during Urban Flooding
- Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo
- Attribute-Based Robotic Grasping with One-Grasp Adaptation
- Learning from Self-Discrepancy via Multiple Co-teaching for Cross-Domain Person Re-Identification
- Enabling Inference Privacy with Adaptive Noise Injection
- Non-contact PPG Signal and Heart Rate Estimation with Multi-hierarchical Convolutional Network
- A Caputo fractional derivative-based algorithm for optimization
- Non-autoregressive Mandarin-English Code-switching Speech Recognition
- A clinical validation of VinDr-CXR, an AI system for detecting abnormal chest radiographs
- Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries
- One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation
- Multi-Scale Context Aggregation Network with Attention-Guided for Crowd Counting
- Content-Aware GAN Compression
- 3D-to-2D Distillation for Indoor Scene Parsing
- HBert + BiasCorp -- Fighting Racism on the Web
- Survey of Imbalanced Data Methodologies
- IronMask: Modular Architecture for Protecting Deep Face Template
- In-Line Image Transformations for Imbalanced, Multiclass Computer Vision Classification of Lung Chest X-Rays
- Hippocampus-heuristic Character Recognition Network for Zero-shot Learning
- DeepEverest: Accelerating Declarative Top-K Queries for Deep Neural Network Interpretation
- TENT: Efficient Quantization of Neural Networks on the tiny Edge with Tapered FixEd PoiNT
- Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios
- IoT Security: Botnet detection in IoT using Machine learning
- Achieving Domain Generalization in Underwater Object Detection by Domain Mixup and Contrastive Learning
- Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs
- Beyond Categorical Label Representations for Image Classification
- Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extraction
- When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes
- Intelligent Building Control Systems for Thermal Comfort and Energy-Efficiency: A Systematic Review of Artificial Intelligence-Assisted Techniques
- Dissecting User-Perceived Latency of On-Device E2E Speech Recognition
- Tuned Compositional Feature Replays for Efficient Stream Learning
- Attention Head Masking for Inference Time Content Selection in Abstractive Summarization
- Designing Efficient and High-performance AI Accelerators with Customized STT-MRAM
- Dopamine Transporter SPECT Image Classification for Neurodegenerative Parkinsonism via Diffusion Maps and Machine Learning Classifiers
- Distributed Deep Reinforcement Learning for Collaborative Spectrum Sharing