Papers
Fri 15 Jul 2022
141 papers
- ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature LearningEnd-to-end autonomous driving → End-to-end system architecture
- This is the Way: Differential Bayesian Filtering for Agile Trajectory SynthesisOffline RL and imitation learning from data → Imitation and offline RL for driving
- Physics-Aware Neural Networks for Boundary Layer Linear Problems
- The Transform-o-meter: A method to forecast the transformative impact of innovation
- From Single Aircraft to Communities: A Neutral Interpretation of Air Traffic Complexity Dynamics
- Flow Moods: Recommending Music by Moods on Deezer
- VTrackIt: A Synthetic Self-Driving Dataset with Infrastructure and Pooled Vehicle Information
- WordSig: QR streams enabling platform-independent self-identification that's impossible to deepfake
- PowerFDNet: Deep Learning-Based Stealthy False Data Injection Attack Detection for AC-model Transmission Systems
- Suppressing Poisoning Attacks on Federated Learning for Medical Imaging
- NFDLM: A Lightweight Network Flow based Deep Learning Model for DDoS Attack Detection in IoT Domains
- A No-Code Low-Code Paradigm for Authoring Business Automations Using Natural Language
- IDET: Iterative Difference-Enhanced Transformers for High-Quality Change Detection
- Realistic mask generation for matter-wave lithography via machine learning
- Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity
- Greykite: Deploying Flexible Forecasting at Scale at LinkedIn
- Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection
- Subgroup Discovery in Unstructured Data
- Segment-level Metric Learning for Few-shot Bioacoustic Event Detection
- Anomalous behaviour in loss-gradient based interpretability methods
- ESFPNet: efficient deep learning architecture for real-time lesion segmentation in autofluorescence bronchoscopic video
- Do Not Sleep on Traditional Machine Learning: Simple and Interpretable Techniques Are Competitive to Deep Learning for Sleep Scoring
- Bootstrap State Representation using Style Transfer for Better Generalization in Deep Reinforcement Learning
- HOME: High-Order Mixed-Moment-based Embedding for Representation Learning
- Human keypoint detection for close proximity human-robot interaction
- Knowledge Representation in Digital Agriculture: A Step Towards Standardised Model
- Adversarial Focal Loss: Asking Your Discriminator for Hard Examples
- Optimizing Data Collection in Deep Reinforcement Learning
- COEM: Cross-Modal Embedding for MetaCell Identification
- Partial Disentanglement via Mechanism Sparsity
- Distributed Learning of Neural Lyapunov Functions for Large-Scale Networked Dissipative Systems
- How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition
- More Data Can Lead Us Astray: Active Data Acquisition in the Presence of Label Bias
- Local Approximations, Real Interpolation and Machine Learning
- Temporal Forward-Backward Consistency, Not Residual Error, Measures the Prediction Accuracy of Extended Dynamic Mode Decomposition
- Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space
- Probing Semantic Grounding in Language Models of Code with Representational Similarity Analysis
- Untrained, physics-informed neural networks for structured illumination microscopy
- Introducing Federated Learning into Internet of Things ecosystems -- preliminary considerations
- POET: Training Neural Networks on Tiny Devices with Integrated Rematerialization and Paging
- Algorithmic Determination of the Combinatorial Structure of the Linear Regions of ReLU Neural Networks
- An Exact Bitwise Reversible Integrator
- Towards Understanding Confusion and Affective States Under Communication Failures in Voice-Based Human-Machine Interaction
- Support Vector Machines with the Hard-Margin Loss: Optimal Training via Combinatorial Benders' Cuts
- Strict baselines for Covid-19 forecasting and ML perspective for USA and Russia
- FLOWGEN: Fast and slow graph generation
- Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models
- A Probabilistic Autoencoder for Type Ia Supernovae Spectral Time Series
- Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning
- GUSOT: Green and Unsupervised Single Object Tracking for Long Video Sequences
- Computing-In-Memory Neural Network Accelerators for Safety-Critical Systems: Can Small Device Variations Be Disastrous?
- Feed-Forward Latent Domain Adaptation
- Brain MRI study for glioma segmentation using convolutional neural networks and original post-processing techniques with low computational demand
- MegaPortraits: One-shot Megapixel Neural Head Avatars
- A Non-Anatomical Graph Structure for isolated hand gesture separation in continuous gesture sequences
- Blessing of Nonconvexity in Deep Linear Models: Depth Flattens the Optimization Landscape Around the True Solution
- Position Prediction as an Effective Pretraining Strategy
- DOLPHINS: Dataset for Collaborative Perception enabled Harmonious and Interconnected Self-driving
- Algorithms to estimate Shapley value feature attributions
- Image and Texture Independent Deep Learning Noise Estimation using Multiple Frames
- Mobile Keystroke Biometrics Using Transformers
- A two-step machine learning approach to statistical post-processing of weather forecasts for power generation
- Outlier detection of vital sign trajectories from COVID-19 patients
- The Nature of Temporal Difference Errors in Multi-step Distributional Reinforcement Learning
- Reasoning about Actions over Visual and Linguistic Modalities: A Survey
- Skill-based Model-based Reinforcement Learning
- CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN
- Pick your Neighbor: Local Gauss-Southwell Rule for Fast Asynchronous Decentralized Optimization
- 3DVerifier: Efficient Robustness Verification for 3D Point Cloud Models
- Selection of the Most Probable Best
- Modeling Quality and Machine Learning Pipelines through Extended Feature Models
- Heuristic-free Optimization of Force-Controlled Robot Search Strategies in Stochastic Environments
- Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation
- Short-Term Trajectory Prediction for Full-Immersive Multiuser Virtual Reality with Redirected Walking
- On the Usefulness of Deep Ensemble Diversity for Out-of-Distribution Detection
- Sparse Relational Reasoning with Object-Centric Representations
- Augmenting Softmax Information for Selective Classification with Out-of-Distribution Data
- Low-bit Shift Network for End-to-End Spoken Language Understanding
- Communication-Efficient Diffusion Strategy for Performance Improvement of Federated Learning with Non-IID Data
- A Systematic Review and Replicability Study of BERT4Rec for Sequential Recommendation
- The Mechanical Neural Network(MNN) -- A physical implementation of a multilayer perceptron for education and hands-on experimentation
- Stable Invariant Models via Koopman Spectra
- USegScene: Unsupervised Learning of Depth, Optical Flow and Ego-Motion with Semantic Guidance and Coupled Networks
- Deep Hedging: Continuous Reinforcement Learning for Hedging of General Portfolios across Multiple Risk Aversions
- Towards unsupervised assessment with open-source data of the accuracy of deep learning-based distributed PV mapping
- Creating an Explainable Intrusion Detection System Using Self Organizing Maps
- Joint Application of the Target Trial Causal Framework and Machine Learning Modeling to Optimize Antibiotic Therapy: Use Case on Acute Bacterial Skin and Skin Structure Infections due to Methicillin-resistant Staphylococcus aureus
- Multi-Object Tracking and Segmentation via Neural Message Passing
- Learning Flexible Translation between Robot Actions and Language Descriptions
- Continual Learning For On-Device Environmental Sound Classification
- LapSeg3D: Weakly Supervised Semantic Segmentation of Point Clouds Representing Laparoscopic Scenes
- Near-Linear Time and Fixed-Parameter Tractable Algorithms for Tensor Decompositions
- Space-based gravitational wave signal detection and extraction with deep neural network
- Plex: Towards Reliability using Pretrained Large Model Extensions
- pathGCN: Learning General Graph Spatial Operators from Paths
- An Approach for Link Prediction in Directed Complex Networks based on Asymmetric Similarity-Popularity
- A simple declarative model of the Federal Disaster Assistance Policy -- modelling and measuring transparency
- Stochastic Market Games
- A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completion
- 3D Instances as 1D Kernels
All 141
- CKD-TransBTS: Clinical Knowledge-Driven Hybrid Transformer with Modality-Correlated Cross-Attention for Brain Tumor Segmentation
- Trainable Joint Bilateral Filters for Enhanced Prediction Stability in Low-dose CT
- Error analysis for deep neural network approximations of parametric hyperbolic conservation laws
- Registration based Few-Shot Anomaly Detection
- Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space
- Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection
- DuetFace: Collaborative Privacy-Preserving Face Recognition via Channel Splitting in the Frequency Domain
- Fuzzy Labeling Semantics for Quantitative Argumentation
- Context-sensitive neocortical neurons transform the effectiveness and efficiency of neural information processing
- Learning Parallax Transformer Network for Stereo Image JPEG Artifacts Removal
- Computer Vision for Volunteer Cotton Detection in a Corn Field with UAS Remote Sensing Imagery and Spot Spray Applications
- Rain regime segmentation of Sentinel-1 observation learning from NEXRAD collocations with Convolution Neural Networks
- Stereo Co-capture System for Recording and Tracking Fish with Frame- and Event Cameras
- Modeling Multi-interest News Sequence for News Recommendation
- Enhancement by Your Aesthetic: An Intelligible Unsupervised Personalized Enhancer for Low-Light Images
- Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain
- Pattern Analysis of Money Flow in the Bitcoin Blockchain
- Towards Privacy-Preserving Person Re-identification via Person Identify Shift
- Z-Index at CheckThat! Lab 2022: Check-Worthiness Identification on Tweet Text
- MIMO-DoAnet: Multi-channel Input and Multiple Outputs DoA Network with Unknown Number of Sound Sources
- Towards Better Dermoscopic Image Feature Representation Learning for Melanoma Classification
- Robust Deep Compressive Sensing with Recurrent-Residual Structural Constraints
- Direction-Aware Adaptive Online Neural Speech Enhancement with an Augmented Reality Headset in Real Noisy Conversational Environments
- WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation
- Riemannian Natural Gradient Methods
- X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval
- Parameterization of Cross-Token Relations with Relative Positional Encoding for Vision MLP
- Boosting Multi-Modal E-commerce Attribute Value Extraction via Unified Learning Scheme and Dynamic Range Minimization
- A Flexible Schema-Guided Dialogue Management Framework: From Friendly Peer to Virtual Standardized Cancer Patient
- Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments
- Set-based value operators for non-stationary Markovian environments
- Weakly Supervised Video Salient Object Detection via Point Supervision
- Lightweight Vision Transformer with Cross Feature Attention
- ScaleNet: Searching for the Model to Scale
- Accelerated Probabilistic Marching Cubes by Deep Learning for Time-Varying Scalar Ensembles
- Improving Task-free Continual Learning by Distributionally Robust Memory Evolution
- Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights
- Single Shot Self-Reliant Scene Text Spotter by Decoupled yet Collaborative Detection and Recognition
- Toward Super-polynomial Quantum Speedup of Equivariant Quantum Algorithms with SU(d) Symmetry
- LineCap: Line Charts for Data Visualization Captioning Models
- Classification of Bark Beetle-Induced Forest Tree Mortality using Deep Learning