Papers
Mon 28 Mar 2022
230 papers
- Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social NavigationOffline RL and imitation learning from data → Social robot navigation
- Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language ModelMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
- Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task DivisionOffline RL and imitation learning from data → Robot manipulation imitation learning
- HetuMoE: An Efficient Trillion-scale Mixture-of-Expert Distributed Training SystemMixture-of-experts → Efficient MoE training and inference systems
- Knowledge Distillation: Bad Models Can Be Good Role ModelsKnowledge distillation → General knowledge distillation methods
- Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic LibraryLLM reasoning → Mathematical reasoning
- STaR: Bootstrapping Reasoning With ReasoningLLM reasoning → Test-time compute and efficient thinking +1
- A collection of invited non-archival papers for the Conference on Health, Inference, and Learning (CHIL) 2022
- Surrogate Assisted Evolutionary Multi-objective Optimisation applied to a Pressure Swing Adsorption system
- Evolution and use of data science vocabulary. How much have we changed in 13 years?
- Generative Design Ideation: A Natural Language Generation Approach
- The MIT Voice Name System
- Discovering material information using hierarchical Reformer model on financial regulatory filings
- Inverse Design and Experimental Verification of a Bianisotropic Metasurface Using Optimization and Machine Learning
- A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness
- Reliability and Validity of the Polar V800 Sports Watch for Estimating Vertical Jump Height
- Robust and Energy-efficient PPG-based Heart-Rate Monitoring
- Stack operation of tensor networks
- On handwriting pressure normalization for interoperability of different acquisition stylus
- TraHGR: Transformer for Hand Gesture Recognition via ElectroMyography
- Instantaneous Frequency Estimation In Multi-Component Signals Using Stochastic EM Algorithm
- FlexFringe: Modeling Software Behavior by Learning Probabilistic Automata
- Learning to Collide: Recommendation System Model Compression with Learned Hash Functions
- A Metaheuristic Algorithm for Large Maximum Weight Independent Set Problems
- Deep Reinforcement Learning Aided Platoon Control Relying on V2X Information
- Adaptive Learning with Artificial Barriers Yielding Nash Equilibria in General Games
- Convex Non-negative Matrix Factorization Through Quantum Annealing
- Subspace-based Representation and Learning for Phonotactic Spoken Language Recognition
- Core Risk Minimization using Salient ImageNet
- Killing Two Birds with One Stone:Efficient and Robust Training of Face Recognition CNNs by Partial FC
- Attacker Attribution of Audio Deepfakes
- Wildfire risk forecast: An optimizable fire danger index
- A machine learning-based severity prediction tool for diabetic sensorimotor polyneuropathy using Michigan neuropathy screening instrumentations
- Tight Bounds on the Hardness of Learning Simple Nonparametric Mixtures
- CMGAN: Conformer-based Metric GAN for Speech Enhancement
- Separate What You Describe: Language-Queried Audio Source Separation
- Human-AI Collaboration Enables More Empathic Conversations in Text-based Peer-to-Peer Mental Health Support
- Towards End-to-End Unified Scene Text Detection and Layout Analysis
- Filler Word Detection and Classification: A Dataset and Benchmark
- LocalBins: Improving Depth Estimation by Learning Local Distributions
- An Online Approach to Solve the Dynamic Vehicle Routing Problem with Stochastic Trip Requests for Paratransit Services
- Text2Pos: Text-to-Point-Cloud Cross-Modal Localization
- Toward Deep Learning Based Access Control
- Visual Odometry for RGB-D Cameras
- LiDAR Snowfall Simulation for Robust 3D Object Detection
- Domain Knowledge Driven Pseudo Labels for Interpretable Goal-Conditioned Interactive Trajectory Prediction
- A Well-Composed Text is Half Done! Composition Sampling for Diverse Conditional Generation
- Investigation of Different Calibration Methods for Deep Speaker Embedding based Verification Systems
- FedADMM: A Federated Primal-Dual Algorithm Allowing Partial Participation
- Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions
- Rethinking Semantic Segmentation: A Prototype View
- Federated Named Entity Recognition
- Understanding out-of-distribution accuracies through quantifying difficulty of test samples
- LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models
- Robust Speaker Recognition with Transformers Using wav2vec 2.0
- Improved singing voice separation with chromagram-based pitch-aware remixing
- New pyramidal hybrid textural and deep features based automatic skin cancer classification model: Ensemble DarkNet and textural feature extractor
- Learning Optical Flow, Depth, and Scene Flow without Real-World Labels
- X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval
- Iterative, Deep Synthetic Aperture Sonar Image Segmentation
- Word Discovery in Visually Grounded, Self-Supervised Speech Models
- CD-Net: Histopathology Representation Learning using Pyramidal Context-Detail Network
- Neurosymbolic hybrid approach to driver collision warning
- Semantic Motion Correction Via Iterative Nonlinear Optimization and Animation
- User Driven Model Adjustment via Boolean Rule Explanations
- Face Verification Bypass
- DeepShadow: Neural Shape from Shadow
- Cycle-Consistent Counterfactuals by Latent Transformations
- A Deep Learning Technique using a Sequence of Follow Up X-Rays for Disease classification
- A distribution-dependent Mumford-Shah model for unsupervised hyperspectral image segmentation
- AUC Maximization in the Era of Big Data and AI: A Survey
- Learning Parameterized Task Structure for Generalization to Unseen Entities
- Solving Disjunctive Temporal Networks with Uncertainty under Restricted Time-Based Controllability using Tree Search and Graph Neural Networks
- A systematic review and meta-analysis of Digital Elevation Model (DEM) fusion: pre-processing, methods and applications
- Few-Shot Object Detection with Fully Cross-Transformer
- Deep Interactive Learning-based ovarian cancer segmentation of H&E-stained whole slide images to study morphological patterns of BRCA mutation
- DAMNETS: A Deep Autoregressive Model for Generating Markovian Network Time Series
- Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images
- TL-GAN: Improving Traffic Light Recognition via Data Synthesis for Autonomous Driving
- Comparing in context: Improving cosine similarity measures with a metric tensor
- Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment
- Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
- LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection
- GIRAFFE HD: A High-Resolution 3D-aware Generative Model
- Energy-based Latent Aligner for Incremental Learning
- Controllable Dynamic Multi-Task Architectures
- Differentiable Microscopy for Content and Task Aware Compressive Fluorescence Imaging
- Differentiable Microscopy Designs an All Optical Phase Retrieval Microscope
- Neural Vocoder is All You Need for Speech Super-resolution
- FedVLN: Privacy-preserving Federated Vision-and-Language Navigation
- Attributable Visual Similarity Learning
- RAVIR: A Dataset and Methodology for the Semantic Segmentation and Quantitative Analysis of Retinal Arteries and Veins in Infrared Reflectance Imaging
- Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision
- UTSA NLP at SemEval-2022 Task 4: An Exploration of Simple Ensembles of Transformers, Convolutional, and Recurrent Neural Networks
- Expanding Low-Density Latent Regions for Open-Set Object Detection
- Optimizing Elimination Templates by Greedy Parameter Search
- Properties and Performance of the ABCDe Random Graph Model with Community Structure
- Learning Where to Learn in Cross-View Self-Supervised Learning
- Multi-Task Learning for Visual Scene Understanding
- Probabilistic Spherical Discriminant Analysis: An Alternative to PLDA for length-normalized embeddings
All 230
- WawPart: Workload-Aware Partitioning of Knowledge Graphs
- HUNIS: High-Performance Unsupervised Nuclei Instance Segmentation
- AWAPart: Adaptive Workload-Aware Partitioning of Knowledge Graphs
- TGL: A General Framework for Temporal GNN Training on Billion-Scale Graphs
- Finnish Parliament ASR corpus - Analysis, benchmarks and statistics
- HIME: Efficient Headshot Image Super-Resolution with Multiple Exemplars
- Time-inhomogeneous diffusion geometry and topology
- WSEBP: A Novel Width-depth Synchronous Extension-based Basis Pursuit Algorithm for Multi-Layer Convolutional Sparse Coding
- Learning Sketches for Decomposing Planning Problems into Subproblems of Bounded Width: Extended Version
- Safe Active Learning for Multi-Output Gaussian Processes
- Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches
- A Framework of Meta Functional Learning for Regularising Knowledge Transfer
- Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition
- Multilingual Simultaneous Speech Translation
- Differentiable, learnable, regionalized process-based models with physical outputs can approach state-of-the-art hydrologic prediction accuracy
- HDR Reconstruction from Bracketed Exposures and Events
- Numerical and geometrical aspects of flow-based variational quantum Monte Carlo
- Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval
- Using Probabilistic Machine Learning to Better Model Temporal Patterns in Parameterizations: a case study with the Lorenz 96 model
- An attention mechanism based convolutional network for satellite precipitation downscaling over China
- Soundness of Data-Aware Processes with Arithmetic Conditions
- Extraction of Visual Information to Predict Crowdfunding Success
- Partially Does It: Towards Scene-Level FG-SBIR with Partial Input
- MixNN: A design for protecting deep learning models
- Limited Parameter Denoising for Low-dose X-ray Computed Tomography Using Deep Reinforcement Learning
- 5G Routing Interfered Environment
- On the Handwriting Tasks' Analysis to Detect Fatigue
- A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition
- A Long Short-term Memory Based Recurrent Neural Network for Interventional MRI Reconstruction
- Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks
- STUDIES: Corpus of Japanese Empathetic Dialogue Speech Towards Friendly Voice Agent
- Adaptive Risk-Tendency: Nano Drone Navigation in Cluttered Environments with Distributional Reinforcement Learning
- Learning Personalized Human-Aware Robot Navigation Using Virtual Reality Demonstrations from a User Study
- Using Domain Knowledge for Low Resource Named Entity Recognition
- Open-VICO: An Open-Source Gazebo Toolkit for Vision-based Skeleton Tracking in Human-Robot Collaboration
- Infinite-Dimensional Sparse Learning in Linear System Identification
- Primitive-based Shape Abstraction via Nonparametric Bayesian Inference
- Image-text Retrieval: A Survey on Recent Research and Development
- Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities
- Hierarchical Transformer Model for Scientific Named Entity Recognition
- MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection
- LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds
- Sketch3T: Test-Time Training for Zero-Shot SBIR
- Training speaker recognition systems with limited data
- REPTILE: A Proactive Real-Time Deep Reinforcement Learning Self-adaptive Framework
- AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval System
- ObjectFormer for Image Manipulation Detection and Localization
- Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space
- Brain-inspired Multilayer Perceptron with Spiking Neurons
- Part-based Pseudo Label Refinement for Unsupervised Person Re-identification
- Using Machine Learning to generate an open-access cropland map from satellite images time series in the Indian Himalayan Region
- Are High-Resolution Event Cameras Really Needed?
- Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creation
- Federated Learning with Position-Aware Neurons
- MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation
- Random matrix analysis of deep neural network weight matrices
- Revisiting Model-based Value Expansion
- Few-Shot Learning with Siamese Networks and Label Tuning
- Automatic Debate Evaluation with Argumentation Semantics and Natural Language Argument Graph Networks
- To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding
- REx: Data-Free Residual Quantization Error Expansion
- SPIQ: Data-Free Per-Channel Static Input Quantization
- Subjective Evaluation of Deep Learning Models for Symbolic Music Composition
- Isomorphic Cross-lingual Embeddings for Low-Resource Languages
- A quantitative comparison of plantar soft tissue strainability distribution and homogeneity between ulcerated and non-ulcerated patients using strain elastography
- FS6D: Few-Shot 6D Pose Estimation of Novel Objects
- Towards Implicit Text-Guided 3D Shape Generation
- Adaptation to CT Reconstruction Kernels by Enforcing Cross-domain Feature Maps Consistency
- Boosting Black-Box Adversarial Attacks with Meta Learning
- The SAME score: Improved cosine based bias score for word embeddings
- New insights into four-boson renormalization group limit cycles
- On-the-Fly Feature Based Rapid Speaker Adaptation for Dysarthric and Elderly Speech Recognition
- S2-Net: Self-supervision Guided Feature Representation Learning for Cross-Modality Images
- Computer Science Named Entity Recognition in the Open Research Knowledge Graph
- Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?
- The Digitalization of Bioassays in the Open Research Knowledge Graph
- Detection threshold for correlated ErdHos-R'enyi graphs via densest subgraphs
- Distributed Task Management in Fog Computing: A Socially Concave Bandit Game
- Style-Guided Domain Adaptation for Face Presentation Attack Detection
- HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network
- The Moral Debater: A Study on the Computational Generation of Morally Framed Arguments
- Visual Mechanisms Inspired Efficient Transformers for Image and Video Quality Assessment
- Pyramid Feature Alignment Network for Video Deblurring
- CenterLoc3D: Monocular 3D Vehicle Localization Network for Roadside Surveillance Cameras
- Gradient-Matching Coresets for Rehearsal-Based Continual Learning
- UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning
- Specialized Document Embeddings for Aspect-based Similarity of Research Papers
- Semi-supervised anomaly detection algorithm based on KL divergence (SAD-KL)
- Reference-based Video Super-Resolution Using Multi-Camera Video Triplets
- Robust Unlearnable Examples: Protecting Data Against Adversarial Learning
- Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimation
- Distributed Finite-Sum Constrained Optimization subject to Nonlinearity on the Node Dynamics
- Translation Consistent Semi-supervised Segmentation for 3D Medical Images
- Optimistic Online Convex Optimization in Dynamic Environments
- REGTR: End-to-end Point Cloud Correspondences with Transformers
- Multi-View Substructure Learning for Drug-Drug Interaction Prediction
- Expressive Talking Head Video Encoding in StyleGAN2 Latent-Space
- Statistical Inference for Heterogeneous Treatment Effects Discovered by Generic Machine Learning in Randomized Experiments
- ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations
- Automated Progressive Learning for Efficient Training of Vision Transformers
- Stratified Transformer for 3D Point Cloud Segmentation
- ANNA: Enhanced Language Representation for Question Answering
- Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection
- Black-box Selective Inference via Bootstrapping
- MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design
- NOC-REK: Novel Object Captioning with Retrieved Vocabulary from External Knowledge
- EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English
- Conjugate Gradient Method for Generative Adversarial Networks
- ARCS: Accurate Rotation and Correspondence Search
- Equivariant Point Cloud Analysis via Learning Orientations for Message Passing
- Optimization of Directional Landmark Deployment for Visual Observer on SE(3)
- Leveraging Clinically Relevant Biometric Constraints To Supervise A Deep Learning Model For The Accurate Caliper Placement To Obtain Sonographic Measurements Of The Fetal Brain
- DNN-Driven Compressive Offloading for Edge-Assisted Semantic Video Segmentation
- Structured Local Radiance Fields for Human Avatar Modeling
- A Novel Remote Sensing Approach to Recognize and Monitor Red Palm Weevil in Date Palm Trees
- Interpretable Research Replication Prediction via Variational Contextual Consistency Sentence Masking
- Enhancing Transformer Efficiency for Multivariate Time Series Classification
- Integrating Physiological Time Series and Clinical Notes with Transformer for Early Prediction of Sepsis
- Multi-model Ensemble Learning Method for Human Expression Recognition
- Large-scale Bilingual Language-Image Contrastive Learning
- OTFace: Hard Samples Guided Optimal Transport Loss for Deep Face Representation
- PAEDID: Patch Autoencoder Based Deep Image Decomposition For Pixel-level Defective Region Segmentation
- 3MASSIV: Multilingual, Multimodal and Multi-Aspect dataset of Social Media Short Videos
- SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration
- Optimisation-free Classification and Density Estimation with Quantum Circuits
- Decoupled Multi-task Learning with Cyclical Self-Regulation for Face Parsing
- An Interactive Image-based Modeling System
- Optimal Correction Cost for Object Detection Evaluation
- Flexible risk design using bi-directional dispersion
- Relaxation Labeling Meets GANs: Solving Jigsaw Puzzles with Missing Borders