Papers
Tue 8 Mar 2022
206 papers
- Diffusion Models for Medical Anomaly DetectionDiffusion models → Medical imaging and segmentation
- Dynamic Dual-Output Diffusion ModelsDiffusion models → Diffusion foundations and sampling
- Towards performant and reliable undersampled MR reconstruction via diffusion model samplingDiffusion models → Medical imaging and segmentation
- Robustly-reliable learners under poisoning attacksLLM safety and security → Backdoor and data poisoning attacks
- Quantifying Privacy Risks of Masked Language Models Using Membership Inference AttacksLLM safety and security → Membership inference attacks
- Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and SpottingMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- Extraction of Sleep Information from Clinical Notes of Patients with Alzheimer's Disease Using Natural Language Processing
- QCRI's COVID-19 Disinformation Detector: A System to Fight the COVID-19 Infodemic in Social Media
- Reinforced MOOCs Concept Recommendation in Heterogeneous Information Networks
- Geolocation estimation of target vehicles using image processing and geometric computation
- Learning to Reduce False Positives in Analytic Bug Detectors
- On-the-fly Strategy Adaptation for ad-hoc Agent Coordination
- Model Positionality and Computational Reflexivity: Promoting Reflexivity in Data Science
- Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4
- An Uncommon Task: Participatory Design in Legal AI
- The Long Arc of Fairness: Formalisations and Ethical Discourse
- Sharing Generative Models Instead of Private Data: A Simulation Study on Mammography Patch Classification
- Structural & Granger CAUSALITY for IoT Digital Twin
- Predicting conversion of mild cognitive impairment to Alzheimer's disease
- How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?
- Self-Supervised Domain Calibration and Uncertainty Estimation for Place Recognition
- Self-Supervision, Remote Sensing and Abstraction: Representation Learning Across 3 Million Locations
- Reproducible Subjective Evaluation
- Estimating the Uncertainty in Emotion Class Labels with Utterance-Specific Dirichlet Priors
- Pointillism: Accurate 3D bounding box estimation with multi-radars
- The Flag Median and FlagIRLS
- Variational Inference with Locally Enhanced Bounds for Hierarchical Models
- Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction
- Harmonicity Plays a Critical Role in DNN Based Versus in Biologically-Inspired Monaural Speech Segregation Systems
- Survival Prediction of Brain Cancer with Incomplete Radiology, Pathology, Genomics, and Demographic Data
- Bayesian Calibration for Activity Based Models
- Score matching enables causal discovery of nonlinear additive noise models
- iSEA: An Interactive Pipeline for Semantic Error Analysis of NLP Models
- Structural Learning of Simple Staged Trees
- Model-free feature selection to facilitate automatic discovery of divergent subgroups in tabular data
- On generative models as the basis for digital twins
- A Novel Deep Learning Model for Hotel Demand and Revenue Prediction amid COVID-19
- Regularized Training of Intermediate Layers for Generative Models for Inverse Problems
- Logic-based AI for Interpretable Board Game Winner Prediction with Tsetlin Machine
- New Coresets for Projective Clustering and Applications
- It's AI Match: A Two-Step Approach for Schema Matching Using Embeddings
- Which side are you on? Insider-Outsider classification in conspiracy-theoretic social media
- Unrolled Primal-Dual Networks for Lensless Cameras
- TTML: tensor trains for general supervised machine learning
- Beam Search for Feature Selection
- Change-point Detection and Segmentation of Discrete Data using Bayesian Context Trees
- MICDIR: Multi-scale Inverse-consistent Deformable Image Registration using UNetMSS with Self-Constructing Graph Latent
- PyNET-QxQ: An Efficient PyNET Variant for QxQ Bayer Pattern Demosaicing in CMOS Image Sensors
- Multi-Scale Adaptive Network for Single Image Denoising
- Cluster Head Detection for Hierarchical UAV Swarm With Graph Self-supervised Learning
- Multi-Agent Broad Reinforcement Learning for Intelligent Traffic Light Control
- Breast cancer detection using artificial intelligence techniques: A systematic literature review
- A Machine Learning Approach to Digital Contact Tracing: TC4TL Challenge
- LSTMSPLIT: Effective SPLIT Learning based LSTM on Sequential Time-Series Data
- Policy Regularization for Legible Behavior
- SuperPoint features in endoscopy
- Live Laparoscopic Video Retrieval with Compressed Uncertainty
- Multi-trial Neural Architecture Search with Lottery Tickets
- Plug-and-play Shape Refinement Framework for Multi-site and Lifespan Brain Skull Stripping
- CaSS: A Channel-aware Self-supervised Representation Learning Framework for Multivariate Time Series Classification
- R'enyi State Entropy for Exploration Acceleration in Reinforcement Learning
- Region Specific Optimization (RSO)-based Deep Interactive Registration
- NaviAirway: a Bronchiole-sensitive Deep Learning-based Airway Segmentation Pipeline
- A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation
- Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences
- Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gap
- Leveraging Initial Hints for Free in Stochastic Linear Bandits
- Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Models
- End-to-End Semi-Supervised Learning for Video Action Detection
- Evaluating feasibility of batteries for second-life applications using machine learning
- Dual Lottery Ticket Hypothesis
- PERCEPT: a new online change-point detection method using topological data analysis
- A Complete Characterization of Linear Estimators for Offline Policy Evaluation
- Adaptative Perturbation Patterns: Realistic Adversarial Learning for Robust Intrusion Detection
- A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds
- Neural Face Identification in a 2D Wireframe Projection of a Manifold Object
- A Practical AoI Scheduler in IoT Networks with Relays
- Towards Universal Texture Synthesis by Combining Texton Broadcasting with Noise Injection in StyleGAN-2
- Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data
- Measuring the Mixing of Contextual Information in the Transformer
- Lightweight Monocular Depth Estimation through Guided Decoding
- AssistQ: Affordance-centric Question-driven Task Completion for Egocentric Assistant
- Follow the Water: Finding Water, Snow and Clouds on Terrestrial Exoplanets with Photometry and Machine Learning
- Trustable Co-label Learning from Multiple Noisy Annotators
- Locate This, Not That: Class-Conditioned Sound Event DOA Estimation
- A Gating Model for Bias Calibration in Generalized Zero-shot Learning
- Reward-Biased Maximum Likelihood Estimation for Neural Contextual Bandits
- RankSeg: Adaptive Pixel Classification with Image Category Ranking for Segmentation
- Enhancing Mechanical Metamodels with a Generative Model-Based Augmented Training Dataset
- Selective-Supervised Contrastive Learning with Noisy Labels
- Tuning-free multi-coil compressed sensing MRI with Parallel Variable Density Approximate Message Passing (P-VDAMP)
- Understanding Person Identification through Gait
- Variational methods for simulation-based inference
- Distributed Control using Reinforcement Learning with Temporal-Logic-Based Reward Shaping
- On the intrinsic dimensionality of Covid-19 data: a global perspective
- Robust Local Preserving and Global Aligning Network for Adversarial Domain Adaptation
- Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity Recognition
- Motron: Multimodal Probabilistic Human Motion Forecasting
- NeReF: Neural Refractive Field for Fluid Surface Reconstruction and Implicit Representation
- YouTube-GDD: A challenging gun detection dataset with rich contextual information
All 206
- Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery
- An Efficient Polyp Segmentation Network
- Quantification of Occlusion Handling Capability of a 3D Human Pose Estimation Framework
- Plumeria at SemEval-2022 Task 6: Robust Approaches for Sarcasm Detection for English and Arabic Using Transformers and Data Augmentation
- VoViT: Low Latency Graph-based Audio-Visual Voice Separation Transformer
- COLA: Consistent Learning with Opponent-Learning Awareness
- Contrastive Enhancement Using Latent Prototype for Few-Shot Segmentation
- Semantic Distillation Guided Salient Object Detection
- Obstacle Aware Sampling for Path Planning
- E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation
- AdaPT: Fast Emulation of Approximate DNN Accelerators in PyTorch
- Lane Detection with Versatile AtrousFormer and Local Semantic Guidance
- Analyzing General-Purpose Deep-Learning Detection and Segmentation Models with Images from a Lidar as a Camera Sensor
- Counting with Adaptive Auxiliary Learning
- Robot Learning of Mobile Manipulation with Reachability Behavior Priors
- BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs
- Graph Attention Transformer Network for Multi-Label Image Classification
- Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations
- Abandoning the Bayer-Filter to See in the Dark
- Shape-invariant 3D Adversarial Point Clouds
- Gait Recognition with Mask-based Regularization
- Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes
- StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
- Bayesian Optimisation-Assisted Neural Network Training Technique for Radio Localisation
- Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes
- Data augmentation with mixtures of max-entropy transformations for filling-level classification
- A Compilation Flow for the Generation of CNN Inference Accelerators on FPGAs
- Mutual Contrastive Low-rank Learning to Disentangle Whole Slide Image Representations for Glioma Grading
- Evolutionary Neural Cascade Search across Supernetworks
- DuMLP-Pin: A Dual-MLP-dot-product Permutation-invariant Network for Set Feature Extraction
- Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration
- Semi-Random Sparse Recovery in Nearly-Linear Time
- DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos
- Sparsification and Filtering for Spatial-temporal GNN in Multivariate Time-series
- Skating-Mixer: Long-Term Sport Audio-Visual Modeling with MLPs
- Adaptor: Objective-Centric Adaptation Framework for Language Models
- SimpleTrack: Rethinking and Improving the JDE Approach for Multi-Object Tracking
- Attention-Based Lip Audio-Visual Synthesis for Talking Face Generation in the Wild
- End-to-end Multiple Instance Learning with Gradient Accumulation
- Online Weak-form Sparse Identification of Partial Differential Equations
- Contrastive Conditional Neural Processes
- GaitEdge: Beyond Plain End-to-end Gait Recognition for Better Practicality
- Universal Prototype Transport for Zero-Shot Action Recognition and Localization
- On Generalizing Beyond Domains in Cross-Domain Continual Learning
- GaitStrip: Gait Recognition via Effective Strip-based Feature Representations and Multi-Level Framework
- Few-Sample Traffic Prediction with Graph Networks using Locale as Relational Inductive Biases
- Generative Cooperative Learning for Unsupervised Video Anomaly Detection
- ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer
- Efficient and Accurate Hyperspectral Pansharpening Using 3D VolumeNet and 2.5D Texture Transfer
- RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering
- An Online Semantic Mapping System for Extending and Enhancing Visual SLAM
- Dynamic Group Transformer: A General Vision Transformer Backbone with Dynamic Group Attention
- Nonlinear Isometric Manifold Learning for Injective Normalizing Flows
- A Preliminary Study on Aging Examining Online Handwriting
- Digital Speech Algorithms for Speaker De-Identification
- PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification
- An Analysis of Measure-Valued Derivatives for Policy Gradients
- Estimating the average causal effect of intervention in continuous variables using machine learning
- Globally-Optimal Event Camera Motion Estimation
- Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation
- Designing Heterogeneous GNNs with Desired Permutation Properties for Wireless Resource Allocation
- End-to-end system for object detection from sub-sampled radar data
- InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER
- Noisy Low-rank Matrix Optimization: Geometry of Local Minima and Convergence Rate
- Geodesic Multi-Modal Mixup for Robust Fine-Tuning
- ClearPose: Large-scale Transparent Object Dataset and Benchmark
- ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation
- Boosting Mask R-CNN Performance for Long, Thin Forensic Traces with Pre-Segmentation and IoU Region Merging
- Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels
- HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks
- High-order Order Proximity-Incorporated, Symmetry and Graph-Regularized Nonnegative Matrix Factorization for Community Detection
- Occupancy Flow Fields for Motion Forecasting in Autonomous Driving
- Visual anomaly detection in video by variational autoencoder
- Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective
- Weakly Supervised Semantic Segmentation using Out-of-Distribution Data
- A New 27 Class Sign Language Dataset Collected from 173 Individuals
- DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act Recognition
- Where Does the Performance Improvement Come From? -- A Reproducibility Concern about Image-Text Retrieval
- UniXcoder: Unified Cross-Modal Pre-training for Code Representation
- Trust in AI and Implications for the AEC Research: A Literature Analysis
- Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
- Self-supervised Social Relation Representation for Human Group Detection
- Multi-Scale Self-Contrastive Learning with Hard Negative Mining for Weakly-Supervised Query-based Video Grounding
- Towards Building an Open-Domain Dialogue System Incorporated with Internet Memes
- Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap
- Deep Rectangling for Image Stitching: A Learning Baseline
- Informative Planning for Worst-Case Error Minimisation in Sparse Gaussian Process Regression
- Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification
- A Unified Framework of Medical Information Annotation and Extraction for Chinese Clinical Text
- CF-ViT: A General Coarse-to-Fine Method for Vision Transformer
- A Variational Hierarchical Model for Neural Cross-Lingual Summarization
- Table Structure Recognition with Conditional Attention
- Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon
- Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction to Treat Diabetic Foot Ulcers
- Towards Efficient Data-Centric Robust Machine Learning with Noise-based Augmentation
- Image Search with Text Feedback by Additive Attention Compositional Learning
- A Fast Scale-Invariant Algorithm for Non-negative Least Squares with Non-negative Data
- Panoramic Human Activity Recognition
- Understanding Iterative Revision from Human-Written Text
- Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wild
- New Insights on Reducing Abrupt Representation Change in Online Continual Learning
- Learning Sensorimotor Primitives of Sequential Manipulation Tasks from Visual Demonstrations
- PAMI-AD: An Activity Detector Exploiting Part-attention and Motion Information in Surveillance Videos
- Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding
- YONO: Modeling Multiple Heterogeneous Neural Networks on Microcontrollers
- Data adaptive RKHS Tikhonov regularization for learning kernels in operators