Papers
Tue 26 Jul 2022
151 papers
- Interactive Imitation Learning in Robotics based on SimulationsOffline RL and imitation learning from data → Imitation learning methods
- Branch Ranking for Efficient Mixed-Integer Programming via Offline Ranking-based Policy LearningOffline RL and imitation learning from data → Imitation learning methods
- Planning and Learning: Path-Planning for Autonomous Vehicles, a Review of the LiteratureEnd-to-end autonomous driving → Imitation-learning end-to-end planners
- Retrieval-Augmented Transformer for Image CaptioningRetrieval-augmented generation → Multimodal RAG
- Offline Reinforcement Learning at Multiple FrequenciesOffline RL and imitation learning from data → Offline RL algorithms
- Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion ModelsRetrieval-augmented generation → Multimodal RAG +1
- Exploring Generalizable Distillation for Efficient Medical Image SegmentationKnowledge distillation → Distillation for medical imaging
- V2L: Leveraging Vision and Vision-language Models into Large-scale Product RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
- Efficient One Pass Self-distillation with Zipf's Label SmoothingKnowledge distillation → General knowledge distillation methods
- Cross-Modal Causal Relational Reasoning for Event-Level Visual Question AnsweringLLM reasoning → Multimodal reasoning
- Classifier-Free Diffusion GuidanceDiffusion models → Diffusion foundations and sampling
- MEG-MASC: a high-quality magneto-encephalography dataset for evaluating natural speech processing
- When BERT Fails -- The Limits of EHR Classification
- AI Approaches in Processing and Using Data in Personalized Medicine
- Let it RAIN for Social Good
- An Urban Population Health Observatory for Disease Causal Pathway Analysis and Decision Support: Underlying Explainable Artificial Intelligence Model
- Bounding Counterfactuals under Selection Bias
- Infant movement classification through pressure distribution analysis
- A Two-Stage Efficient 3-D CNN Framework for EEG Based Emotion Recognition
- Deep COVID-19 Recognition using Chest X-ray Images: A Comparative Analysis
- Location retrieval using visible landmarks based qualitative place signatures
- Tree edit distance for hierarchical data compatible with HMIL paradigm
- Debiasing Deep Chest X-Ray Classifiers using Intra- and Post-processing Methods
- Visual correspondence-based explanations improve AI robustness and human-AI team accuracy
- DADAO: Decoupled Accelerated Decentralized Asynchronous Optimization
- Multimodal Neural Machine Translation with Search Engine Based Image Retrieval
- FastGeodis: Fast Generalised Geodesic Distance Transform
- Physics-Informed Neural Networks for Shell Structures
- Physical Systems Modeled Without Physical Laws
- Remote Medication Status Prediction for Individuals with Parkinson's Disease using Time-series Data from Smartphones
- A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialog
- Deep Model-Based Architectures for Inverse Problems under Mismatched Priors
- Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perception
- GCN-WP -- Semi-Supervised Graph Convolutional Networks for Win Prediction in Esports
- On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classification
- Learning-Based Keypoint Registration for Fetoscopic Mosaicking
- SAR-to-EO Image Translation with Multi-Conditional Adversarial Networks
- Unsupervised Learning under Latent Label Shift
- Sliced Wasserstein Variational Inference
- One Simple Trick to Fix Your Bayesian Neural Network
- YOLO and Mask R-CNN for Vehicle Number Plate Identification
- TINYCD: A (Not So) Deep Learning Model For Change Detection
- Unsupervised Contrastive Learning of Image Representations from Ultrasound Videos with Hard Negative Mining
- Semi-analytical Industrial Cooling System Model for Reinforcement Learning
- LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity
- Sample Complexity of Forecast Aggregation
- Analysis and Design of Quadratic Neural Networks for Regression, Classification, and Lyapunov Control of Dynamical Systems
- Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment
- Task Agnostic and Post-hoc Unseen Distribution Detection
- Future-Dependent Value-Based Off-Policy Evaluation in POMDPs
- DETRs with Hybrid Matching
- NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers
- Video Manipulations Beyond Faces: A Dataset with Human-Machine Analysis
- NewsStories: Illustrating articles with visual summaries
- Efficient High-Resolution Deep Learning: A Survey
- Domain Adaptation under Open Set Label Shift
- Is Attention Interpretation? A Quantitative Assessment On Sets
- Modeling the Social Influence of COVID-19 via Personalized Propagation with Deep Learning
- Efficient Algorithms for Sparse Moment Problems without Separation
- Hansel: A Chinese Few-Shot and Zero-Shot Entity Linking Benchmark
- Monocular 3D Object Detection with Depth from Motion
- Explaining Deep Neural Networks for Point Clouds using Gradient-based Visualisations
- Tracking Every Thing in the Wild
- TransFiner: A Full-Scale Refinement Approach for Multiple Object Tracking
- Nondestructive Quality Control in Powder Metallurgy using Hyperspectral Imaging
- Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation
- From Interpretable Filters to Predictions of Convolutional Neural Networks with Explainable Artificial Intelligence
- Contextual Text Block Detection towards Scene Text Understanding
- AMF: Adaptable Weighting Fusion with Multiple Fine-tuning for Image Classification
- Learning structures of the French clinical language:development and validation of word embedding models using 21 million clinical reports from electronic health records
- Semantic Segmentation for Autonomous Driving: Model Evaluation, Dataset Generation, Perspective Comparison, and Real-Time Capability
- A Reliable Online Method for Joint Estimation of Focal Length and Camera Rotation
- A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance
- Learning-Augmented Maximum Flow
- AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction
- Cross-Modality Image Registration using a Training-Time Privileged Third Modality
- LaKo: Knowledge-driven Visual Question Answering via Late Knowledge-to-Text Injection
- Detection of road traffic crashes based on collision estimation
- CFLIT: Coexisting Federated Learning and Information Transfer
- Representing Random Utility Choice Models with Neural Networks
- Repeated Environment Inference for Invariant Learning
- Generalized Probabilistic U-Net for medical image segementation
- FRIB: Low-poisoning Rate Invisible Backdoor Attack based on Feature Repair
- Adaptive occlusion sensitivity analysis for visually explaining video recognition networks
- SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence
- Bessel Equivariant Networks for Inversion of Transmission Effects in Multi-Mode Optical Fibres
- Fixed-Time Convergence for a Class of Nonconvex-Nonconcave Min-Max Problems
- Unsupervised Domain Adaptation for Video Transformers in Action Recognition
- KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
- Partial-Monotone Adaptive Submodular Maximization
- Multimodal-GuideNet: Gaze-Probe Bidirectional Guidance in Obstetric Ultrasound Scanning
- Lifelong DP: Consistently Bounded Differential Privacy in Lifelong Machine Learning
- Compositional Human-Scene Interaction Synthesis with Semantic Control
- S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning
- Bodily Behaviors in Social Interaction: Novel Annotations and State-of-the-Art Evaluation
- Class-Aware Universum Inspired Re-Balance Learning for Long-Tailed Recognition
- Neural Design for Genetic Perturbation Experiments
- PIXEL: Physics-Informed Cell Representations for Fast and Accurate PDE Solvers
- Static and Dynamic Concepts for Self-supervised Video Representation Learning
- Equivariant and Invariant Grounding for Video Question Answering
All 151
- An Explainable Decision Support System for Predictive Process Analytics
- Reconciling Security and Communication Efficiency in Federated Learning
- Quiver neural networks
- A Study on the Use of Edge TPUs for Eye Fundus Image Segmentation
- Criteria Comparative Learning for Real-scene Image Super-Resolution
- Clustering Object-Centric Event Logs
- Using Abstraction for Interpretable Robot Programs in Stochastic Domains
- Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases
- Controllable User Dialogue Act Augmentation for Dialogue State Tracking
- Thermodynamics of learning physical phenomena
- ScoreCAM GNN: une explication optimale des r'eseaux profonds sur graphes
- Distribution Learning Based on Evolutionary Algorithm Assisted Deep Neural Networks for Imbalanced Image Classification
- P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos
- An Automated News Bias Classifier Using Caenorhabditis Elegans Inspired Recursive Feedback Network Architecture
- Convolutional neural networks and multi-threshold analysis for contamination detection in the apparel industry
- XInsight: eXplainable Data Analysis Through The Lens of Causality
- The derivatives of Sinkhorn-Knopp converge
- MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones
- Comparison of Deep Learning and Machine Learning Models and Frameworks for Skin Lesion Classification
- Active Learning of Ordinal Embeddings: A User Study on Football Data
- Advanced Conditional Variational Autoencoders (A-CVAE): Towards interpreting open-domain conversation generation via disentangling latent feature representation
- CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving
- Single MCMC Chain Parallelisation on Decision Trees
- A Kendall Shape Space Approach to 3D Shape Estimation from 2D Landmarks
- Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability
- A Data Driven Method for Multi-step Prediction of Ship Roll Motion in High Sea States
- Time Majority Voting, a PC-based EEG Classifier for Non-expert Users
- Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training
- Bilateral Self-unbiased Learning from Biased Implicit Feedback
- Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds
- Semi-supervised 3D Object Detection with Proficient Teachers
- ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection
- Can Deep Learning Assist Automatic Identification of Layered Pigments From XRF Data?
- Asymmetric Scalable Cross-modal Hashing
- Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter- and Intra-body Graphs
- Learning Hierarchy Aware Features for Reducing Mistake Severity
- Learning Bipedal Walking On Planned Footsteps For Humanoid Robots
- Variance estimation in graphs with the fused lasso
- A Learning and Control Perspective for Microfinance
- Bundle MCR: Towards Conversational Bundle Recommendation
- Multi-Attention Network for Compressed Video Referring Object Segmentation
- Large-displacement 3D Object Tracking with Hybrid Non-local Optimization
- Exploring the Design of Adaptation Protocols for Improved Generalization and Machine Learning Safety
- Physics Embedded Machine Learning for Electromagnetic Data Imaging
- Differentially Private Estimation via Statistical Depth
- Learning Hierarchical Protein Representations via Complete 3D Graph Networks
- A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metrics
- PTGCF: Printing Texture Guided Color Fusion for Impressionism Oil Painting Style Rendering
- How should I compute my candidates? A taxonomy and classification of diagnosis computation algorithms
- RenderNet: Visual Relocalization Using Virtual Viewpoints in Large-Scale Indoor Environments
- A Retrospective on ICSE 2022