Papers
Fri 24 Mar 2023
217 papers
- Prompt Tuning based Adapter for Vision-Language Model AdaptionMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- VILA: Learning Image Aesthetics from User Comments with Vision-Language PretrainingMultimodal LLMs / vision-language models → Image editing and quality assessment
- DiffuScene: Denoising Diffusion Models for Generative Indoor Scene SynthesisDiffusion models → 3D, point cloud and scene generation
- Learning from Few Demonstrations with Frame-Weighted Motion GenerationOffline RL and imitation learning from data → Robot learning from demonstration
- Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion PriorDiffusion models → 3D, point cloud and scene generation
- MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural DiffusionDiffusion models → Medical imaging and segmentation
- CoLa-Diff: Conditional Latent Diffusion Model for Multi-Modal MRI SynthesisDiffusion models → Medical imaging and segmentation
- Accelerating Vision-Language Pretraining with Free Language ModelingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Interpretable Motion Planner for Urban Driving via Hierarchical Imitation LearningEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
- Mixed-Type Wafer Classification For Low Memory Devices Using Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
- Optimal Transport for Offline Imitation LearningOffline RL and imitation learning from data → Offline RL algorithms
- DisC-Diff: Disentangled Conditional Diffusion Model for Multi-Contrast MRI Super-ResolutionDiffusion models → Medical imaging and segmentation
- Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content CreationDiffusion models → 3D, point cloud and scene generation
- CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene LayoutDiffusion models → 3D, point cloud and scene generation
- Decoupled Multimodal Distilling for Emotion RecognitionKnowledge distillation → Multimodal distillation
- Edge-free but Structure-aware: Prototype-Guided Knowledge Distillation from GNNs to MLPsKnowledge distillation → Graph neural network distillation
- Conditional Image-to-Video Generation with Latent Flow Diffusion ModelsDiffusion models → Video generation
- WM-MoE: Weather-aware Multi-scale Mixture-of-Experts for Blind Adverse Weather RemovalMixture-of-experts → Vision mixture-of-experts
- Video Pre-trained Transformer: A Multimodal Mixture of Pre-trained Experts
- Fault diagnosis for PV arrays considering dust impact based on transformed graphical feature of characteristic curves and convolutional neural network with CBAM modules
- PromptORE -- A Novel Approach Towards Fully Unsupervised Relation Extraction
- Data-driven multiscale modeling for correcting dynamical systems
- Machine learning-based spin structure detection
- Computationally Efficient Labeling of Cancer Related Forum Posts by Non-Clinical Text Information Retrieval
- Large Language Models for Healthcare Data Augmentation: An Example on Patient-Trial Matching
- Mathematical Challenges in Deep Learning
- Pitchclass2vec: Symbolic Music Structure Segmentation with Chord Embeddings
- PeakNet: An Autonomous Bragg Peak Finder with Deep Neural Networks
- Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front-Facing Views
- Towards Outcome-Driven Patient Subgroups: A Machine Learning Analysis Across Six Depression Treatment Studies
- Image Deblurring by Exploring In-depth Properties of Transformer
- Derivative-based Shapley value for global sensitivity analysis and machine learning explainability
- Hybrid Augmented Automated Graph Contrastive Learning
- DreamStone: Image as Stepping Stone for Text-Guided 3D Shape Generation
- Robust Path Following on Rivers Using Bootstrapped Reinforcement Learning
- Natural Language-Based Synthetic Data Generation for Cluster Analysis
- AgileGAN3D: Few-Shot 3D Portrait Stylization by Augmented Transfer Learning
- Efficient Lipschitzian Global Optimization of H"older Continuous Multivariate Functions
- Applications of Gaussian Processes at Extreme Lengthscales: From Molecules to Black Holes
- Voice-Based Conversational Agents and Knowledge Graphs for Improving News Search in Assisted Living
- Feature Space Sketching for Logistic Regression
- Sequential Knockoffs for Variable Selection in Reinforcement Learning
- Depression detection in social media posts using affective and social norm features
- Learning to Operate in Open Worlds by Adapting Planning Models
- The Exact Sample Complexity Gain from Invariances for Kernel Regression
- A Self-supervised Framework for Improved Data-Driven Monitoring of Stress via Multi-modal Passive Sensing
- Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments
- PACE: Data-Driven Virtual Agent Interaction in Dense and Cluttered Environments
- Towards Diverse and Coherent Augmentation for Time-Series Forecasting
- A-MuSIC: An Adaptive Ensemble System For Visual Place Recognition In Changing Environments
- Implicit Balancing and Regularization: Generalization and Convergence Guarantees for Overparameterized Asymmetric Matrix Sensing
- DyLiN: Making Light Field Networks Dynamic
- IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients
- Data Depth and Core-based Trend Detection on Blockchain Transaction Networks
- Adaptive Base-class Suppression and Prior Guidance Network for One-Shot Object Detection
- SIGMORPHON 2023 Shared Task of Interlinear Glossing: Baseline Model
- Causality Detection for Efficient Multi-Agent Reinforcement Learning
- Synthetic Combinations: A Causal Inference Framework for Combinatorial Interventions
- Machine Guided Discovery of Novel Carbon Capture Solvents
- Lay Text Summarisation Using Natural Language Processing: A Narrative Literature Review
- The Battle of Information Representations: Comparing Sentiment and Semantic Features for Forecasting Market Trends
- Variational Inference for Longitudinal Data Using Normalizing Flows
- Curricular Contrastive Regularization for Physics-aware Single Image Dehazing
- Optimal Smoothing Distribution Exploration for Backdoor Neutralization in Deep Learning-based Traffic Systems
- DeepEpiSolver: Unravelling Inverse problems in Covid, HIV, Ebola and Disease Transmission
- Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning
- WildLight: In-the-wild Inverse Rendering with a Flashlight
- FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
- TRAK: Attributing Model Behavior at Scale
- Scaling Expert Language Models with Unsupervised Domain Discovery
- A Hybrid ANN-SNN Architecture for Low-Power and Low-Latency Visual Perception
- Inherent Consistent Learning for Accurate Semi-supervised Medical Image Segmentation
- How many dimensions are required to find an adversarial example?
- UrbanGIRAFFE: Representing Urban Scenes as Compositional Generative Neural Feature Fields
- BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects
- Efficient Scale-Invariant Generator with Column-Row Entangled Pixel Synthesis
- Local Contrastive Learning for Medical Image Recognition
- Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts
- Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
- "Get ready for a party": Exploring smarter smart spaces with help from large language models
- Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges
- The crime of being poor
- CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images
- Towards Scalable Neural Representation for Diverse Videos
- Semantic Prompt for Few-Shot Image Recognition
- Improving Prediction Performance and Model Interpretability through Attention Mechanisms from Basic and Applied Research Perspectives
- Principles of Forgetting in Domain-Incremental Semantic Segmentation in Adverse Weather Conditions
- Object Motion Sensitivity: A Bio-inspired Solution to the Ego-motion Problem for Event-based Cameras
- Unsupervised Automata Learning via Discrete Optimization
- Prediction of the morphological evolution of a splashing drop using an encoder-decoder
- Distributed Silhouette Algorithm: Evaluating Clustering on Big Data
- Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck
- PanoVPR: Towards Unified Perspective-to-Equirectangular Visual Place Recognition via Sliding Windows across the Panoramic View
- NeuFace: Realistic 3D Neural Face Rendering from Multi-view Images
- Physics-informed neural networks in the recreation of hydrodynamic simulations from dark matter
- Optimizing the Procedure of CT Segmentation Labeling
- OPDMulti: Openable Part Detection for Multiple Objects
- Differentially Private Synthetic Control
- Online Learning for the Random Feature Model in the Student-Teacher Framework
- Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Data
All 217
- DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling
- Improved Adversarial Training Through Adaptive Instance-wise Loss Smoothing
- Search By Image: Deeply Exploring Beneficial Features for Beauty Product Retrieval
- ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge
- A CNN-LSTM Architecture for Marine Vessel Track Association Using Automatic Identification System (AIS) Data
- SEAL: Semantic Frame Execution And Localization for Perceiving Afforded Robot Actions
- Learning Reward Machines in Cooperative Multi-Agent Tasks
- Communicating Complex Decisions in Robot-Assisted Therapy
- MusicFace: Music-driven Expressive Singing Face Synthesis
- Class-Incremental Exemplar Compression for Class-Incremental Learning
- Euler Characteristic Tools For Topological Data Analysis
- PENTACET data -- 23 Million Contextual Code Comments and 250,000 SATD comments
- Poincar'e ResNet
- CF-Font: Content Fusion for Few-shot Font Generation
- SPEC: Summary Preference Decomposition for Low-Resource Abstractive Summarization
- 'Team-in-the-loop': Ostrom's IAD framework 'rules in use' to map and measure contextual impacts of AI
- ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale
- Category Query Learning for Human-Object Interaction Classification
- Vulnerability of Face Morphing Attacks: A Case Study on Lookalike and Identical Twins
- Grid-guided Neural Radiance Fields for Large Urban Scenes
- PowerPruning: Selecting Weights and Activations for Power-Efficient Neural Network Acceleration
- LINe: Out-of-Distribution Detection by Leveraging Important Neurons
- Physical Backdoor Trigger Activation of Autonomous Vehicle using Reachability Analysis
- Paraphrase Detection: Human vs. Machine Content
- Machine Psychology
- Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AI
- Gradient scarcity with Bilevel Optimization for Graph Learning
- Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion
- Factorizers for Distributed Sparse Block Codes
- PIAT: Parameter Interpolation based Adversarial Training for Image Classification
- AssetField: Assets Mining and Reconfiguration in Ground Feature Plane Representation
- CCL: Continual Contrastive Learning for LiDAR Place Recognition
- Knowledge Graphs: Opportunities and Challenges
- MUG: A General Meeting Understanding and Generation Benchmark
- Topological Reconstruction of Particle Physics Processes using Graph Neural Networks
- Generative AI Assistants in Software Development Education: A vision for integrating Generative AI into educational practice, not instinctively defending against it
- Overview of the ICASSP 2023 General Meeting Understanding and Generation Challenge (MUG)
- MSdocTr-Lite: A Lite Transformer for Full Page Multi-script Handwriting Recognition
- Particle Mean Field Variational Bayes
- Removing confounding information from fetal ultrasound images
- Convolutional Neural Networks for the classification of glitches in gravitational-wave data streams
- Self-Supervised Reversed Image Signal Processing via Reference-Guided Dynamic Parameter Selection
- Benchmarking the Impact of Noise on Deep Learning-based Classification of Atrial Fibrillation in 12-Lead ECG
- GarmentTracking: Category-Level Garment Pose Tracking
- Wave-U-Net Discriminator: Fast and Lightweight Discriminator for Generative Adversarial Network-Based Speech Synthesis
- A Three-Player GAN for Super-Resolution in Magnetic Resonance Imaging
- Robust Test-Time Adaptation in Dynamic Scenarios
- Remind of the Past: Incremental Learning with Analogical Prompts
- Regularization of polynomial networks for image recognition
- Effective black box adversarial attack with handcrafted kernels
- ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data
- Symbolic Music Structure Analysis with Graph Representations and Changepoint Detection Methods
- Query-Dependent Video Representation for Moment Retrieval and Highlight Detection
- Physically Adversarial Infrared Patches with Learnable Shapes and Locations
- Few Shot Medical Image Segmentation with Cross Attention Transformer
- MagicEye: An Intelligent Wearable Towards Independent Living of Visually Impaired
- Two-level Graph Network for Few-Shot Class-Incremental Learning
- Unleashing GPT on the Metaverse: Savior or Destroyer?
- Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settings
- 2PCNet: Two-Phase Consistency Training for Day-to-Night Unsupervised Domain Adaptive Object Detection
- Weakly-supervised Single-view Image Relighting
- Towards Learning and Explaining Indirect Causal Effects in Neural Networks
- Feature Separation and Recalibration for Adversarial Robustness
- Anomaly Detection under Distribution Shift
- FishDreamer: Towards Fisheye Semantic Completion via Unified Image Outpainting and Segmentation
- HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures
- Editing Driver Character: Socially-Controllable Behavior Generation for Interactive Traffic Simulation
- Efficient Mixed-Type Wafer Defect Pattern Recognition Using Compact Deformable Convolutional Transformers
- Hard Sample Matters a Lot in Zero-Shot Quantization
- HandNeRF: Neural Radiance Fields for Animatable Interacting Hands
- kNN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
- Factor Decomposed Generative Adversarial Networks for Text-to-Image Synthesis
- Prior-RadGraphFormer: A Prior-Knowledge-Enhanced Transformer for Generating Radiology Graphs from X-Rays
- ABLE-NeRF: Attention-Based Rendering with Learnable Embeddings for Neural Radiance Field
- Multimodal Adaptive Fusion of Face and Gait Features using Keyless attention based Deep Neural Networks for Human Identification
- Generalist: Decoupling Natural and Robust Generalization
- Evidence-aware multi-modal data fusion and its application to total knee replacement prediction
- Error Analysis Prompting Enables Human-Like Translation Evaluation in Large Language Models
- marl-jax: Multi-Agent Reinforcement Leaning Framework
- PFT-SSR: Parallax Fusion Transformer for Stereo Image Super-Resolution
- Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container
- UniTS: A Universal Time Series Analysis Framework Powered by Self-Supervised Representation Learning
- Toward Open-domain Slot Filling via Self-supervised Co-training
- Aligning Step-by-Step Instructional Diagrams to Video Demonstrations
- Converging Measures and an Emergent Model: A Meta-Analysis of Human-Automation Trust Questionnaires
- 2D Floor Plan Segmentation Based on Down-sampling
- Personalizing Task-oriented Dialog Systems via Zero-shot Generalizable Reward Function
- Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction
- Efficient and Accurate Co-Visible Region Localization with Matching Key-Points Crop (MKPC): A Two-Stage Pipeline for Enhancing Image Matching Performance
- Forecasting Competitions with Correlated Events
- Progressively Optimized Local Radiance Fields for Robust View Synthesis
- Towards Fair Patient-Trial Matching via Patient-Criterion Level Fairness Constraint
- Application-Driven AI Paradigm for Person Counting in Various Scenarios
- Towards Making the Most of ChatGPT for Machine Translation
- Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR
- GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Images
- GSplit: Scaling Graph Neural Network Training on Large Graphs via Split-Parallelism
- Graph Neural Networks for the Offline Nanosatellite Task Scheduling Problem
- Unknown Sniffer for Object Detection: Don't Turn a Blind Eye to Unknown Objects
- Learning Spatial-Temporal Implicit Neural Representations for Event-Guided Video Super-Resolution
- GQE-Net: A Graph-based Quality Enhancement Network for Point Cloud Color Attribute
- Unsupervised Hierarchical Domain Adaptation for Adverse Weather Optical Flow
- Structural Imbalance Aware Graph Augmentation Learning
- GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning
- Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers
- EMS-Net: Efficient Multi-Temporal Self-Attention For Hyperspectral Change Detection
- Leveraging Old Knowledge to Continually Learn New Classes in Medical Images
- LON-GNN: Spectral GNNs with Learnable Orthonormal Basis
- Achieving Occam's Razor: Deep Learning for Optimal Model Reduction
- EdgeTran: Co-designing Transformers for Efficient Inference on Mobile Edge Platforms
- TEGLO: High Fidelity Canonical Texture Mapping from Single-View Images
- An investigation of licensing of datasets for machine learning based on the GQM model
- How Does Attention Work in Vision Transformers? A Visual Analytics Attempt
- A Survey on Secure and Private Federated Learning Using Blockchain: Theory and Application in Resource-constrained Computing
- Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation
- Natural language processing to automatically extract the presence and severity of esophagitis in notes of patients undergoing radiotherapy
- ReCOGS: How Incidental Details of a Logical Form Overshadow an Evaluation of Semantic Interpretation