Papers
Wed 17 Aug 2022
172 papers
- Dual Modality Prompt Tuning for Vision-Language Pre-Trained ModelMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
- Leukocyte Classification using Multimodal Architecture Enhanced by Knowledge DistillationKnowledge distillation → Distillation for medical imaging
- ILLUME: Rationalizing Vision-Language Models through Human InteractionsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with ModelsLLM reasoning → Prompting and chain-of-thought reasoning
- An Empirical Study on the Membership Inference Attack against Tabular Data Synthesis ModelsLLM safety and security → Membership inference attacks
- Designing with Non-Finite Output Dimension via Fourier Coefficients of Neural Waveforms
- Quality Diversity Evolutionary Learning of Decision Trees
- NeurIPS Competition Instructions and Guide: Causal Insights for Learning Paths in Education
- Getting Quechua Closer to Final Users through Knowledge Graphs
- Detect to Learn: Structure Learning with Attention and Decision Feedback for MIMO-OFDM Receive Processing
- Autism spectrum disorder classification based on interpersonal neural synchrony: Can classification be improved by dyadic neural biomarkers using unsupervised graph representation learning?
- EEG-BBNet: a Hybrid Framework for Brain Biometric using Graph Connectivity
- Conviformers: Convolutionally guided Vision Transformer
- Heart Disease Detection using Quantum Computing and Partitioned Random Forest Methods
- Modelling the long-term fairness dynamics of data-driven targeted help on job seekers
- SensorSCAN: Self-Supervised Learning and Deep Clustering for Fault Diagnosis in Chemical Processes
- Towards Learning in Grey Spatiotemporal Systems: A Prophet to Non-consecutive Spatiotemporal Dynamics
- Object Detection for Autonomous Dozers
- ObfuNAS: A Neural Architecture Search-based DNN Obfuscation Approach
- High Probability Bounds for Stochastic Subgradient Schemes with Heavy Tailed Noise
- Physical Computing for Materials Acceleration Platforms
- Restructurable Activation Networks
- Geometric Scattering on Measure Spaces
- A Framework for Understanding and Visualizing Strategies of RL Agents
- Estimating individual treatment effects under unobserved confounding using binary instruments
- DF-Captcha: A Deepfake Captcha for Preventing Fake Calls
- Visual Cross-View Metric Localization with Dense Uncertainty Estimates
- Analyzing Robustness of End-to-End Neural Models for Automatic Speech Recognition
- On the evolution of research in hypersonics: application of natural language processing and machine learning
- Learning with Local Gradients at the Edge
- Choquet regularization for reinforcement learning
- Text-to-Image Generation via Implicit Visual Guidance and Hypernetwork
- NET-FLEET: Achieving Linear Convergence Speedup for Fully Decentralized Federated Learning with Heterogeneous Data
- Understanding Scaling Laws for Recommendation Models
- EmoMent: An Emotion Annotated Mental Health Corpus from two South Asian Countries
- Complex-Value Spatio-temporal Graph Convolutional Neural Networks and its Applications to Electric Power Systems AI
- Nearly Optimal Latent State Decoding in Block MDPs
- "Task-relevant autoencoding" enhances machine learning for human neuroscience
- Detect and Approach: Close-Range Navigation Support for People with Blindness and Low Vision
- CTRL: Clustering Training Losses for Label Error Detection
- Performance Evaluation of Selective Fixed-filter Active Noise Control based on Different Convolutional Neural Networks
- MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenes
- Learning to Structure an Image with Few Colors and Beyond
- Multi-View Correlation Consistency for Semi-Supervised Semantic Segmentation
- Label Flipping Data Poisoning Attack Against Wearable Human Activity Recognition System
- SYNTHESIS: A Semi-Asynchronous Path-Integrated Stochastic Gradient Method for Distributed Learning in Computing Clusters
- Extracting Medication Changes in Clinical Narratives using Pre-trained Language Models
- Summarizing Patients Problems from Hospital Progress Notes Using Pre-trained Sequence-to-Sequence Models
- Self-Supervised Depth Estimation in Laparoscopic Image using 3D Geometric Consistency
- Conformal Inference for Online Prediction with Arbitrary Distribution Shifts
- The Counterfactual-Shapley Value: Attributing Change in System Metrics
- LAMA-Net: Unsupervised Domain Adaptation via Latent Alignment and Manifold Learning for RUL Prediction
- Neural Embeddings for Text
- Deep Generative Views to Mitigate Gender Classification Bias Across Gender-Race Groups
- A Computational Interface to Translate Strategic Intent from Unstructured Language in a Low-Data Setting
- Ask Question First for Enhancing Lifelong Language Learning
- Extract fundamental frequency based on CNN combined with PYIN
- FCN-Transformer Feature Fusion for Polyp Segmentation
- Minimum Cost Adaptive Submodular Cover
- Open Long-Tailed Recognition in a Dynamic World
- Discovering Agents
- Semantic Communications with Discrete-time Analog Transmission: A PAPR Perspective
- SO(3)-Pose: SO(3)-Equivariance Learning for 6D Object Pose Estimation
- BIC: Twitter Bot Detection with Text-Graph Interaction and Semantic Consistency
- Video-TransUNet: Temporally Blended Vision Transformer for CT VFSS Instance Segmentation
- SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning
- Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing
- Transformer-Based Deep Learning Model for Stock Price Prediction: A Case Study on Bangladesh Stock Market
- An Evolutionary, Gradient-Free, Query-Efficient, Black-Box Algorithm for Generating Adversarial Instances in Deep Networks
- ParaColorizer: Realistic Image Colorization using Parallel Generative Networks
- IDAN: Image Difference Attention Network for Change Detection
- Inference on Strongly Identified Functionals of Weakly Identified Functions
- Deep learning based projection domain metal segmentation for metal artifact reduction in cone beam computed tomography
- Noisy Nonnegative Tucker Decomposition with Sparse Factors and Missing Data
- Exploiting Unlabeled Data for Target-Oriented Opinion Words Extraction
- On the Privacy Effect of Data Enhancement via the Lens of Memorization
- Prediction of Oral Food Challenge Outcomes via Ensemble Learning
- Semi-Supervised Anomaly Detection Based on Quadratic Multiform Separation
- Multimodal foundation models are better simulators of the human brain
- On the Elements of Datasets for Cyber Physical Systems Security
- An Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework based on Semantic Blocks
- Domain Knowledge in A*-Based Causal Discovery
- Performance Optimization for Semantic Communications: An Attention-based Reinforcement Learning Approach
- DPA-1: Pretraining of Attention-based Deep Potential Model for Molecular Simulation
- CSGO: Constrained-Softassign Gradient Optimization For Large Graph Matching
- Deep Autoencoder Model Construction Based on Pytorch
- Two-Stage Robust and Sparse Distributed Statistical Inference for Large-Scale Data
- MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation
- Auto-segmentation of Hip Joints using MultiPlanar UNet with Transfer learning
- On the Role of Negative Precedent in Legal Outcome Prediction
- Blind-Spot Collision Detection System for Commercial Vehicles Using Multi Deep CNN Architecture
- Which Factors are associated with Open Access Publishing? A Springer Nature Case Study
- Towards an Error-free Deep Occupancy Detector for Smart Camera Parking System
- ODformer: Spatial-Temporal Transformers for Long Sequence Origin-Destination Matrix Forecasting Against Cross Application Scenario
- How does the degree of novelty impacts semi-supervised representation learning for novel class retrieval?
- Path Planning of Cleaning Robot with Reinforcement Learning
- Time flies by: Analyzing the Impact of Face Ageing on the Recognition Performance with Synthetic Data
- Understanding Long Documents with Different Position-Aware Attentions
- AHEAD: A Triple Attention Based Heterogeneous Graph Anomaly Detection Approach
- Assurance Cases as Foundation Stone for Auditing AI-enabled and Autonomous Systems: Workshop Results and Political Recommendations for Action from the ExamAI Project
All 172
- Benchmarking Compositionality with Formal Languages
- Transformer Vs. MLP-Mixer: Exponential Expressive Gap For NLP Problems
- DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
- Deep Learning-Based Discrete Calibrated Survival Prediction
- Visual Comparison of Language Model Adaptation
- Expressivity of Hidden Markov Chains vs. Recurrent Neural Networks from a system theoretic viewpoint
- Random Search Hyper-Parameter Tuning: Expected Improvement Estimation and the Corresponding Lower Bound
- Data-Efficient Vision Transformers for Multi-Label Disease Classification on Chest Radiographs
- Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning
- KAM -- a Kernel Attention Module for Emotion Classification with EEG Data
- Error in the Euclidean Preference Model
- On Establishing Robust Consistency in Answer Set Programs
- A Monotonicity Constrained Attention Module for Emotion Classification with Limited EEG Data
- A Concept and Argumentation based Interpretable Model in High Risk Domains
- Stereo Superpixel Segmentation Via Decoupled Dynamic Spatial-Embedding Fusion Network
- Differential Privacy in Natural Language Processing: The Story So Far
- Shallow neural network representation of polynomials
- Gradient-Based Meta-Learning Using Uncertainty to Weigh Loss for Few-Shot Learning
- Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning
- Maximising the Utility of Validation Sets for Imbalanced Noisy-label Meta-learning
- Knowledge Graph Curation: A Practical Framework
- Extreme-scale Talking-Face Video Upsampling with Audio-Visual Priors
- Road detection via a dual-task network based on cross-layer graph fusion modules
- DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning
- PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation
- Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions
- Disentangling Identity and Pose for Facial Expression Recognition
- Understanding Attention for Vision-and-Language Tasks
- CommitBART: A Large Pre-trained Model for GitHub Commits
- SelF-Eval: Self-supervised Fine-grained Dialogue Evaluation
- Paint2Pix: Interactive Painting based Progressive Image Synthesis and Editing
- In-vehicle alertness monitoring for older adults
- Progressive Cross-modal Knowledge Distillation for Human Action Recognition
- Constrained Few-Shot Learning: Human-Like Low Sample Complexity Learning and Non-Episodic Text Classification
- Autonomous Resource Management in Construction Companies Using Deep Reinforcement Learning Based on IoT
- Detection and Mitigation of Byzantine Attacks in Distributed Training
- AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets
- Two Heads are Better than One: Robust Learning Meets Multi-branch Models
- A Hybrid SFANC-FxNLMS Algorithm for Active Noise Control based on Deep Learning
- Multimodal Lecture Presentations Dataset: Understanding Multimodality in Educational Slides
- Look in Different Views: Multi-Scheme Regression Guided Cell Instance Segmentation
- Significance of Skeleton-based Features in Virtual Try-On
- An Efficient Multi-Step Framework for Malware Packing Identification
- Quantum Bayesian Computation
- K-ASTRO: Structure-Aware Adaptation of LLMs for Code Vulnerability Detection
- NECE: Narrative Event Chain Extraction Toolkit
- Efficient dynamic point cloud coding using Slice-Wise Segmentation
- Semi-supervised Learning with Deterministic Labeling and Large Margin Projection
- Sampling Through the Lens of Sequential Decision Making
- A Sequence Tagging based Framework for Few-Shot Relation Extraction
- Imperceptible and Robust Backdoor Attack in 3D Point Cloud
- PDRF: Progressively Deblurring Radiance Field for Fast and Robust Scene Reconstruction from Blurry Images
- REGAS: REspiratory-GAted Synthesis of Views for Multi-Phase CBCT Reconstruction from a single 3D CBCT Acquisition
- Urban feature analysis from aerial remote sensing imagery using self-supervised and semi-supervised computer vision
- The Conversational Short-phrase Speaker Diarization (CSSD) Task: Dataset, Evaluation Metric and Baselines
- InterTrack: Interaction Transformer for 3D Multi-Object Tracking
- A Survey on Incomplete Multi-view Clustering
- Artificial Intelligence Empowered Multiple Access for Ultra Reliable and Low Latency THz Wireless Networks
- LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction
- EGCR: Explanation Generation for Conversational Recommendation
- A Context-Aware Approach for Textual Adversarial Attack through Probability Difference Guided Beam Search
- Few-shot Named Entity Recognition with Entity-level Prototypical Network Enhanced by Dispersedly Distributed Prototypes
- Streaming Adaptive Submodular Maximization
- Interference Cancellation GAN Framework for Dynamic Channels
- Towards Generating Robust, Fair, and Emotion-Aware Explanations for Recommender Systems
- Cross-Domain Few-Shot Classification via Inter-Source Stylization
- ShortcutLens: A Visual Analytics Approach for Exploring Shortcuts in Natural Language Understanding Dataset
- Transformer Encoder for Social Science
- Investigating the Impact of Model Width and Density on Generalization in Presence of Label Noise
- DeeperDive: The Unreasonable Effectiveness of Weak Supervision in Document Understanding A Case Study in Collaboration with UiPath Inc
- What Artificial Neural Networks Can Tell Us About Human Language Acquisition
- Deep Learning Enabled Time-Lapse 3D Cell Analysis