Papers
Thu 24 Nov 2022
154 papers
- Shifted Diffusion for Text-to-image GenerationDiffusion models → Image generation, text-to-image and editing
- Double Deep Q-Learning in Opponent ModelingMixture-of-experts → MoE in reinforcement learning and robotics
- Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward LearningOffline RL and imitation learning from data → Imitation learning methods
- PuzzleFusion: Unleashing the Power of Diffusion Models for Spatial Puzzle SolvingDiffusion models → 3D, point cloud and scene generation
- Design and Prototyping Distributed CNN Inference Acceleration in Edge ComputingEfficient LLM inference and serving → Early exit and edge inference
- Diffusion-SDF: Conditional Generative Modeling of Signed Distance FunctionsDiffusion models → 3D, point cloud and scene generation
- Sketch-Guided Text-to-Image Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
- Seeds Don't Lie: An Adaptive Watermarking Framework for Computer Vision ModelsLLM safety and security → Watermarking generated content and models
- Self-supervised vision-language pretraining for Medical visual question answeringMultimodal LLMs / vision-language models → Medical vision-language models
- DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural NetworksLLM safety and security → Watermarking generated content and models
- Spatial Mixture-of-ExpertsMixture-of-experts → MoE for time series and graphs
- NQE: N-ary Query Embedding for Complex Query Answering over Hyper-Relational Knowledge GraphsLLM reasoning → Knowledge- and tool-augmented reasoning
- Fast Sampling of Diffusion Models via Operator LearningDiffusion models → Diffusion foundations and sampling
- Seeing What You Miss: Vision-Language Pre-training with Semantic Completion LearningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
- Mediastinal Lymph Node Detection and Segmentation Using Deep Learning
- Using Natural Language Processing to Predict Costume Core Vocabulary of Historical Artifacts
- Relation-based Motion Prediction using Traffic Scene Graphs
- Target-centered Subject Transfer Framework for EEG Data Augmentation
- DBA: Efficient Transformer with Dynamic Bilinear Low-Rank Attention
- Utilising physics-guided deep learning to overcome data scarcity
- Localized Shortcut Removal
- Self Supervised Clustering of Traffic Scenes using Graph Representations
- AI Knows Which Words Will Appear in Next Year's Korean CSAT
- Video Test-Time Adaptation for Action Recognition
- AIREPAIR: A Repair Platform for Neural Networks
- Neural Network Complexity of Chaos and Turbulence
- Software Simulation and Visualization of Quantum Multi-Drone Reinforcement Learning
- Explainable Artificial Intelligence (XAI) from a user perspective- A synthesis of prior literature and problematizing avenues for future research
- Non-inferiority of Deep Learning Acute Ischemic Stroke Segmentation on Non-Contrast CT Compared to Expert Neuroradiologists
- Learning Integrable Dynamics with Action-Angle Networks
- Bidirectional Representations for Low Resource Spoken Language Understanding
- Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Space
- Learning-enhanced Nonlinear Model Predictive Control using Knowledge-based Neural Ordinary Differential Equations and Deep Ensembles
- Joint segmentation and discontinuity-preserving deformable registration: Application to cardiac cine-MR images
- Neural Weight Search for Scalable Task Incremental Learning
- Detecting Entities in the Astrophysics Literature: A Comparison of Word-based and Span-based Entity Recognition Methods
- Using Selective Masking as a Bridge between Pre-training and Fine-tuning
- Multi-label Few-shot ICD Coding as Autoregressive Generation with Prompt
- Improving Siamese Based Trackers with Light or No Training through Multiple Templates and Temporal Network
- Detecting Anomalies using Generative Adversarial Networks on Images
- GEFF: Improving Any Clothes-Changing Person ReID Model using Gallery Enrichment with Face Features
- On the Linguistic and Computational Requirements for Creating Face-to-Face Multimodal Human-Machine Interaction
- Sequential Gradient Coding For Straggler Mitigation
- Estimation of a Causal Directed Acyclic Graph Process using Non-Gaussianity
- Question Answering and Question Generation for Finnish
- Tensor Decomposition of Large-scale Clinical EEGs Reveals Interpretable Patterns of Brain Physiology
- Semantic Communication Enabling Robust Edge Intelligence for Time-Critical IoT Applications
- PyTAIL: Interactive and Incremental Learning of NLP Models with Human in the Loop for Online Data
- German Phoneme Recognition with Text-to-Phoneme Data Augmentation
- SAGA: Spectral Adversarial Geometric Attack on 3D Meshes
- Generative Joint Source-Channel Coding for Semantic Image Transmission
- Towards Practical Control of Singular Values of Convolutional Layers
- On Designing Light-Weight Object Trackers through Network Pruning: Use CNNs or Transformers?
- ScanNeRF: a Scalable Benchmark for Neural Radiance Fields
- Contrastive pretraining for semantic segmentation is robust to noisy positive pairs
- TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network
- Melting Pot 2.0
- Attention-based Feature Compression for CNN Inference Offloading in Edge Computing
- SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration
- Assessing Quality-Diversity Neuro-Evolution Algorithms Performance in Hard Exploration Problems
- Explainable Model-Agnostic Similarity and Confidence in Face Verification
- On Pitfalls of Measuring Occlusion Robustness through Data Distortion
- Deep Demosaicing for Polarimetric Filter Array Cameras
- Probabilistic Time Series Forecasting for Adaptive Monitoring in Edge Computing Environments
- Question-type Identification for Academic Questions in Online Learning Platform
- Lightweight Event-based Optical Flow Estimation via Iterative Deblurring
- Estimating Regression Predictive Distributions with Sample Networks
- Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective
- Emotion-guided Cross-domain Fake News Detection using Adversarial Domain Adaptation
- Trust Your nabla: Gradient-based Intervention Targeting for Causal Discovery
- Undesirable Biases in NLP: Addressing Challenges of Measurement
- Reduction Algorithms for Persistence Diagrams of Networks: CoralTDA and PrunIT
- Multitask Learning for Low Resource Spoken Language Understanding
- CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion
- Certified data-driven physics-informed greedy auto-encoder simulator
- Hand Guided High Resolution Feature Enhancement for Fine-Grained Atomic Action Segmentation within Complex Human Assemblies
- To be or not to be stable, that is the question: understanding neural networks for inverse problems
- Meta-Learning for Automated Selection of Anomaly Detectors for Semi-Supervised Datasets
- Perception-Oriented Single Image Super-Resolution using Optimal Objective Estimation
- A Self-Attention Ansatz for Ab-initio Quantum Chemistry
- Zeroth-Order Alternating Gradient Descent Ascent Algorithms for a Class of Nonconvex-Nonconcave Minimax Problems
- Cross-domain Transfer of defect features in technical domains based on partial target data
- Federated Learning Hyper-Parameter Tuning from a System Perspective
- Learning with Partial Labels from Semi-supervised Perspective
- Cross Aggregation Transformer for Image Restoration
- End-to-end Wind Turbine Wake Modelling with Deep Graph Representation Learning
- Prototypical Fine-tuning: Towards Robust Performance Under Varying Data Sizes
- ACROBAT -- a multi-stain breast cancer histological whole-slide-image data set from routine diagnostics for computational pathology
- ML Interpretability: Simple Isn't Easy
- Ham2Pose: Animating Sign Language Notation into Pose Sequences
- PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization
- Collaborative Training of Medical Artificial Intelligence Models with non-uniform Labels
- Responsible Active Learning via Human-in-the-loop Peer Study
- How to predict and optimise with asymmetric error metrics
- Learning to Suggest Breaks: Sustainable Optimization of Long-Term User Engagement
- The intersection of machine learning with forecasting and optimisation: theory and applications
- Knowledge-Aware Federated Active Learning with Non-IID Data
- Learning Invariant Rules from Data for Interpretable Anomaly Detection
- Physics-Based Object 6D-Pose Estimation during Non-Prehensile Manipulation
- More comprehensive facial inversion for more effective expression recognition
All 154
- How "open" are the conversations with open-domain chatbots? A proposal for Speech Event based evaluation
- Fingerprint Image-Quality Estimation and its Application to Multialgorithm Verification
- Quality-Based Conditional Processing in Multi-Biometrics: Application to Sensor Interoperability
- SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networks
- Online Regularized Learning Algorithm for Functional Data
- A Privacy-Preserving Outsourced Data Model in Cloud Environment
- Prosody-controllable spontaneous TTS with neural HMMs
- 3D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object Detection
- Beyond Mahalanobis-Based Scores for Textual OOD Detection
- GAN Prior based Null-Space Learning for Consistent Super-Resolution
- Roboflow 100: A Rich, Multi-Domain Object Detection Benchmark
- Chinese Character Recognition with Radical-Structured Stroke Trees
- TSGP: Two-Stage Generative Prompting for Unsupervised Commonsense Question Answering
- The Second-place Solution for ECCV 2022 Multiple People Tracking in Group Dance Challenge
- 1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results
- Multi-Task Learning of Object State Changes from Uncurated Videos
- GitHub Considered Harmful? Analyzing Open-Source Projects for the Automatic Generation of Cryptographic API Call Sequences
- Few-shot Object Detection with Refined Contrastive Learning
- Immersive Neural Graphics Primitives
- Pose-disentangled Contrastive Learning for Self-supervised Facial Representation
- Towards computer vision technologies: Semi-automated reading of automated utility meters
- The Second-place Solution for CVPR 2022 SoccerNet Tracking Challenge
- Explainable and Safe Reinforcement Learning for Autonomous Air Mobility
- Minority-Oriented Vicinity Expansion with Attentive Aggregation for Video Long-Tailed Recognition
- Efficient Zero-shot Visual Search via Target and Context-aware Transformer
- Hierarchical Consistent Contrastive Learning for Skeleton-Based Action Recognition with Growing Augmentations
- On the Importance of Image Encoding in Automated Chest X-Ray Report Generation
- Design of Turing Systems with Physics-Informed Neural Networks
- Automated Quantification of Traffic Particulate Emissions via an Image Analysis Pipeline
- Deep unfolding as iterative regularization for imaging inverse problems
- On the Complexity of Counterfactual Reasoning
- Delving into Out-of-Distribution Detection with Vision-Language Representations
- Iterative Data Refinement for Self-Supervised MR Image Reconstruction
- Solving Bilevel Knapsack Problem using Graph Neural Networks
- A Benchmark of Long-tailed Instance Segmentation with Noisy Labels
- LaCAM: Search-Based Algorithm for Quick Multi-Agent Pathfinding
- Multi-Job Intelligent Scheduling with Cross-Device Federated Learning
- UV-Based 3D Hand-Object Reconstruction with Grasp Optimization
- Deepfake Detection via Joint Unsupervised Reconstruction and Supervised Classification
- Network Security Modelling with Distributional Data
- Data Origin Inference in Machine Learning
- Object Detection in Foggy Scenes by Embedding Depth and Reconstruction into Domain Adaptation
- Graph Contrastive Learning for Materials
- Differentially Private Image Classification from Features
- MP-GELU Bayesian Neural Networks: Moment Propagation by GELU Nonlinearity
- CPPF++: Uncertainty-Aware Sim2Real Object Pose Estimation by Vote Aggregation
- One-Shot General Object Localization
- FedCut: A Spectral Analysis Framework for Reliable Detection of Byzantine Colluders
- MaskPlace: Fast Chip Placement via Reinforced Visual Representation Learning
- InDEX: Indonesian Idiom and Expression Dataset for Cloze Test
- Lifting Weak Supervision To Structured Prediction
- Tapping the Potential of Coherence and Syntactic Features in Neural Models for Automatic Essay Scoring
- Turning the Tables: Biased, Imbalanced, Dynamic Tabular Datasets for ML Evaluation
- MPT: Mesh Pre-Training with Transformers for Human Pose and Mesh Reconstruction