Papers
Fri 22 Jul 2022
151 papers
- Distributed Deep Learning Inference Acceleration using Seamless Collaboration in Edge ComputingEfficient LLM inference and serving → Early exit and edge inference
- Receptive Field-based Segmentation for Distributed CNN Inference Acceleration in Collaborative Edge ComputingEfficient LLM inference and serving → Early exit and edge inference
- Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free ReplayKnowledge distillation → Distillation for continual learning
- Classification via score-based generative modellingDiffusion models → Diffusion foundations and sampling
- Hyper-Representations for Pre-Training and Transfer LearningKnowledge distillation → General knowledge distillation methods
- 4G 5G Cell-level Multi-indicator Forecasting based on Dense-MLP
- Guided Evolutionary Neural Architecture Search With Efficient Performance Estimation
- Enhancing Oceanic Variables Forecast in the Santos Channel by Estimating Model Error with Random Forests
- V-Coder: Adaptive AutoEncoder for Semantic Disclosure in Knowledge Graphs
- HiKonv: Maximizing the Throughput of Quantized Convolution With Novel Bit-wise Management and Computation
- DeFakePro: Decentralized DeepFake Attacks Detection using ENF Authentication
- Redundancy-aware unsupervised ranking based on game theory -- application to gene enrichment analysis
- Applying Spatiotemporal Attention to Identify Distracted and Drowsy Driving with Vision Transformers
- Towards Fairness-Aware Multi-Objective Optimization
- Complementing Semi-Supervised Learning with Uncertainty Quantification
- Do Perceptually Aligned Gradients Imply Adversarial Robustness?
- Evaluation of Different Annotation Strategies for Deployment of Parking Spaces Classification Systems
- Neural-Sim: Learning to Generate Training Data with NeRF
- EgoEnv: Human-centric environment representations from egocentric video
- Knowledge-Grounded Conversational Data Augmentation with Generative Conversational Networks
- Machine Learning Modeling to Evaluate the Value of Football Players
- Quantum Machine Learning for Distributed Quantum Protocols with Local Operations and Noisy Classical Communications
- A Supervised Tensor Dimension Reduction-Based Prognostics Model for Applications with Incomplete Imaging Data
- Deep neural network heatmaps capture Alzheimer's disease patterns reported in a large meta-analysis of neuroimaging studies
- An Impartial Take to the CNN vs Transformer Robustness Contest
- Toward Fairness in Speech Recognition: Discovery and mitigation of performance disparities
- Dynamic Graph Reasoning for Multi-person 3D Pose Estimation
- First AI for deep super-resolution wide-field imaging in radio astronomy: unveiling structure in ESO 137--006
- Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules
- Video Swin Transformers for Egocentric Video Understanding @ Ego4D Challenges 2022
- Learning from Multiple Annotator Noisy Labels via Sample-wise Label Fusion
- PieTrack: An MOT solution based on synthetic data training and self-supervised domain adaptation
- Exploring Wasserstein Distance across Concept Embeddings for Ontology Matching
- A flexible PageRank-based graph embedding framework closely related to spectral eigenvector embeddings
- Tradeoffs in Preventing Manipulation in Paper Bidding for Reviewer Assignment
- HybMT: Hybrid Meta-Predictor based ML Algorithm for Fast Test Vector Generation
- Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspective
- JAM: The JavaScript Agent Machine for Distributed Computing and Simulation with reactive and mobile Multi-agent Systems -- A Technical Report
- Accelerated and Quantitative 3D Semisolid MT/CEST Imaging using a Generative Adversarial Network (GAN-CEST)
- TRUST-LAPSE: An Explainable and Actionable Mistrust Scoring Framework for Model Monitoring
- PanGu-Coder: Program Synthesis with Function-Level Language Modeling
- Panoptic Scene Graph Generation
- Deep Learning Hyperparameter Optimization for Breast Mass Detection in Mammograms
- Multiface: A Dataset for Neural Face Rendering
- Discrete Key-Value Bottleneck
- E2N: Error Estimation Networks for Goal-Oriented Mesh Adaptation
- Neural Groundplans: Persistent Neural Scene Representations from a Single Image
- Improving Predictive Performance and Calibration by Weight Fusion in Semantic Segmentation
- Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization
- Statistical and Computational Trade-offs in Variational Inference: A Case Study in Inferential Model Selection
- Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection
- Provable Defense Against Geometric Transformations
- Explaining Dynamic Graph Neural Networks via Relevance Back-propagation
- Verifying Fairness in Quantum Machine Learning
- Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark
- METER-ML: A Multi-Sensor Earth Observation Benchmark for Automated Methane Source Mapping
- High dimensional stochastic linear contextual bandit with missing covariates
- Generalized Identifiability Bounds for Mixture Models with Grouped Samples
- Adaptive Soft Contrastive Learning
- Lagrangian Method for Q-Function Learning (with Applications to Machine Translation)
- Network Revenue Management with Demand Learning and Fair Resource-Consumption Balancing
- SPRT-based Efficient Best Arm Identification in Stochastic Bandits
- CQE in OWL 2 QL: A "Longest Honeymoon" Approach (extended version)
- Learn Continuously, Act Discretely: Hybrid Action-Space Reinforcement Learning For Optimal Execution
- InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images
- Deep neural networks on diffeomorphism groups for optimal shape reparameterization
- Motion Planning and Control for Multi Vehicle Autonomous Racing at High Speeds
- Optimism in Face of a Context: Regret Guarantees for Stochastic Contextual MDP
- Adaptive Graph-Based Feature Normalization for Facial Expression Recognition
- On Controller Tuning with Time-Varying Bayesian Optimization
- Rethinking the Reference-based Distinctive Image Captioning
- Near Real-Time Distributed State Estimation via AI/ML-Empowered 5G Networks
- Fast strategies for multi-temporal speckle reduction of Sentinel-1 GRD images
- DeVIS: Making Deformable Transformers Work for Video Instance Segmentation
- Physiology-based simulation of the retinal vasculature enables annotation-free segmentation of OCT angiographs
- Zero-Shot Video Captioning with Evolving Pseudo-Tokens
- Multi-temporal speckle reduction with self-supervised deep neural networks
- Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videos
- Do Artificial Intelligence Systems Understand?
- Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers
- Multi-Level Fine-Tuning, Data Augmentation, and Few-Shot Learning for Specialized Cyber Threat Intelligence
- RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos
- Latent Space Unsupervised Semantic Segmentation
- 3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal
- Graph Spatio-Spectral Total Variation Model for Hyperspectral Image Denoising
- Context-aware controller inference for stabilizing dynamical systems from scarce data
- Quantized Sparse Weight Decomposition for Neural Network Compression
- Spatial-Temporal Feature Extraction and Evaluation Network for Citywide Traffic Condition Prediction
- GesSure- A Robust Face-Authentication enabled Dynamic Gesture Recognition GUI Application
- MobileDenseNet: A new approach to object detection on mobile devices
- A Transferable Intersection Reconstruction Network for Traffic Speed Prediction
- Custom Structure Preservation in Face Aging
- Open video data sharing in developmental and behavioural science
- Layer-Wise Partitioning and Merging for Efficient and Scalable Deep Learning
- Fact sheet: Automatic Self-Reported Personality Recognition Track
- Gradual Drift Detection in Process Models Using Conformance Metrics
- AdaptCL: Adaptive Continual Learning for Tackling Heterogeneity in Sequential Datasets
- POP: Mining POtential Performance of new fashion products via webly cross-modal query expansion
- Rapid Lung Ultrasound COVID-19 Severity Scoring with Resource-Efficient Deep Feature Extraction
- Meta-Registration: Learning Test-Time Optimization for Single-Pair Image Registration
All 151
- Learning Generalized Non-Rigid Multimodal Biomedical Image Registration from Generic Point Set Data
- Taguchi based Design of Sequential Convolution Neural Network for Classification of Defective Fasteners
- Algorithmic Fairness in Business Analytics: Directions for Research and Practice
- Few-shot Object Counting and Detection
- NeurAR: Neural Uncertainty for Autonomous 3D Reconstruction with Implicit Neural Representations
- Efficient All-reduce for Distributed DNN Training in Optical Interconnect System
- Kinematics Modeling Network for Video-based Human Pose Estimation
- Opportunistic hip fracture risk prediction in Men from X-ray: Findings from the Osteoporosis in Men (MrOS) Study
- Principal Geodesic Analysis of Merge Trees (and Persistence Diagrams)
- QueryProp: Object Query Propagation for High-Performance Video Object Detection
- Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection
- Visible and Near Infrared Image Fusion Based on Texture Information
- Vision-based Human Fall Detection Systems using Deep Learning: A Review
- Scale dependant layer for self-supervised nuclei encoding
- Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection
- Multilabel Prototype Generation for Data Reduction in k-Nearest Neighbour classification
- Aries: Efficient Testing of Deep Neural Networks via Labeling-Free Accuracy Estimation
- Respecting Time Series Properties Makes Deep Time Series Forecasting Perfect
- Dense RGB-D-Inertial SLAM with Map Deformations
- Statistical Hypothesis Testing Based on Machine Learning: Large Deviations Analysis
- Long-tailed Instance Segmentation using Gumbel Optimized Loss
- What's in the laundromat? Mapping and characterising offshore owned domestic property in London
- PLD-SLAM: A Real-Time Visual SLAM Using Points and Line Segments in Dynamic Scenes
- Optimization of Forcemyography Sensor Placement for Arm Movement Recognition
- DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection
- Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness
- Impact of RoCE Congestion Control Policies on Distributed Training of DNNs
- Efficient Modeling of Future Context for Image Captioning
- Privacy and Transparency in Graph Machine Learning: A Unified Perspective
- 3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization
- Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation
- FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification
- XAI based Performance Preserving Adaptive Image Compression for Efficient Satellite Communication
- My View is the Best View: Procedure Learning from Egocentric Videos
- An Ensemble Approach for Multiple Emotion Descriptors Estimation Using Multi-task Learning
- Assessing mortality prediction through different representation models based on concepts extracted from clinical notes
- Optimizing Image Compression via Joint Learning with Denoising
- Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation
- Contrastive Self-Supervised Learning Leads to Higher Adversarial Susceptibility
- Transformer with Implicit Edges for Particle-based Physics Simulation
- Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter
- Two-Stage Fine-Tuning: A Novel Strategy for Learning Class-Imbalanced Data
- Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation
- Spatio-Temporal Deformable Attention Network for Video Deblurring
- Uncertainty-aware Multi-modal Learning via Cross-modal Random Network Prediction
- ASR Error Detection via Audio-Transcript entailment
- Robust Knowledge Adaptation for Dynamic Graph Neural Networks
- Characterizing Coherent Integrated Photonic Neural Networks under Imperfections
- Few-shot Image Generation Using Discrete Content Representation
- Automated Dilated Spatio-Temporal Synchronous Graph Modeling for Traffic Prediction
- Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation