Papers
Sat 3 Sep 2022
69 papers
- MMKGR: Multi-hop Multi-modal Knowledge Graph ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
- Training Strategies for Improved Lip-readingKnowledge distillation → Speech and audio distillation
- Kinova Gemini: Interactive Robot Grasping with Visual Reasoning and Conversational AILLM reasoning → Spatial and embodied reasoning
- A Novel Self-Knowledge Distillation Approach with Siamese Representation Learning for Action RecognitionKnowledge distillation → General knowledge distillation methods
- Deep autoencoders for physics-constrained data-driven nonlinear materials modeling
- Simplified Quadratic Gradient: A Unified Framework Bridging Gradient Descent and Newton-Type Methods by Synthesizing Hessians and Gradients
- Transfer Learning of an Ensemble of DNNs for SSVEP BCI Spellers without User-Specific Training
- Low-Power Hardware-Based Deep-Learning Diagnostics Support Case Study
- Neural Networks for Chess
- Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions
- StreamNet: A WAE for White Matter Streamline Analysis
- Learning Differential Operators for Interpretable Time Series Modeling
- Model-Free Deep Reinforcement Learning in Software-Defined Networks
- A Hybrid Tracking Control Strategy for an Unmanned Underwater Vehicle Aided with Bioinspired Neural Dynamics
- A Novel Knowledge-Based Genetic Algorithm for Robot Path Planning in Complex Environments
- Equivariant Self-Supervision for Musical Tempo Estimation
- Learning the Dynamics of Particle-based Systems with Lagrangian Graph Neural Networks
- Neural Sign Reenactor: Deep Photorealistic Sign Language Retargeting
- Machine learning for dynamically predicting the onset of renal replacement therapy in chronic kidney disease patients using claims data
- Phishing URL Detection: A Network-based Approach Robust to Evasion
- A comprehensive survey on recent deep learning-based methods applied to surgical data
- Reinforcement Learning with Prior Policy Guidance for Motion Planning of Dual-Arm Free-Floating Space Robot
- From Monte Carlo to neural networks approximations of boundary value problems
- STAD: Self-Training with Ambiguous Data for Low-Resource Relation Extraction
- Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition
- Deep Live Video Ad Placement on the 5G Edge
- Suppressing Noise from Built Environment Datasets to Reduce Communication Rounds for Convergence of Federated Learning
- Negative Selection Approach to support Formal Verification and Validation of BlackBox Models' Input Constraints
- Closed-Loop View of the Regulation of AI: Equal Impact across Repeated Interactions
- Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies
- Explainability via Short Formulas: the Case of Propositional Logic with Implementation
- Deep learning automates bidimensional and volumetric tumor burden measurement from MRI in pre- and post-operative glioblastoma patients
- Vision Transformers and YoloV5 based Driver Drowsiness Detection Framework
- Optimizing Partial Area Under the Top-k Curve: Theory and Practice
- Disconnected Emerging Knowledge Graph Oriented Inductive Link Prediction
- Hypergraph convolutional neural network-based clustering technique
- How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models
- SaleNet: A low-power end-to-end CNN accelerator for sustained attention level evaluation using EEG
- Classification of Breast Tumours Based on Histopathology Images Using Deep Features and Ensemble of Gradient Boosting Methods
- RNN(p) for Power Consumption Forecasting
- A Variational Approach for Joint Image Recovery and Feature Extraction Based on Spatially-Varying Generalised Gaussian Models
- Identify The Beehive Sound Using Deep Learning
- TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning
- CrossDial: An Entertaining Dialogue Dataset of Chinese Crosstalk
- Sharp bounds on the price of bandit feedback for several models of mistake-bounded online learning
- DualCam: A Novel Benchmark Dataset for Fine-grained Real-time Traffic Light Detection
- Masked Sinogram Model with Transformer for ill-Posed Computed Tomography Reconstruction: a Preliminary Study
- Semantic Segmentation in Learned Compressed Domain
- Improving Compositional Generalization in Math Word Problem Solving
- Semi-supervised Training for Knowledge Base Graph Self-attention Networks on Link Prediction
- HammingMesh: A Network Topology for Large-Scale Deep Learning
- Generative Modeling via Tree Tensor Network States
- Federated XGBoost on Sample-Wise Non-IID Data
- DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation
- FedAR+: A Federated Learning Approach to Appliance Recognition with Mislabeled Data in Residential Buildings
- Neural Approaches to Multilingual Information Retrieval
- Noise-Robust Bidirectional Learning with Dynamic Sample Reweighting
- Class-Specific Channel Attention for Few-Shot Learning
- Semi-Supervised Semantic Segmentation with Cross Teacher Training
- Continual Learning for Steganalysis
- Classifying Spatial Trajectories
- Deep Stable Representation Learning on Electronic Health Records
- Synthesizing Photorealistic Virtual Humans Through Cross-modal Disentanglement
- Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing Labels
- Multimodal and Crossmodal AI for Smart Data Analysis
- TransPolymer: a Transformer-based language model for polymer property predictions
- vieCap4H-VLSP 2021: Vietnamese Image Captioning for Healthcare Domain using Swin Transformer and Attention-based LSTM
- Geometry of EM and related iterative algorithms
- Source-Free Unsupervised Domain Adaptation with Norm and Shape Constraints for Medical Image Segmentation