Papers
Sun 3 Jan 2021
51 papers
- Exploring Transfer Learning on Face Recognition of Dark Skinned, Low Quality and Low Resource Face Data
- Parkinson's Disease Diagnosis Using Deep Learning
- A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning
- Meta-Learning Conjugate Priors for Few-Shot Bayesian Optimization
- Synthetic Embedding-based Data Generation Methods for Student Performance
- Bankruptcy prediction using disclosure text features
- Algorithmic Complexities in Backpropagation and Tropical Neural Networks
- Automatic Defect Detection of Print Fabric Using Convolutional Neural Network
- A Novel Multi-Stage Training Approach for Human Activity Recognition from Multimodal Wearable Sensor Data Using Deep Neural Network
- Adversarial Unsupervised Domain Adaptation for Harmonic-Percussive Source Separation
- The structure of conservative gradient fields
- Cycle Registration in Persistent Homology with Applications in Topological Bootstrap
- Neural Networks for Keyword Spotting on IoT Devices
- Learning General Policies from Small Examples Without Supervision
- CovTANet: A Hybrid Tri-level Attention Based Network for Lesion Segmentation, Diagnosis, and Severity Prediction of COVID-19 Chest CT Scans
- Segmentation and genome annotation algorithms
- Enhanced Pub/Sub Communications for Massive IoT Traffic with SARSA Reinforcement Learning
- An Evolution of CNN Object Classifiers on Low-Resolution Images
- Fake Visual Content Detection Using Two-Stream Convolutional Neural Networks
- Sentiment Analysis for Open Domain Conversational Agent
- Recoding latent sentence representations -- Dynamic gradient-based activation modification in RNNs
- Learning optimal Bayesian prior probabilities from data
- Weakly Supervised Multi-Object Tracking and Segmentation
- Combining Graph Neural Networks and Spatio-temporal Disease Models to Predict COVID-19 Cases in Germany
- Depth as Attention for Face Representation Learning
- A Tutorial on the Mathematical Model of Single Cell Variational Inference
- AttnMove: History Enhanced Trajectory Recovery via Attentional Network
- News Image Steganography: A Novel Architecture Facilitates the Fake News Identification
- Privacy-sensitive Objects Pixelation for Live Video Streaming
- A Switched View of Retinex: Deep Self-Regularized Low-Light Image Enhancement
- Phase Transitions in Recovery of Structured Signals from Corrupted Measurements
- Copula Flows for Synthetic Data Generation
- Progressive Correspondence Pruning by Consensus Learning
- RegNet: Self-Regulated Network for Image Classification
- diff-SAT -- A Software for Sampling and Probabilistic Reasoning for SAT and Answer Set Programming
- Style Normalization and Restitution for Domain Generalization and Adaptation
- Multi-label Ranking: Mining Multi-label and Label Ranking Data
- Neural network algorithm and its application in temperature control of distillation tower
- Dynamics, behaviours, and anomaly persistence in cryptocurrencies and equities surrounding COVID-19
- Improved Convergence Guarantees for Learning Gaussian Mixture Models by EM and Gradient EM
- StarNet: Gradient-free Training of Deep Generative Models using Determined System of Linear Equations
- ASIST: Annotation-free Synthetic Instance Segmentation and Tracking by Adversarial Simulations
- Learning Neural Networks on SVD Boosted Latent Spaces for Semantic Classification
- Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier
- Six-channel Image Representation for Cross-domain Object Detection
- Silicon Photonic Microring Based Chip-Scale Accelerator for Delayed Feedback Reservoir Computing
- Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning
- A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization
- An Efficient Transformer Decoder with Compressed Sub-layers
- Attentive Tree-structured Network for Monotonicity Reasoning
- RV-GAN: Segmenting Retinal Vascular Structure in Fundus Photographs using a Novel Multi-scale Generative Adversarial Network