- Attention! A Lightweight 2D Hand Pose Estimation Approach: Paper, Code (Submitted to IEEE Signal Processing Letters)
- Integration of adversarial autoencoders with residual dense convolutional networks for estimation of non-Gaussian hydraulic conductivities: Paper (Submitted to Wiley Water Resources Research)
- Connecting Optical Morphology, Environment, and H I Mass Fraction for Low-Redshift Galaxies Using Deep Learning: Paper, Code
- Learning Neural Activations: Paper, Code
- Learning to Reconstruct Crack Profiles for Eddy Current Nondestructive Testing: Paper, Code (Accepted to 33rd NeurIPS ML4PS (Machine Learning and the Physical Sciences) Workshop)
- Classification of Hyperspectral Image Based on Double-Branch Dual-Attention Mechanism Network: Paper, Code
- A Survey of the Recent Architectures of Deep Convolutional Neural Networks: Paper
- fastai—A Layered API for Deep Learning: Paper, Code, Blog
- Soft-Root-Sign Activation Function: Paper
- RMNv2: Reduced Mobilenet V2 for CIFAR10: Paper, Thesis, Purdue University
- An Unsupervised Deep Learning System for Acoustic Scene Analysis : Paper
- U-Det: A Modified U-Net architecture with bidirectional feature network for lung nodule segmentation : Paper
- Dynamic ReLU : Paper (Microsoft Research (MSR))
- TanhExp: A Smooth Activation Function with High Convergence Speed for Lightweight Neural Networks : Paper (Submitted to IET Computer Vision)
- MV-RAN: Multiview recurrent aggregation network for echocardiographic sequences segmentation and full cardiac cycle analysis : Paper (Submitted to Computers in Biology and Medicine)
- TResNet: High Performance GPU-Dedicated Architecture: Paper
- MXR-U-Nets for Real Time Hyperspectral Reconstruction: Paper, Code
- Neural Architectures Design and Search for Deep Learning and Continual Learning: Thesis
- Analyzing Lung Disease Using Highly Effective Deep Learning Techniques: Paper
- YOLOv4: Optimal Speed and Accuracy of Object Detection: Paper, Code
- sEMG Gesture Recognition With a Simple Model of Attention: Paper, Code
- Deep-Learning-Based Active Hyperspectral Imaging Classification Method Illuminated by the Supercontinuum Laser: Paper
- Optimized Light-Weight Convolutional Neural Networks for Histopathologic Cancer Detection: Paper
- NTIRE 2020 Challenge on Spectral Reconstruction from an RGB Image: Paper (Review of the New Trends in Image Restoration and Enhancement workshop and challenges on image and video restoration and enhancement in conjuction with CVPR 2020)
- Style transfer with variational autoencoders is a promising approach to RNA-Seq data harmonization and analysis: Paper
- Neural Networks Versus Conventional Filters for Inertial-Sensor-based Attitude Estimation: Paper
- Carbon Dioxide Level Prediction for Indoor Air Using Neural networks: Master's Thesis, University of Oulu
- Domain Specific, Semi-Supervised Transfer Learning for Medical Imaging: Paper
- Integration of adversarial autoencoders with residual dense convolutional networks for inversion of solute transport in non-Gaussian conductivity fields: Paper
- Discovering Parametric Activation Functions: Paper
- A Review of Activation Function for Artificial Neural Network: Paper(Published at IEEE 18th World Symposium on Applied Machine Intelligence and Informatics (SAMI 2020))
- Attention Mechanism Exploits Temporal Contexts: Real-Time 3D Human Pose Reconstruction: Paper, Code, Project Page (Published at The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020)
- A Note on Deepfake Detection with Low-Resources: Paper
- An Embedded Deep Learning Object Detection Model For Traffic In Asian Countries: Paper
- MSMD-Net: Deep Stereo Matching with Multi-scale and Multi-dimension Cost Volume: Paper, Code
- PATS: A New Neural Network Activation Function with Parameter: Paper, Code
- Deep Learning Based Analysis of Prostate Cancer from MP-MRI: Thesis, Aalto University
- Multi-View Pose Generator Based on Deep Learning for Monocular 3D Human Pose Estimation: Paper
- Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networks: Paper
- Sound Event Detection in Domestic Environments using Dense Recurrent Neural Network : Paper
- Federated Self-Supervised Learning of Multi-Sensor Representations for Embedded Intelligence: Paper (Accepted to IEEE Internet of Things Journal)
- Regularized Flexible Activation Function Combinations for Deep Neural Networks: Paper
- Designing a lightweight 1D convolutional neural network with Bayesian optimization for wheel flat detection using carbody accelerations: Paper (Accepted to International Journal of Rail Transportation)
- Hand Pose Estimation from RGBD Images: Paper