Latest Research
Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Control
• combra-lab/pop-spiking-deep-rl
• 
Here, we propose a population-coded spiking actor network (PopSAN) trained in conjunction with a deep critic network using deep reinforcement learning (DRL).
PySBD: Pragmatic Sentence Boundary Disambiguation
In this paper, we present a rule-based sentence boundary disambiguation Python package that works out-of-the-box for 22 languages.
Probabilistic Linear Solvers for Machine Learning
Linear systems are the bedrock of virtually all numerical computation.
The RELX Dataset and Matching the Multilingual Blanks for Cross-Lingual Relation Classification
Relation classification is one of the key topics in information extraction, which can be used to construct knowledge bases or to provide useful information for question answering.
A combined full-reference image quality assessment method based on convolutional activation maps
In this study, we explore a novel, combined approach which predicts the perceptual quality of a distorted image by compiling a feature vector from convolutional activation maps.
MaskNet: A Fully-Convolutional Network to Estimate Inlier Points
• vinits5/masknet
•
We demonstrate these improvements on synthetic and real-world datasets.
Detecting Hands and Recognizing Physical Contact in the Wild
• cvlab-stonybrook/ContactHands
•
The first attention mechanism is based on the hand and a region's affinity, enclosing the hand and the object, and densely pools features from this region to the hand region.
Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation
• wbw520/NoisyLSTM
•
Semantic video segmentation is a key challenge for various applications.
SEMANTIC SEGMENTATION VIDEO SEGMENTATION VIDEO SEMANTIC SEGMENTATION
Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders
• sisl/EvidentialSparsification
•
Discrete latent spaces in variational autoencoders have been shown to effectively capture the data distribution for many real-world problems such as natural language understanding, human intent prediction, and visual scene representation.
IMAGE GENERATION MOTION PLANNING NATURAL LANGUAGE UNDERSTANDING
GASNet: Weakly-supervised Framework for COVID-19 Lesion Segmentation
• xzwthu/GASNet
•
Segmentation of infected areas in chest CT volumes is of great significance for further diagnosis and treatment of COVID-19 patients.
ADVERSARIAL TRAINING LESION SEGMENTATION SEMANTIC SEGMENTATION