In this work, we propose a novel feature enhancement network to simultaneously model short- and long-term temporal correlation.
Off-policy evaluation is critical in a number of applications where new policies need to be evaluated offline before online deployment.
However, the number of stored latent codes in autoencoder increases linearly with the scale of data and the trained encoder is redundant for the replaying stage.
Localizing the root cause of network faults is crucial to network operation and maintenance.
As business of Alibaba expands across the world among various industries, higher standards are imposed on the service quality and reliability of big data cloud computing platforms which constitute the infrastructure of Alibaba Cloud.
In this paper, we present an anchor-free ellipse detection network, namely EllipseNet, which detects the cardiac and thoracic regions in ellipse and automatically calculates the CTR and cardiac axis for fetal cardiac biometrics in 4-chamber view.
Surprisingly, by varying the granularity of division on feature maps, we are able to modulate the reconstruction capability of the model for both normal and abnormal samples.
Periodicity detection is a crucial step in time series tasks, including monitoring and forecasting of metrics in many areas, such as IoT applications and self-driving database management system.
The key lies in generalization of prior knowledge learned from large-scale base classes and fast adaptation of the classifier to novel classes.
In particular, we propose a novel multi-stage training strategy which learns incremental triplet margin and improves triplet loss effectively.
Deep region-based object detector consists of a region proposal step and a deep object recognition step.
To this end, we have proposed a simple but effective Multi-column Convolutional Neural Network (MCNN) architecture to map the image to its crowd density map.
Ranked #5 on Crowd Counting on Venice