In this paper, we present a multiple knowledge representation (MKR) framework and discuss
its potential for developing big data artificial intelligence (AI) techniques with possible …

In this article, we revisit two popular convolutional neural networks in person re-identification
(re-ID): verification and identification models. The two models have their respective …

Matching images and sentences demands a fine understanding of both modalities. In this
article, we propose a new system to discriminatively embed the image and text to a shared …

Person re-identification (re-ID) is mostly viewed as an image retrieval problem. This task
aims to search a query person in a large image pool. In practice, person re-ID usually adopts …

Recent advances in facial landmark detection achieve success by learning discriminative
features from rich deformation of face shapes and poses. Besides the variance of faces …

Person re-identification (re-ID) is a cross-camera retrieval task that suffers from image style
variations caused by different cameras. The art implicitly addresses this problem by learning …

This paper considers the problem of multi-label thorax disease classification on chest X-ray
images. Identifying one or more pathologies from a chest X-ray image is often hindered by …

Time-efficient anomaly detection and localization in video surveillance still remains
challenging due to the complexity of “anomaly”. In this paper, we propose a cuboid-patch …

Due to domain bias, directly deploying a deep person re-identification (re-ID) model trained
on one dataset often achieves considerably poor accuracy on another dataset. In this article …

Recent skeleton-based action recognition approaches achieve great improvement by using
recurrent neural network (RNN) models. Currently, these approaches build an end-to-end …