This paper presents a novel approach for automatically generating image descriptions:
visual detectors, language models, and multimodal similarity models learnt directly from a …

… Hao-Shu Fang1∗, Shuqin Xie1, Yu-Wing Tai2, Cewu Lu1§ 1Shanghai Jiao Tong University,
China 2 Tencent … ∗part of this work was done when Hao-Shu Fang was an student intern …

This article reviews the mechanisms of shale gas storage and discusses the major risks or
uncertainties for shale gas exploration in China. At a given temperature and pressure, the gas …

Effective management of diabetes relies on the frequent monitoring of blood glucose
concentrations. The current approach of blood sampling and glucose concentration determination …

In this paper we describe the Microsoft COCO Caption dataset and evaluation server. When
completed, the dataset will contain over one and a half million captions describing over …

Accurate whole-body multi-person pose estimation and tracking is an important yet challenging
topic in computer vision. To capture the subtle actions of humans for complex behavior …

Object grasping is critical for many applications, which is also a challenging computer vision
problem. However, for cluttered scene, current researches suffer from the problems of …

Multi-person pose estimation is fundamental to many computer vision tasks and has made
significant progress in recent years. However, few previous methods explored the problem of …

Distributed controllers have been proposed for Software Defined Networking to address the
issues of scalability and reliability that a centralized controller suffers from. One key limitation …

Large, high-capacity models trained on diverse datasets have shown remarkable successes
on efficiently tackling downstream applications. In domains from NLP to Computer Vision, …