Kaiqi Huang

Also known as 黄凯奇, Kai-Qi Huang

Kaiqi Huang is a computer vision researcher at the Institute of Automation, Chinese Academy of Sciences (CASIA), whose work spans visual surveillance, object tracking and game-playing AI. After a PhD at Southeast University, he joined CASIA's National Laboratory of Pattern Recognition in 2004 and became a full professor there in 2011. He won first prize in the PASCAL VOC object detection task in 2010 and 2011, and in 2018 he coauthored GOT-10k, a tracking benchmark of more than 10,000 video segments. The International Association for Pattern Recognition named him a fellow in 2022 for contributions to video analysis and human vision-inspired visual models. Today he directs CASIA's Center for Research on Intelligent System and Engineering, and in 2025 he coauthored WGSR-Bench, a wargame benchmark for strategic reasoning in large language models.

Now at: Institute of Automation, Chinese Academy of Sciences and University of Chinese Academy of Sciences
Works: 352
Citations: 16,227
h-index: 53
Badges: Loyal

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

By 2004

A PhD at Southeast University

He earns bachelor's and master's degrees at Nanjing University of Science and Technology and a PhD at Southeast University. His 2004 ICASSP paper presents a color image enhancement and evaluation algorithm based on the human visual system.
2004–2011

Postdoc to professor at NLPR

He joins the National Laboratory of Pattern Recognition (NLPR) at the Institute of Automation, Chinese Academy of Sciences (CASIA), as a postdoc in March 2004. He becomes an associate professor there in December 2005 and a full professor in 2011. From 2006 to 2008, he also serves as deputy general secretary of the IEEE Beijing Section.
2011

Biologically inspired surveillance features

His research covers visual surveillance, image understanding and biologically based vision. In 2011, he publishes "Biologically Inspired Features for Scene Classification in Video Surveillance" in IEEE Transactions on Systems, Man and Cybernetics, Part B.
2010–2014

PASCAL VOC and ImageNet prizes

He wins first prize in the PASCAL VOC object detection task in 2010 and 2011. In 2014, he takes a first prize at the ImageNet challenge in its additional-data track.
2013–2017

A CCF-IEEE CS Young Scientist Award

In 2013, he receives an Excellent Young Scholars award from the National Science Foundation of China. The China Computer Federation gives him the CCF-IEEE CS Young Scientist Award in 2016 for contributions to computer vision and its applications. In 2017, he receives the Chinese Academy of Sciences' Ten Outstanding Young Scientist Award.
2018

The GOT-10k tracking benchmark

In October 2018, with Lianghua Huang and Xin Zhao, he introduces GOT-10k, a tracking benchmark with more than 10,000 video segments and 1.5 million hand-labeled bounding boxes whose test classes do not overlap with its training classes. The team also releases evaluation toolkits, an online evaluation server and a leaderboard, and the paper is accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence.
2021–2022

Game AI and an IAPR fellowship

In 2021, he coauthors "AI in Human-computer Gaming: Techniques, Challenges and Opportunities", a survey of board, card, first-person shooting and real-time strategy game AIs such as Libratus, OpenAI Five and AlphaStar. The International Association for Pattern Recognition names him a fellow in 2022 for contributions to video analysis and human vision-inspired visual models.
As of October 2026

Directing CRISE at CASIA

He is a professor with NLPR at CASIA and director of the institute's Center for Research on Intelligent System and Engineering. In June 2025, he coauthors WGSR-Bench, which tests strategic reasoning in large language models using wargames.