We are the Trustworthy Visual Intelligence Group. We focus on pushing the boundaries of Computer Vision, Embodied Intelligence, and Reliable AI.
The Trustworthy Visual Intelligence (TVI) group is a core part of the Image Cognition Group at Chongqing University of Posts and Telecommunications. Founded in 2020, we are a dynamic research team led by Associate Professor Jiaxu Leng .
Our Focus:
Trustworthy AI
Video Anomaly Detection
Video Analysis
Embodied Intelligence
Our members have led projects including the National Natural Science Foundation of China and the Chongqing Bo Xin Plan. We actively publish in top-tier venues:
The team's latest news, events, and announcements will be continuously updated.
In the wave of deep integration between neuroscience and artificial intelligence, the 3rd Chongqing Brain and Intelligence Academic Symposium was successfully held at the Chongqing Center for Brain and Intelligence Sciences from January 10 to 11, 2026.
Read more →
On December 12, 2025, the award ceremony for the 3rd Wuxi International Artificial Intelligence Innovation Application Competition was grandly held at the InterContinental Wuxi, and the team won first place.
Read more →
The works were jointly supervised by Professor Xinbo Gao and Associate Professor Jiaxu Leng. The two papers focus on cross-modal person re-identification and face super-resolution in AI-computer vision, respectively.
Read more →The team's latest news, events, and announcements will be continuously updated.
Garden adopts a collaborative architecture of 'small perception model + large multimodal model'. It enables precise garbage recognition, road cleanliness evaluation, and intelligent scheduling across multiple scenarios in complex terrains.