Jingwen Zhao — accepted AI-conference papers

2025

Hallucination Reduction in Video-Language Models via Hierarchical Multimodal Consistency

Jisheng Dang, Shengjun Deng, Haochen Chang, Teng Wang, Bimei Wang, Shude Wang +4

IJCAI 2025

The rapid advancement of large language models (LLMs) has led to the widespread adoption of video-language models (VLMs) across various domains. However, VLMs are often hindered by their limited semantic discrimination capability, exacerbated by the limited diversity and biased sample distribution o

Cited by 0 Source ↗PDF ↗Scholar ↗

2017

3D tracking swimming fish school with learned kinematic model using LSTM network

Shuohong Wang, Jingwen Zhao, Xiang Liu, Zhiming Qian, Ye Liu, Yan Qiu Chen

ICASSP 2017accepted

This paper proposes a reliable 3D fish tracking method using a novel master-slave camera setup. Instead of conventional dynamic models that rely on prior knowledge about target kinematics, the proposed method learns the kinematic model with a Long Short-Term Memory (LSTM) network. On this basis, the…

Cited by 0 Source ↗Scholar ↗