Fanqing Meng

Fanqing Meng

Auto-generated profile, based on publicly available information

Fanqing Meng

OpenGVLab, Shanghai AI Laboratory, Shanghai, China

Research Focus & Metrics

Academic Career Length

23Years (2004-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 October 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Open access
BQBo Qin
Bo Qin
FMFanqing Meng
Fanqing Meng
Shijin YuanShijin Yuan
Shijin Yuan
BMBin Mu
Bin Mu
XFXianghui Fang
Xianghui Fang
GDGuokun Dai
Guokun Dai
Existing convolution recurrent neural networks (ConvRNNs)-based memory cells majorly take advantage of gated structures and attention mechanisms to extract discontinuous latent associations for spatial-temporal sequence forecast (STSF) problems, which may lead to serious over-fitting and spurious relationships with correlated noise. It is a consensus that incorporating cause-effect relationships in modeling can alleviate these problems. In this paper, we propose a Causality Attention Unit (CAU) to assist ConvRNNs by complementing the causal inference ability in a plug-and-play way. Specifically, CAU serially consists of the attention module and causality module. The former is constructed by a spatial-channel attention layer, which preliminarily generates the correlated future with the correlations between historical memories and the current state. The latter borrows the idea of transfer entropy ( TE ) to detect the latent cause-effect relationships and precisely correct the correlated future. A space-time exchange strategy for accelerating the calculation of TE in CAU is also designed. CAU can be easily combined with the existing ConvRNN cells, and we construct a simple general model to predict long-term spatial-temporal series, which consists of encoder/decoder and stacked CAU paralleled to stacked ConvRNN cells. After determining the optimal model structure, we carry out a series of experiments to evaluate model performance, including comparisons with other advanced models, training loss analysis, and multiple ablation and sensitivity studies. Experimental results show that our proposed model can effectively improve the performances of existing ConvRNNs to the state-of-the-are level on representative public datasets, including Moving MNIST, KTH, BAIR, and WeatherBench. The ablation and sensitivity studies verify the superiority of CAU. The learned causal maps precisely distinguish the pixel attributions and motion characteristics in sophisticated entangled scenarios.

1 December 2013
Verified
Conference Paper
Closed access
MFMeng Fanqing
Meng Fanqing
FYFu-cheng You
Fu-cheng You
In order to improve the speed of tracking based on keypoint, we proposed an ORB-based tracking algorithm. We used the Gaussian mixture model to estimate the background. The difference of frame and background was treated as the foreground. All the ORB keypoints composed the feature set of object, which were extracted from foreground. In the foreground of each frame, we extracted ORB feature to match with the feature set of object and selected the good keypoints. We employed the Hamming distance to evaluate the quality of match. Then, these keypoints were used to find the position and update the feature set. The experiment results show that our tracking algorithm has a higher speed compared with SIFT-based algorithm and SURF-based algorithm, and accurately find the position of object.

30 January 2025 in IEEE Transactions on Big Data
Verified
Journal Article
Closed access
WSWenqi Shao
Wenqi Shao
MLMeng Lei
Meng Lei
YHYutao Hu
Yutao Hu
PGPeng Gao
Peng Gao
PXPeng Xu
Peng Xu
PLPing Luo
Ping Luo
Large Vision-Language Models (LVLMs) have made significant strides in various multimodal tasks. Notably, GPT4V, Claude, Gemini, and others showcase exceptional multimodal capabilities, marked by profound comprehension and reasoning skills. This study introduces a comprehensive and efficient evaluation framework, TinyLVLM-eHub, to assess LVLMs’ performance, including proprietary models. TinyLVLM-eHub covers six key multimodal capabilities, such as visual perception, knowledge acquisition, reasoning, commonsense understanding, object hallucination, and embodied intelligence. The benchmark, utilizing 2.1K image-text pairs, provides a user-friendly and accessible platform for LVLM evaluation. The evaluation employs the ChatGPT Ensemble Evaluation (CEE) method, which improves alignment with human evaluation compared to word-matching approaches. Results reveal that closed-source API models like GPT4V and GeminiPro-V excel in most capabilities compared to previous open-source LVLMs, though they show some vulnerability in object hallucination. This evaluation underscores areas for LVLM improvement in real-world applications and serves as a foundational assessment for future multimodal advancements.

15 September 2004
Verified
Book Chapter
Closed access
FMFanqing Meng
Fanqing Meng
WLWenhai Lu
Wenhai Lu
CXChangkai Xu
Changkai Xu
YWYaocai Wang
Yaocai Wang
JWJunwei Wang
Junwei Wang