Chuanbo Zhu

PhD Candidate of Computer Science and Technology

Wuhan National Laboratory for Optoelectronics (WNLO)

Huazhong University of Science and Technology (HUST)

Life is like a train, a train bound for the tomb, there will be a lot of stations on the road, it was difficult to keep accompany to walk. When you get out, even if is not, the grateful, then waved goodbye. When goodbye, never say goodbye.

Love life, love to study, dare to try, dare to challenge, never give up!

Interests

Multimodal Intelligence
Sentiment Analysis
Emotion Recognition
Sarcasm Detection

Education

Phd candidate in China, 2019

Huazhong University of Science and Technology
B.A. in China, 2015-2019

Huazhong Agricultural University

Featured Publications

Chuanbo Zhu, Min Chen, Sheng Zhang, Chao Sun, Han Liang, Yifan Liu, Jincai Chen

August 2023 In Information Fusion (INFFUS)

SKEAFN: Sentiment Knowledge Enhanced Attention Fusion Network for multimodal sentiment analysis

Propose a sentiment knowledge-enhanced attention fusion network (SKEAFN); Build an additional knowledge graph to leverage explicit sentiment information; Use a multi-head attention mechanism to model the interactions among modalities; Develop feature-wised attention to adjust the contributions of multiple modalities.

Yifan Liu, Jincai Chen, Ping Lu, Chuanbo Zhu, Yugen Jian, Chao Sun, Han Liang

June 2023 In Computers & Graphics (CAJ)

Snowed autoencoders are efficient snow removers

An efficient desnowing method named Snowed Autoencoder (SAE) is proposed; A multi-encoder for SAE using snow information with an attention module is proposed; A multi-decoder for SAE with fewer sub-decoders than sub-encoders is proposed; SAE outperformed state-of-the-art on four desnowing datasets.

Yifan Liu, Jincai Chen, Ping Lu, Chuanbo Zhu, Yugen Jian, Chao Sun, Han Liang

April 2023 In The Journal of Supercomputing (TJSC)

MOONLIT: momentum-contrast and large-kernel for multi-fine-grained deraining

Deep learning-based methods have achieved excellent performance in image-deraining tasks. Unfortunately, most existing deraining methods incorrectly assume a uniform rain streak distribution and a fixed fine-grained level. And this uncertainty of rain streaks will result in the model not being competent at repairing all fine-grained rain streaks. In addition, some existing convolution-based methods extend the receptive field mainly by stacking convolution kernels, which frequently results in inaccurate feature extraction. In this work, we propose momentum-contrast and large-kernel for multi-fine-grained deraining network (MOONLIT). To address the problem that the model is not competent at all fine-grained levels, we use the unsupervised dictionary contrastive learning method to treat different fine-grained rainy images as different degradation tasks. Then, to address the problem of inaccurate feature extraction, we carefully constructed a restoration network based on large-kernel convolution with a larger and more accurate receptive field. In addition, we designed a data enhancement method to weaken features other than rain streaks in order to be better classified for different degradation tasks. Extensive experiments on synthetic and real-world deraining datasets show that the proposed method MOONLIT achieves the state-of-the-art performance on some datasets. Code is available at https://github.com/awhitewhale/moonlit.

Yifan Liu, Jincai Chen, Ping Lu, Chuanbo Zhu, Yugen Jian, Chao Sun, Han Liang

March 2023 In Displays

MFID-Net: Multi-scaled feature-fused image dehazing via dynamic weights

Multi-scaled feature-fused image dehazing network called MFID-Net is proposed; MFID-Net uses dynamic dehazing convolution and activation to improve image dehazing; The proposed dynamic dehazing convolution utilizes dynamic weight fusion; The proposed dynamic dehazing activation uses input global context encoding function; MFID-Net achieves the state-of-the-art performance on dehazing datasets.

Sheng Zhang, Min Chen, Jincai Chen, Yuan-Fang Li, Yiling Wu, Minglei Li, Chuanbo Zhu

October 2021 In Knowledge-Based Systems (KBS)

Combining cross-modal knowledge transfer and semi-supervised learning for speech emotion recognition

To alleviate the above issue, we propose a new architecture that combines cross-modal knowledge transfer from visual to audio modality into our semi-supervised learning method with consistency regularization. We posit that introducing visual emotional knowledge by the cross-modal transfer method can increase the diversity and accuracy of pseudo-labels and improve the robustness of the model. To combine knowledge from cross-modal transfer and semi-supervised learning, we design two fusion algorithms, i.e. weighted fusion and consistent & random.