1.Name

Sijie Mai

2.Biography

From August 2015 to June 2019， He pursued and obtained a Bachelor of Engineering degree in Intelligent Science and Technology at Sun Yat-sen University. Continuing my academic journey， He got a Doctor degree of Engineering from the same institution， focusing on Artificial Intelligence， Machine Learning， Multimodal Affective Computing， Knowledge Graphs， and AI4Science， from August 2019 to June 2024.

Since October 2024， He has been serving as a Tier-1 Outstanding Young Talent (Professor Position) at the School of Computer Science， South China Normal University.

Over the past five years， He has published over 20 representative SCI papers and 6 conference papers. As the first author， He has contributed to 16 publications， including 4 top-tier international AI conference papers， 12 SCI papers， and 13 papers recommended by the Chinese Association for Artificial Intelligence as Class A. Among my first-authored SCI papers， there are 8 published in IEEE/ACM Transactions and 5 in journals recommended as Class A by Tsinghua University. Additionally， He has co-authored 5 papers as the second lead author， with 2 being IEEE Transactions papers and one being a CCF Class A paper. My publications have garnered over 1300 citations on Google Scholar， with three of my first-authored papers each cited over 100 times， achieving an H-index of 19. He also servse as a reviewer for several renowned journals and conferences.

3.Research Interests

Artificial Intelligence， Machine Learning， Multimodal Affective Computing， Knowledge Graphs， and AI4Science

4.Email

sijiemai@m.scnu.edu.cn

5.Academic

[1] Mai， Sijie， Sun， Ya， Xiong， Aolin， Zeng， Ying， Hu， Haifeng. Multimodal Boosting: Addressing Noisy Modalities and Identifying Modality Contribution.  IEEE Transactions on Multimedia， IEEE ， 2024
[2] Zeng， Ying， Mai， Sijie， Yan， Wenjun， Hu， Haifeng. Multimodal reaction: Information modulation for cross-modal representation learning.  IEEE Transactions on Multimedia， IEEE ， 2024
[3] Mai， Sijie， Zeng， Ying， Hu， Haifeng. Learning from the global view: Supervised contrastive learning of multimodal representation.  Information Fusion， Elsevier ， 2023， 100: 101920
[4] Mai， Sijie*， Zeng， Ying*， Zheng， Shuangjia， Hu， Haifeng. Hybrid contrastive learning of tri-modal representation for multimodal sentiment analysis.  IEEE Transactions on Affective Computing， IEEE ， 2023， 14(3): 2276--2289
[5] Mai， Sijie*， Zeng， Ying*， Hu， Haifeng. Multimodal information bottleneck: Learning minimal sufficient unimodal and multimodal representations.  IEEE Transactions on Multimedia， IEEE ， 2023， 25: 4121--4134
[6] Mai， Sijie， Sun， Ya， Zeng， Ying， Hu， Haifeng. Excavating multimodal correlation for representation learning.  Information Fusion， Elsevier ， 2023， 91: 542--555
[7] Zheng， Shuangjia*， Mai， Sijie*， Sun， Ya*， Hu， Haifeng， Yang， Yuedong. Subgraph-aware few-shot inductive link prediction via meta-learning.  IEEE Transactions on Knowledge and Data Engineering， IEEE ， 2023， 35(6): 6512--6517
[8] Sun， Ya*， Mai， Sijie*， Hu， Haifeng. Learning to learn better unimodal representations via adaptive multimodal meta-learning.  IEEE Transactions on Affective Computing， IEEE ， 2023， 14(3): 2209--2223
[9] Mai， Sijie， Xing， Songlong， He， Jiaxuan， Zeng， Ying， Hu， Haifeng. Multimodal graph for unaligned multimodal sequence analysis via graph convolution and graph pooling.  ACM Transactions on Multimedia Computing， Communications and Applications， ACM New York， NY ， 2023， 19(2): 1--24
Xing， Songlong， Mai， Sijie， Hu， Haifeng. Adapted dynamic memory network for emotion recognition in conversation.  IEEE Transactions on Affective Computing， IEEE ， 2022， 13(3): 1426--1439
[11] Mai， Sijie， Hu， Haifeng， Xu， Jia， Xing， Songlong. Multi-fusion residual memory network for multimodal human sentiment comprehension.  IEEE Transactions on Affective Computing， IEEE ， 2022， 13(1): 320--334
[12] Mai， Sijie， Hu， Haifeng， Xing， Songlong. A unimodal representation learning and recurrent decomposition fusion structure for utterance-level multimodal embedding learning.  IEEE Transactions on Multimedia， IEEE ， 2022， 24: 2488--2501
[13] Wu， Jianfeng， Mai， Sijie， Hu， Haifeng. Interpretable multimodal capsule fusion.  IEEE/ACM Transactions on Audio， Speech， and Language Processing， IEEE ， 2022， 30: 1815--1826
[14] Mai， Sijie， Zheng， Shuangjia， Sun， Ya， Zeng， Ying， Yang， Yuedong， Hu， Haifeng. Dynamic graph dropout for subgraph-based relation prediction.  Knowledge-Based Systems， Elsevier ， 2022， 250: 109172
[15] Mai， Sijie， Xing， Songlong， Hu， Haifeng. Analyzing multimodal sentiment via acoustic-and visual-LSTM with channel-aware temporal convolution network.  IEEE/ACM Transactions on Audio， Speech， and Language Processing， IEEE ， 2021， 29: 1424--1437
[16] Sun， Ya*， Mai， Sijie*， Hu， Haifeng. Learning to balance the learning rates between various modalities via adaptive tracking factor.  IEEE Signal Processing Letters， IEEE ， 2021， 28: 1650--1654
[17] He， Jiaxuan*， Mai， Sijie*， Hu， Haifeng. A unimodal reinforced transformer with time squeeze fusion for multimodal sentiment analysis.  IEEE Signal Processing Letters， IEEE ， 2021， 28: 992--996
[18] Mai， Sijie， Xing， Songlong， Hu， Haifeng. Locally confined modality fusion network with a global perspective for multimodal human affective computing.  IEEE Transactions on Multimedia， IEEE ， 2020， 22(1): 122--137
[19] Mai， Sijie， Hu， Haifeng， Xu， Jia. Attentive matching network for few-shot learning.  Computer Vision and Image Understanding， Elsevier ， 2019， 187: 102781
[20] Mai， Sijie， Hu， Haifeng， Xing， Songlong. Modality to modality translation: An adversarial representation learning and graph fusion network for multimodal fusion.  proceedings of the AAAI conference on artificial intelligence， 2020 ， 34(01): 164--172
[21] Mai， Sijie， Hu， Haifeng， Xing， Songlong. Divide， conquer and combine: Hierarchical feature fusion network with local and global perspectives for multimodal affective computing.  Proceedings of the 57th annual meeting of the association for computational linguistics， 2019 : 481--492
[22] Mai， Sijie*， Zheng， Shuangjia*， Yang， Yuedong， Hu， Haifeng. Communicative message passing for inductive relation reasoning.  Proceedings of the AAAI Conference on Artificial Intelligence， 2021 ， 35(5): 4294--4302
[23] Wu， Jianfeng， Mai， Sijie， Hu， Haifeng. Graph capsule aggregation for unaligned multimodal sequences.  Proceedings of the 2021 international conference on multimodal interaction， 2021 : 521--529
[24] Zeng， Ying*， Mai， Sijie*， Hu， Haifeng. Which is Making the Contribution: Modulating Unimodal and Cross-modal Dynamics for Multimodal Sentiment Analysis.  Findings of the Association for Computational Linguistics: EMNLP 2021， 2021 : 1262--1274
[25] Mai， Sijie， Sun， Ya， Hu， Haifeng. Curriculum Learning Meets Weakly Supervised Multimodal Correlation Learning.  Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing， 2022 : 3191--3203