卓涛,副研究员,硕士生导师,2016年在西北工业大学取得博士学位。博士毕业后,曾在新加坡国立大学计算机学院从事博士后研究工作。主要研究方向包括多媒体分析、计算机视觉、机器学习。发表CCF A类会议论文、中科院一区/IEEE汇刊共16篇,其中包括ACM MM、ICLR、TIP、TCSVT、TMM、PR等。主持国家自然科学基金青年项目和山东省海外优秀青年基金项目各1项,入选山东省山东省高校青年创新团队。
研究方向:多媒体分析、计算机视觉、机器学习。
科研项目
国家自然科学基金 (青年),No.62002188,基于逻辑规则的图像内容理解和推理研究,2021.01-2023.12,24 万,主持
山东省优秀青年科学基金(海外),2023HWYQ-114,图像状态转换的视觉推理研究,2023.01–2025.12,60 万,主持
国家自然科学基金 (面上),No. 62272254. 面向推荐系统公平性问题中的多边曝光偏差研究, 2023-01-01 至 2026-12-31, 54万,参与
国家自然科学基金 (面上),No.61571362. 基于高阶正则化半监督学习的多跟踪器框架模型及融合策略研究,2016.01-2019.12,67 万,参与
山东省高等学校青创科技支持计划,社会公共安全智能视频分析及其应用研究,2020.03-2023.02,20 万,参与
山东省科教产融合创新试点工程, 可解释通用人工智能关键技术研究及应用,2022.01-2023.12,1200 万,参与
BWIN必赢官网(山东省科学院),新一代人工智能重大基础理论研究,2020.01-2021.12,288 万,参与
部分代表性论文
[1] Tao Zhuo, Mohan Kankanhalli. Effective Abstract Reasoning with Dual-Contrast Network. International Conference on Learning Representations (ICLR), 2021.
[2] Tao Zhuo, Qiang Huang, Mohan Kankanhalli. Unsupervised Abstract Reasoning via Noisy Contrast and Decentralization, IEEE Transactions on Image Processing (TIP), 2021.
[3] Tao Zhuo, Zhiyong Cheng, Peng Zhang, Yongkang Wong, Mohan Kankanhalli. Unsupervised Online Video Object Segmentation with Motion Property Understanding. IEEE Transactions on Image Processing (TIP), 2019.
[4] Tao Zhuo, Zhiyong Cheng, Peng Zhang, Yongkang Wong, Mohan Kankanhalli. Explainable Video Action Reasoning via Prior Knowledge and State Transitions. ACM Multimedia (ACM MM), 2019.
[5] Wenna Wang, Tao Zhuo (共同一作), Xiuwei Zhang, mingjun sun, Hanlin Yin, Yinghui Xing, Yanning Zhang. Automatic Network Architecture Search for RGB-D Semantic Segmentation. (ACM MM), 2023.
[6] Zan Gao, Xinglei Cui, yibo Zhao, Tao Zhuo, Weili Guan, Meng Wang. A Novel Temporal Channel Enhancement and Contextual Excavation Network for Temporal Action Localization. (ACM MM), 2023
[7] Hehe Fan, Tao Zhuo, Xin Yu, Yi Yang, and Mohan Kankanhalli, Understanding Atomic Hand-Object Interaction with Human Intention, IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022
[8] Yi Cheng, Ying Sun, Hehe Fan, Tao Zhuo, Joo-Hwee Lim, Mohan Kankanhalli, Entropy Guided Attention Network for Weakly-supervised Action Localization (Pattern Recognition), 2022
[9] Yuze Hao, Jianrong Zhang, Tao Zhuo, Fuan Wen, Hehe Fan. Hand-Centric Motion Refinement for 3D Hand-Object Interaction via Hierarchical Spatial-Temporal Modeling, AAAI, 2024
[10] Hehe Fan, Tao Zhuo, Xiaoyu Feng, Guoshun Nan. How Deep Neural Networks Understand Motion? Toward Interpretable Motion Modeling by Leveraging the Relative Change in Position. Intelligent Computing, 2023