Welcome to Haichao Shi’s Pages

石海超

工学博士

中国科学院信息工程研究所

邮箱：shihaichao@iie.ac.cn

地址：北京市海淀区树村路19号，邮编100085

[DBLP], [Google Scholar]

English Version

石海超，电气和电子工程师协会（IEEE）、国际计算机学会（ACM）、中国计算机学会（CCF）、中国图象图形学学会（CSIG）、北京图象图形学学会（BSIG）会员，入选北京市科协2024-2026青年托举人才工程。于2022年博士毕业于中国科学院信息工程研究所，2022年至今在中国科学院信息工程研究所任职，入选优才计划C类，主要研究方向包括多模态学习、行为识别与检测、模式识别等相关问题。

学术论文

  • Masked Face Transformer. IEEE Trans. Inf. Forensics Secur. 19: 265-279, 2024.
  • Denoised Dual-level Contrastive Network for Weakly-supervised Temporal Sentence Grounding. The 12th international conference on Computational Visual Media (CVM), 2024.
  • StochasticFormer: Stochastic Modeling for Weakly Supervised Temporal Action Localization. IEEE Trans. Image Process. 32: 1379-1389,2023.
  • Prism: Real-Time Privacy Protection Against Temporal Network Traffic Analyzers. IEEE Trans. Inf. Forensics Secur. 18: 2524-2537, 2023.
  • ProGraph: Robust Network Traffic Identification With Graph Propagation. IEEE/ACM Trans. Netw. 31(3): 1385-1399, 2023.
  • Rumor Detection with Diverse Counterfactual Evidence. The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 3321-3331, 2023.
  • Dynamic Graph Modeling for Weakly-Supervised Temporal Action Localization. The 30th ACM International Conference on Multimedia (ACM MM), 3820-3828, 2022.
  • OW-TAL: Learning Unknown Human Activities for Open-World Temporal Action Localization. Pattern Recognition, 133: 109027, 2023.
  • Consistent Sub-Decision Network for Low-Quality Masked Face Recognition. IEEE Signal Process. Lett, 29: 1147-1151, 2022.
  • Action Shuffling for Weakly Supervised Temporal Localization. IEEE Trans. Image Process. 31: 4447-4457, 2022.
  • TwinNet: Twin Structured Knowledge Transfer Network for Weakly Supervised Action Localization. Int. J. Autom. Comput. 19(3): 227-246, 2022.
  • Weakly-Supervised Action Recognition and Localization via Iterative Optimization of Embedding and Modeling. Pattern Recognition, 2021.
  • AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization. IEEE TNNLS, 2020.
  • Multi-instance Multi-label Action Recognition and Localization Based on Spatio-Temporal Pre-trimming for Untrimmed Videos. The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), 12886-12893, 2020.
  • Learning Transferable Self-attentive Representations for Action Recognition in Untrimmed Videos with Weak Supervision. The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), 9227-9234, 2019.
  • Active semi-supervised learning based on self-expressive correlation with generative adversarial networks. Neurocomputing, 345: 103-113, 2019.
  • SSGAN: Secure Steganography Based on Generative Adversarial Networks. Pacific-Rim Conference on Multimedia (PCM), 534-544, 2017.
  • SAPS Self-Attentive Pathway Search for Weakly-supervised Action Localization with Background-Action Augmentation. Computer Vision and Image Understanding (CVIU), 210: 103256, 2021.
  • Flexible Non-Autoregressive Extractive Summarization with Threshold: How to Extract a Non-Fixed Number of Summary Sentences. The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), 13134-13142, 2021.
  • DistilSum: Distilling the Knowledge for Extractive Summarization. The 29th ACM International Conference on Information and Knowledge Management (CIKM), 2069-2072, 2020.
  • Image captioning based on deep reinforcement learning. Proceedings of the 10th International Conference on Internet Multimedia Computing and Service (ICIMCS), 45:1-45:5, 2018.
  • Synchronized Detection and Recovery of Steganographic Messages with Adversarial Learning. International Conference on Computational Science (ICCS), 31-43, 2019.
  • Weakly-Supervised Action Recognition and Localization via Knowledge Transfer. Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 205-216, 2019.
  • Weakly Supervised Action Recognition and Localization based on Twin Structured Transferable Self-attentive Representation. The 8th international conference on Computational Visual Media (CVM), 2020.

    • 专利

  • 一种基于图结构信息交互增强的行为检测方法及电子装置，ZL 2020 1 0698168.X.
  • 一种基于自表达相关的数据分类方法和装置，ZL 2018 1 1518273.X.
  • 一种基于生成对抗网络的安全隐写方法和装置，ZL 2017 1 0670786.1.
  • 一种基于三重编码的弱监督行为识别定位方法和装置，CN110490055A.
  • 一种基于动作片段排序的弱监督行为定位方法和装置，CN114049581A.
  • 一种基于双级对比学习与噪声鲁棒的弱监督时序语言定位方法和装置，CN116883886A.
  • 基于领域自适应的GAN逆转图像重建方法和装置，2023已申请.
  • 基于流量指纹蒸馏的设备入网行为检测方法与系统，2023已申请.

    • 社会工作

    荣誉和奖励

    科研竞赛