韓冀中

韓冀中，男，中國科學院大學博士生導師，正高級工程師。

中國科學院信息工程研究所網路空間技術實驗室執行主任，網路空間安全測評中心副主任

基本介紹

• 中文名：韓冀中
• 國籍：中國
• 學位/學歷： 博士
• 職業：教師
• 專業方向：多媒體信息智慧型化處理
• 性別：男

研究方向

研究方向為多媒體信息智慧型化處理，大數據存儲與智慧型處理等，近期研究工作涉及多媒體信息處理，信息內容分析與智慧型計算架構。擔任科技創新2030“新一代人工智慧”重大項目負責人，並已承擔或參與完成國家973、863、國家自然科學基金重大與面上項目、中科院知識創新工程等項目30餘項，取得多項成果。在CVPR、AAAI、IJCAI等期刊和國際會議發表論文60餘篇，獲得國家發明專利授權20餘項，出版譯著2部。

主要成就

多媒體信息處理

1. Tianrui Hui, Shaofei Huang, Si Liu, Zihan Ding, Guanbin Li, Wenguan Wang, Jizhong Han, Fei Wang, Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation, In CVPR 2021.

2. Peng Chen, Jin Liu, Tao Liang, Guangzhi Zhou, Hongchao Gao, Jiao Dai, Jihzong Han, FSSPOTTER: Spotting Face-Swapped Video by Spatial and Temporal Clues. In ICME 2020.

3. Guanghui Ren, Lejian Ren, Yue Liao, Si Liu, Bo Li, Jizhong Han, Shuicheng Yan, Scene Graph Generation with Hierarchical Context, In TNNLS 2020.

4. Shaofei Huang, Si Liu, Tianrui Hui, Jizhong Han, Bo Li, Jiashi Feng, Shuicheng Yan, ORDNet: Capturing Omni-Range Dependencies for Scene Parsing. In TIP 2020.

5.Tianrui Hui, Si Liu, Shaofei Huang, Guanbin Li, Sansi Yu, Faxi Zhang, Jizhong Han. Linguistic Structure Guided Context Modeling for Referring Image Segmentation. In ECCV 2020.

6. Chunyuan Yuan, Qianwen Ma, Junyang Chen, Wei Zhou, Xiaodan Zhang, Xuehai Tang, Jizhong Han, Songlin Hu. Exploiting Heterogeneous Artist and Listener Preference Graph for Music Genre Classification. In ACM MM 2020.

7. Shaofei Huang, Tianrui Hui, Si Liu, Guanbin Li, Yunchao Wei, Jizhong Han, Luoqi Liu, Bo Li. Referring Image Segmentation via Cross-Modal Progressive Comprehension. In CVPR 2020.

8. Qianwen Ma, Chunyuan Yuan, Wei Zhou, Jizhong Han, Songlin Hu. Beyond Statistical Relations: Integrating Knowledge Relations into Style Correlations for Multi-Label Music Style Classification. WSDM 2020.

信息內容分析

1. Jinzhu Yang, Wei Zhou, Lingwei Wei, Junyu Lin, Jizhong Han, Songlin Hu. RE-GCN. Relation Enhanced Graph Convolutional Network for Entity Alignment in Heterogeneous Knowledge Graphs. In DASFAA 2020: 432-447.

2. Yan Zhou, Wei Jiang, Po Song, Yipeng Su, Tao Guo, Jizhong Han, Songlin Hu. Graph Convolutional Networks for Target-oriented Opinion Words Extraction with Adversarial Training. In IJCNN 2020. Best Student Paper Award.

3. Chunyuan Yuan, Qianwen Ma, Wei Zhou, Jizhong Han and Songlin Hu. Early Detection of Fake News by Utilizing the Credibility of News, Publishers, and Users Based on Weakly Supervised Learning. In COLING 2020.

4. Shangwen Lv, Fuqing Zhu, Songlin Hu. Integrating External Event Knowledge for Script Learning. In COLING 2020.

5. Chunyuan Yuan, Jiacheng Li, Wei Zhou, Yijun Lu, Xiaodan Zhang, Songlin Hu. DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users’ Dynamic Preferences for Information Diffusion Prediction. In ECML-PKDD 2020.

6. Lingwei Wei, Dou Hu, Wei Zhou, Xuehai Tang, Xiaodan Zhang, Xin Wang, Jizhong Han, Songlin Hu. Hierarchical Interaction Networks with Rethinking Mechanism for Document-level Sentiment Analysis. In ECML-PKDD 2020.

7. Shangwen Lv, Longtao Huang, Liangjun Zang, Wei Zhou, Jizhong Han, Songlin Hu. Yet another approach to understanding news event evolution. World Wide Web J. 2020.

8. Mingming Li, Shuai Zhang, Fuqing Zhu, Liangjun Zang, Jizhong Han, Songlin Hu. Symmetric Metric Learning with Adaptive Margin for Recommendation. AAAI 2020.

智慧型計算架構

1. Jinrong Guo, Songlin Hu, Wang Wang, Chunrong Yao, Jizhong Han, Ruixuan Li, Yijun Lu. Tail: An Automated and Lightweight Gradient Compression Framework for Distributed Deep Learning. In DAC 2020.

2. Jinrong Guo, Wantao Liu, Wang Wang, Jizhong Han, Ruixuan Li, Yijun Lu, Songlin Hu. Accelerating Distributed Deep Learning By Adaptive Gradient Quantization. In ICASSP 2020.

3. Jinrong Guo, Wantao Liu, Wang Wang, Chunrong Yao, Jizhong Han, Ruixuan Li, Yijun Lu and Songlin Hu. AccUDNN: A GPU Memory Efficient Accelerator for Training Ultra-deep Neural Network. ICCD 2019.