no code implementations • CVPR 2022 • Linjun Zhou, Peng Cui, Yinan Jiang, Shiqiang Yang
In this paper, we propose a novel setting of transferable black-box attack: attackers may use external information from a pre-trained model with available network parameters, however, different from previous studies, no additional training data is permitted to further change or tune the pre-trained model.
no code implementations • CVPR 2020 • Linjun Zhou, Peng Cui, Xu Jia, Shiqiang Yang, Qi Tian
Few-shot learning has attracted intensive research attention in recent years.
no code implementations • CVPR 2019 • Linjun Zhou, Peng Cui, Shiqiang Yang, Wenwu Zhu, Qi Tian
We then propose an out-of-sample embedding method to learn the embedding of a new class represented by a few samples through its visual analogy with base classes and derive the classification parameters for the new class.
2 code implementations • AAAI 2017 • Xiao Wang, Peng Cui, Jing Wang, Jian Pei, Wenwu Zhu, Shiqiang Yang
While previous network embedding methods primarily preserve the microscopic structure, such as the first- and second-order proximities of nodes, the mesoscopic community structure, which is one of the most prominent feature of networks, is largely ignored.
no code implementations • 27 May 2015 • Linyun Yu, Peng Cui, Fei Wang, Chaoming Song, Shiqiang Yang
As cascades are typical dynamic processes, it is always interesting and important to predict the cascade size at any time, or predict the time when a cascade will reach a certain size (e. g. an threshold for outbreak).
Social and Information Networks Physics and Society
1 code implementation • 10 Feb 2014 • Kang Zhang, Jiyang Li, Yijing Li, Weidong Hu, Lifeng Sun, Shiqiang Yang
In this paper, we propose a novel binary-based cost computation and aggregation approach for stereo matching problem.