no code implementations • 11 Mar 2024 • Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, Jihong Guan
This paper is an extended abstract of our original work published in KDD23, where we won the best research paper award (Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, and Jihong Guan.
no code implementations • 28 Dec 2023 • Bangyi Zhao, Weixia Xu, Jihong Guan, Shuigeng Zhou
Following that, we conduct graph structure learning on the MSG (i. e., molecule-level graph structure learning) to get the final molecular embeddings, which are the results of fusing both GNN encoded molecular representations and the relationships among molecules, i. e., combining both intra-molecule and inter-molecule information.
1 code implementation • 27 Dec 2023 • Weikang Jiang, Jinxian Wang, Jihong Guan, Shuigeng Zhou
CICL consists of a Transformer encoder, a clustering head, a projection head and a contrastive loss module.
1 code implementation • ACM Multimedia 2023 • Xianliang Huang, Jiajie Gou, Shuhang Chen, Zhizhou Zhong, Jihong Guan, Shuigeng Zhou
To validate the effectiveness and robustness of IDDR-NGP, we provide a wide range of distractors with corresponding annotated labels added to both realistic and synthetic scenes.
no code implementations • 9 Oct 2023 • Yang Wang, Jiaogen Zhou, Jihong Guan
In this paper, we develop a lightweight video anomaly detection model.
no code implementations • 5 Oct 2023 • Siyuan Guo, Jihong Guan, Shuigeng Zhou
Extensive experiments with two benchmark datasets QM9 and ZINC250k show that the molecules generated by our proposed method have better validity, uniqueness, novelty, Fr\'echet ChemNet Distance (FCD), QED, and PlogP than those generated by current SOTA models.
no code implementations • ICCV 2023 • Lu Zhang, Chenbo Zhang, Jiajia Zhao, Jihong Guan, Shuigeng Zhou
Zero-shot object detection aims to localize and recognize objects of unseen classes.
no code implementations • 31 Jul 2023 • Minyi Zhao, Yi Xu, Bingjia Li, Jie Wang, Jihong Guan, Shuigeng Zhou
Observing the quality issue of HR images, in this paper we propose a novel idea to boost STISR by first enhancing the quality of HR images and then using the enhanced HR images as supervision to do STISR.
1 code implementation • 26 Jul 2023 • Yuxi Mi, Hongquan Liu, Yewei Xia, Yiheng Sun, Jihong Guan, Shuigeng Zhou
The emergence of vertical federated learning (VFL) has stimulated concerns about the imperfection in privacy protection, as shared feature embeddings may reveal sensitive information under privacy attacks.
no code implementations • 20 Jul 2023 • Hanchen Yang, Wengen Li, Shuyu Wang, Hui Li, Jihong Guan, Shuigeng Zhou, Jiannong Cao
Compared with typical ST data (e. g., traffic data), ST ocean data is more complicated but with unique characteristics, e. g., diverse regionality and high sparsity.
1 code implementation • 4 Jul 2023 • Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, Jihong Guan
Inspired by the prompt learning in natural language processing (NLP), which has presented significant effectiveness in leveraging prior knowledge for various NLP tasks, we study the prompting topic for graphs with the motivation of filling the gap between pre-trained models and various graph tasks.
no code implementations • 13 Mar 2023 • Ziqiao Zhang, Ailin Xie, Jihong Guan, Shuigeng Zhou
Contrastive learning have been widely used as pretext tasks for self-supervised pre-trained molecular representation learning models in AI-aided drug design and discovery.
1 code implementation • 8 Oct 2022 • Lu Zhang, Yang Wang, Jiaogen Zhou, Chenbo Zhang, Yinglu Zhang, Jihong Guan, Yatao Bian, Shuigeng Zhou
In this paper, we propose and solve a new problem called hierarchical few-shot object detection (Hi-FSOD), which aims to detect objects with hierarchical categories in the FSOD paradigm.
no code implementations • NAACL 2022 • Minyi Zhao, Lu Zhang, Yi Xu, Jiandong Ding, Jihong Guan, Shuigeng Zhou
However, to the best of our knowledge, most existing methods consider only either the diversity or the quality of augmented data, thus cannot fully mine the potential of DA for NLP.
no code implementations • 27 Mar 2022 • Tianying Liu, Lu Zhang, Yang Wang, Jihong Guan, Yanwei Fu, Jiajia Zhao, Shuigeng Zhou
To this end, the Few-Shot Object Detection (FSOD) has been topical recently, as it mimics the humans' ability of learning to learn, and intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes.
no code implementations • 9 Feb 2022 • Yuxi Mi, Yiheng Sun, Jihong Guan, Shuigeng Zhou
For instance, studies have revealed that federated learning is vulnerable to backdoor attacks, whereby a compromised participant can stealthily modify the model's behavior in the presence of backdoor triggers.
no code implementations • CVPR 2021 • Lu Zhang, Shuigeng Zhou, Jihong Guan, Ji Zhang
Most object detection methods require huge amounts of annotated data and can detect only the categories that appear in the training set.
no code implementations • 17 Mar 2019 • Kai Tian, Shuigeng Zhou, Jianping Fan, Jihong Guan
Most of the existing methods for anomaly detection use only positive data to learn the data distribution, thus they usually need a pre-defined threshold at the detection stage to determine whether a test instance is an outlier.
no code implementations • 22 Jun 2018 • Fan Wu, Kai Tian, Jihong Guan, Shuigeng Zhou
In this paper, we propose an end-to-end framework, called Global Semantic Consistency Network (GSC-Net for short), which makes complete use of the semantic information of both seen and unseen classes, to support effective zero-shot learning.