no code implementations • 18 Apr 2024 • Shunpu Tang, Chen Liu, Qianqian Yang, Shibo He, Dusit Niyato
To address this issue, we propose a novel secure semantic communication (SemCom) approach for image transmission, which integrates steganography technology to conceal private information within non-private images (host images).
1 code implementation • 2 Apr 2024 • Lilin Xu, Chaojie Gu, Rui Tan, Shibo He, Jiming Chen
Human activity recognition (HAR) will be an essential function of various emerging applications.
no code implementations • 14 Mar 2024 • Chen Liu, Shibo He, Haoyu Liu, Jiming Chen
To decrease the inference time, we reduce the variable dimensions in the intention-aware diffusion process and restrict the initial distribution of the action-aware diffusion process, which leads to fewer diffusion steps.
no code implementations • 26 Jan 2024 • Chen Liu, Shibo He, Qihang Zhou, Shizhong Li, Wenchao Meng
To overcome the limitation, we propose \textbf{AnomalyLLM}, a knowledge distillation-based time series anomaly detection approach where the student network is trained to mimic the features of the large language model (LLM)-based teacher network that is pretrained on large-scale datasets.
1 code implementation • 20 Jan 2024 • Chen Liu, Shibo He, Haoyu Liu, Shizhong Li
Then, the subsequence features are extracted to determine the presence of collective anomalies.
1 code implementation • 17 Dec 2023 • Qihang Zhou, Shibo He, Haoyu Liu, Jiming Chen, Wenchao Meng
In this paper, we propose MTGFlow, an unsupervised anomaly detection approach for MTS anomaly detection via dynamic Graph and entity-aware normalizing Flow.
no code implementations • 8 Dec 2023 • Zhenguo Zhang, Qianqian Yang, Shibo He, Jiming Chen
Semantic communication has emerged as a promising approach for improving efficient transmission in the next generation of wireless networks.
no code implementations • 22 Nov 2023 • Yuhao Chen, Yuxuan Yan, Qianqian Yang, Yuanchao Shu, Shibo He, Jiming Chen
Transformer-based large language models (LLMs) have demonstrated impressive capabilities in a variety of natural language processing (NLP) tasks.
no code implementations • 10 Nov 2023 • Yuhao Chen, Yuxuan Yan, Qianqian Yang, Yuanchao Shu, Shibo He, Zhiguo Shi, Jiming Chen
Moreover, we propose a bit-level computation-efficient data compression scheme to compress the data to be transmitted between devices during training.
3 code implementations • 29 Oct 2023 • Qihang Zhou, Guansong Pang, Yu Tian, Shibo He, Jiming Chen
It is a crucial task when training data is not accessible due to various concerns, eg, data privacy, yet it is challenging since the models need to generalize to anomalies across different domains where the appearance of foreground objects, abnormal regions, and background features, such as defects/tumors on different products/organs, can vary significantly.
no code implementations • 21 Jul 2023 • Zehan Zhu, Ye Tian, Yan Huang, Jinming Xu, Shibo He
Perfect synchronization in distributed machine learning problems is inefficient and even impossible due to the existence of latency, package losses and stragglers.
no code implementations • 18 Nov 2022 • Bicheng Guo, Shuxuan Guo, Miaojing Shi, Peng Chen, Shibo He, Jiming Chen, Kaicheng Yu
Differentiable architecture search (DARTS) has been a mainstream direction in automatic machine learning.
Ranked #10 on Neural Architecture Search on NAS-Bench-201, CIFAR-100
2 code implementations • 3 Aug 2022 • Qihang Zhou, Jiming Chen, Haoyu Liu, Shibo He, Wenchao Meng
Multivariate time series anomaly detection has been extensively studied under the semi-supervised setting, where a training dataset with all normal instances is required.
no code implementations • 22 Jul 2022 • Yunlong Ran, Jing Zeng, Shibo He, Lincheng Li, Yingfeng Chen, Gimhee Lee, Jiming Chen, Qi Ye
In this paper, we explore for the first time the possibility of using implicit neural representations for autonomous 3D scene reconstruction by addressing two key challenges: 1) seeking a criterion to measure the quality of the candidate viewpoints for the view planning based on the new representations, and 2) learning the criterion from data that can generalize to different scenes instead of a hand-crafting one.
1 code implementation • 27 May 2022 • Qiyuan Wang, Qianqian Yang, Shibo He, Zhiguo Shi, Jiming Chen
In an asynchronous federated learning framework, the server updates the global model once it receives an update from a client instead of waiting for all the updates to arrive as in the synchronous setting.
no code implementations • 25 May 2022 • Tianxiao Han, Qianqian Yang, Zhiguo Shi, Shibo He, Zhaoyang Zhang
Deep learning (DL) based semantic communication methods have been explored for the efficient transmission of images, text, and speech in recent years.
no code implementations • 8 Feb 2022 • Zhenguo Zhang, Qianqian Yang, Shibo He, Mingyang Sun, Jiming Chen
In particular, the proposed model includes a multilevel semantic feature extractor, that extracts both the highlevel semantic information, such as the text semantics and the segmentation semantics, and the low-level semantic information, such as local spatial details of the images.
no code implementations • 7 Feb 2022 • Tianxiao Han, Qianqian Yang, Zhiguo Shi, Shibo He, Zhaoyang Zhang
We also propose a two-stage training scheme, which speeds up the training of the proposed DL model.
1 code implementation • 30 Jan 2022 • Bicheng Guo, Tao Chen, Shibo He, Haoyu Liu, Lilin Xu, Peng Ye, Jiming Chen
The NAR explores the quality tiers of the search space globally and classifies each individual to the tier they belong to according to its global ranking.
no code implementations • 6 Oct 2021 • Yuhao Chen, Qianqian Yang, Shibo He, Zhiguo Shi, Jiming Chen
Our numerical results demonstrate that FTPipeHD is 6. 8x faster in training than the state of the art method when the computing capacity of the best device is 10x greater than the worst one.
no code implementations • 17 Mar 2021 • Haoyu Liu, Fenglong Ma, Shibo He, Jiming Chen, Jing Gao
Meanwhile, we propose a post-processing framework to tune the original ensemble results through a stacking process so that we can achieve a trade off between fairness and detection performance.
no code implementations • 1 Sep 2020 • Jingchen Sun, Jiming Chen, Tao Chen, Jiayuan Fan, Shibo He
Vision-based dynamic pedestrian intrusion detection (PID), judging whether pedestrians intrude an area-of-interest (AoI) by a moving camera, is an important task in mobile surveillance.