no code implementations • 12 Apr 2024 • Tianyu Zhang, Zixuan Zhao, Jiaqi Huang, Jingyu Hua, Sheng Zhong
As Large Language Models (LLMs) of Prompt Jailbreaking are getting more and more attention, it is of great significance to raise a generalized research paradigm to evaluate attack strengths and a basic model to conduct subtler experiments.
no code implementations • 21 Mar 2024 • Shilv Cai, Xiaoguo Liang, Shuning Cao, Luxin Yan, Sheng Zhong, Liqun Chen, Xu Zou
Image compression and denoising represent fundamental challenges in image processing with many real-world applications.
no code implementations • 27 Feb 2024 • Deqian Kong, Yuhao Huang, Jianwen Xie, Edouardo Honig, Ming Xu, Shuanghong Xue, Pei Lin, Sanping Zhou, Sheng Zhong, Nanning Zheng, Ying Nian Wu
Designing molecules with desirable properties, such as drug-likeliness and high binding affinities towards protein targets, is a challenging problem.
no code implementations • 4 Oct 2023 • Zhijun Zhang, Xu Zou, Jiahuan Zhou, Sheng Zhong, Ying Wu
Analysis of human actions in videos demands understanding complex human dynamics, as well as the interaction between actors and context.
1 code implementation • 24 May 2023 • Shilv Cai, Liqun Chen, Sheng Zhong, Luxin Yan, Jiahuan Zhou, Xu Zou
Experimental results show that our proposed joint solution achieves a significant improvement over different combinations of existing state-of-the-art sequential ``Compress before Enhance'' or ``Enhance before Compress'' solutions for low-light images, which would make lossy low-light image compression more meaningful.
1 code implementation • 14 May 2023 • Sheng Zhong, Nima Fazeli, Dmitry Berenson
Rather than attempting to estimate the true pose of the object, which is not tractable without a large number of contacts, we seek to estimate a plausible set of poses which obey the constraints imposed by the sensor data.
no code implementations • 19 Apr 2023 • Yunlong Mao, Zexi Xin, Zhenyu Li, Jue Hong, Qingyou Yang, Sheng Zhong
Split learning of deep neural networks (SplitNN) has provided a promising solution to learning jointly for the mutual interest of a guest and a host, which may come from different backgrounds, holding features partitioned vertically.
1 code implementation • 12 Sep 2022 • Shilv Cai, Zhijun Zhang, Liqun Chen, Luxin Yan, Sheng Zhong, Xu Zou
We implement the IAT in a mathematical invertible manner on a single rate Invertible Neural Network (INN) based model and the quality level (QLevel) would be fed into the IAT to generate scaling and bias tensors.
1 code implementation • ICASSP 2022 • Xiaopeng Ke, Boyu Chang, Hao Wu, Fengyuan Xu, Sheng Zhong
Recently, video summarization (VS) techniques are widely used to alleviate huge processing pressure brought by numerous long videos.
no code implementations • CVPR 2022 • Leizhen Dong, Zhimin Li, Kunlun Xu, Zhijun Zhang, Luxin Yan, Sheng Zhong, Xu Zou
Specifically, the Object Query would be initialized via category priors represented by an external object detection model to yield better performance.
no code implementations • 24 Feb 2022 • Kunlun Xu, Zhimin Li, Zhijun Zhang, Leizhen Dong, Wenhui Xu, Luxin Yan, Sheng Zhong, Xu Zou
Moreover, we also use an actor branch to get interaction prediction of the actor and propose a novel composition strategy based on center-point indexing to generate the final HOI prediction.
no code implementations • 14 Dec 2021 • Zhimin Li, Cheng Zou, Yu Zhao, Boxun Li, Sheng Zhong
Human-Object Interaction (HOI) detection is a fundamental task in high-level human-centric scene understanding.
no code implementations • 1 Dec 2021 • Yanjie Wang, Xu Zou, Zhijun Zhang, Wenhui Xu, Liqun Chen, Sheng Zhong, Luxin Yan, Guodong Wang
Detecting oriented objects along with estimating their rotation information is one crucial step for analyzing remote sensing images.
no code implementations • 18 Jun 2021 • Shucheng Li, Fengyuan Xu, Runchuan Wang, Sheng Zhong
In our model, two pretext tasks designed from spatial and temporal perspectives help us effectively learn useful node embedding from the huge amount of unlabelled transaction data.
no code implementations • 4 Feb 2021 • Lizhi Sun, Shuocheng Wang, Hao Wu, Yuhang Gong, Fengyuan Xu, Yunxin Liu, Hao Han, Sheng Zhong
ARM TrustZone is widely deployed on commercial-off-the-shelf mobile devices for secure execution.
Cryptography and Security
1 code implementation • 23 Oct 2020 • Sheng Zhong, Zhenyuan Zhang, Nima Fazeli, Dmitry Berenson
We propose an approach to online model adaptation and control in the challenging case of hybrid and discontinuous dynamics where actions may lead to difficult-to-escape "trap" states, under a given controller.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Shucheng Li, Lingfei Wu, Shiwei Feng, Fangli Xu, Fengyuan Xu, Sheng Zhong
In particular, we investigated our model for solving two problems, neural semantic parsing and math word problem.
no code implementations • 22 Jan 2020 • Sheng Zhong, Shifu Zhou
But the results of existing methods still exhibit many unpleasant artifacts and distortions even for the cases where the desired ground truth target images are available for supervised learning such as in single image super resolution (SISR).
no code implementations • 21 Nov 2017 • Taihang Dong, Sheng Zhong
Discriminative correlation filters (DCF) have recently shown excellent performance in visual object tracking area.
no code implementations • 21 Nov 2017 • Taihang Dong, Sheng Zhong
We change the search area according to the prediction of target motion.
no code implementations • ICCV 2017 • Yi Chang, Luxin Yan, Sheng Zhong
This paper addresses the problem of line pattern noise removal from a single image, such as rain streak, hyperspectral stripe and so on.
no code implementations • 1 Sep 2017 • Yi Chang, Luxin Yan, Houzhang Fang, Sheng Zhong, Zhijun Zhang
To overcome these limitations, in this work, we propose a unified low-rank tensor recovery model for comprehensive HSI restoration tasks, in which non-local similarity between spectral-spatial cubic and spectral correlation are simultaneously captured by 3-order tensors.
Ranked #12 on Hyperspectral Image Denoising on ICVL-HSI-Gaussian50
no code implementations • CVPR 2017 • Yi Chang, Luxin Yan, Sheng Zhong
Recent low-rank based matrix/tensor recovery methods have been widely explored in multispectral images (MSI) denoising.