no code implementations • 23 Apr 2024 • Siqi Ping, Yuzhu Mao, Yang Liu, Xiao-Ping Zhang, Wenbo Ding
Although large-scale pre-trained models hold great potential for adapting to downstream tasks through fine-tuning, the performance of such fine-tuned models is often limited by the difficulty of collecting sufficient high-quality, task-specific data.
no code implementations • 22 Apr 2024 • Zixuan Zhou, Xuefei Ning, Ke Hong, Tianyu Fu, Jiaming Xu, Shiyao Li, Yuming Lou, Luning Wang, Zhihang Yuan, Xiuhong Li, Shengen Yan, Guohao Dai, Xiao-Ping Zhang, Yuhan Dong, Yu Wang
This paper presents a comprehensive survey of the existing literature on efficient LLM inference.
1 code implementation • 13 Apr 2024 • Yingjie Zhou, ZiCheng Zhang, Wei Sun, Xiaohong Liu, Xiongkuo Min, Zhihua Wang, Xiao-Ping Zhang, Guangtao Zhai
In the realm of media technology, digital humans have gained prominence due to rapid advancements in computer technology.
1 code implementation • 8 Feb 2024 • Hongyi Chen, Jingtao Ding, Yong Li, Yue Wang, Xiao-Ping Zhang
In this paper, we propose a social physics-informed diffusion model named SPDiff to mitigate the above gap.
1 code implementation • 2 Feb 2024 • Wenhao Jiang, Duo Li, Menghan Hu, Guangtao Zhai, Xiaokang Yang, Xiao-Ping Zhang
To tackle the issues of catastrophic forgetting and overfitting in few-shot class-incremental learning (FSCIL), previous work has primarily concentrated on preserving the memory of old knowledge during the incremental phase.
no code implementations • 24 Jan 2024 • Shoujie Li, Ran Yu, Tong Wu, JunWen Zhong, Xiao-Ping Zhang, Wenbo Ding
In this work, we propose a framework named GExp, which enables robots to explore and learn autonomously without human intervention.
1 code implementation • 9 Jan 2024 • Kuo Yang, Duo Li, Menghan Hu, Guangtao Zhai, Xiaokang Yang, Xiao-Ping Zhang
This approach allows the model to perceive the uncertainty of pseudo-labels at different training stages, thereby adaptively adjusting the selection thresholds for different classes.
no code implementations • 13 Sep 2023 • Zihao Zhao, Yang Liu, Wenbo Ding, Xiao-Ping Zhang
Existing research has either adapted the Probably Approximately Correct (PAC) Bayesian framework for federated learning (FL) or used information-theoretic PAC-Bayesian bounds while introducing their theorems, but few considering the non-IID challenges in FL.
1 code implementation • ICCV 2023 • Guangyi Chen, Xiao Liu, Guangrun Wang, Kun Zhang, Philip H. S. Torr, Xiao-Ping Zhang, Yansong Tang
To bridge these gaps, in this paper, we propose Tem-Adapter, which enables the learning of temporal dynamics and complex semantics by a visual Temporal Aligner and a textual Semantic Aligner.
Ranked #1 on Video Question Answering on SUTD-TrafficQA
no code implementations • 8 Aug 2023 • Hengxi Zhang, Huaze Tang, Wenbo Ding, Xiao-Ping Zhang
The Space-Air-Ground Integrated Network (SAGIN), integrating heterogeneous devices including low earth orbit (LEO) satellites, unmanned aerial vehicles (UAVs), and ground users (GUs), holds significant promise for advancing smart city applications.
no code implementations • 1 Aug 2023 • Zihao Zhao, Yuzhu Mao, Zhenpeng Shi, Yang Liu, Tian Lan, Wenbo Ding, Xiao-Ping Zhang
In response, this paper introduces AQUILA (adaptive quantization in device selection strategy), a novel adaptive framework devised to effectively handle these issues, enhancing the efficiency and robustness of FL.
1 code implementation • IEEE Transactions on Circuits and Systems for Video Technology 2023 • Yixuan Gao, Xiongkuo Min, Yucheng Zhu, Xiao-Ping Zhang, Guangtao Zhai
On the other hand, we also prove the feasibility of the proposed method in predicting the MOS of image quality on several popular IQA databases, including CSIQ, TID2013, LIVE MD, and LIVE Challenge.
1 code implementation • 7 Jul 2023 • Xiao Liu, Guangyi Chen, Yansong Tang, Guangrun Wang, Xiao-Ping Zhang, Ser-Nam Lim
Composing simple elements into complex concepts is crucial yet challenging, especially for 3D action generation.
no code implementations • 21 Apr 2023 • Chengyu Zheng, Peng Li, Xiao-Ping Zhang, Xuequan Lu, Mingqiang Wei
The IS is designed to simulate the detection procedure of human recognition for identifying transparent glass by global context and edge information.
no code implementations • 15 Mar 2023 • Hengxi Zhang, Zhendong Shi, Yuanquan Hu, Wenbo Ding, Ercan E. Kuruoglu, Xiao-Ping Zhang
Quantitative markets are characterized by swift dynamics and abundant uncertainties, making the pursuit of profit-driven stock trading actions inherently challenging.
no code implementations • 3 Jan 2023 • Yicong Li, Yang Tan, Jingyun Yang, Yang Li, Xiao-Ping Zhang
Furthermore, within the same modality, transferring from the source task that has stronger RoI shape similarity with the target task can significantly improve the final transfer performance.
no code implementations • 30 Nov 2022 • Shoujie Li, Haixin Yu, Wenbo Ding, Houde Liu, Linqi Ye, Chongkun Xia, Xueqian Wang, Xiao-Ping Zhang
Here, a visual-tactile fusion framework for transparent object grasping under complex backgrounds and variant light conditions is proposed, including the grasping position detection, tactile calibration, and visual-tactile fusion based classification.
1 code implementation • 3 Aug 2022 • Yoga Suhas Kuruba Manjunath, Sihao Zhao, Hatem Abou-zeid, Akram Bin Sediq, Ramy Atawia, Xiao-Ping Zhang
The commonality of statistical features among the network flow segments motivates us to propose novel segmented learning that includes essential vector representation and a simple-segment method of classification.
no code implementations • 12 Jul 2022 • Yang Tan, Enming Zhang, Yang Li, Shao-Lun Huang, Xiao-Ping Zhang
We propose two novel transferability metrics F-OTCE (Fast Optimal Transport based Conditional Entropy) and JC-OTCE (Joint Correspondence OTCE) to evaluate how much the source model (task) can benefit the learning of the target task and to learn more transferable representations for cross-domain cross-task transfer learning.
1 code implementation • 11 Jul 2022 • Ting Yao, Yehao Li, Yingwei Pan, Yu Wang, Xiao-Ping Zhang, Tao Mei
Dual-ViT is henceforth able to reduce the computational complexity without compromising much accuracy.
1 code implementation • 6 Apr 2022 • Yiyang Shen, Mingqiang Wei, Sen Deng, Wenhan Yang, Yongzhen Wang, Xiao-Ping Zhang, Meng Wang, Jing Qin
To bridge the two domain gaps, we propose a semi-supervised detail-recovery image deraining network (Semi-DRDNet) with dual sample-augmented contrastive learning.
no code implementations • 5 Apr 2022 • Yuzhu Mao, Zihao Zhao, Meilin Yang, Le Liang, Yang Liu, Wenbo Ding, Tian Lan, Xiao-Ping Zhang
It is demonstrated that SAFARI under unreliable communications is guaranteed to converge at the same rate as the standard FedAvg with perfect communications.
1 code implementation • 23 Mar 2022 • Haoran Zhou, Honghua Chen, Yingkui Zhang, Mingqiang Wei, Haoran Xie, Jun Wang, Tong Lu, Jing Qin, Xiao-Ping Zhang
Differently, our network is designed to refine the initial normal of each point by extracting additional information from multiple feature representations.
no code implementations • 2 Mar 2022 • Yixuan Gao, Xiongkuo Min, Wenhan Zhu, Xiao-Ping Zhang, Guangtao Zhai
Experimental results verifythe feasibility of using alpha stable model to describe the IQSD, and prove the effectiveness of objective alpha stable model basedIQSD prediction method.
no code implementations • 14 Feb 2022 • Sihao Zhao, Ningyan Guo, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu
In this paper, we develop a new optimal LAS method in the TDBS, namely LAS-SDT, by taking advantage of the sequential Doppler shift and TOA measurements.
no code implementations • CVPR 2021 • Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Xiao-Ping Zhang, Dong Wu, Tao Mei
Video content is multifaceted, consisting of objects, scenes, interactions or actions.
no code implementations • 13 Nov 2021 • Sihao Zhao, Ningyan Guo, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu
Numerical results in a 3D scenario verify the theoretical analysis that the estimation accuracy of the new CFTWLAS method reaches CRLB in the presented experiments when the number of the ANs is large, the geometry is appropriate, and the noise is small.
no code implementations • 29 Sep 2021 • Yoga Suhas Kuruba Manjunath, Sihao Zhao, Xiao-Ping Zhang
The network traffic classification (NTC) is an essential tool to explore behaviours of network flows, and NTC is required for Internet service providers (ISPs) to manage the performance of the IoT network.
no code implementations • 21 Sep 2021 • Sihao Zhao, Hatem Abou-zeid, Ramy Atawia, Yoga Suhas Kuruba Manjunath, Akram Bin Sediq, Xiao-Ping Zhang
To the best of the authors' knowledge, this is the first measurement study and analysis conducted using a commercial cloud VR gaming platform, and under both fixed and adaptive bitrate streaming.
no code implementations • 27 Jul 2021 • Hang Liu, Menghan Hu, Yuzhen Chen, Qingli Li, Guangtao Zhai, Simon X. Yang, Xiao-Ping Zhang, Xiaokang Yang
This work demonstrates that it is practicable for the blind people to feel the world through the brush in their hands.
no code implementations • 15 Jun 2021 • Sen Deng, Yidan Feng, Mingqiang Wei, Haoran Xie, Yiping Chen, Jonathan Li, Xiao-Ping Zhang, Jing Qin
Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image.
no code implementations • 1 Apr 2021 • Tianyu Hua, Hongdong Zheng, Yalong Bai, Wei zhang, Xiao-Ping Zhang, Tao Mei
Our method tends to synthesize plausible layouts and objects, respecting the interplay of multiple objects in an image.
no code implementations • 17 Mar 2021 • Sihao Zhao, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu
In this article, we design a new time-of-arrival (TOA) system for simultaneous user device (UD) localization and synchronization with a periodic asymmetric ranging network, namely PARN.
no code implementations • 3 Mar 2021 • Zhipeng Su, Yixiong Zhang, Xiao-Ping Zhang, Feng Qi
Second, aggregating channels could help our model to concentrate on channels more related to image background instead of rain streaks.
no code implementations • 3 Mar 2021 • Sihao Zhao, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu
In two-way time-of-arrival (TOA) systems, a user device (UD) obtains its position by round-trip communications to a number of anchor nodes (ANs) at known locations.
1 code implementation • ICCV 2021 • Xiaodong Chen, Xinchen Liu, Wu Liu, Xiao-Ping Zhang, Yongdong Zhang, Tao Mei
In this paper, we propose a post-hoc method, named Attribute-guided Metric Distillation (AMD), to explain existing ReID models.
Ranked #44 on Person Re-Identification on DukeMTMC-reID
no code implementations • 30 Jan 2021 • Ningyan Guo, Sihao Zhao, Xiao-Ping Zhang, Zheng Yao, Xiaowei Cui, Mingquan Lu
Compared with the conventional iterative method, the proposed new CFJLAS method does not require initialization, obtains the optimal solution under the small noise condition, and has a low computational complexity.
no code implementations • 5 Jan 2021 • Sihao Zhao, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu
We show that the LSPM-D is a special case of the LSPM-KVD when the UD is stationary with zero velocity.
no code implementations • 25 Nov 2020 • Sihao Zhao, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu
Numerical results verify the theoretical analysis on positioning accuracy, and show that the new CDL method has superior performance over the state-of-the-art closed-form method.
no code implementations • 24 Nov 2020 • Sihao Zhao, Xiao-Ping Zhang, Xiaowei Cui, Mingquan Lu
We show that the conventional two-way TOA method is a special case of the TWLAS when the UD is stationary, and the TWLAS has high estimation accuracy than the conventional one-way TOA method.
no code implementations • 20 Oct 2020 • Chang Yao, Jingyu Tang, Menghan Hu, Yue Wu, Wenyi Guo, Qingli Li, Xiao-Ping Zhang
Sturge-Weber syndrome (SWS) is a vascular malformation disease, and it may cause blindness if the patient's condition is severe.
no code implementations • 20 Oct 2020 • Yunlu Wang, Cheng Yang, Menghan Hu, Jian Zhang, Qingli Li, Guangtao Zhai, Xiao-Ping Zhang
This paper presents an unobtrusive solution that can automatically identify deep breath when a person is walking past the global depth camera.
no code implementations • 28 Sep 2020 • Hang Du, Hailin Shi, Dan Zeng, Xiao-Ping Zhang, Tao Mei
To start with, we present an overview of the end-to-end deep face recognition.
no code implementations • 8 Apr 2020 • Xiao Jiang, Gang Li, Yu Liu, Xiao-Ping Zhang, You He
To solve this problem, this paper presents a new homogeneous transformation model termed deep homogeneous feature fusion (DHFF) based on image style transfer (IST).
no code implementations • 12 Mar 2020 • Chengcheng Jia, Bo Wu, Xiao-Ping Zhang
Dynamic spatial graph construction is a challenge in graph neural network (GNN) for time series data problems.
no code implementations • 12 Feb 2020 • Yunlu Wang, Menghan Hu, Qingli Li, Xiao-Ping Zhang, Guangtao Zhai, Nan Yao
During the epidemic prevention and control period, our study can be helpful in prognosis, diagnosis and screening for the patients infected with COVID-19 (the novel coronavirus) based on breathing characteristics.
no code implementations • 20 Feb 2019 • Jianze Li, Xiao-Ping Zhang, Tuan Tran
In this paper, we propose a new algorithm for point cloud denoising based on the tensor Tucker decomposition.
no code implementations • 10 Sep 2018 • Jianfeng Zhang, Liezhuo Zhang, Yuankai Teng, Xiao-Ping Zhang, Song Wang, Lili Ju
Binary image segmentation plays an important role in computer vision and has been widely used in many applications such as image and video editing, object extraction, and photo composition.
no code implementations • 22 Jan 2017 • Chang-Hwan Son, Xiao-Ping Zhang
Different from conventional fusion approaches, the proposed method conducts a series of transfers: contrast, detail, and color transfers.
no code implementations • 3 Oct 2016 • Chang-Hwan Son, Xiao-Ping Zhang
Based on this error map, both the sparse codes of rain and non-rain dictionaries are used jointly to represent the image structures of objects and avoid the edge artifacts in the non-rain regions.
no code implementations • 3 Oct 2016 • Chang-Hwan Son, Xiao-Ping Zhang
Next, residual rain patches are selected randomly, and then added to the given target image along a raster scanning direction.
no code implementations • 3 Oct 2016 • Chang-Hwan Son, Xiao-Ping Zhang
This paper introduces a new coloring method to add colors to near-infrared gray images based on a contrast-preserving mapping model.
no code implementations • 1 Oct 2016 • Chang-Hwan Son, Xiao-Ping Zhang
It is also shown that the proposed color regularization can remove the edge artifacts which arise from the use of the conventional dark prior model.
no code implementations • CVPR 2016 • Xueyang Fu, Delu Zeng, Yue Huang, Xiao-Ping Zhang, Xinghao Ding
We propose a weighted variational model to estimate both the reflectance and the illumination from an observed image.
no code implementations • 12 Feb 2013 • Yue Huang, John Paisley, Qin Lin, Xinghao Ding, Xueyang Fu, Xiao-Ping Zhang
The size of the dictionary and the patch-specific sparsity pattern are inferred from the data, in addition to other dictionary learning variables.