Search

Your search keyword '"Hu, Tao"' showing total 328 results
Start Over Author "Hu, Tao" Publisher ieee
328 results on '"Hu, Tao"'

15. Federated Learning-Assisted Vehicular Edge Computing: Architecture and Research Directions.

Author

Zhang, Xinran, Liu, Jingyuan, Hu, Tao, Chang, Zheng, Zhang, Yanru, and Min, Geyong

Abstract

Recently, realizing machine learning (ML)-based technologies with the aid of mobile edge computing (MEC) in the vehicular network to establish an intelligent transportation system (ITS) has gained considerable interest. To fully utilize the data and onboard units of vehicles, it is possible to implement federated learning (FL), which can locally train the model and centrally aggregate the results, in the vehicular edge computing (VEC) system for a vision of connected and autonomous vehicles. In this article, we review and present the concept of FL and introduce a general architecture of FL-assisted VEC to advance development of FL in the vehicular network. The enabling technologies for designing such a system are discussed and, with a focus on the vehicle selection algorithm, performance evaluations are conducted. Recommendations on future research directions are highlighted as well. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

16. Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflection

Author

Ge, Wenhang, Hu, Tao, Zhao, Haoyu, Liu, Shu, Chen, Ying-Cong, Ge, Wenhang, Hu, Tao, Zhao, Haoyu, Liu, Shu, and Chen, Ying-Cong

Abstract

Neural implicit surface learning has shown significant progress in multi-view 3D reconstruction, where an object is represented by multilayer perceptrons that provide continuous implicit surface representation and view-dependent radiance. However, current methods often fail to accurately reconstruct reflective surfaces, leading to severe ambiguity. To overcome this issue, we propose Ref-NeuS, which aims to reduce ambiguity by attenuating the effect of reflective surfaces. Specifically, we utilize an anomaly detector to estimate an explicit reflection score with the guidance of multiview context to localize reflective surfaces. Afterward, we design a reflection-aware photometric loss that adaptively reduces ambiguity by modeling rendered color as a Gaussian distribution, with the reflection score representing the variance. We show that together with a reflection direction-dependent radiance, our model achieves high-quality surface reconstruction on reflective surfaces and outperforms the state-of-the-arts by a large margin. Besides, our model is also comparable on general surfaces. © 2023 IEEE.

Published
2023

29. GaTector: A Unified Framework for Gaze Object Prediction

Author

Wang, Binglu, Hu, Tao, Li, Baoshan, Chen, Xiaojuan, and Zhang, Zhijie

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition
Abstract

Gaze object prediction is a newly proposed task that aims to discover the objects being stared at by humans. It is of great application significance but still lacks a unified solution framework. An intuitive solution is to incorporate an object detection branch into an existing gaze prediction method. However, previous gaze prediction methods usually use two different networks to extract features from scene image and head image, which would lead to heavy network architecture and prevent each branch from joint optimization. In this paper, we build a novel framework named GaTector to tackle the gaze object prediction problem in a unified way. Particularly, a specific-general-specific (SGS) feature extractor is firstly proposed to utilize a shared backbone to extract general features for both scene and head images. To better consider the specificity of inputs and tasks, SGS introduces two input-specific blocks before the shared backbone and three task-specific blocks after the shared backbone. Specifically, a novel Defocus layer is designed to generate object-specific features for the object detection task without losing information or requiring extra computations. Moreover, the energy aggregation loss is introduced to guide the gaze heatmap to concentrate on the stared box. In the end, we propose a novel wUoC metric that can reveal the difference between boxes even when they share no overlapping area. Extensive experiments on the GOO dataset verify the superiority of our method in all three tracks, i.e. object detection, gaze estimation, and gaze object prediction., CVPR 2022, camera ready

Published
2022

30. Human-Object Interaction Detection via Disentangled Transformer

Author

Zhou, Desen, Liu, Zhichao, Wang, Jian, Wang, Leshan, Hu, Tao, Ding, Errui, and Wang, Jingdong

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition
Abstract

Human-Object Interaction Detection tackles the problem of joint localization and classification of human object interactions. Existing HOI transformers either adopt a single decoder for triplet prediction, or utilize two parallel decoders to detect individual objects and interactions separately, and compose triplets by a matching process. In contrast, we decouple the triplet prediction into human-object pair detection and interaction classification. Our main motivation is that detecting the human-object instances and classifying interactions accurately needs to learn representations that focus on different regions. To this end, we present Disentangled Transformer, where both encoder and decoder are disentangled to facilitate learning of two sub-tasks. To associate the predictions of disentangled decoders, we first generate a unified representation for HOI triplets with a base decoder, and then utilize it as input feature of each disentangled decoder. Extensive experiments show that our method outperforms prior work on two public HOI benchmarks by a sizeable margin. Code will be available., Accepted by CVPR2022

Published
2022

36. Smoothed L0-Constraint Dictionary Learning for Low-Dose X-Ray CT Reconstruction

Author

Temitope Emmanuel Komolafe, Gang Yuan, Kang Wang, Cheng Zhang, Jian Zheng, Qiang Du, Ming Li, Xiaodong Yang, and Hu Tao

Subjects
Computer tomography (CT), General Computer Science, Computer science, General Engineering, streaking artifacts and bias, Regularization (mathematics), 030218 nuclear medicine & medical imaging, Image (mathematics), Constraint (information theory), 03 medical and health sciences, 0302 clinical medicine, Image texture, smoothed L₀ norm-constraint dictionary learning (SL0-DL), low dose, 030220 oncology & carcinogenesis, Norm (mathematics), General Materials Science, Noise (video), lcsh:Electrical engineering. Electronics. Nuclear engineering, Representation (mathematics), Algorithm, lcsh:TK1-9971
Abstract

The iterative algorithms of computed tomography (CT) reconstruction derived from the dictionary learning (DL) regularization have been developed to make high quality recovery from the under-sampled data acquired by a low dose protocol. However, when they are applied to noisy data with low sampling rate, streaking artifacts and bias tends to appear in early iteration results. Since the dictionary is over-complete, the artifacts and bias can also be represented well by the dictionary, resulting in the reservation of these unexpected structures in the final image. We proposed a smoothed L0 norm-constraint dictionary learning (SL0-DL) algorithm to deal with these unexpected structures. For the proposed algorithm, we introduce smoothed-L0 norm regularization to the objective function. In each iteration process, the intermediate image generated by the DL representation will be smoothed using SL0 norm, and then the smoothed image is used to update the output of this iteration. The raw data from both the numerical simulation and actual CT acquisition are used to test the performances of the proposed SL0-DL method. Experimental results demonstrate that the proposed method performs better than other competing algorithms with better noise and artifacts suppression performance while preserving image texture details. And the results show a significant improvement in the quality of the reconstructed image, which demonstrates that the proposed algorithm is really effective.

Published
2020

37. Research on Adaptive Energy-Efficient Reference Broadcasting Synchronization

Author

Jianjun Tan, Zhu Li, Hu Tao, Yi Jinqiao, Yixin Su, Xianbo Sun, and Yong Huang

Subjects
state monitoring, General Computer Science, Computer science, Real-time computing, 0211 other engineering and technologies, 02 engineering and technology, Broadcasting, Synchronization, Reduction (complexity), Broadcasting (networking), Synchronization (computer science), 0202 electrical engineering, electronic engineering, information engineering, General Materials Science, time synchronization, Edge computing, 021103 operations research, business.industry, Photovoltaic system, General Engineering, 020206 networking & telecommunications, Energy consumption, WSN, AERBS, lcsh:Electrical engineering. Electronics. Nuclear engineering, Large-scale photovoltaic module, business, Wireless sensor network, lcsh:TK1-9971, Efficient energy use
Abstract

For large-scale photovoltaic module monitoring, wireless sensor network technology has been widely used, in which time synchronization is a significant factor. However, there are still outstanding issues in existing time synchronization algorithms for large-scale networking. To this end, this paper proposes a new Adaptive Energy-efficient Reference Broadcasting Synchronization method (AERBS) for wireless sensor networks, aiming to reduce the energy consumption whilst improving the synchronization precision. Moreover, the proposed method can reduce the number of synchronization information exchanges and self-adaptively determine the re-synchronization cycle. Simulation experiments demonstrate that our proposed AERBS outperforms the existing ERBS algorithm, in terms of reducing the synchronization number and the achieved reduction in energy consumption. The algorithm herein can be fully applied in the monitoring of large-scale photovoltaic module. At the same time, as a typical application of IoT (Internet of Things), it also provides a reference for distributed edge computing.

Published
2020

42. Reliability Improvement to UPFC With Routine Test to the Abnormal State.

Author

Li, Shenghu, Hu, Tao, and Li, Yikai

Subjects
*ELECTRICAL load, *MATRIX converters, *RADIO frequency, *VOLTAGE control
Abstract

The unified power flow controller (UPFC) helps to control the power flow, but its outage due to the abnormal state is a threat to power systems. In this paper, based on the proportion of the random failure, the transition rates of the abnormal state are newly derived. The impact of the routine test (RT) on the transition rates is quantified. The state space models of the UPFC based on voltage-source converter (VSC) and modular multilevel converter (MMC) are extended with the states introduced by the RT. The frequency and duration method is used to aggregate the states. The sensitivities of the availability and outage frequency of the UPFC with respect to the failure rates of the components are newly derived to find the vulnerable component and the optimal RT interval. The numerical results show that the RT reduces the probability of the abnormal state, reduces the failure duration, and improves the availability of the UPFC. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results