检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Meng, Lingchen Dai, Xiyang Chen, Yinpeng Zhang, Pengchuan Chen, Dongdong Liu, Mengchen Wang, Jianfeng Wu, Zuxuan Yuan, Lu Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Microsoft United States

Combining multiple datasets enables performance boost on many computer vision tasks. But similar trend has not been witnessed in object detection when combining multiple datasets due to two inconsistencies among detection datasets: taxonomy difference and domain gap. In this paper, we address these challenges by a new design (named Detection Hub) that is dataset-aware and category-aligned. It not only mitigates the dataset inconsistency but also provides coherent guidance for the detector to learn across multiple datasets. In particular, the dataset-aware design is achieved by learning a dataset embedding that is used to adapt object queries as well as convolutional kernels in detection heads. The categories across datasets are semantically aligned into a unified space by replacing one-hot category representations with word embedding and leveraging the semantic coherence of language embedding. Detection Hub fulfills the benefits of large data on object detection. Experiments demonstrate that joint training on multiple datasets achieves significant performance gains over training on each dataset alone. Detection Hub further achieves SoTA performance on UODB benchmark with wide variety of datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Automatic Construction of Classification Dimensions on Texts

SSRN

引用

SSRN 2022年

作者： Ma, Bing Zhuge, Hai The Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China The Great Bay University Dongguan China

A way to efficiently manage large sets of texts is to construct multiple dimensions on texts and manage the texts from different dimensions. An approach to automatically constructing classification dimensions is to generate class trees on texts and a label for each class so that texts can be efficiently managed based on the generated trees and labels. The key issue is to classify texts into classes according to common semantics defined by a representation model of text. The vector space model represents texts in a space of high dimensions as it regards word as dimension. The classification methods based on the vector space is to classify texts according to the calculation of the distance between vectors of texts. However, the characteristics of the distances like the triangle inequality of distances is unsuitable to restrict the semantic relations between texts and measure the similarity of a set of more than two texts. The frequently occurred common words within a set of texts is a way to represent the texts but the traditional frequent-term-set based text clustering approaches generate a wide range of frequent term sets from one word to a maximum set of words satisfying the pre-determined minimum support degree, the initial classes it generates are not in line with the original classes, and it often generates the meaningless initial classes according to frequent-term sets. Topic model is not suitable for generating class trees on texts as topics are represented by probability distribution on all words. This paper proposes an approach to use common words of texts to represent the texts and calculates the similarity of a class of texts by calculating the sum of the weights of common words of the class where the common words of a class of texts represent the common semantics of these texts and the idea is in line with human classification of texts. Based on the common words representation, a bottom-up text clustering approach is proposed to construct class trees of t

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

MotionEditor: Editing Video Motion via Content-Aware Diffusion

arXiv

引用

arXiv 2023年

作者： Tu, Shuyuan Dai, Qi Cheng, Zhi-Qi Hu, Han Han, Xintong Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Microsoft Research Asia China Carnegie Mellon University United States Huya Inc China

Existing diffusion-based video editing models have made gorgeous advances for editing attributes of a source video over time but struggle to manipulate the motion information while preserving the original protagonist’s appearance and background. To address this, we propose MotionEditor, a diffusion model for video motion editing. MotionEditor incorporates a novel content-aware motion adapter into ControlNet to capture temporal motion correspondence. While ControlNet enables direct generation based on skeleton poses, it encounters challenges when modifying the source motion in the inverted noise due to contradictory signals between the noise (source) and the condition (reference). Our adapter complements ControlNet by involving source content to transfer adapted control signals seamlessly. Further, we build up a two-branch architecture (a reconstruction branch and an editing branch) with a high-fidelity attention injection mechanism facilitating branch interaction. This mechanism enables the editing branch to query the key and value from the reconstruction branch in a decoupled manner, making the editing branch retain the original background and protagonist appearance. We also propose a skeleton alignment algorithm to address the discrepancies in pose size and position. Experiments demonstrate the promising motion editing ability of MotionEditor, both qualitatively and quantitatively. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation

arXiv

引用

arXiv 2022年

作者： Chen, Haoran Han, Xintong Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China Huya Inc China

Most existing methods for unsupervised domain adaptation (UDA) rely on a shared network to extract domain-invariant features. However, when facing multiple source domains, optimizing such a network involves updating the parameters of the entire network, making it both computationally expensive and challenging, particularly when coupled with min-max objectives. Inspired by recent advances in prompt learning that adapts high-capacity models for downstream tasks in a computationally economic way, we introduce Multi-Prompt Alignment (MPA), a simple yet efficient framework for multi-source UDA. Given a source and target domain pair, MPA first trains an individual prompt to minimize the domain gap through a contrastive loss. Then, MPA denoises the learned prompts through an auto-encoding process and aligns them by maximizing the agreement of all the reconstructed prompts. Moreover, we show that the resulting subspace acquired from the auto-encoding process can easily generalize to a streamlined set of target domains, making our method more efficient for practical usage. Extensive experiments show that MPA achieves state-of-the-art results on three popular datasets with an impressive average accuracy of 54.1% on DomainNet. Code is available at https://***/HaoranChen/Multi-Prompt-Alignment-for-MSUDA. © 2022, CC BY.

关键词： signal encoding

来源：评论

学校读者我要写书评

暂无评论

Multi-Layer Visual Perception for No-Reference Image Quality Assessment

Multi-Layer Visual Perception for No-Reference Image Quality...

引用

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： Junwei Qi Yingzhen Wang Qingchun Wang Yingsong Li College of Computer Science and Technology Harbin Engineering University Harbin China College of Information and Communication Engineering Harbin Engineering University Harbin China Shanghai Yanding Information Technology Co. Ltd. Shanghai China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei Anhui China

In this work, we propose a no-reference image quality evaluation approach, aiming to solve the problem that the traditional convolutional neural network is insufficient to express the global information of the image. Therefore, in order to make the captured image features have the coherence of global context information, we combine a Transformer structure widely used in NLP (natural language processing) with the traditional CNN to realize the attention mechanism in the human visual perception characteristics. Firstly, the self-attention mechanism of Transformer is used to learn the global representation of the image from the multi-layer features extracted from different levels of CNN. Additionally, to forecast the ultimate image quality score, the global and local attributes are combined. Finally, the proposed algorithm is evaluated on three public datasets commonly used in CSIQ [1], TID2013 [2] and LIVE [3]. Compared with eight traditional no-reference image quality evaluation algorithms and five methods based on deep learning, the proposed algorithm achieves competitive results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Capacitive Flexible Three-Axis Force Tactile Sensor Based on Porous Composite Dielectric Layer for Dexterous Robotic Manipulation

SSRN

引用

SSRN 2022年

作者： Guo, Xiaohui Li, Cuicui Zheng, Guoqing Wang, Jingyi Tang, Guopeng Hong, Weiqiang Wang, Yifan Pan, Mingqi Xu, Yaohua Hong, Qi Zhao, Yunong Zhang, Hongwei Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China Anhui Province Key Laboratory of Target Recognition and Feature Extraction Lu’an237010 China East China Institute of Photo-electron ICs Jiangsu Suzhou215163 China

Flexible tactile sensors that can detect both normal and tangential forces with good flexibility, high sensitivity, wide detection range and rapid dynamic response are imminently needed for electronic skin (e-skin). Thus, we innovatively demonstrated a flexible capacitive three-axis tactile sensor with satisfactory flexibility, high sensitivity (0.693 N -1 at 0-5 N and 0.483 N -1 at 5-14 N for normal force, as well as 0.551 N -1 at 0-2 N and 0.481 N -1 at 2-6 N for tangential force), fast response time (30 ms) and a low hysteresis (6.8%), which was fabricated by combining advanced sensor structure with porous composite dielectric layer in a simple and low-cost three-dimensional (3D) printing method and layer-by-layer (LBL) self-assembly method. The working principle and sensing characteristics of the sensor were elaborated by establishing the theoretical mechanism, and further simulation verification was carried out by the finite element modeling (FEM). Our sensor was employed in soft manipulator grasping and gamepad rotation, suggestive of the application potential of the three-axis force tactile sensor as flexible e-skin in the field of tactile sensing. Our work may pave a way to softness haptic perception strategy, which could be widely utilized in e-skin, soft robot, dexterous robotic manipulation, and intelligent prosthesis. © 2022, The Authors. All rights reserved.

关键词： Composite materials

来源：评论

学校读者我要写书评

暂无评论

Super-Broadband Rectifier With Wide-band Resistance Compression Network and Harmonic Cycling for RF-Harvesting

TechRxiv

引用

TechRxiv 2022年

作者： Liu, Xin Zhang, Dawei Li, Yingsong Huang, Zhixiang College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China Anhui Province Key Laboratory of Target Recognition and Feature Extraction Lu'An230088 China

In this paper, a super-broadband (SBB) rectifier using a wideband resistance compression network (WRCN) and harmonic cycling is proposed, simulated, fabricated, measured and analyzed in detail for the harvesting of ambient Radio frequency (RF) energy. Meanwhile, impedance compression and matching are achieved to implement the SBB using WRCN and impedance operation networks. Additionally, harmonic cycling structure and bending technology are employed to improve the power conversion efficiency (PCE) and reduce the size, respectively. For demonstration, a prototype of the proposed rectifier is fabricated and measured. The measured results are in good accordance with the simulated ones, indicating that the rectifier can provide high efficiency and ultra-broadband rectification characteristics. A PCE over 50% is realized at 3.5 GHz with an input power range of 6–24 dBm, and a PCE of 75% is obtained at an input power of 18 dBm. The PCE is greater than 50% at 17 dBm with an input frequency of 2.7–4.6 GHz. This work can find significant applications in the development of RF-harvesting. © 2022, CC BY.

关键词： Harvesting

来源：评论

学校读者我要写书评

暂无评论

Motion Guided Region Message Passing for Video Captioning

Motion Guided Region Message Passing for Video Captioning

引用

International Conference on Computer Vision (ICCV)

作者： Shaoxiang Chen Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai Collaborative Innovation Center on Intelligent Visual Computing

ISBN: (纸本)9781665428132

Video captioning is an important vision task and has been intensively studied in the computer vision community. Existing methods that utilize the fine-grained spatial information have achieved significant improvements, however, they either rely on costly external object detectors or do not sufficiently model the spatial/temporal relations. In this paper, we aim at designing a spatial information extraction and aggregation method for video captioning without the need of external object detectors. For this purpose, we propose a Recurrent Region Attention module to better extract diverse spatial features, and by employing Motion-Guided Cross-frame Message Passing, our model is aware of the temporal structure and able to establish high-order relations among the diverse regions across frames. They jointly encourage information communication and produce compact and powerful video representations. Furthermore, an Adjusted Temporal Graph Decoder is proposed to flexibly update video features and model high-order temporal relations during decoding. Experimental results on three benchmark datasets: MSVD, MSR-VTT, and VATEX demonstrate that our proposed method can outperform state-of-the-art methods.

关键词： Location awareness Computer vision Visualization Message passing Computational modeling Detectors Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Efficient Facial Landmark Detector by Knowledge Distillation

Efficient Facial Landmark Detector by Knowledge Distillation

引用

International Conference on Automatic Face and Gesture Recognition

作者： Yuyang Sha Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing CAS China

ISBN: (纸本)9781665431774

Facial landmark detection aims to locate some predefined points on human face images, which is the basis of many facial analysis tasks and applications. Compared with traditional methods, facial landmark detector based on deep learning has made significant progress in accuracy and efficiency. However, the model parameters and computational cost have not received enough attention, leading to the algorithm facing many challenges in practical applications. In this paper, we propose a novel method named efficient facial landmark detector (EFLD), which significantly compresses the model size and computational cost while achieving superior performance compared with state-of-the-art frameworks. We introduce a knowledge distillation framework suitable for facial landmark detection, which can transfer geometric information from the pre-trained teacher model to the lightweight student model. In addition, we integrate adversarial learning into the knowledge distillation framework to guide the student model to imitate the heatmap distribution generated by the teacher model. Extensive experiments demonstrate the superior performance of our approach against state-of-the-art methods.

关键词： Knowledge engineering Heating systems Computational modeling Face recognition Neural networks Detectors Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

An intelligent self-sustained RAN slicing framework for diverse service provisioning in 5G-beyond and 6G networks

引用

intelligent and Converged Networks 2020年第3期1卷 281-294页

作者： Jie Mei Xianbin Wang Kan Zheng Electrical and Computer Engineering Western UniversityLondonON N6A 5B9Canada Intelligent Computing and Communication(IC2)Lab Wireless Signal Processing and Network(WSPN)LabKey Laboratory of Universal Wireless CommunicationMinistry of EducationBeijing University of Posts and Telecommunications(BUPT)Beijing 100876China

Network slicing is a key technology to support the concurrent provisioning of heterogeneous Quality of Service(QoS)in the 5th Generation(5G)-beyond and the 6th Generation(6G)***,effective slicing of Radio Access Network(RAN)is very challenging due to the diverse QoS requirements and dynamic conditions in the 6G *** this paper,we propose a self-sustained RAN slicing framework,which integrates the self-management of network resources with multiple granularities,the self-optimization of slicing control performance,and self-learning together to achieve an adaptive control strategy under unforeseen network *** proposed RAN slicing framework is hierarchically structured,which decomposes the RAN slicing control into three levels,i.e.,network-level slicing,next generation NodeB(gNodeB)-level slicing,and packet scheduling level *** the network level,network resources are assigned to each gNodeB at a large timescale with coarse resource *** the gNodeB-level,each gNodeB adjusts the configuration of each slice in the cell at the large *** the packet scheduling level,each gNodeB allocates radio resource allocation among users in each network slice at a small ***,we utilize the transfer learning approach to enable the transition from a model-based control to an autonomic and self-learning RAN slicing *** the proposed RAN slicing framework,the QoS performance of emerging services is expected to be dramatically enhanced.

关键词： Radio Access Network(RAN) network slicing network resource management intelligent network

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：