检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Qipeng Zhu Jie Chen Junping Zhang Jian Pu Shanghai Key Lab of Intelligent Information Processing and School of Computer Science Fudan University Shanghai China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Graph neural networks (GNNs) demonstrate impressive performance in graph classification, albeit exhibiting challenges in terms of generalizability and robustness. Despite its proven efficacy in enhancing the robustness and generalizability of GNNs, ensemble learning encounters practical limitations due to its extensive computational and memory requirements. This paper presents a novel low-cost ensemble learning method for graph classification, which utilizes a Graph Multi-Input and Multi-Output framework (G-MIMO) to allow multiple sub-networks within a single GNN simultaneously treated. Extensive experiments demonstrate that G-MIMO effectively enhances GNN performance across multiple graph classification tasks without introducing much computational overhead. G-MIMO outperforms existing graph augmentations and ensemble approaches, delivering a 3.33% and 4.25% increase in average accuracy over standard GCN and GIN models, respectively. The source code has been released at https://***/smurf-1119/GMIMO.

关键词： Representation learning Costs Accuracy Source coding Computational modeling Memory management Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation 38

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmenta...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SocialCache: A Pervasive Social-Aware Caching Strategy for Self-Operated Content Delivery Networks of Online Social Networks

SocialCache: A Pervasive Social-Aware Caching Strategy for S...

引用

IEEE International Conference on Communications (ICC)

作者： Tiancheng Guo Yuke Ma Mengying Zhou Xin Wang Jun Wu Yang Chen Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China

Online Social Networks (OSNs) play a significant role in people's daily life. Increasing OSN traffic promotes the requirement for building self-operated Content Delivery Networks (CDNs) to deliver OSN media data efficiently and reduce traffic costs. OSN data in CDNs is heavily influenced by social connectivity, such as friendships. To reduce CDN network traffic by better using social connectivity information, we propose SocialCache, a pervasive social-aware caching strategy in self-operated CDNs. SocialCache supports several social connectivity metric options that reflect the importance of the OSN users and the popularity of the media files. Through the improvement of the cache replacement algorithm in the CDN node and the communication design between nodes, SocialCache realizes the optimization of network traffic. Worth mentioning, SocialCache can easily integrate into mainstream CDN architectures while protecting user privacy. We implement SocialCache on Mininet, using real-world network measurements for CDN hierarchy and a hill-climbing algorithm for parameter selection. SocialCache outperforms a range of state-of-the-art baselines on three real-world OSN datasets. On the Twitter dataset, SocialCache reduces the network traffic volume by 6.40% and improves the cache hit ratio by 14.22%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

STDNet: Spatio-Temporal Decomposed Network for Video Grounding

STDNet: Spatio-Temporal Decomposed Network for Video Groundi...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Xu, Yuanwu Zhang, Yuejie Feng, Rui Zhao, Rui-Wei Zhang, Tao Lu, Xuequan Gao, Shang School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing China Academy for Engineering and Technology Fudan University China School of Information Management and Engineering Shanghai University of Finance and Economics Shanghai Key Laboratory of Financial Information Technology China School of Information Technology Deakin University Australia

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Previous methods for video grounding treated either the query or the video as a whole, while neglecting their respective semantics in the orthogonal space and time dimensions. Since spatial semantics appears frequently in a video, temporal semantics is more discriminative and deserves more attention. Based on such considerations, we propose a novel Spatio-Temporal Decomposed Network (STDNet) which decomposes the query and the video into their spatial and temporal semantics, respectively. Specifically, spatial and temporal words are selected from the query, and the video is split into two pathways. Spatial cross-modal attention is computed first and serves as prior knowledge for temporal attention. A new localization strategy is also devised which regresses the segment's start conditioned on the end and essentially breaks the independence assumption made in previous methods. Experimental results on three public benchmark datasets show that our STDNet outperforms the state-of-the-art methods. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Semantic-Driven Saliency-Context Separation for Video Captioning

Semantic-Driven Saliency-Context Separation for Video Captio...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Jing, Heming Zhang, Yuejie Feng, Rui Zhao, Rui-Wei Zhang, Tao Lu, Xuequan Gao, Shang School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University China Fudan University Academy for Engineering and Technology China School of Information Management and Engineering Shanghai Key Laboratory of Financial Information Technology Shanghai University of Finance and Economics China School of Information Technology Deakin University Australia

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Video captioning aims at generating a natural language de-scription for a given video clip including not only salient sce-narios but also contextual scenarios. The former reveal the highlight of a video and are usually the focus of most existing captioning methods. The latter, however, are not well ex-plored and even ignored easily, though they may provide cer-tain detailed and latent information that can help with a better understanding of the video. To effectively exploit the infor-mation contained in both, a novel video captioning network is proposed. It has two key modules: Cross-Modality Selection (CMS) and Saliency-Context Adaptive Decoder (SCAD). Specifically, CMS mainly focuses on utilizing the semantic information to distinguish saliency and context. Meanwhile, SCAD adaptively identifies both the saliency and context to generate more detailed and precise captions. Experiments on two benchmark datasets, i.e., MSVD and MSR-VTT, demon-strate the effectiveness of our model through the comparison with state-of-the-art methods. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Hiren: Towards Higher Supervision Quality Forbetter Scene Text Image Super-Resolution

SSRN

引用

SSRN 2024年

作者： Zhao, Minyi Xu, Yi Li, Bingjia Wang, Jie Guan, Jihong Zhou, Shuigeng Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China ByteDance Inc China Department of Computer Science and Technology Tongji University China

Scene text image super-resolution (STISR) is an important pre-processing technique for text recognition from low-resolution scene images. Nowadays, various methods have been proposed to extract text-specific information from high-resolution (HR) images to supervise STISR model training. However, due to uncontrollable factors (e.g. shooting equipment, focus, and environment) in manually photographing HR images, the quality of HR images cannot be guaranteed, which unavoidably impacts STISR performance. Observing the quality issue of HR images, in this paper we propose a novel idea to boost STISR by first enhancing the quality of HR images and then using the enhanced HR images as supervision to do STISR. Concretely, we develop a new STISR framework, called High-Resolution ENhancement (HiREN) that consists of two branches and a quality estimation module. The first branch is developed to recover the low-resolution (LR) images, and the other is an HR quality enhancement branch aiming at generating high-quality (HQ) text images based on the HR images to provide more accurate supervision to the LR images. As the degradation from HQ to HR may be diverse, and there is no pixel-level supervision for HQ image generation, we design a kernel-guided enhancement network to handle various degradation, and exploit the feedback from a recognizer and text-level annotations as weak supervision signal to train the HR enhancement branch. Then, a quality estimation module is employed to evaluate the qualities of HQ images, which are used to suppress the erroneous supervision information by weighting the loss of each image. Extensive experiments on TextZoom show that HiREN can work well with most existing STISR methods and significantly boost their performances. © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

CMC_v2: Towards More Accurate COVID-19 Detection with Discriminative Video Priors 17th

CMC_v2: Towards More Accurate COVID-19 Detection with Discr...

引用

17th European Conference on computer Vision, ECCV 2022

作者： Hou, Junlin Xu, Jilan Zhang, Nan Wang, Yi Zhang, Yuejie Zhang, Xiaobo Feng, Rui School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China Shanghai AI Laboratory Shanghai China National Children’s Medical Center Children’s Hospital of Fudan University Shanghai China

ISBN: (纸本)9783031250811

This paper presents our solution for the 2nd COVID-19 Competition, occurring in the framework of the AIMIA Workshop at the European Conference on computer Vision (ECCV 2022). In our approach, we employ the winning solution last year which uses a strong 3D Contrastive Mixup Classification network (CMC_v1) as the baseline method, composed of contrastive representation learning and mixup classification. In this paper, we propose CMC_v2 by introducing natural video priors to COVID-19 diagnosis. Specifically, we adapt a pre-trained (on video dataset) video transformer backbone to COVID-19 detection. Moreover, advanced training strategies, including hybrid mixup and cutmix, slice-level augmentation, and small resolution training are also utilized to boost the robustness and the generalization ability of the model. Among 14 participating teams, CMC_v2 ranked 1st in the 2nd COVID-19 Competition with an average Macro F1 Score of 89.11%. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

LCGen: mining in low-certainty generation for view-consistent text-to-3D 24

LCGen: mining in low-certainty generation for view-consisten...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Zeng Tao Tong Yang Junxiong Lin Xinji Mai Haoran Wang Beining Wang Enyu Zhou Yan Wang Wenqiang Zhang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China School of Computer Science Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China and Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China

ISBN: (纸本)9798331314385

The Janus Problem is a common issue in SDS-based text-to-3D methods. Due to view encoding approach and 2D diffusion prior guidance, the 3D representation model tends to learn content with higher certainty from each perspective, leading to view inconsistency. In this work, we first model and analyze the problem, visualizing the specific causes of the Janus Problem, which are associated with discrete view encoding and shared priors in 2D lifting. Based on this, we further propose the LCGen method, which guides text-to-3D to obtain different priors with different certainty from various viewpoints, aiding in view-consistent generation. Experiments have proven that our LCGen method can be directly applied to different SDS-based text-to-3D methods, alleviating the Janus Problem without introducing additional information, increasing excessive training burden, or compromising the generation effect. Project page is https://***/zeng-tao/LCGen.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wearable and interactive multicolored photochromic fiber display

引用

Light(science & Applications) 2024年第3期13卷 454-465页

作者： Pan Li Yuwei Wang Xiaoxian He Yuyang Cui Jingyu Ouyang Ju Ouyang Zicheng He Jiayu Hu Xiaojuan Liu Hang Wei Yu Wang Xiaoling Lu Qian Ji Xinyuan Cai Li Liu Chong Hou Ning Zhou Shaowu Pan Xiangru Wang Huamin Zhou Cheng-Wei Qiu Yan-Qing Lu Guangming Tao State Key Laboratory of Material Processing and Die&Mould Technology School of Materials Science and Engineering and Wuhan National Laboratory for OptoelectronicsHuazhong University of Science and TechnologyWuhan 430074China Key Laboratory of Vascular Aging(HUST) Ministry of EducationWuhan 430030China School of Optoelectronic Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore National Laboratory of Solid State Microstructures Key Laboratory of Intelligent Optical Sensing and ManipulationCollege of Engineering and Applied Sciencesand Collaborative Innovation Center of Advanced MicrostructuresNanjing UniversityNanjing 210023China School of Performing Arts Wuhan Conservatory of MusicWuhan 430060China School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China School of Architecture and Urban Planning Huazhong University of Science and TechnologyWuhan 430074China School of Fashion Beijing Institute of Fashion TechnologyBeijing 100029China School of Optical and Electronic Information Huazhong University of Science and TechnologyWuhan 430074China Tongji Medical College Huazhong University of Science and TechnologyWuhan 430074China State Key Laboratory for Modification of Chemical Fibers and Polymer Materials College of Materials Science and EngineeringDonghua UniversityShanghai 201620China

Endowing flexible and adaptable fiber devices with light-emitting capabilities has the potential to revolutionize the current design philosophy of intelligent,wearable interactive ***,significant challenges remain in developing fiber devices when it comes to achieving uniform and customizable light effects while utilizing lightweight ***,we introduce a mass-produced,wearable,and interactive photochromic fiber that provides uniform multicolored light *** designed independent waveguides inside the fiber to maintain total internal reflection of light as it traverses the *** impact of excessive light leakage on the overall illuminance can be reduced by utilizing the saturable absorption effect of fluorescent materials to ensure light emission uniformity along the transmission *** addition,we coupled various fluorescent composite materials inside the fiber to achieve artificially controllable spectral radiation of multiple color systems in a single *** prepared fibers on mass-produced kilometer-long using the thermal drawing *** fibers can be directly integrated into daily wearable devices or clothing in various patterns and combined with other signal input components to control and display patterns as *** work provides a new perspective and inspiration to the existing field of fiber display interaction,paving the way for future human–machine integration.

关键词： fiber interactive colored

来源：评论

学校读者我要写书评

暂无评论

ControlCap: Controllable Captioning via No-Fuss Lexicon

ControlCap: Controllable Captioning via No-Fuss Lexicon

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Qiujie Xie Qiming Feng Yuejie Zhang Rui Feng Tao Zhang Shang Gao School of Computer Science Shanghai Key Lab of Intelligent Information Processing Fudan University China School of Information Management and Engineering Shanghai University of Finance and Economics China School of Information Technology Deakin University Australia

Controllable captioning has received much attention in recent years. Although substantial progress has been made, existing methods still face challenges such as high training costs, intricate control signals and limited control capabilities. To address these issues, we propose a straightforward and unified framework called ControlCap. It uses a no-fuss lexicon as control signal and controls the style and content of visual descriptions through Soft Guidance (a global guide to the caption distribution) and Hard Force (integrating signals without additional training). Extensive experiments, both quantitative and qualitative, have been conducted on three benchmark captioning tasks. Results demonstrate the control ability of ControlCap: it can produce controlled captions that are coherent and diverse while keeping the core content intact.

关键词：

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：