检索结果-内蒙古大学图书馆

FDVTS’s Solution for 2nd COV19D Competition on COVID-19 Detection and Severity Analysis

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hou, Junlin Xu, Jilan Feng, Rui Zhang, Yuejie School of Computer Science Shanghai Key Lab of Intelligent Information Processing Fudan University China

This paper presents our solution for the 2nd COVID-19 Competition, occurring in the framework of the AIMIA Workshop in the European Conference on computer Vision (ECCV 2022). In our approach, we employ an effective 3D Contrastive Mixup Classification network for COVID-19 diagnosis on chest CT images, which is composed of contrastive representation learning and mixup classification. For the COVID-19 detection challenge, our approach reaches 0.933 macro F1 score on 484 validation CT scans, which significantly outperforms the baseline method by 16.3%. In the COVID-19 severity detection challenge, our approach achieves 0.770 macro F1 score on 61 validation samples, which also surpasses the baseline by 14%. © 2022, CC BY.

关键词： COVID-19

Predicting Token Impact Towards Efficient Vision Transformer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Hong Yang, Su Huang, Xiaoke Zhang, Weishan Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China School of Computer Science and Technology China University of Petroleum China

Token filtering to reduce irrelevant tokens prior to self-attention is a straightforward way to enable efficient vision Transformer. This is the first work to view token filtering from a feature selection perspective, where we weigh the importance of a token according to how much it can change the loss once masked. If the loss changes greatly after masking a token of interest, it means that such a token has a significant impact on the final decision and is thus relevant. Otherwise, the token is less important for the final decision, so it can be filtered out. After applying the token filtering module generalized from the whole training data, the token number fed to the self-attention module can be obviously reduced in the inference phase, leading to much fewer computations in all the subsequent self-attention layers. The token filter can be realized using a very simple network, where we utilize multi-layer perceptron. Except for the uniqueness of performing token filtering only once from the very beginning prior to self-attention, the other core feature making our method different from the other token filters lies in the predictability of token impact from a feature selection point of view. The experiments show that the proposed method provides an efficient way to approach a light weighted model after optimized with a backbone by means of fine tune, which is easy to be deployed in comparison with the existing methods based on training from scratch. © 2023, CC BY.

关键词： Feature extraction

SIAM: A Simple Alternating Mixer for Video Prediction

学校读者我要写书评

暂无评论

SIAM: A Simple Alternating Mixer for Video Prediction

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xin Zheng Ziang Peng Yuan Cao Hongming Shan Junping Zhang School of Computer Science Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China Department of Aeronautics and Astronautics 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

Video prediction, predicting future frames from the previous ones, has broad applications such as autonomous driving and weather forecasting. Existing state-of-the-art methods typically focus on extracting either spatial, temporal, or spatiotemporal features from videos. Different feature focuses, resulting from different network architectures, may make the resultant models excel at some video prediction tasks but perform poorly on others. Towards a more generic video prediction solution, we explicitly model these features in a unified encoder-decoder framework and propose a simple alternating Mixer (SIAM). The novelty of SIAM lies in the design of dimension alternating mixing (DaMi) blocks, which can model spatial, temporal, and spatiotemporal features through alternating the dimensions of the feature maps. Extensive experimental results demonstrate the superior performance of the proposed SIAM on four benchmark video datasets covering both synthetic and real-world scenarios.

关键词： Weather forecasting Predictive models Streaming media Network architecture Benchmark testing Feature extraction Spatiotemporal phenomena

Question Answering Systems Based on Pre-trained Language Models: Recent Progress 13th

学校读者我要写书评

暂无评论

Question Answering Systems Based on Pre-trained Language Mo...

13th IFIP TC 12 International Conference on intelligent information processing, IIP 2024

作者： Luo, Xudong Luo, Ying Yang, Binxia School of Computer Science and Engineering Guangxi Normal University Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology of Ministry of Education Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining and Security Guilin541004 China

ISBN: (纸本)9783031578076

Although Pre-trained Language Model (PLM) ChatGPT as a Question-Answering System (QAS) is so successful, it is still necessary to study further the QASs based on PLMs. In this paper, we survey state-of-the-art systems of this kind, identify the issues that current researchers are concerned about, explore various PLM-based methods for addressing them, and compare their pros and cons. We also discuss the datasets used for fine-tuning the corresponding PLMs and evaluating these PLM-based methods. Moreover, we summarise the criteria for evaluating these methods and compare their performance against these criteria. Finally, based on our analysis of the state-of-the-art PLM-based methods for QA, we identify some challenges for future research. © IFIP International Federation for information processing 2024.

关键词： Computational linguistics

Uncertainty-Aware Dynamic Fusion for Multimodal Clinical Prediction Tasks

学校读者我要写书评

暂无评论

Uncertainty-Aware Dynamic Fusion for Multimodal Clinical Pre...

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

作者： Jiayu Guo Ying Cheng Wen He Yuejie Zhang Rui Feng Xiaobo Zhang School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China National Children’s Medical Center Children’s Hospital of Fudan University Shanghai China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multimodal fusion offers significant potential for enhancing medical diagnosis, particularly in the Intensive Care Unit (ICU), where integrating diverse data sources is crucial. Traditional static fusion models often fail to account for sample-wise variations in modality importance, which can impact prediction accuracy. To address this issue, we propose a dynamic Uncertainty-Aware Weighting (UAW) strategy that adaptively adjusts the importance of different modalities based on their reliability. This strategy is coupled with an Expert Ensemble Fusion (EEF) module, which leverages self-attention mechanisms and modality-specific FeedForward Networks (FFNs) to preserve and integrate critical information from various modalities. The proposed method demonstrates its efficacy through extensive experiments on phenotype classification and mortality prediction tasks, showing improved accuracy and robustness in handling diverse clinical data.

关键词： Accuracy Phenotypes Soft sensors Mortality Signal processing Predictive models Robustness Medical diagnosis Speech processing X-ray imaging

Research on cross-chain and interoperability for blockchain system

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2021年第5期28卷 1-17,26页

作者： Li Ming Qiu Honglin Xu Quanqing Song Wenpeng Liu Baixiang Shanghai Key Laboratory of Intelligent Information Processing Fudan UniversityShanghai 200433China School of Computer Science Fudan UniversityShanghai 200433China China Electronics Standardization Institute Beijing 100007China Ant Group Hangzhou 310063China

At present, there is an urgent need for blockchain interoperability technology to realize interconnection between various blockchains, data communication and value transfer between blockchains, so as to break the ‘value silo’ phenomenon of each blockchain. Firstly, it lists what people understand about the concept of interoperability. Secondly, it gives the key technical issues of cross-chain, including cross-chain mechanism, interoperability, eventual consistency, and universality. Then, the implementation of each cross-chain key technology is analyzed, including Hash-locking, two-way peg, notary schemes, relay chain scheme, cross-chain protocol, and global identity system. Immediately after that, five typical cross-chain systems are introduced and comparative analysis is made. In addition, two examples of cross-chain programmability and their analysis are given. Finally, the current state of cross-chain technology is summarized from two aspects: key technology implementation and cross-chain application enforcement. The cross-chain technology as a whole has formed a centralized fixed mechanism, as well as a trend of modular design, and some of the solutions to mature applications were established in the relevant standards organizations, and the cross-chain technology architecture tends to be unified, which is expected to accelerate the evolution of the open cross-chain network that supports the real needs of the interconnection of all chains.

关键词： blockchain distributed ledger technology cross-chain interoperability Hash-locking notary relay multi-chain

Efficient Algorithms for Minimizing the Kirchhoff Index via Adding Edges

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhou, Xiaotian Zehmakan, Ahad N. Zhang, Zhongzhi Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Research Institute of Intelligent Complex Systems Fudan University Shanghai200433 China School of Computing Australian National University Canberra Australia

The Kirchhoff index, which is the sum of the resistance distance between every pair of nodes in a network, is a key metric for gauging network performance, where lower values signify enhanced performance. In this paper, we study the problem of minimizing the Kirchhoff index by adding edges. We first provide a greedy algorithm for solving this problem and give an analysis of its quality based on the bounds of the submodularity ratio and the curvature. Then, we introduce a gradient-based greedy algorithm as a new paradigm to solve this problem. To accelerate the computation cost, we leverage geometric properties, convex hull approximation, and approximation of the projected coordinate of each point. To further improve this algorithm, we use pre-pruning and fast update techniques, making it particularly suitable for large networks. Our proposed algorithms have nearly-linear time complexity. We provide extensive experiments on ten real networks to evaluate the quality of our algorithms. The results demonstrate that our proposed algorithms outperform the state-of-the-art methods in terms of efficiency and effectiveness. Moreover, our algorithms are scalable to large graphs with over 5 million nodes and 12 million edges. Copyright © 2025, The Authors. All rights reserved.

关键词： Consensus algorithm

Video Captioning via Relation-Aware Graph Learning

学校读者我要写书评

暂无评论

Video Captioning via Relation-Aware Graph Learning

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

作者： Yi Zheng Heming Jing Qiujie Xie 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

Recent neural models for video captioning usually employed an encoder-decoder framework. However, most approaches either neglected the spatial and temporal interactions between objects in a video or implicitly modelled the interactions, resulting in less desired performance. In this paper, we propose a novel relation-aware graph learning framework. It explicitly models both spatial and temporal relations for objects. In particular, a relation-aware graph is designed to depict the spatial relations between different objects in a scene. Parallelly, a temporal graph network is designed to perform relational reasoning for the same objects in adjacent frames. Features of both types of relations are learned and fused for the follow-up language decoder. Experiments on two bench-mark datasets show the effectiveness of our framework. It achieves state-of-the-art performance with CIDEr scores on MSVD and MSR-VTT.

关键词： Visualization Signal processing Cognition Acoustics Decoding Speech processing

DuMo: Dual Encoder Modulation Network for Precise Concept Erasure

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Han, Feng Chen, Kai Gong, Chao Wei, Zhipeng Chen, Jingjing Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China

The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copyright infringement. To address these concerns, previous methods safeguard the models by eliminating inappropriate concepts. Nonetheless, these models alter the parameters of the backbone network and exert considerable influences on the structural (low-frequency) components of the image, which undermines the model’s ability to retain non-target concepts. In this work, we propose our Dual encoder Modulation network (DuMo), which achieves precise erasure of inappropriate target concepts with minimum impairment to non-target concepts. In contrast to previous methods, DuMo employs the Eraser with PRior Knowledge (EPR) module which modifies the skip connection features of the U-NET and primarily achieves concept erasure on details (high-frequency) components of the image. To minimize the damage to non-target concepts during erasure, the parameters of the backbone U-NET are frozen and the prior knowledge from the original skip connection features is introduced to the erasure process. Meanwhile, the phenomenon is observed that distinct erasing preferences for the image structure and details are demonstrated by the EPR at different timesteps and layers. Therefore, we adopt a novel Time-Layer MOdulation process (TLMO) that adjusts the erasure scale of EPR module’s outputs across different layers and timesteps, automatically balancing the erasure effects and model’s generative ability. Our method achieves state-of-the-art performance on Explicit Content Erasure (detecting only 34 nude parts), Cartoon Concept Removal (with an average LPIPSda of 0.428, 0.113 higher than SOTA at 0.315), and Artistic Style Erasure (with an average LPIPSda of 0.387, 0.088 higher than SOTA at 0.299), clearly outperforming alternative methods. Code is available at https://***/Maplebb/DuMo Copyright © 2025, The Author

关键词： HTTP