检索结果-内蒙古大学图书馆

6th International Conference on Image and Graphics processing, ICIGP 2023

作者： Xu, Liu Wang, Xiao Yuan, Xin Mao, Zhu Xu, Xin School of Computer Science and Technology Wuhan University of Science and Technology China School of Computer Science and Technology Wuhan University of Science and Technology ChinaHubei Prov. Key Lab. of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology China

ISBN: (纸本)9781450398572

Person re-identification (re-ID), which is to connect pedestrians with the same identity in different scenarios, has been more widely used in case detection of security. The re-ID datasets and technology have contributed greatly to advancing community research. There are currently no available low-light datasets due to the difficulty of collecting and labeling images of people in low-light scenes. As a result, the vast majority of current re-ID methods do not have the recognition capability in low-light scenes. However, the recognition of persons in the low-light surveillance video has become an important issue to be solved for urban security, which plays an important role in improving the crime-solving rate of public safety departments and protecting people's lives and property. In this paper, we propose an Adversarial Recovery Network (ARN) that, unlike other approaches, enables a re-ID model with low-light recognition capability without the need for low-light data. Specifically, we first degrade the original images to generate multi-level low-light images;then obtain recovered images through the adversarial recovery module, and finally input the recovered images into the CNN network to extract pedestrian recognition knowledge. In addition, to validate the effectiveness of the proposed method, we also propose a low-light re-ID dataset (LOLR). Extensive experiments on LOLR have shown that our method outperforms other competitors by a wide margin. The dataset and code are available online at https://***/xl02111/ARN. © 2023 ACM.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

ProofInfer: Generating Proof via Iterative Hierarchical Inference

ProofInfer: Generating Proof via Iterative Hierarchical Infe...

引用

2022 Conference on Empirical Methods in Natural Language processing, EMNLP 2022

作者： Fei, Zichu Zhang, Qi Zhou, Xin Gui, Tao Huang, Xuanjing School of Computer Science Fudan Unviersity China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China

Proof generation focuses on deductive reasoning: given a hypothesis and a set of theories, including some supporting facts and logical rules expressed in natural language, the model generates a proof tree indicating how to deduce the hypothesis from given theories. Current models with state-of-the-art performance employ the stepwise method, linking an individual node to the proof step-by-step. However, these methods actually focus on generating several proof paths rather than a whole tree. To address this problem, we propose ProofInfer, which generates the proof tree via iterative hierarchical inference. At each step, ProofInfer generates the entire layer for proof tree, where all nodes in this layer are generated simultaneously. Since the conventional autoregressive generation architecture cannot simultaneously predict multiple nodes, ProofInfer employs text-to-text paradigm to avoid it. To this end, we propose a divide- and-conquer algorithm to encode the proof tree as the plain text recursively without structure information loss. Experimental results show that ProofInfer significantly outperforms the state-of-the-art (SOTA) models on several widely-used datasets. In addition, ProofInfer still performs well with data-limited, achieving comparable performance to the SOTA models with only 40% of the training data. © 2022 Association for Computational Linguistics.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A Copyright-Preserving and Fair Image Trading SchemeBased on Blockchain

引用

Tsinghua science and Technology 2023年第5期28卷 849-861页

作者： Feng Yu Jiahui Peng Xianxian Li Chunpei Li Bin Qu School of Computer Science&Engineering Guangxi Normal UniversityGuilin 541004Chinaand with the Key Lab of Education Blockchain and Intelligent TechnologyMinistry of EducationGuangxi Normal UniversityGuilin 541004Chinaand also with Guangxi Collaborative Innovation Center of Multi-Source Information Integration and Intelligent ProcessingGuangxi Normal UniversityGuilin 541004China Guangxi Power Grid Materials Co Ltd Nanning 530022China

With the proliferation of the Internet,particularly the rise of social media,digital images have gradually become an important part of life,and trading platforms have emerged for buying and selling ***,traditional image trading service providers may disclose users’private information for ***,many image trading platforms disregard the fairness of a transaction and the issue of copyright protection after an image is *** neglect harms the interests of users and affects their enthusiasm for trading.A secure way to safely transact images is *** proposed a copyright-preserving and fair image trading scheme based on blockchain,which combines amplifying locality-sensitive hashing with searchable symmetric encryption to achieve safe image retrieval on blockchain and ensure the credibility of the image retrieval ***,we use digital fingerprint and watermark technologies to realize the copyright protection of images and use smart contracts to achieve fair transaction *** experimental results show that our scheme can protect image copyrights and realize a fair trading process while ensuring efficiency.

关键词： blockchain copyright-preserving trade fair trade tadors code

来源：评论

学校读者我要写书评

暂无评论

LFKQG: A Controlled Generation Framework with Local Fine-tuning for Question Generation over Knowledge Bases 29

LFKQG: A Controlled Generation Framework with Local Fine-tun...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Fei, Zichu Zhou, Xin Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan Unviersity China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Institute of Modern Languages and Linguistics Fudan University Shanghai China

Question generation over knowledge bases (KBQG) aims to generate natural questions about a subgraph that can be answered by a given answer entity. Existing KBQG models still face two main challenges: (1) Most models often focus on the most relevant part of the answer entity, while neglecting the rest of the subgraph. (2) There are a large number of out-of-vocabulary (OOV) predicates in real-world scenarios, which are hard to adapt for most KBQG models. To address these challenges, we propose LFKQG, a controlled generation framework for Question Generation over Knowledge Bases. (1) LFKQG employs a simple controlled generation method to generate the questions containing the critical entities in the subgraph, ensuring the question is relevant to the whole subgraph. (2) We propose an optimization strategy called local fine-tuning, which makes good use of the rich information hidden in the pre-trained model to improve the ability of the model to adapt the OOV predicates. Extensive experiments show that our method outperforms existing methods greatly on three widely-used benchmark datasets SimpleQuestion, PathQuestions, and WebQuestions . © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning

Chinese Text Recognition with A Pre-Trained CLIP-Like Model ...

引用

International Conference on computer Vision (ICCV)

作者： Haiyang Yu Xiaocong Wang Bin Li Xiangyang Xue School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University

Scene text recognition has been studied for decades due to its broad applications. However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few methods have been proposed for Chinese Text Recognition (CTR). Particularly, the characteristic of large categories poses challenges in dealing with zero-shot and few-shot Chinese characters. In this paper, inspired by the way humans recognize Chinese texts, we propose a two-stage framework for CTR. Firstly, we pre-train a CLIP-like model through aligning printed character images and Ideographic Description Sequences (IDS). This pre-training stage simulates humans recognizing Chinese characters and obtains the canonical representation of each character. Subsequently, the learned representations are employed to supervise the CTR model, such that traditional single-character recognition can be improved to text-line recognition through image-IDS matching. To evaluate the effectiveness of the proposed method, we conduct extensive experiments on both Chinese character recognition (CCR) and CTR. The experimental results demonstrate that the proposed method performs best in CCR and outperforms previous methods in most scenarios of the CTR benchmark. It is worth noting that the proposed method can recognize zero-shot Chinese characters in text images without fine-tuning, whereas previous methods require fine-tuning when new classes appear. The code is available at https://***/FudanVI/FudanOCR/tree/main/image-ids-CTR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BBTv2: Towards a Gradient-Free Future with Large Language Models

BBTv2: Towards a Gradient-Free Future with Large Language Mo...

引用

2022 Conference on Empirical Methods in Natural Language processing, EMNLP 2022

作者： Sun, Tianxiang He, Zhengfu Qian, Hong Zhou, Yunhua Huang, Xuanjing Qiu, Xipeng School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China School of Computer Science and Technology East China Normal University China

Most downstream adaptation methods tune all or part of the parameters of pre-trained models (PTMs) through gradient descent, where the tuning cost increases linearly with the growth of the model size. By contrast, gradient-free methods only require the forward computation of the PTM to tune the prompt, retaining the benefits of efficient tuning and deployment. Though, past work on gradient-free tuning often introduces gradient descent to seek a good initialization of prompt and lacks versatility across tasks and PTMs. In this paper, we present BBTv2, an improved version of Black-Box Tuning (Sun et al., 2022b), to drive PTMs for few-shot learning. We prepend continuous prompts to every layer of the PTM and propose a divide-and-conquer gradient-free algorithm to optimize the prompts at different layers alternately. Extensive experiments across various tasks and PTMs show that BBTv2 can achieve comparable performance to full model tuning and state-of-the-art parameter-efficient methods (e.g., Adapter, LoRA, BitFit, etc.) under few-shot settings while maintaining much fewer tunable parameters. © 2022 Association for Computational Linguistics.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

EVE: Towards End-to-End Video Subtitle Extraction with Vision-Language Models

arXiv

引用

arXiv 2025年

作者： Yu, Haiyang Lu, Jinghui Wang, Yanjie Li, Yang Wang, Han Huang, Can Li, Bin Shanghai Key Laboratory of Intelligent Information Processing China School of Computer Science Fudan University China ByteDance Inc China

The advent of Large Vision-Language Models (LVLMs) has advanced the video-based tasks, such as video captioning and video understanding. Some previous research indicates that taking texts in videos as input can further improve the performance of video understanding. As a type of indispensable information in short videos or movies, subtitles can assist LVLMs to better understand videos. Most existing methods for video subtitle extraction are based on a multi-stage framework, handling each frame independently. They can hardly exploit the temporal information of videos. Although some LVLMs exhibit the robust OCR capability, predicting accurate timestamps for subtitle texts is still challenging. In this paper, we propose an End-to-end Video Subtitle Extraction method, called EVE, which consists of three modules: a vision encoder, an adapter module, and a large language model. To effectively compress the visual tokens from the vision encoder, we propose a novel adapter InterleavedVT to interleave two modalities. It contains a visual compressor and a textual region compressor. The proposed InterleavedVT exploits both the merits of average pooling and Q-Former in token compression. Taking the temporal information of videos into account, we introduce a sliding-window mechanism in the textual region compressor. To benchmark the video subtitle extraction task, we propose a large dataset ViSa including 2.5M videos. Extensive experiments on ViSa demonstrate that the proposed EVE can outperform existing open-sourced tools and LVLMs. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Hyperledger sawtooth based supplychain traceability system for counterfeit drugs" [Comput. Ind. Eng. 190 (2024) 110021] (computers & Industrial Engineering (2024) 190, (S0360835224001426), (10.1016/***.2024.110021))

引用

computers and Industrial Engineering 2025年 204卷

作者： Nawaz, Anum Wang, Liguan Irfan, Muhammad Westerlund, Tomi Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Turku Intelligent and Embedded Robotic Systems Lab Faculty of Technology University of Turku Finland

关键词：

来源：评论

学校读者我要写书评

暂无评论

Isoform Function Prediction Based on Heterogeneous Graph Attention Networks

Isoform Function Prediction Based on Heterogeneous Graph Att...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Guo, Kuo Li, Yifan Chen, Hao Shen, Hong-Bin Yang, Yang Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Institute of Image Processing and Pattern Recognition Shanghai200240 China Carnegie Mellon University School of Computer Science Computational Biology Department PittsburghPA15213 United States

ISBN: (纸本)9798350337488

Isoforms refer to different mRNA molecules transcribed from the same gene, which can be translated into proteins with varying structures and functions. Predicting the functions of isoforms is an essential topic in bioinformatics as it can provide valuable insights into the intricate mechanisms of gene regulation and biological processes. Conventionally, gene function labels are standardized in Gene Ontology (GO) terms. However, traditional methods for predicting isoform function are largely limited by the absence of isoform-specific labels, sparse annotations, and the vast number of GO terms. To address these issues, we propose HANIso, a deep learning-based method for isoform function prediction. HANIso leverages a pretrained protein language model to extract features from protein sequences. It also integrates heterogeneous information, such as isoform sequence features, GO annotations, and isoform interaction data, using a Heterogeneous Graph Attention Network (HAN). This allows the model to learn the importance of different sources of information and their semantic relationships through the attention mechanism. Our method can predict function labels at both the gene level and isoform level. We conduct experiments on two species datasets, and the results demonstrate that our method outperforms existing methods on both AUROC and AUPRC. HANIso has the potential to overcome the limitations of traditional methods and provide a more accurate and comprehensive understanding of isoform function. © 2023 IEEE.

关键词： alternative splicing gene ontology heterogeneous graph attention network isoform function prediction protein language model

来源：评论

学校读者我要写书评

暂无评论

InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance

arXiv

引用

arXiv 2024年

作者： Wang, Pengyu Zhang, Dong Li, Linyang Tan, Chenkun Wang, Xinghao Ren, Ke Jiang, Botian Qiu, Xipeng School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing Fudan University China

With the rapid development of large language models (LLMs), they are not only used as general-purpose AI assistants but are also customized through further fine-tuning to meet the requirements of different applications. A pivotal factor in the success of current LLMs is the alignment process. Current alignment methods, such as supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF), focus on training-time alignment and are often complex and cumbersome to implement. Therefore, we develop InferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. InferAligner utilizes safety steering vectors extracted from safety-aligned model to modify the activations of the target model when responding to harmful inputs, thereby guiding the target model to provide harmless responses. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics, as well as to multimodal large language models (MLLMs) such as LLaVA. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

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：