检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yuyi Liu Xinhang Song Weijie Li Xiaohan Wang Shuqiang Jiang Key Lab of Intelligent Information Processing Laboratory of the Chinese Academy of Sciences (CAS) Institute of Computing Technology Beijing University of Chinese Academy of Sciences Beijing

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

This paper presents a novel category agnostic model for visual rearrangement task, which can help an embodied agent to physically recover the shuffled scene configuration without any category concepts to the goal configuration. Previous methods usually follow a similar architecture, completing the rearrangement task by aligning the scene changes of the goal and shuffled configuration, according to the semantic scene graphs. However, constructing scene graphs requires the inference of category labels, which not only causes the accuracy drop of the entire task but also limits the application in real world scenario. In this paper, we delve deep into the essence of visual re-arrangement task and focus on the two most essential issues, scene change detection and scene change matching. We utilize the movement and the protrusion of point cloud to accurately identify the scene changes and match these changes depending on the similarity of category agnostic appearance feature. Moreover, to assist the agent to explore the environment more efficiently and comprehensively, we propose a closer-aligned-retrace exploration policy, aiming to observe more details of the scene at a closer distance. We conduct extensive experiments onAI2THOR Rearrangement Challenge based on RoomR dataset and a new multi-room multi-instance dataset MrMiR collected by us. The experimental results demonstrate the effectiveness of our proposed method.

关键词： Point cloud compression Visualization Computer vision Accuracy Semantics Feature extraction Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Dual Prompt Learning Framework for Few-Shot Dialogue State Tracking 23

A Dual Prompt Learning Framework for Few-Shot Dialogue State...

引用

2023 World Wide Web Conference, WWW 2023

作者： Yang, Yuting Lei, Wenqiang Huang, Pei Cao, Juan Li, Jintao Chua, Tat-Seng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China Sichuan University Sichuan China Stanford University CA United States National University of Singapore Singapore Singapore

ISBN: (纸本)9781450394161

Dialogue State Tracking (DST) module is an essential component of task-oriented dialog systems to understand users' goals and needs. Collecting dialogue state labels including slots and values can be costly, requiring experts to annotate all (slot, value) information for each turn in dialogues. It is also difficult to define all possible slots and values in advance, especially with the wide application of dialogue systems in more and more new-rising applications. In this paper, we focus on improving DST module to generate dialogue states in circumstances with limited annotations and knowledge about slot ontology. To this end, we design a dual prompt learning framework for few-shot DST. The dual framework aims to explore how to utilize the language understanding and generation capabilities of pre-trained language models for DST efficiently. Specifically, we consider the learning of slot generation and value generation as dual tasks, and two kinds of prompts are designed based on this dual structure to incorporate task-related knowledge of these two tasks respectively. In this way, the DST task can be formulated as a language modeling task efficiently under few-shot settings. To evaluate the proposed framework, we conduct experiments on two task-oriented dialogue datasets. The results demonstrate that the proposed method not only outperforms existing state-of-the-art few-shot methods, but also can generate unseen slots. It indicates that DST-related knowledge can be probed from pre-trained language models and utilized to address low-resource DST efficiently with the help of prompt learning. © 2023 Owner/Author.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

An Efficient Authentication and Key Agreement Scheme for CAV Internal Applications 19th

An Efficient Authentication and Key Agreement Scheme for C...

引用

19th EAI International Conference on Collaborative computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Li, Yang Zhang, Qingyang Cao, Wenwen Cui, Jie Zhong, Hong Anhui Province Key Laboratory of Cyberspace Security Situation Awareness and Evaluation Hefei230037 China School of Computer Science and Technology Anhui University Hefei230039 China Anhui Engineering Laboratory of IoT Security Technologies Anhui University Hefei230039 China Institute of Physical Science and Information Technology Anhui University Hefei230039 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei230039 China

ISBN: (纸本)9783031545276

The data of applications in connected and autonomous vehicles are important, which is usually collected by service providers to improve their services, such as object detection model. But, wireless communication is susceptible to various kinds of attacks. Thus, the data of the application module needs to be securely shared to the corresponding service provider. However, current schemes are with limited performance while a service provider collects multiple application data at the same time. By adopting signcryption and chaotic map, an efficient authentication and key agreement scheme is proposed, while batch authentication is achieved for efficient message authentication of multiple applications, and the efficient revocation is realized based on Chinese remainder theorem under the assistance of trusted execution environment supported vehicle computing/communication unit. The formal security proof shows that the scheme is secure under the random oracle model, and the experiment results shows that the scheme is more efficient than related schemes and can meet the requirements of CAV. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Glancing Future for Simultaneous Machine Translation

Glancing Future for Simultaneous Machine Translation

引用

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

作者： Shoutao Guo Shaolei Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences (ICT/CAS) University of Chinese Academy of Sciences Beijing China

Simultaneous machine translation (SiMT) outputs translation while reading the source sentence. Unlike conventional sequence-to-sequence (seq2seq) training, existing SiMT methods adopt the prefix-to-prefix (prefix2prefix) training, where the model predicts target tokens based on partial source tokens. However, the prefix2prefix training diminishes the ability of the model to capture global information and introduces forced predictions due to the absence of essential source information. Consequently, it is crucial to bridge the gap between the prefix2prefix training and seq2seq training to enhance the translation capability of the SiMT model. In this paper, we propose a novel method that glances future in curriculum learning to achieve the transition from the seq2seq training to prefix2prefix training. Specifically, we gradually reduce the available source information from the whole sentence to the prefix corresponding to that latency. Our method is applicable to a wide range of SiMT methods and experiments demonstrate that our method outperforms strong baselines 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

A graph reasoning method for multi-object unordered stacking scenarios

A graph reasoning method for multi-object unordered stacking...

引用

IEEE International Conference on Real-time computing and Robotics (RCAR)

作者： Guoyu Zuo Zihao Wang Daoxiong Gong Gao Huang Faculty of Information Technology Beijing University of Technology Beijing China Beijing Key Laboratory of Computing Intelligence and Intelligent Systems Beijing China

In order to enable the robot to safely pick the target object from it in the face of a scene with multiple objects stacked in a disorderly manner. It is of great importance for intelligent robot grasping to get the operation order by obtaining the position relationship between the target object and other objects in space. In this paper, an end-to-end detection inference network is proposed, in which features are extracted from the input RGB information by EfficientNet-B0 combined with BiFPN in terms of feature extraction, and in terms of operation relationships, object pairs without up-down position relationships are first eliminated to reduce the amount of operations, and graph attention networks (GAT) are later used to reason about the positions between objects. The network model is trained and tested on the VMRD dataset, and the experiments show that this model has good results in inference of object spatial position relationships for multi-object unordered stacked scenes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Retinopathy Identification in OCT Images with A Semi-supervised Learning Approach via Complementary Expert Pooling and Expert-wise Batch Normalization

Retinopathy Identification in OCT Images with A Semi-supervi...

引用

Optoelectronics Global Conference (OGC)

作者： Arman Mohammad Nakib Yuan Li Yuemei Luo Jiangsu Provincial Key Laboratory of Intelligent Medical Image Computing (iMIC) School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China

ISBN: (数字)9798350391466

ISBN: (纸本)9798350391473

In the medical field, the automatic detection of retinopathy using deep learning is an important application. However, traditional deep learning techniques face two significant challenges: the need for large amounts of labeled data, which are costly and difficult to obtain, and the imbalance of OCT ocular disease categories in practical applications, which can significantly affect model performance. This paper proposes a semi-supervised deep learning method based on complementary expert pooling (CEP). This method utilizes transfer learning with pre-trained models and enhances the model’s generalization capabilities through data augmentation strategies. Our approach implements a custom classification model on the VGG-16 architecture, employing CEP to model different category distributions across multiple experts and introducing Expert-wise Batch Normalization (EBN) to resolve feature distribution mismatches, thereby improving the model’s accuracy in recognizing minority classes. We evaluated our method on two datasets, using only 20% of the images as labeled data. Our method achieved $\mathbf{9 6. 5 5 \%}$ and $\mathbf{9 7. 7 8 \%}$ classification accuracies on these public datasets. Moreover, our approach demonstrated superior performance compared to various supervised learning methods using all available labeled data and other semi-supervised learning methods, proving its effectiveness in OCT ocular disease detection and its potential to assist clinicians in diagnosing ophthalmic diseases.

关键词： Accuracy Image resolution Retinopathy Transfer learning Supervised learning Semisupervised learning Data models Batch normalization Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Practical Applications of ChatGPT and BERT: Long Text Summarization and Model Feature Ablation Study for Stock Comment Topic Identification 24

Practical Applications of ChatGPT and BERT: Long Text Summar...

引用

2024 Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence, DEAI 2024

作者： Xu, Mingyan Chen, Hongyu Deng, Fuwen Liu, Yuan Zhao, Feng Zhang, Yong School of Statistics Shandong Technology and Business University Yantai264000 China School of Hospital Shandong Technology and Business University Yantai264000 China School of Computer Science and Technology Shandong Technology and Business University Yantai264000 China Yantai Key Laboratory of Big Data Modeling and Intelligent Computing School of Computer Science and Technology Shandong Technology and Business University Yantai China School of Information and Electrotic Shandong Technology and Business University Yantai264000 China

ISBN: (纸本)9798400717147

Topic identification of expert stock comments is an important task in the field of finance, which helps investors understand the market dynamics and expert opinions so that they can make more informed investment decisions. The Bidirectional Encoder Representations from Transformers (BERT) model is one of the widely used methods for text topic identification. To improve the identification accuracy and overcome the limitations of the BERT model, two strategies are proposed in this study. First, given the BERT model's input length limitation when dealing with long texts, we used the summaries created by Chat Generative Pre-training Transformer (ChatGPT) as inputs to the model. The generative summarization capability of ChatGPT not only reduces the length of the text effectively but also preserves the key information of the original text, which enables the model to better understand and deal with long texts. Second, we perform multi-layer feature ablation on the BERT model to find the most representative features for text topic identification. The multi-layer features of the BERT model can be more effectively utilized to improve the accuracy of text topic identification. Experiments show that our proposed strategies exhibit excellent performance and provide effective paths to improve the accuracy of stock comment topic identification. © 2024 ACM.

关键词： Ablation

来源：评论

学校读者我要写书评

暂无评论

EmoDubber: Towards High Quality and Emotion Controllable Movie Dubbing

arXiv

引用

arXiv 2024年

作者： Cong, Gaoxiang Pan, Jiadong Li, Liang Qi, Yuankai Peng, Yuxin van den Hengel, Anton Yang, Jian Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS China Macquarie University Australia Peking University China University of Adelaide Australia

Given a piece of text, a video clip, and a reference audio, the movie dubbing task aims to generate speech that aligns with the video while cloning the desired voice. The existing methods have two primary deficiencies: (1) They struggle to simultaneously hold audio-visual sync and achieve clear pronunciation;(2) They lack the capacity to express user-defined emotions. To address these problems, we propose EmoDubber, an emotion-controllable dubbing architecture that allows users to specify emotion type and emotional intensity while satisfying high-quality lip sync and pronunciation. Specifically, we first design Lip-related Prosody Aligning (LPA), which focuses on learning the inherent consistency between lip motion and prosody variation by duration level contrastive learning to incorporate reasonable alignment. Then, we design Pronunciation Enhancing (PE) strategy to fuse the video-level phoneme sequences by efficient conformer to improve speech intelligibility. Next, the speaker identity adapting module aims to decode acoustics prior and inject the speaker style embedding. After that, the proposed Flow-based User Emotion Controlling (FUEC) is used to synthesize waveform by flow matching prediction network conditioned on acoustics prior. In this process, the FUEC determines the gradient direction and guidance scale based on the user’s emotion instructions by the positive and negative guidance mechanism, which focuses on amplifying the desired emotion while suppressing others. Extensive experimental results on three benchmark datasets demonstrate favorable performance compared to several state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Speech intelligibility

来源：评论

学校读者我要写书评

暂无评论

Edge-Preserving Multi-Exposure Fusion with Guided Filtering for Structural Patch Decomposition 6

Edge-Preserving Multi-Exposure Fusion with Guided Filtering ...

引用

6th IEEE International Conference on Electronic information and Communication technology, ICEICT 2023

作者： Zhen, Yang Qi, Junwei Li, Yingsong College of Information and Communication Engineering Harbin Engineering University Harbin150001 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing Hefei China College of Computer Science and Technology Harbin Engineering University Harbin150001 China

ISBN: (纸本)9798350399059

Multi-exposure image fusion (MEF) is one of the effective ways to obtain high dynamic range (HDR) images. Multi-scale structural patch decomposition based MEF(MSPD) and edge-preserving structural patch decomposition (MESPD) have achieved state-of-the-art fusion quality. MESPD incorporates edge-preserving factors into MSPD to preserve details in a single-scale setting. However, we find that the edge-preserving factors put too much emphasis on the edge, resulting in artifacts on some edges and loss of details. To tackle this issue, guided filter is introduced into MSPD, which is directly used as an edge-preserving filter instead of mean filter to implicitly decompose images. In addition, we have designed a flexible adaptive weight, which can further maintain details of the light and dark areas. Likewise, we inherit MESPD and MSPD to extend our method to multi-scale framework. Extensive experimental results demonstrate our method can produce satisfactory results in both static and dynamic scenes with fewer artifacts and low computational cost. © 2023 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

FIRE: a dataset for feedback integration and refinement evaluation of multimodal models 24

FIRE: a dataset for feedback integration and refinement eval...

引用

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

作者： Pengxiang Li Zhi Gao Bofei Zhang Tao Yuan Yuwei Wu Mehrtash Harandi Yunde Jia Song-Chun Zhu Qing Li Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and State Key Laboratory of General Artificial Intelligence BIGAI State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University State Key Laboratory of General Artificial Intelligence BIGAI Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology and Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University Department of Electrical and Computer System Engineering Monash University Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University and Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology State Key Laboratory of General Artificial Intelligence BIGAI and State Key Laboratory of General Artificial Intelligence Peking University and Department of Automation Tsinghua University

ISBN: (纸本)9798331314385

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset.

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：