检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Qi, Huiyan Cheng, Lechao Chen, Jingjing Yu, Yue Song, Xue Fengg, Zunlei Jiang, Yu-Gang School of Computer Science Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Zhejiang Lab China Zhejiang University China

Transfer learning aims to improve the performance of target tasks by transferring knowledge acquired in source tasks. The standard approach is pre-training followed by fine-tuning or linear probing. Especially, selecting a proper source domain for a specific target domain under predefined tasks is crucial for improving efficiency and effectiveness. It is conventional to solve this problem via estimating transferability. However, existing methods can not reach a trade-off between performance and cost. To comprehensively evaluate estimation methods, we summarize three properties: stability, reliability and efficiency. Building upon them, we propose Principal Gradient Expectation (PGE), a simple yet effective method for assessing transferability. Specifically, we calculate the gradient over each weight unit multiple times with a restart scheme, and then we compute the expectation of all gradients. Finally, the transferability between the source and target is estimated by computing the gap of normalized principal gradients. Extensive experiments show that the proposed metric is superior to state-of-the-art methods on all properties. © 2022, CC BY.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Richelieu: self-evolving LLM-based agents for AI diplomacy 24

Richelieu: self-evolving LLM-based agents for AI diplomacy

引用

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

作者： Zhenyu Guan Xiangyu Kong Fangwei Zhong Yizhou Wang Institute for Artificial Intelligence Peking University College of Computer Science Beijing Information Science and Technology University and State Key Laboratory of General Artificial Intelligence BIGAI School of Artificial Intelligence Beijing Normal University and State Key Laboratory of General Artificial Intelligence BIGAI Center on Frontiers of Computing Studies School of Computer Science Nat'l Eng. Research Center of Visual Technology Peking University and Institute for Artificial Intelligence Peking University

ISBN: (纸本)9798331314385

Diplomacy is one of the most sophisticated activities in human society, involving complex interactions among multiple parties that require skills in social reasoning, negotiation, and long-term strategic planning. Previous AI agents have demonstrated their ability to handle multi-step games and large action spaces in multi-agent tasks. However, diplomacy involves a staggering magnitude of decision spaces, especially considering the negotiation stage required. While recent agents based on large language models (LLMs) have shown potential in various applications, they still struggle with extended planning periods in complex multi-agent settings. Leveraging recent technologies for LLM-based agents, we aim to explore AI's potential to create a human-like agent capable of executing comprehensive multi-agent missions by integrating three fundamental capabilities: 1) strategic planning with memory and reflection; 2) goal-oriented negotiation with social reasoning; and 3) augmenting memory through self-play games for self-evolution without human in the loop. Project page: https://***/view/richelieu-diplomacy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on liquid crystal display technology based on regional dynamic dimming algorithm

Research on liquid crystal display technology based on regio...

引用

IEEE International Conference on Data science in Cyberspace (DSC)

作者： Zhitao Yu Peng Sun Mingle Zhou Qianlong Liu Shilong Zhao Hisense Video Technology Co. Ltd Qing Dao China Hisense Visual Technology Co. Ltd Qing Dao China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

In vehicle liquid crystal display (LCD) technology has attracted much attention for its wide range of applications in automotive infotainment systems. However, conventional LCD technologies have limitations in terms of energy consumption and display quality, especially in the context of the increasing demand for high contrast and low energy consumption. To address these challenges, this paper carries out a study of LCD technology based on an area dynamic dimming algorithm. The technology significantly improves the contrast ratio of LCDs and effectively reduces energy consumption by dividing the backlight module into multiple independently adjustable regions and dynamically adjusting the backlight brightness of each region according to the image content. The results show that the region dynamic dimming algorithm proposed in this paper can effectively adjust the brightness of the backlight according to the image content, achieving higher display contrast and lower energy consumption.

关键词： Energy consumption Heuristic algorithms Brightness Light emitting diodes Liquid crystal displays Robustness Entropy Energy efficiency Vehicle dynamics Optimization

来源：评论

学校读者我要写书评

暂无评论

Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision

arXiv

引用

arXiv 2023年

作者： Xu, Jilan Hou, Junlin Zhang, Yuejie Feng, Rui Wang, Yi Qiao, Yu Xie, Weidi School of Computer Science Shanghai Key Lab of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Shanghai AI Laboratory China Shanghai Jiaotong University China

In this paper, we consider the problem of open-vocabulary semantic segmentation (OVS), which aims to segment objects of arbitrary classes instead of pre-defined, closed-set categories. The main contributions are as follows: First, we propose a transformer-based model for OVS, termed as OVSegmentor, which only exploits web-crawled image-text pairs for pre-training without using any mask annotations. OVSegmentor assembles the image pixels into a set of learnable group tokens via a slot-attention based binding module, and aligns the group tokens to the corresponding caption embedding. Second, we propose two proxy tasks for training, namely masked entity completion and cross-image mask consistency. The former aims to infer all masked entities in the caption given the group tokens, that enables the model to learn fine-grained alignment between visual groups and text entities. The latter enforces consistent mask predictions between images that contain shared entities, which encourages the model to learn visual invariance. Third, we construct CC4M dataset for pre-training by filtering CC12M with frequently appeared entities, which significantly improves training efficiency. Fourth, we perform zero-shot transfer on three benchmark datasets, PASCAL VOC 2012, PASCAL Context, and COCO Object. Our model achieves superior segmentation results over the state-of-the-art method by using only 3% data (4M vs 134M) for pre-training. Code and pre-trained models will be released for future research. © 2023, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Feature Rotation Invariance Learning for Point Cloud Analysis 10

Feature Rotation Invariance Learning for Point Cloud Analysi...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Shi, Lu Cao, Qi Zhang, Guoqing Yi, Jin Huang, Yansen Cen, Yigang Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation The School of Computer Science and Technology Visual Intellgence +X International Cooperation Joint Laboratory of Moe Beijing100044 China University of Glasgow The School of Computing Science 567739 Singapore Beijing Jiaotong University With the Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education The State Key Laboratory of Advanced Rail Autonomous Operation The School of Computer and Information Technology Beijing100044 China Guizhou University Guizhou Lianjian Civil Engineering Quality Testing Monitoring Center Co. Ltd The College of Civil Engineering Guizhou550025 China

ISBN: (纸本)9798331520861

While deep learning has significantly advanced point cloud analysis, extracting effective features from their disordered structure remains challenging. Existing approaches often rely on complex network architectures or manual feature engineering to achieve rotation invariance, which increases inference latency. This paper offers a novel perspective on this challenge, showing that rotation-sensitive models can achieve performance comparable to rotation-invariant models when trained with rotation-augmented data. Given the significant differences in the feature distributions of rotation-sensitive and rotation-invariant models, we propose Feature Rotation Invariance Learning (FRIL), a framework that leverages Distance Metric Learning and rotation-based constraints to help rotation-sensitive models extract rotation-invariant features. This approach eliminates the need for additional modules, enabling robust performance against rotations. Extensive experiments demonstrate that FRIL consistently outperforms existing rotation-invariant methods across various visual tasks. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

SELF-SUPERVISED VIDEO REPRESENTATION LEARNING WITH MOTION-CONTRASTIVE PERCEPTION

arXiv

引用

arXiv 2022年

作者： Liu, Jinyu Cheng, Ying Zhang, Yuejie Zhao, Rui-Wei Feng, Rui School of Computer Science Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China Academy for Engineering and Technology Fudan University China

visual-only self-supervised learning has achieved significant improvement in video representation learning. Existing related methods encourage models to learn video representations by utilizing contrastive learning or designing specific pretext tasks. However, some models are likely to focus on the background, which is unimportant for learning video representations. To alleviate this problem, we propose a new view called long-range residual frame to obtain more motion-specific information. Based on this, we propose the Motion-Contrastive Perception Network (MCPNet), which consists of two branches, namely, Motion Information Perception (MIP) and Contrastive Instance Perception (CIP), to learn generic video representations by focusing on the changing areas in videos. Specifically, the MIP branch aims to learn fine-grained motion features, and the CIP branch performs contrastive learning to learn overall semantics information for each instance. Experiments on two benchmark datasets UCF-101 and HMDB-51 show that our method outperforms current state-of-the-art visual-only self-supervised approaches. Copyright © 2022, The Authors. All rights reserved.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

PUTraceAD: Trace Anomaly Detection with Partial Labels based on GNN and PU Learning

PUTraceAD: Trace Anomaly Detection with Partial Labels based...

引用

International Symposium on Software Reliability Engineering (ISSRE)

作者： Ke Zhang Chenxi Zhang Xin Peng Chaofeng Sha School of Computer Science Fudan University China Shanghai Key Laboratory of Data Science Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

ISBN: (数字)9781665451321

ISBN: (纸本)9781665451338

Distributed tracing has been an important part of microservice infrastructure and learning-based trace analysis has been used to detect anomalies in microservice systems. Existing learning-based trace anomaly detection approaches ei-ther assume that trace patterns can be learned from normal execution or rely on fault injection to produce labeled traces (i.e., normal/anomalous ones). However, in practice it is often difficult to ensure that the normal execution does not involve anomalous traces or obtain a large variety of normal and anomalous traces through fault injection. In this paper, we propose PUTraceAD, a trace anomaly detection approach that can alleviate the above problems. PUTraceAD represents a trace as a span causal graph with node features such as operation name, response code, duration time. Based on the graph representation, PUTraceAD trains a GNN- and PU learning-based trace anomaly detection model. During the process, PU (Positive and Unlabeled) learning optimizes model parameters through estimating the data distribution. Therefore, PUTraceAD can train the model based on a small set of labeled anomalous traces and a large set of unlabeled traces. Our evaluation shows that PUTraceAD outperforms existing unsupervised trace anomaly detection approaches and only slightly underperforms a supervised learning-based approach that takes full advantage of labeled traces.

关键词： Codes Microservice architectures Data models Software reliability Time factors Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Real-Time 3D-Aware Portrait Video Relighting

Real-Time 3D-Aware Portrait Video Relighting

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Ziqi Cai Kaiwen Jiang Shu-Yu Chen Yu-Kun Lai Hongbo Fu Boxin Shi Lin Gao Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing Jiaotong University University of California San Diego Cardiff University City University of Hong Kong The Hong Kong University of Science and Technology National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Engineering Research Center of Visual Technology School of Computer Science Peking University University of Chinese Academy of Sciences

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Synthesizing realistic videos of talking faces under custom lighting conditions and viewing angles benefits various downstream applications like video conferencing. However, most existing relighting methods are either time-consuming or unable to adjust the viewpoints. In this paper, we present the first real-time 3D-aware method for relighting in-the-wild videos of talking faces based on Neural Radiance Fields (NeRF). Given an input portrait video, our method can synthesize talking faces under both novel views and novel lighting conditions with a photo-realistic and disentangled 3D representation. Specifically, we infer an albedo tri-plane, as well as a shading tri-plane based on a desired lighting condition for each video frame with fast dual-encoders. We also leverage a temporal consistency network to ensure smooth transitions and reduce flickering artifacts. Our method runs at 32.98 fps on consumer-level hardware and achieves state-of-the-art results in terms of reconstruction quality, lighting error, lighting instability, temporal consistency and inference speed. We demonstrate the effectiveness and interactivity of our method on various portrait videos with diverse lighting and viewing conditions.

关键词： computer vision Three-dimensional displays Lighting Neural radiance field Real-time systems Hardware Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Rethinking the Functionality of Latent Representation: A Logarithmic Rate-Distortion Model for Learned Image Compression

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Ge, Ziqing Huang, Zhimeng Jia, Chuanmin Ma, Siwei Gao, Wen School of Computer Science Peking University State Key Laboratory of Multimedia Information Processing Beijing100871 China Institute of Computing Technology Beijing100190 China University of Chinese Academy of Sciences Beijing100190 China Peking University National Engineering Research Center of Visual Technology School of Computer Science Beijing100871 China Peking University Wangxuan Institute of Computer Technology Beijing100871 China Peking University State Key Laboratory of Multimedia Information Processing School of Computer Science Beijing100871 China Chinese Academy of Sciences Beijing100190 China

End-to-end optimized Learned Image Compression (LIC) has demonstrated remarkable performance in terms of Rate-Distortion (R-D) efficiency. However, the R-D characteristics of LIC codecs remain underexplored. Previous research has attempted to investigate the R-D behavior through numerical and statistical approaches, but these methods often provide only empirical results, lacking theoretical insights. In this work, we introduce a novel methodology for studying the R-D characteristics of LIC. By rethinking the LIC paradigm from a fresh perspective, we propose a plug-and-play module, the Latent-domain Auto-Encoder (LAE). This innovative approach not only naturally leads to Variable Bit-Rate (VBR) compression, but also allows for a theoretical modeling of the R-D behavior of LIC codecs. Our findings reveal that the bit-rate is the logarithmic sum of the neurons nλ in our designed network's last layer, plus a constant C introduced by image content, formally expressed as Rλ = Σ log nλ + C. This insight is pivotal, as it underscores how the bit-rate can be systematically derived from the latent representations. Further analysis demonstrates that our proposed R-λ model enables effective rate control for learned image codecs, enhancing their adaptability and accuracy. Experimental results validate that our VBR method surpasses fixed-rate coding by 2.9% in terms of BD-rate. Additionally, the proposed R-λ model exhibits superior rate control performance, suggesting that it not only elucidates the underlying R-D characteristics of LIC but also significantly enhances its practical deployment in real-world applications. © 1991-2012 IEEE.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Hubs and Hyperspheres: Reducing Hubness and Improving Transductive Few-Shot Learning with Hyperspherical Embeddings

Hubs and Hyperspheres: Reducing Hubness and Improving Transd...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Daniel J. Trosten Rwiddhi Chakraborty Sigurd Løksc Kristoffer Knutsen Wickstrøm Robert Jenssen Michael C. Kampffmeyer Department of Physics and Technology UiT The Arctic University of Norway UiT Machine Learning group (machine-learning.uit. no) and Visual Intelligence Centre (visual-intelligence.no) Norwegian Computing Center Department of Computer Science University of Copenhagen Pioneer Centre for AI (aicentre.dk)

Distance-based classification is frequently used in transductive few-shot learning (FSL). However, due to the high-dimensionality of image representations, FSL classifiers are prone to suffer from the hubness problem, where a few points (hubs) occur frequently in multiple nearest neighbour lists of other points. Hubness negatively impacts distance-based classification when hubs from one class appear often among the nearest neighbors of points from another class, degrading the classifier's performance. To address the hubness problem in FSL, we first prove that hubness can be eliminated by distributing representations uniformly on the hypersphere. We then propose two new approaches to embed representations on the hypersphere, which we prove optimize a tradeoff between uniformity and local similarity preservation - reducing hubness while retaining class structure. Our experiments show that the proposed methods reduce hubness, and significantly improves transductive FSL accuracy for a wide range of classifiers 1 1 Code available at https://***/uitml/noHub..

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：