检索结果-内蒙古大学图书馆

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2045-2058页

作者： Yiming Zhang Xuenan Xu Ruoyi Du Haohe Liu Yuan Dong Zheng-Hua Tan Wenwu Wang Zhanyu Ma Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Centre for Vision Speech and Signal Processing University of Surrey Guildford U.K. Department of Electronic Systems Aalborg University Aalborg Denmark

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test set from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, and this issue has received little attention. To address these issues, we propose a new zero-shot method for audio captioning. Our method is built on the contrastive language-audio pre-training (CLAP) model. During training, the model reconstructs the ground-truth caption using the CLAP text encoder. In the inference stage, the model generates text descriptions from the CLAP audio embeddings of given audio inputs. To enhance the ability of the model in transitioning from text-to-text generation to audio-to-text generation, we propose to use the mixed-augmentations-based soft prompt to learn more robust latent representations, leveraging instance replacement and embedding augmentation. Additionally, we introduce the retrieval-based acoustic-aware hard prompt to improve the cross-domain performance of the model by employing the domain-agnostic label information of sound events. Extensive experiments on AudioCaps and Clotho benchmarks show the effectiveness of our proposed method, which outperforms other zero-shot audio captioning approaches for in-domain scenarios and outperforms the compared methods for cross-domain scenarios, underscoring the generalization ability of our method.

关键词： Training Decoding Semantics Data models Acoustics Electronic mail Benchmark testing Transformers Robustness Perturbation methods

来源：评论

学校读者我要写书评

暂无评论

Detection of elliptical traffic signs 9th

Detection of elliptical traffic signs

引用

9th International Conference on Image and Signal Processing, ICISP 2020

作者： El Baz, Manal Zaki, Taher Douzi, Hassan Image and Pattern Recognition - Intelligent and Communicating Systems Laboratory Faculty of Sciences Ibn Zohr University Agadir Morocco

ISBN: (纸本)9783030519346

Detection of elliptical features is a challenging and important task in computer vision. In fact, ellipses can describe many objects in real images like manufactured objects, cells, ball, or traffic signs. Furthermore, an ellipse is defined by five parameters: the center coordinates, the semi major axe, the semi minor axe and the orientation, which require more computational power to estimate them. Some non-ideal ellipses cause also difficulties for detection such as occlusion, appearance of multiple ellipses at same time and non-parallel ellipse. In this paper, we are interested in detecting elliptical traffic signs. We present a method for detecting different cases of ellipses: simple, partially occluded, non-parallel, multiple ellipses in images. The method selects three lines to find the ellipse center, and then it calculates the value of the semi minor and major axes of the ellipse. Experiments show that the proposed method performs well on real images in the presence or not of noises. © Springer Nature Switzerland AG 2020.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

Steganography algorithm for adaptive multi-rate wideband speech based on algebraic codebook search

引用

The Journal of China Universities of Posts and Telecommunications 2018年第3期25卷 71-79页

作者： Ruan Ye Xu Yanyan Ke Dengfeng Su Kaile School of Information Science and Technology Beijing Forestry University National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of Sciences Institute for Integrated and Intelligent Systems Griffith University College of Information Science and Technology Jinan University

With the popularity of adaptive multi-rate wideband （AMR-WB） audio in mobile communication, many AMR- WB based techniques, such as a similar compression architecture to transmit secret information during the process of compression, were proposed to transmit covert messages. However, if a sender does not have the original waveform audio format （WAV） audio, the architecture cannot be used. In this paper, a new covert message method, which takes effect after WAV audio is compressed into AMR-WB speech, is proposed. This method takes advantage of algebraic codebook search. Aiming at improving speed and reducing search space, it does not perform algebraic codebook search using the optimal search algorithm, and it does not reach the positions of non-zero pulses via depth-first tree search that characterizes the energy of audio. According to the features of search methods and the codebook index construction, every track in each subframe is analyzed to find the proper positions for embedding secret information. Experimental results show that the proposed method has satisfactory capacity and simplicity regardless of compression process.

关键词： steganography algorithm WAV audio compressed audio adaptive multi-rate wideband speech

来源：评论

学校读者我要写书评

暂无评论

Temporal segmentation of association football from TV broadcasting

Temporal segmentation of association football from TV broadc...

引用

17th IEEE International Conference on intelligent Engineering systems, INES 2013

作者： Siles, Francisco Pattern Recognition and Intelligent Systems Laboratory School of Electrical Engineering Universidad de Costa Rica San José Costa Rica

ISBN: (纸本)9781479908288

This paper presents the first module of our system Ace for the automated interpretation of association football games. This module is in charge of the temporal segmentation of the input broadcasting TV video into scenes. The temporal segmentation is based on a new devised dissimilarity measure using the Bhattacharyya distance of the hue and local spatial variance histograms, to incorporate chromatic and structural properties of the images. Great results of extended experiments conducted on the last FIFA's World Cup are presented. © 2013 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A new graph-based image segmentation algorithm

引用

International Conference on Informatics and Management Science, IMS 2012

作者： Zhang, Qian Feng, Fujian Xin, Lin Wang, Lin Pattern Recognition and Intelligent Systems Laboratory of Guizhou Guiyang Guizhou China Academic Affairs Office Guizhou University for Nationalities Guiyang Guizhou China

ISBN: (纸本)9781447147954

Based on graph theory, we choose two-dimensional Gaussian as a dynamic adaptive index for weighting function, difference function Dex for inter-area and Din for one area were defined by structural similarity index (SSIM), the function determines different area to be merged or segmented is achieved. The algorithm was implemented on Mat lab successfully. Experimental results show that the algorithm the segmentation is better than others in effect and calculate time. © 2013 Springer-Verlag.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Detection of dynamic overlays for association football from TV broadcasting

Detection of dynamic overlays for association football from ...

引用

14th IEEE International Symposium on Computational Intelligence and Informatics, CINTI 2013

作者： Siles, Ing. Francisco PRIS-lab: Pattern Recognition and Intelligent Systems Laboratory School of Electrical Engineering Universidad de Costa Rica San José Costa Rica

ISBN: (纸本)9781479901975

This paper presents a new dissimilarity measure for the detection of dynamic overlays in football games from TV broadcasting. The detection of the dynamic overlays is used for finding the replays in the input video, that are to be removed for further processing. The replays' detection and removal is part of the first module of the system ACE-Football for the automated interpretation of association football games, which is being developed at the PRIS-lab. Positive results of experiments conducted on several games of the latest FIFA's World Cup are presented. © 2013 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Genome Copy Number Feature Selection Based on Chromosomal Regions Alterations and Chemosensitivity Subtypes

Genome Copy Number Feature Selection Based on Chromosomal Re...

引用

2018 IEEE International Work Conference on Bioinspired Intelligence, IWOBI 2018

作者： Vargas, J. Mora-Rodriguez, Rodrigo Siles, F. Department of Electrical Engineering School of Engineering Universidad de Costa Rica Pattern Recognition and Intelligent Systems Laboratory Sna José Costa Rica

ISBN: (纸本)9781538675069

Cancer disease causes millions of deaths throughout the world and thousands in Costa Rica, and cancer treatment causes an immense economic burden on the social security system because drugs against the disease are extremely expensive. Through DNA sequencing techniques, the copy number of each gene could be found in order to describe how many times a gene is repeated within chromosomes. This type of data is of great importance since the cancer manifests a phenomenon called aneuploidy that consists of alterations in the number of chromosomes copies. Theories about the importance of aneuploidy in cancer supposed this phenomenon is a evolutionary engine that allows the disease to grow and resist changes produced by the organism and the treatments applied to these tissues. Studies have collected data on the number of copies in well-known databases such as CCLE and TCGA, which can be used to analyze the relationship between alterations in DNA and resistance to chemotherapies. In this study as a contribution, it was proposed to use statistical pattern recognition methods in order to identify chromosomal regions of DNA related to cancer chemosensitivity subtypes (resistant and sensitive subgroups) and then use these regions for CCLE cell lines labeling and TCGA samples classification. © 2018 IEEE.

关键词： Chemotherapy

来源：评论

学校读者我要写书评

暂无评论

Deceived bilateral filter for improving the classification of football players from TV broadcast 3

Deceived bilateral filter for improving the classification o...

引用

3rd IEEE International Work-Conference on Bioinspired Intelligence, IWOBI 2014

作者： Ramírez, Saúl Calderón Canales, Francisco Siles PRIS-LAB: Pattern Recognition and Intelligent Systems Laboratory School of Electrical Engineering Faculty of Engineering Universidad de Costa Rica San José Costa Rica

ISBN: (纸本)9781479961740

This paper presents a novel image abstraction tech- nique, the deceived bilateral filter (DBF). The DBF combines border sharpening with simplification of homogeneous regions to achieve moderate de-blurring and colour emphasis. The aim of the DBF is to remove noise of colour and shape descriptors (histograms and contours) of the blobs corresponding to football players. The experiment implemented for this paper consists in an unsupervised histogram based classification of the blobs based on the team of the football players aiming to evaluate histogram denoising. The results show an average classification success rate improvement of 11%. © 2014 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Teleoperation of a Humanoid Robot Using an Optical Motion Capture System

Teleoperation of a Humanoid Robot Using an Optical Motion Ca...

引用

2018 IEEE International Work Conference on Bioinspired Intelligence, IWOBI 2018

作者： Nunez, L. Dajles, D. Siles, F. Department of Electrical Engineering School of Engineering Universidad de Costa Rica PRIS-Lab: Pattern Recognition and Intelligent Systems Laboratory San Jose Costa Rica

ISBN: (纸本)9781538675069

Given the resemblance between the human body and that of a humanoid robot, a very intuitive control system might use motion capture;the system would track the motion of different key joints along the body of the human operator and the robot should mimic the action. To mimic the human's actions, a structure that supports and solves the issues related to motion tracking, human-robot figure relation, motion stability, and other issues is needed. This project consist of the development of a teleoperation system, which would allow a NAO humanoid robot to behave as a human motion imitator, using an optical motion capture system. © 2018 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Perturbation Analysis for QR Factorization of Unitary-Symmetric Matrix

引用

电子学报(英文版) 2006年第3期15卷 455-459页

作者： ZOU Hongxing WANG Dianjun DAI Qionghai LI Yanda Department of Automation Tsinghua University Beijing 100084 China State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing 100084 China National Laboratory of Pattern Recognition Institute of Automation The Chinese Academy of Sciences Beijing 100080 China Department of Mathematical Sciences Tsinghua University Beijing 100084 China

This paper considers the problem of perturbation analysis for the QR factorization of a special architecture called unitary-symmetric matrix. The perturbation bounds of the triangular factor and orthogonal factor in the QR factorization of unitary-symmetric matrix arc derived, together with the perturbation bound correspondences between the unitary-symmetric matrix and its mother matrix highlighted.

关键词： QR因数分解扰动分析对称矩阵正交因子

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：