检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

50 篇 会议
2 册 图书

馆藏范围

52 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

46 篇 工学
- 45 篇 计算机科学与技术...
- 41 篇 软件工程
- 5 篇 信息与通信工程
- 5 篇 生物工程
- 4 篇 电气工程
- 3 篇 光学工程
- 3 篇 化学工程与技术
- 2 篇 安全科学与工程
- 1 篇 机械工程
- 1 篇 土木工程
- 1 篇 生物医学工程（可授...
31 篇 医学
- 31 篇 临床医学
9 篇 理学
- 5 篇 生物学
- 4 篇 物理学
- 3 篇 数学
- 3 篇 化学
- 3 篇 统计学（可授理学、...
- 1 篇 地质学
1 篇 管理学
- 1 篇 图书情报与档案管...

主题

4 篇 deep learning
4 篇 continual learni...
4 篇 computer vision
2 篇 variational infe...
2 篇 segmentation
2 篇 transformer
2 篇 image quality as...
2 篇 image segmentati...
2 篇 face recognition
2 篇 brain tumor segm...
2 篇 contrastive lear...
2 篇 remote sensing
2 篇 machine learning
2 篇 computer imaging...
2 篇 vision-language ...
2 篇 unsupervised lea...
1 篇 image enhancemen...
1 篇 vision transform...
1 篇 computational ar...
1 篇 crossmodal retri...

机构

3 篇 indian inst tech...
2 篇 iiit hyderabad h...
2 篇 iit jodhpur jodh...
2 篇 indian inst tech...
2 篇 lnm inst informa...
1 篇 int inst informa...
1 篇 department of ar...
1 篇 indian inst tech...
1 篇 department of co...
1 篇 iiit hyderabad c...
1 篇 indian inst tech...
1 篇 centre of resear...
1 篇 indian inst sci ...
1 篇 department of me...
1 篇 indian inst sci ...
1 篇 department of co...
1 篇 printing technol...
1 篇 iiit hyderabad c...
1 篇 ahmedabad univ a...
1 篇 indian inst tech...

作者

3 篇 banerjee biplab
2 篇 palit sanchar
2 篇 gupta phalguni
2 篇 namboodiri anoop
2 篇 mukhopadhyay jay...
2 篇 zhang hao
2 篇 jha ankit
1 篇 s. vimal
1 篇 nilesh nitin
1 篇 alavala sasidhar
1 篇 jaisankar vijay
1 篇 das sukhendu
1 篇 kathalkar om raj...
1 篇 chaudhari sachin
1 篇 santhosh vaibhav
1 篇 qin jiacheng
1 篇 li yang
1 篇 das partha prati...
1 篇 biswas sandika
1 篇 gad r. s.

语言

52 篇 英文

检索条件"任意字段=15th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2024"

共 52 条记录，以下是31-40 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Extended Multi-spectral Face Recognition Across Two Different Age Groups: An Empirical Study 16

Extended Multi-spectral Face Recognition Across Two Differen...

引用

10th indian conference on computer vision, graphics and image processing (icvgip)

作者： Vetrekar, N. T. Raghavendra, R. Gaonkar, A. A. Naik, G. M. Gad, R. S. Goa Univ Taleigao Goa India NTNU Trondheim Norway

ISBN: (纸本)9781450347532

Face recognition has attained a greater importance in biometric authentication due to its non-intrusive property of identifying individuals at varying stand-off distance. Face recognition based on multi-spectral imaging has recently gained prime importance due to its ability to capture spatial and spectral information across the spectrum. Our first contribution in this paper is to use extended multi-spectral face recognition in two different age groups. the second contribution is to show empirically the performance of face recognition for two age groups. thus, in this paper, we developed a multi-spectral imaging sensor to capture facial database for two different age groups (<= 15years and >= 20years) at nine different spectral bands covering 530nm to 1000nm range. We then collected a new facial images corresponding to two different age groups comprises of 168 individuals. Extensive experimental evaluation is performed independently on two different age group databases using four different state-of-the-art face recognition algorithms. We evaluate the verification and identification rate across individual spectral bands and fused spectral band for two age groups. the obtained evaluation results shows higher recognition rate for age groups >= 20years than <= 15years, which indicates the variation in face recognition across the different age groups.

关键词： Face Recognition Facial Age Groups Multi-spectral Imaging Feature Extraction Collaborative Representation

来源：评论

学校读者我要写书评

暂无评论

TRAQID - Traffic-Related Air Quality image Dataset 24

TRAQID - Traffic-Related Air Quality Image Dataset

引用

15th indian conference on computer vision graphics and image processing

作者： Kathalkar, Om Rajendra Nilesh, Nitin Chaudhari, Sachin Namboodiri, Anoop Int Inst Informat Technol Signal Proc & Commun Res Ctr Hyderabad Telangana India Int Inst Informat Technol Ctr Visual Informat Technol CVIT Hyderabad Telangana India

ISBN: (纸本)9798400710759

Air quality estimation through sensor-based methods is widely used. Nevertheless, their frequent failures and maintenance challenges constrain the scalability of air pollution monitoring efforts. Recently, it has been demonstrated that air quality estimation can be done using image-based methods. these methods offer several advantages including ease of use, scalability, and low cost. However, the accuracy of these methods hinges significantly on the diversity and magnitude of the dataset utilized. the advancement of air quality estimation through image analysis has been limited due to the lack of available datasets. Addressing this gap, we present TRAQID - Traffic-Related Air Quality image Dataset, a novel dataset capturing 26,678 front and rear images of traffic alongside co-located weather parameters, multiple levels of Particulate Matters (PM) and Air Quality Index (AQI) values. Spanning over multiple seasons, with over 70 hours of data collection in the twin cities of Hyderabad and Secunderabad, India, the TRAQID offers diverse day and night imagery amid unstructured traffic conditions, encompassing six AQI categories ranging from "Good" to "Severe". State-of-the-art air quality estimation techniques, which were trained on a smaller and less-diverse dataset, showed poor results on the dataset presented in this paper. TRAQID models various uncertainty types, including seasonal changes, unstructured traffic patterns, and lighting conditions. the information from the two views (front and rear) of the traffic can be combined to improve the estimation performance in such challenging conditions. As such, the TRAQID serves as a benchmark for image-based air quality estimation tasks and AQI prediction, given its diversity and magnitude. Dataset Link

关键词： image Dataset Air Quality Estimation Vehicle-Induced Pollution Environmental Data

来源：评论

学校读者我要写书评

暂无评论

Variational Distribution and Experience Replay for 3D Reconstruction in a Continual Learning Framework 24

Variational Distribution and Experience Replay for 3D Recons...

引用

15th indian conference on computer vision graphics and image processing

作者： Palit, Sanchar Biswas, Sandika Indian Inst Technol Elect Engn Mumbai Maharashtra India Monash Univ Melbourne Vic Australia

ISBN: (纸本)9798400710759

Single-image 3D reconstruction is a research challenge focused on predicting 3D object shapes from single-view images, requiring all training data for all objects to be available from the start. In dynamic environments, it's impractical to gather data for all objects at once;data becomes available in phases with restrictions on past data access. therefore, the model must reconstruct new objects while retaining the ability to reconstruct previous objects without accessing prior data. Additionally, existing 3D reconstruction methods in continual learning fail to reproduce previous shapes accurately, as they are not designed to manage changing shape information in dynamic scenes. To this end, we propose a continual learning-based 3D reconstruction method. Our goal is to design a model that can accurately reconstruct previously seen classes even after training on new ones, ensuring faithful reconstruction of both current and previous objects. To achieve this, we propose using variational distribution from the latent space, which represent abstract shapes and effectively retain shape information within a simplified code structure that requires minimal memory. Additionally, saliency maps preserve object attributes, capturing both local minor shape details and the overall shape structure. We employ experience replay to leverage these saliency maps effectively. Both methods ensure that the shape is faithfully reconstructed, preserving all minor details from the previous dataset. this is vital due to resource constraints in storing extensive training data. thorough experiments show competitive results compared to established methods, both quantitatively and qualitatively.

关键词： 3D reconstruction Continual Learning Variational Inference image saliency

来源：评论

学校读者我要写书评

暂无评论

Exploring the Limits of VLMs: A Dataset for Evaluating Text-to-Video Generation 24

Exploring the Limits of VLMs: A Dataset for Evaluating Text-...

引用

15th indian conference on computer vision graphics and image processing

作者： Srivastava, Avnish Sista, Raviteja Chakrabarti, Partha P. Sheet, Debdoot Indian Inst Technol Kharagpur Kharagpur W Bengal India

ISBN: (纸本)9798400710759

vision language models (VLMs) integrate vision and text by learning from images and their textual descriptions for generating text from images and vice-versa. VLMs are used for various tasks such as image captioning, and visual question answering. As VLMs extend to video generation tasks, significant challenges arise. the generated videos often lack temporal consistency, and there exist issues with alignment between the generated video content and the input text. this work proposes a set of prompts for systematically evaluating VLMs on text-to-video generation focused on object coherence and temporal consistency. this dataset of prompt covers two categories: first, the complexity of prompts, and second, the number of objects and actions. the first category consists of four levels of prompt complexity: simple, mid-level, high-level, and unique and rare object prompts. the second category also consists of four levels: single object, single object in action, multiple objects, and multiple objects in action. thus, the dataset is a combination of 16 different prompt scenarios where each scenarios has 10 prompts resulting in a dataset of 160 prompts. this work explores and evaluates the outputs of three models from the family of diffusion-based VLMs for the task of text to video generation. the videos generated by the models were assessed by five participants on a 0-5 Likert scale. VLMs under study were able to generate temporally consistent videos and proper object in video in only 33.63% and 39.43% of the total evaluation scenario prompts. Most of these prompts belong to the categories of single object and simple prompts. the performance of models drops with increase in objects, actions and prompt complexity. the scenarios of actions, with rare prompts are where all models perform poorly. thus, reflecting on limitations of VLMs in generating videos. the proposed dataset can be extended to other video generation models to benchmark their performances on the basic aspects

关键词： Benchmark dataset Diffusion models Temporal consistency Video generation vision language models

来源：评论

学校读者我要写书评

暂无评论

Revised Regularization for Efficient Continual Learning through Correlation-Based Parameter Update in Bayesian Neural Networks 24

Revised Regularization for Efficient Continual Learning thro...

引用

15th indian conference on computer vision graphics and image processing

作者： Palit, Sanchar Banerjee, Biplab Chaudhuri, Subhasis Indian Inst Technol Bombay Maharashtra India

ISBN: (纸本)9798400710759

We propose a Bayesian neural network-based continual learning algorithm using Variational Inference, aiming to overcome several drawbacks of existing methods. Specifically, in continual learning scenarios, storing network parameters at each step to retain knowledge poses challenges. this is compounded by the crucial need to mitigate catastrophic forgetting, particularly given the limited access to past datasets, which complicates maintaining correspondence between network parameters and datasets across all sessions. Current methods using Variational Inference with KL divergence risk catastrophic forgetting during uncertain node updates and coupled disruptions in certain nodes. To address these challenges, we propose the following strategies. To reduce the storage of the dense layer parameters, we propose a parameter distribution learning method that significantly reduces the storage requirements. In the continual learning framework employing variational inference, our study introduces a regularization term that specifically targets the dynamics and population of the mean and variance of the parameters. this term aims to retain the benefits of KL divergence while addressing related challenges. To ensure proper correspondence between network parameters and the data, our method introduces an importance-weighted Evidence Lower Bound term to capture data and parameter correlations. this enables storage of common and distinctive parameter hyperspace bases. the proposed method partitions the parameter space into common and distinctive subspaces, with conditions for effective backward and forward knowledge transfer, elucidating the network-parameter dataset correspondence. the experimental results demonstrate the effectiveness of our method across diverse datasets and various combinations of sequential datasets, yielding superior performance compared to existing approaches.

关键词： Continual Learning Variational Inference Evidence Lower Bound Bayesian neural network

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Transformer-CNN Network for Brain Tumor Segmentation and Survival Prediction 24

Multi-Scale Transformer-CNN Network for Brain Tumor Segmenta...

引用

15th indian conference on computer vision graphics and image processing

作者： Mazumdar, Indrajit Mukhopadhyay, Jayanta Indian Inst Technol Kharagpur Dept Comp Sci & Engn Kharagpur W Bengal India

ISBN: (纸本)9798400710759

Accurately segmenting brain tumors and predicting survival is crucial for diagnostic and personalized treatment plans. Recently, convolutional neural networks (CNNs) based on U-Net architecture have been extensively used to segment brain tumors. It is essential to capture both local and global dependencies to segment brain tumors accurately. therefore, several studies have considered U-Net variants by combining a CNN and a Transformer. However, the skip connections in these Transformer-based U-Net variants do not incorporate the features from multiple scales available at the encoder. To address this issue, we propose a new 3D U-Net variant called Multi-Scale Transformer-CNN Network (MTC-Net) that incorporates a Multi-Scale Transformer Convolution (MTC) block into the skip connections. the MTC block extracts local multi-scale features from the CNN encoder blocks and global features using Swin Transformer blocks to handle the wide variability in tumor size and enhance the feature representation capability. the segmentation mask predicted by the proposed MTC-Net is subsequently used to predict a patient's overall survival time. Most studies on overall survival prediction have used handcrafted radiomic features that lack the ability to fully model complex tumor patterns. In contrast, deep features are specifically adapted to brain tumors. We observed that instead of using only a CNN, combining it with a Transformer produces deep features that provide more accurate predictions. For this purpose, we extract deep features using our Transformer-based network MTC-Net to construct a regression model for predicting overall survival. Comprehensive experimentation on the BraTS 2020 and 2021 benchmark datasets proved the efficacy of the proposed components. MTC-Net outperformed the CNN- and Transformer-based state-of-the-art segmentation networks. Moreover, our approach outperformed the state-of-the-art survival prediction systems.

关键词： Brain tumor segmentation Deep learning CNN Transformer Survival prediction Machine learning

来源：评论

学校读者我要写书评

暂无评论

CHAPVIDMR: Chapter-based Video Moment Retrieval using Natural Language Queries 24

CHAPVIDMR: Chapter-based Video Moment Retrieval using Natura...

引用

15th indian conference on computer vision graphics and image processing

作者： Agarwal, Uday Kumar, Yogesh Shahid, Abu Gatti, Prajwal Gupta, Manish Mishra, Anand IIT Jodhpur Jodhpur Rajasthan India Univ Bristol Bristol Avon England MicrosoftIndia Hyderabad Andhra Pradesh India Indian Inst Technol Jodhpur CSE Jodhpur Rajasthan India

ISBN: (纸本)9798400710759

Video Moment Retrieval (VMR) is the task of linking a query with a relevant moment from a video. Although, recently, there has been work on the VMR task where a query is linked to a single moment, the corresponding task where the query needs to be linked to multiple moments has been understudied. In this paper, we aim to work on the VMR task primarily by leveraging chapters of YouTube videos, i.e., video segments. YouTube chapters provide a meaningful segmentation of videos annotated by content authors. these annotated segmented regions help the viewer to navigate to a specific segment of the long video in which the user is interested. We present the CHAPVIDMR (Chapter-based Video Moment Retrieval) dataset, containing 10.8K user queries (obtained using GPT4) formed using multiple chapter names and other metadata extracted from videos using the YouTube API. Furthermore, we benchmark the proposed dataset on two VMR tasks: chapter classification-based VMR and segmentation-based VMR. In the chapter classification-based VMR task, the model classifies which of the chapters associated with a video are most relevant to the query. We represent a chapter by exploiting text (subtitles), audio, and visual (captions, video) modalities using state-of-the-art feature representation techniques and experiment with an exhaustive ablation for each modality. In segmentation-based VMR, the video is divided into various segments, and the segments most likely to answer the query are identified and returned. We benchmark our dataset on the state-of-the-art methods for segmentation tasks. We find that for the chapter classification-based VMR task, Sentence-BERT with subtitles and visual captions leads to the best results, while for the segmentation-based VMR, UniVTG is the most accurate. We make our code and data publicly available(1).

关键词： video moment retrieval CHAPVIDMR VMR chapter-based retrieval

来源：评论

学校读者我要写书评

暂无评论

image Segmentation and Geometric Feature Based Approach for Fast Video Summarization of Surveillance Videos 1

引用

3rd Workshop on computer vision Applications, WCVA 2018, held in conjunction with the 11th indian conference on computer vision, graphics and image processing, icvgip 2018

作者： Rohan, Raju Dhanakshirur ara Patel, Zeba Yadavannavar, Smita C. Sujata, C. Mudengudi, Uma KLE Technological University Hubli India

ISBN: (数字)9789811513879

ISBN: (纸本)9789811513862

In this paper, we propose a geometric feature and frame segmentation based approach for video summarization. Video summarization aims to generate a summarized video with all the salient activities of the input video. We propose to retain the salient frames towards generation of video summary. We detect saliency in foreground and background of the image separately. We propose to model the image as MRF (Markov Random Field) and use MAP (Maximum a-posteriori) as final solution to segment the image into foreground and background. the salient frame is defined by the variation in feature descriptors using the geometric features. We propose to combine the probabilities of foreground and background segments being salient using DSCR (Dempster Shafer Combination Rule). We consider the summarized video as a combination of salient frames for a user defined time. We demonstrate the results using several videos in BL-7F dataset and compare the same with state of art techniques using retention ratio and condensation ratio as quality parameters. © Springer Nature Singapore Pte Ltd, 2019.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Dynamic image Networks for Human Fall Detection in 360-degree Videos 1

引用

3rd Workshop on computer vision Applications, WCVA 2018, held in conjunction with the 11th indian conference on computer vision, graphics and image processing, icvgip 2018

作者： Saurav, Sumeet Madhu Kiran, T.N.D. Sravan Kumar Reddy, B. Sanjay Srivastav, K. Singh, Sanjay Saini, Ravi CSIR-CEERI Pilani India Birla Institute of Technology and Sciences Pilani India

ISBN: (数字)9789811513879

ISBN: (纸本)9789811513862

Detection of falls of elderly people is a trivial yet an immediate problem due to the growing age of the population. this demands the need for autonomous self care systems for providing a quick assistance. the three basic approaches used for fall detection include non-invasive vision based devices, ambient based devices and wearable devices. the paper tries to improve upon the state-of-art of accuracy to 98% using vision based system. this was achieved through transfer learning by extending the idea of action recognition using dynamic images which is a standard RGB image containing the appearance and dynamics of a whole video sequence. Such information is vital in dealing with applications like human action recognition. Since we are also looking for a cheap and scalable solution, the use of a 360∘ camera seems reasonable and reliable. the top view provided by this camera gives a better perspective than any other alternatives by giving an un-obstructive view of the subjects. © Springer Nature Singapore Pte Ltd, 2019.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

MATIC: Memory-Guided Adaptive Transformer for image Captioning 12th

MATIC: Memory-Guided Adaptive Transformer for Image Captioni...

引用

12th indian conference on computer vision, graphics, and image processing, icvgip 2021

作者： Gajhiye, Gaurav O. Nandedkar, Abhijeet V. Nanded India

ISBN: (纸本)9789811941351

Transforming the visual knowledge into linguistic description is a demanding and essential task known as image captioning, which necessitates a vision-language-based system to co-relate the multi-modal information. Transformer architecture has recently become cutting-edge in addressing the image captioning-related problems. In this paper, the utility of the transformer is explored by bridging single layer memory-guided encoder and multi-layer adaptive attention decoder framework entitled as Memory-guided Adaptive Transformer for image Captioning. the memory-based encoder is used to capture the relative spatial information from CNN-based visual features and transfer it to the decoder, which then learns the inter-modality affinity between visual and linguistic features. the decoder with multi-headed adaptive attention reconciles the visual and linguistic information to describe the visual contents in a comprehensible way by balancing visual and semantic patterns through adaptive gate channeling. the performance of the proposed method is evaluated on widely used captioning datasets viz. Flickr8k and Flickr30k. the proposed method performs remarkable and earns a superior caption generation score on both datasets as compared to state-of-the-art. © 2022, the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共6页 << < 1 2 3 4 5 6 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：