11,715 Hits in 6.1 sec

Convolutional Neural Network-Based Cross-Media Semantic Matching and User Adaptive Satisfaction Analysis Model

Lanlan Jiang, Gengxin Sun
2022 Computational Intelligence and Neuroscience  
The spatial correlation of cross-media semantic matching further improves the classification accuracy of hyperspectral images and reduces the classification time under user adaptive satisfaction complexity  ...  the feature information of the image and uses dilated instead of traditional convolution.  ...  Introduction With the popularity and development of the global network, data such as text, images, and videos from various social networking sites, news sites, and mobile apps are in explosive growth every  ... 
doi:10.1155/2022/4244675 pmid:35535181 pmcid:PMC9078763 fatcat:5gdiv7u6rra6xjcmfe4jim77ne

Cross-Modal Search for Social Networks via Adversarial Learning

Nan Zhou, Junping Du, Zhe Xue, Chong Liu, Jinxuan Li
2020 Computational Intelligence and Neuroscience  
In addition, the semantic sparseness of cross-modal data from social networks results in the text and visual modalities misleading each other.  ...  In contrast to traditional cross-modal search, social network cross-modal information search is restricted by data quality for arbitrary text and low-resolution visual features.  ...  As the semantic labels of images, the text has clear semantic features; thus, the tasks of text-to-image and image-to-text search show good computing properties in local semantic mining and matching for  ... 
doi:10.1155/2020/7834953 pmid:32733547 pmcid:PMC7369674 fatcat:jphqvfhc7nbdbgg5xgguqtwp4q

Learning Semantic Correlation of Web Images and Text with Mixture of Local Linear Mappings

Youtian Du, Kai Yang
2015 Proceedings of the 23rd ACM international conference on Multimedia - MM '15  
This paper proposes a new approach, called mixture of local linear mappings (MLLM ), to the modeling of semantic correlation between web images and text.  ...  MLLM is with good interpretability due to its explicit closed form and concept-related local components, and it avoids the determination of capacity that is often considered for nonlinear transformations  ...  This paper proposes a new approach to the analysis of semantic correlation between text and images based on mixture of local linear mappings (MLLM ).  ... 
doi:10.1145/2733373.2806331 dblp:conf/mm/DuY15 fatcat:l4r5e5xytvhfverk235ffylpdu

Modality-Dependent Cross-Modal Retrieval Based on Graph Regularization

Guanhua Wang, Hua Ji, Dexin Kong, Na Zhang
2020 Mobile Information Systems  
Firstly, considering the potential feature correlation and semantic correlation, different projection matrices are learned for different retrieval tasks, such as image query text (I2T) or text query image  ...  At the same time, the semantic information of class labels is used to reduce the semantic gaps between different modalities data and realize the interdependence and interoperability of heterogeneous data  ...  Acknowledgments is work was partially supported by the National Natural Science Foundation of China (grant nos. 61772322, 61572298, 61702310, and 61873151).  ... 
doi:10.1155/2020/4164692 fatcat:2ku7xp5x65bkhggvu7x7skspja

Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval

Yale Song, Mohammad Soleymani
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this work, we introduce Polysemous Instance Embedding Networks (PIE-Nets) that compute multiple and diverse representations of an instance by combining global context with locally-guided features via  ...  We demonstrate our approach on both image-text and video-text retrieval scenarios using MS-COCO, TGIF, and our new MRW dataset.  ...  [33] use canonical correlation analysis (CCA) to maximize correlation between images and text, while Gong et al.  ... 
doi:10.1109/cvpr.2019.00208 dblp:conf/cvpr/SongS19 fatcat:hkpltx3oxncczf4b2eyvafh7gi

Cross-media cloud computing

Zhongzhi Shi, Guang Jiang, Bo Zhang, Jinpeng Yue, Xiaofei Zhao
2012 2012 IEEE 2nd International Conference on Cloud Computing and Intelligence Systems  
Cross-media is the outstanding characteristics of the age of big data with large scale and complicated processing task.  ...  Furthermore, we propose a framework for cross-media semantic understanding which contains discriminative modeling, generative modeling and cognitive modeling.  ...  Semantic spaces of images and text are isomorphic and can be considered same when cases both images and text appear in the same document classes.  ... 
doi:10.1109/ccis.2012.6664429 dblp:conf/ccis/ShiJZYZ12 fatcat:wefyscguf5bmjj2uzjafdjc2ty

Research on Domain Information Mining and Theme Evolution of Scientific Papers [article]

Changwei Zheng, Zhe Xue, Meiyu Liang, Feifei Kou, Zeli Guan
2022 arXiv   pre-print
This paper introduces the research status at home and abroad in terms of domain information mining and topic evolution law of scientific and technological papers from three aspects: the semantic feature  ...  representation learning of scientific and technological papers, the field information mining of scientific and technological papers, and the mining and prediction of research topic evolution rules of  ...  Acknowledgment This work was supported by National Key R&D Program of China (2018YFB1402600), and by the National Natural Science Foundation of China (61802028, 61772083, 61877006, 62002027). references  ... 
arXiv:2204.08476v1 fatcat:7cte3exhajbilbkvhktjgyvqha

A Massive Image Recognition Algorithm Based on Attribute Modelling and Knowledge Acquisition

Guohua Li, An Liu, Huajie Shen, Miaochao Chen
2021 Advances in Mathematical Physics  
The strengths and weaknesses of existing image semantic modelling algorithms are analysed.  ...  For the complexity of association relationships between attributes of incomplete data, a single-output subnetwork modelling method for incomplete data is proposed to build a neural network model with each  ...  Acknowledgments This work was supported by the Yunnan Provincial Science and Technology Department, Yunnan Provincial Innovation and Entrepreneurship Space "Woodcraft innovation space" (no. xctd201801)  ... 
doi:10.1155/2021/4632070 fatcat:ff2c5fmiovgczpe6kwbi5nnoda

Why Do We Click: Visual Impression-aware News Recommendation [article]

Jiahao Xun, Shengyu Zhang, Zhou Zhao, Jieming Zhu, Qi Zhang, Jingjie Li, Xiuqiang He, Xiaofei He, Tat-Seng Chua, Fei Wu
2021 arXiv   pre-print
To accommodate the research of visual impression-aware news recommendation, we extend the text-dominated news recommendation dataset MIND by adding snapshot impression images and will release it to nourish  ...  In addition, we inspect the impression from a global view and take structural information, such as the arrangement of different fields and spatial position of different words on the impression, into the  ...  Global Impression Modeling. Local impression modeling captures impression cues separately, which means we disregard the correlations and interactions between different impression cues.  ... 
arXiv:2109.12651v1 fatcat:pcjk6p7c4rbbrgc2hovl6zyfku

Hybrid Attention Network for Language-Based Person Search

Yang Li, Huahu Xu, Junsheng Xiao
2020 Sensors  
Third, a cross-modal attention mechanism and a joint loss function for cross-modal learning, which can pay more attention to the relevant parts between text and image features.  ...  It can better exploit both the cross-modal and intra-modal correlation and can better solve the problem of cross-modal heterogeneity.  ...  The CMAM is able to fully acquire the correlation between text and image feature and focuses on the correlated parts between features.  ... 
doi:10.3390/s20185279 pmid:32942720 pmcid:PMC7570628 fatcat:hrqu7lz4frg4vdvoicory4vm6e

A Novel Method for Satellite Image Retrieval using Semantic Mining and Hashing

Linda Mary, Kiran Ashok
2016 International Journal of Computer Applications  
Therefore, Content based image retrieval using high semantic features has been developed to overcome problems related to text retrieval and challenges associated with semantic gap.  ...  Keeping in consideration the importance of semantic features for CBIR, the proposed method introduces a novel method using Semantic mining and Hashing for fast retrieval and attainment of accurate results  ...  Semantic mining and Hashing have been combined in order to obtain better results with accurate precision and recall.  ... 
doi:10.5120/ijca2016911140 fatcat:7tejedlyljgnnjuzs35wtvooda

Cross-modal Image Retrieval with Deep Mutual Information Maximization [article]

Chunbin Gu, Jiajun Bu, Xixi Zhou, Chengwei Yao, Dongfang Ma, Zhi Yu, Xifeng Yan
2021 arXiv   pre-print
Specifically, our method narrows the modality gap between the text modality and the image modality by maximizing mutual information between their not exactly semantically identical representation.  ...  a similarity metric between the desired image and the source image + modified text by using deep metric learning.  ...  As section 3.1, we increase the dependence between the fusion modality and the image modality by global MI, local MI and prior matching objectives.  ... 
arXiv:2103.06032v1 fatcat:zqjxweq3nbgwfgi5ib5pesgp5e

A Survey on Visual Content-Based Video Indexing and Retrieval

Weiming Hu, Nianhua Xie, Li Li, Xianglin Zeng, S. Maybank
2011 IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)  
boundary detection, key frame extraction and scene segmentation, extraction of features including static key frame features, object features and motion features, video data mining, video annotation, video  ...  retrieval including query interfaces, similarity measure and relevance feedback, and video browsing.  ...  [154] propose an online video semantic classification framework, in which local and global sets of optimized classification models are online trained by sufficiently exploiting both local and global  ... 
doi:10.1109/tsmcc.2011.2109710 fatcat:qtenus4htffcfbyuiwidgjojku

Visual topic model for web image annotation

Xianming Liu, Hongxun Yao, Rongrong Ji, Pengfei Xu, Xiaoshuai Sun, Qi Tian
2010 Proceedings of the Second International Conference on Internet Multimedia Computing and Service - ICIMCS '10  
The framework aims at analyzing image semantics fusing both content and context, by considering tag correlations and ambiguities.  ...  Furthermore, a keyword selection and image annotation algorithm is also developed and applied to Flickr database with 175,770 images.  ...  only global features, and some local descriptors may be more helpful for object level applications.  ... 
doi:10.1145/1937728.1937758 dblp:conf/icimcs/LiuYJXST10 fatcat:deu7gz4xzndxppasmaxgzygt6y

Diachronic Cross-modal Embeddings

David Semedo, Joao Magalhaes
2019 Proceedings of the 27th ACM International Conference on Multimedia - MM '19  
Understanding the semantic shifts of multimodal information is only possible with models that capture cross-modal interactions over time.  ...  Quantitative experiments, confirm that DCM is able to preserve semantic cross-modal correlations at each instant t while also providing better alignment capabilities.  ...  With this strategy we maximise correlation between modalities using images and texts that occur together, allowing us to better capture intra-category semantic diversity.  ... 
doi:10.1145/3343031.3351036 dblp:conf/mm/SemedoM19a fatcat:sv6uekobmbfxteqybxt6tnv26i
« Previous Showing results 1 — 15 out of 11,715 results