Filters








6,470 Hits in 5.8 sec

Guest editorial: web multimedia semantic inference using multi-cues

Yahong Han, Yi Yang, Xiaofang Zhou
2015 World wide web (Bussum)  
The paper, titled "A Cross-media Distance Metric Learning Framework based on Multi-view Correlation Mining and Matching", presents a novel cross-media distance metric learning framework based on sparse  ...  Cross-media distance metric learning focuses on correlation measure between multimedia data of different modalities.  ... 
doi:10.1007/s11280-015-0360-2 fatcat:vc4plge5qvg7hfmza3dffmawki

2018 Index IEEE Transactions on Knowledge and Data Engineering Vol. 30

2019 IEEE Transactions on Knowledge and Data Engineering  
., þ, TKDE April 2018 717-728 Learning (artificial intelligence) A Comprehensive Study on Social Network Mental Disorders Detection via Online Social Media Mining.  ...  ., þ, TKDE Nov. 2018 2185-2198 Paradoxical Correlation Pattern Mining. Zhou, W., þ, TKDE Aug. 2018 1561-1574 SLA Definition for Multi-Tenant DBMS and its Impact on Query Optimization.  ... 
doi:10.1109/tkde.2018.2882359 fatcat:asiids266jagrkx5eac6higrlq

Multi-modal Deep Analysis for Multimedia

Wenwu Zhu, Xin Wang, Hongzhi Li
2019 IEEE transactions on circuits and systems for video technology (Print)  
More specifically, on data-driven correlational representation, we highlight three important categories of methods, such as multi-modal deep representation, multi-modal transfer learning, and multi-modal  ...  answering, multi-modal video summarization, multi-modal visual pattern mining and multi-modal recommendation.  ...  ACKNOWLEDGMENT We thank Guohao Li, Shengze Yu and Yitian Yuan for providing relevant materials and valuable opinions. This work will never be accomplished without their useful suggestions.  ... 
doi:10.1109/tcsvt.2019.2940647 fatcat:l4tchrkgrnaeradvc4nhfan2w4

D-Sempre: Learning Deep Semantic-Preserving Embeddings for User interests-Social Contents Modeling [article]

Shuang Ma, Chang Wen Chen
2018 arXiv   pre-print
As a result, D-Sempre effectively integrates the multi-modal data from heterogeneous social media feeds and captures the hidden semantic correlations between users' interests and social contents.  ...  At last, a Deep Semantic-Preserving Embedding (D-Sempre) is learned, and the ranking results can be given by calculating distances between social contents and users.  ...  term for the cross-view matching task. • We point out the importance of visual content, external social context and social relation.  ... 
arXiv:1802.06451v1 fatcat:kzjmdotq2bgffiplfhxlu3qldm

Joint graph regularization based semantic analysis for cross-media retrieval: a systematic review

Monelli Ayyavaraiah, Dr Bondu Venkateswarlu
2018 International Journal of Engineering & Technology  
Many research is done on the cross-media retrieval with different methods and provide the different result.  ...  If the query is given as the text and acquired result are present in text. The users demand the cross-media retrieval for their queries and it is very consistent in providing the result.  ...  [11] , proposed the model for the cross-media uniform representation and also done the cross-media correlation with understanding and deep mining.  ... 
doi:10.14419/ijet.v7i2.7.10592 fatcat:6quy3kb2g5dhvg2ccv2vppg7be

Adversarial Attentive Multi-modal Embedding Learning for Image-Text Matching

Kaimin Wei, Zhibo Zhou
2020 IEEE Access  
Mining the correlation between image and text to learn effective multi-modal features is crucial for image-text matching.  ...  In this work, we propose a novel model named Adversarial Attentive Multi-modal Embedding Learning (AAMEL) for image-text matching.  ...  Mining this type of correlation is useful to learn more effective multi-modal representation for image-text matching.  ... 
doi:10.1109/access.2020.2996407 fatcat:ilgrbt4k2zebbe3nlf532c3jma

Cross-media Multi-level Alignment with Relation Attention Network [article]

Jinwei Qi, Yuxin Peng, Yuxin Yuan
2018 arXiv   pre-print
Second, we propose cross-media multi-level alignment to explore global, local and relation alignments across different media types, which can mutually boost to learn more precise cross-media correlation  ...  Relation understanding is essential for cross-media correlation learning, which is ignored by prior cross-media retrieval works.  ...  Acknowledgments This work was supported by National Natural Science Foundation of China under Grant 61771025 and Grant 61532005.  ... 
arXiv:1804.09539v1 fatcat:7bpfoixw2rbfji3b4h7jytyvly

Mining and searching association relation of scientific papers based on deep learning [article]

Jie Song and Meiyu Liang and Zhe Xue and Feifei Kou and Ang Li
2022 arXiv   pre-print
Therefore, the research on mining and searching the association relationship of scientific papers based on deep learning has far-reaching practical significance.  ...  There is a complex correlation among the data of scientific papers.  ...  ACM-GCN [18] proposes a new metric based on similarity matrix, considering the influence of graph structure and input features on GNN, and then proposes an Adaptive Channel Mixing (ACM) framework to  ... 
arXiv:2204.11488v1 fatcat:zxwvpnids5bopberzumjofgupq

Twitter100k: A Real-world Dataset for Weakly Supervised Cross-Media Retrieval [article]

Yuting Hu, Liang Zheng, Yi Yang, Yongfeng Huang
2017 arXiv   pre-print
As a minor contribution, inspired by the characteristic of Twitter100k, we propose an OCR-based cross-media retrieval method.  ...  This paper contributes a new large-scale dataset for weakly supervised cross-media retrieval, named Twitter100k.  ...  Deep learning methods. Some cross-media retrieval methods are based on deep learning.  ... 
arXiv:1703.06618v1 fatcat:qhvet57kmjhs7hcbcc2nslegfy

Deep Coordinated Textual and Visual Network for Sentiment-Oriented Cross-Modal Retrieval [chapter]

Jiamei Fu, Dongyu She, Xingxu Yao, Yuxiang Zhang, Jufeng Yang
2018 Lecture Notes in Computer Science  
The visual branch is based on a convolutional neural network (CNN) pre-trained on a large dataset, which is optimized with the classification loss.  ...  This paper proposes a deep coordinated textural and visual network with two branches to learn a joint semantic embedding space for both images and texts.  ...  U1533104), and the Open Project Program of the National Laboratory of Pattern Recognition (NLPR).  ... 
doi:10.1007/978-3-319-97304-3_52 fatcat:sqqwb5u7ivhe3k6jyf3si6mjj4

MULTI-MODAL RETRIEVAL IN NEWS FEED APP USING GCDL TECHNIQUE

2017 International Journal of Recent Trends in Engineering and Research  
sparse hashing (LSSH), discriminative coupled dictionary hashing (DCDH) , Cross-view Hashing (CVH), and so on.  ...  Since each modality having different representation methods and correlational structures, a variety of methods studied the problem from the aspect of learning correlations between different modalities.  ...  across the views to enable cross-view similarity search.  Discriminative coupled dictionary hashing generates a coupled dictionary for each modality based on category labels.  Multi view discriminative  ... 
doi:10.23883/ijrter.2017.3365.aeikk fatcat:6dmfmfsmtbaejale6t63ts7may

The Re-identification Challenge [chapter]

Shaogang Gong, Marco Cristani, Chen Change Loy, Timothy M. Hospedales
2014 Person Re-Identification  
As a result, the field has drawn growing and wide interest from academic researchers and industrial developers.  ...  to solving some of the fundamental challenges in person re-identification, benefiting from research in computer vision, pattern recognition and machine learning, and drawing insights from video analytics  ...  Learning Distance Metric A popular alternative to colour transformation learning is distance metric learning.  ... 
doi:10.1007/978-1-4471-6296-4_1 dblp:series/acvpr/GongCLH14 fatcat:l7jbhs4g2jgcxdjceywbszb374

Deep Learning Techniques for Future Intelligent Cross-Media Retrieval [article]

Sadaqat ur Rehman, Muhammad Waqas, Shanshan Tu, Anis Koubaa, Obaid ur Rehman, Jawad Ahmad, Muhammad Hanif, Zhu Han
2020 arXiv   pre-print
In this paper, we provide a novel taxonomy according to the challenges faced by multi-modal deep learning approaches in solving cross-media retrieval, namely: representation, alignment, and translation  ...  These challenges are evaluated on deep learning (DL) based methods, which are categorized into four main groups: 1) unsupervised methods, 2) supervised methods, 3) pairwise based methods, and 4) rank based  ...  These methods enforce some constraints on alignment, such as the temporal ordering of sequences and similarity metric existence between the modalities. To align multi-view time series Kruskal et al.  ... 
arXiv:2008.01191v1 fatcat:t63bg55w2vdqjcprzaaidrmprq

User-curated image collections: Modeling and recommendation

Yuncheng Li, Tao Mei, Yang Cong, Jiebo Luo
2015 2015 IEEE International Conference on Big Data (Big Data)  
For image collection modeling, we consider each image collection as a whole in a group sparse reconstruction framework and extract concise collection descriptors given the pretrained dictionaries.  ...  We then consider image collection recommendation as a dynamic similarity measurement problem in response to user's clicked image set, and employ a metric learner to measure the similarity between the image  ...  recommendation based on metric learning.  ... 
doi:10.1109/bigdata.2015.7363803 dblp:conf/bigdataconf/LiMCL15 fatcat:ebw6hirf6jbz7iqdrzp5dhzysy

Multi-Face: Self-supervised Multiview Adaptation for Robust Face Clustering in Videos [article]

Krishna Somandepalli, Rajat Hebbar, Shrikanth Narayanan
2020 arXiv   pre-print
We propose a nearest-neighbor search in the embedding space to mine hard examples from the face tracks followed by domain adaptation using multiview shared subspace learning.  ...  Robust face clustering is a key step towards computational understanding of visual character portrayals in media.  ...  We used the model trained on the VggFace2. SphereFace [24] is a metric-learning method which combines the ideas of cross-entropy and angular margin loss to improve classification.  ... 
arXiv:2008.11289v1 fatcat:mjmo66psm5ggxbebaacx4f525y
« Previous Showing results 1 — 15 out of 6,470 results