A Multimedia Semantic Retrieval Mobile System Based on HCFGs

Yang, Yimin; Ha, Hsin-Yu; Fleites, Fausto C.; Chen, Shu‐Ching

doi:10.1109/mmul.2013.33

Cited by 15 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Affinity propagation is an unsupervised deterministic clustering method, which has been extended to group correlated features as clusters in our previous work [7]. In this paper, we propose the new importance factor (IF) measures for feature selection by integrating these two methods so that the IF measures for the selected features can be generated to represent their weights with respect to a certain class.…”

Section: Feature Selectionmentioning

confidence: 99%

“…In this chapter, a hierarchical semantic information representation schema will be elaborated, which ranges from low-level feature to high-level semantics. Specifically, a Hidden Coherent Feature Groups (HCFGs) analysis approach will be introduced to support multimedia semantic retrieval on mobile applications [7]. Furthermore, a highlevel semantic object extraction method is proposed for efficient object retrieval by fusing spatial color and texture information [62].…”

Section: Multimedia Content Representationmentioning

confidence: 99%

“…With the aforementioned existing problems and challenges, we propose a correlation based feature analysis method to explore Hidden Coherent Feature Groups (HCFGs) and present a novel, multi-model fusion scheme [7]. Specifically, we analyze the correlation between each feature pair and use the affinity propagation algorithm to separate the original feature set into different feature groups (HCFGs), where the intra-group correlation is maximized and the inter-group correlation is minimized.…”

Section: Hidden Coherent Feature Groups For Multimedia Semantic Retrimentioning

confidence: 99%

“…In our previous work [7], it has been successfully applied for concept retrieval. Compared with the traditional clustering algorithms, such as k-means and mixtures of Gaussian, the AP algorithm is able to automatically determine the number of clusters with both the lower error and computational complexity.…”

Section: Feature Affinity Propagationmentioning

confidence: 99%

“…Data Imbalance: Learning from imbalanced data sets for binary classification problems has been a hot and challenging topic in the research societies and has many realworld applications, such as fraud detection [2], medical diagnosis [3], intrusion detec- tion [4], face recognition [5], information retrieval [6,7] and video event detection [8].…”

mentioning

confidence: 99%

See 4 more Smart Citations

Exploring Hidden Coherent Feature Groups and Temporal Semantics for Multimedia Big Data Analysis

Yang¹

Self Cite

View full text Add to dashboard Cite

Section: Feature Selectionmentioning

confidence: 99%

Section: Multimedia Content Representationmentioning

confidence: 99%

Section: Hidden Coherent Feature Groups For Multimedia Semantic Retrimentioning

confidence: 99%

Section: Feature Affinity Propagationmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Exploring Hidden Coherent Feature Groups and Temporal Semantics for Multimedia Big Data Analysis

Yang¹

Self Cite

View full text Add to dashboard Cite

Multimedia Internet of Things: A Comprehensive Survey

et al. 2020

View full text Add to dashboard Cite

The immense increase in multimedia-on-demand traffic that refers to audio, video, and images, has drastically shifted the vision of the Internet of Things (IoT) from scalar to Multimedia Internet of Things (M-IoT). IoT devices are constrained in terms of energy, computing, size, and storage memory. Delaysensitive and bandwidth-hungry multimedia applications over constrained IoT networks require revision of IoT architecture for M-IoT. This paper provides a comprehensive survey of M-IoT with an emphasis on architecture, protocols, and applications. This article starts by providing a horizontal overview of the IoT. Then, we discuss the issues considering the characteristics of multimedia and provide a summary of related M-IoT architectures. Various multimedia applications supported by IoT are surveyed, and numerous use cases related to road traffic management, security, industry, and health are illustrated to show how different M-IoT applications are revolutionizing human life. We explore the importance of Quality-of-Experience (QoE) and Quality-of-Service (QoS) for multimedia transmission over IoT. Moreover, we explore the limitations of IoT for multimedia computing and present the relationship between the M-IoT and emerging technologies including event processing, feature extraction, cloud computing, Fog/Edge computing and Software-Defined-Networks (SDNs). We also present the need for better routing and Physical-Medium Access Control (PHY-MAC) protocols for M-IoT. Finally, we present a detailed discussion on the open research issues and several potential research areas related to emerging multimedia communication in IoT. INDEX TERMS Multimedia Internet of Things (M-IoT), multimedia communication, Internet of Multimedia Things (IoMT), multimedia computing, Quality-of-Experience (QoE), Quality-of-Service (QoS), multimedia routing, medium access control (MAC).

show abstract