Proceedings of the 9th IEEE International Conference on Collaborative Computing: Networking, Applications and Worksharing 2013
DOI: 10.4108/icst.collaboratecom.2013.254110
|View full text |Cite
|
Sign up to set email alerts
|

Building Multi-model Collaboration in Detecting Multimedia Semantic Concepts

Abstract: The booming multimedia technology is incurring a thriving multi-media data propagation. As multimedia data have become more essential, taking over a major potion of the content processed by many applications, it is important to leverage data mining methods to associate the low-level features extracted from multimedia data to high-level semantic concepts. In order to bridge the semantic gap, researchers have investigated the correlation among multiple modalities involved in multimedia data to effectively detect… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2015
2015
2015
2015

Publication Types

Select...
3
1

Relationship

1
3

Authors

Journals

citations
Cited by 4 publications
(4 citation statements)
references
References 22 publications
0
4
0
Order By: Relevance
“…Altogether, all existing methods proposed for bringing a system closer to a reference data or to a user decision, in principle shorten the semantic gap, although only some authors directly pointed this out in their publications [9], [10], [1], [6]. Moreover, only part of the high improvement achieved by bridging the gap is generalized, the bigger part is subjective and specific to that reference data or to the particular user.…”
Section: Effects Of the Semantic Gap On Biasing Learning Systemsmentioning
confidence: 99%
See 1 more Smart Citation
“…Altogether, all existing methods proposed for bringing a system closer to a reference data or to a user decision, in principle shorten the semantic gap, although only some authors directly pointed this out in their publications [9], [10], [1], [6]. Moreover, only part of the high improvement achieved by bridging the gap is generalized, the bigger part is subjective and specific to that reference data or to the particular user.…”
Section: Effects Of the Semantic Gap On Biasing Learning Systemsmentioning
confidence: 99%
“…While previous research addressed this as a "vocabulary problem" [7], [8], showing that it is unlikely for two people to assign the same label to a given object; this problem has not been considered in the context of the well-known semantic gap. Research on the semantic gap has considered differences between user and computer interpretations of an image, and proposed methods to bridge it, such as introducing various machine learning algorithms [9], using different feature descriptors [3], using correlations among multiple data modalities (e.g., image, text, meta-data) [10], discovering semantic rules between users and computers [1], and using interactive models [6]. The proposed methods have been verified either by comparing results to reference data, or by measuring the degree of user acceptance in the interactive systems.…”
Section: Introductionmentioning
confidence: 99%
“…Other than the correlation captured at the feature level, the relationship between different models and model confidence toward extracting semantic concepts should also be learned [31,32,33]. In [34], separate generative probabilistic models are learned for different classifiers respectively.…”
Section: Multi-modal Multi-layer Fusionmentioning
confidence: 99%
“…Originally, MCA was extended from the standard correspondence analysis to analyze the correlation among variables. Later, it has demonstrated its competence in enhancing multimedia retrieval research topics through capturing the correlations among high-level semantic concepts and low-level features [74,111,116], and modeling posterior probability [73,110,134].…”
Section: Mca-based Iar Weight Estimationmentioning
confidence: 99%