Adaptive video indexing and automatic/semi-automatic relevance feedback

Munesawang, P.; Guan, Ling

doi:10.1109/tcsvt.2005.852412

Cited by 10 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This improvement is preferred in video retrieval since the user aims to retrieve the desired video in as few feedback steps as possible. This precision is better rather than results of ARFN proposed system in Munesawang and Guan (2005). In Munesawang and Guan (2005) for depth of 15 and after 20 user feedback achieve to 79% of precision.…”

Section: Resultsmentioning

confidence: 68%

“…This precision is better rather than results of ARFN proposed system in Munesawang and Guan (2005). In Munesawang and Guan (2005) for depth of 15 and after 20 user feedback achieve to 79% of precision. For visual example, a query shot of database is selected and its key frame is shown in Figure 8.…”

Section: Resultsmentioning

confidence: 68%

“…Because feature space is non-linear, so there is no distinction boundary between feature related to key frames of relevant and irrelevant shots. The average of precision retrieval in initial iteration (without RF), is 33% and after four user feedback, the proposed system (SVM with RBF) achieves 84% of precision, whereas, after seven iterations the retrieval precision of the ARFN proposed system (Munesawang and Guan, 2005) only reaches 79%. Thus, the proposed approach is able to reach the retrieval goal in only a few iterations.…”

Section: Resultsmentioning

confidence: 96%

“…SVM has a very good performance for pattern classification problems by minimising the Vapnik-Chervonenkis dimensions and achieving a minimal structural risk (Vapnik, 1995). Munesawang and Guan (2005) incorporated a self-learning neural network to implement an automatic RF method. Since neural network models perform effectively when matching given patterns against a large number of possible templates, he can adopt this organisation for similarity matching in video retrieval.…”

Section: Related Work On Relevance Feedbackmentioning

confidence: 99%

See 3 more Smart Citations

SVM-based Relevance Feedback for semantic video retrieval

Yazdi

Javidi

Pourreza

2009

IJSISE

View full text Add to dashboard Cite

This paper presents a novel method for efficient key frame extraction from video shot representation and employs a Support-Vector-Machine-based Relevance Feedback (SVM-RF) to bridging semantic gap between low-level feature and high-level concepts of shots. We introduce a new approach for key frame extraction using a hierarchical approach based on clustering. Using this key frame representation, the most representative key frame is then selected for each shot. Furthermore, our system incorporates user to judge about the result of retrieval and labelled retrieved shot in two groups, relevant and irrelevant. Then, by mean feature of relevant and irrelevant shots train an SVM classifier. In the next step, video database is classified in two groups, relevant and irrelevant shots. Suitable Graphic User Interface (GUI) is shown for capturing RF of user. This process continued until user satisfied with results. The proposed system is checked over collected shots from Trecvid2001 database and home videos include 800 shots of different concepts (10 semantic groups). Experimental results demonstrate the effectiveness of the proposed method.

show abstract

Section: Resultsmentioning

confidence: 68%

Section: Resultsmentioning

confidence: 68%

Section: Resultsmentioning

confidence: 96%

Section: Related Work On Relevance Feedbackmentioning

confidence: 99%

See 2 more Smart Citations

SVM-based Relevance Feedback for semantic video retrieval

Yazdi

Javidi

Pourreza

2009

IJSISE

View full text Add to dashboard Cite

show abstract

“…In order to index video clips, we present in "Section 3" the adaptive video indexing technique [26] for visual content analysis. In "Section 4", we present a statistical technique for audio content analysis using Laplacian mixture model [28].…”

Section: Proposed Methodsmentioning

confidence: 99%

A New Learning Algorithm for the Fusion of Adaptive Audio–Visual Features for the Retrieval and Classification of Movie Clips

Muneesawang

Guan

Amin

2008

J Sign Process Syst Sign Image Video Technol

View full text Add to dashboard Cite

This paper presents a new learning algorithm for audiovisual fusion and demonstrates its application to video classification for film database. The proposed system utilized perceptual features for content characterization of movie clips. These features are extracted from different modalities and fused through a machine learning process. More specifically, in order to capture the spatio-temporal information, an adaptive video indexing is adopted to extract visual feature, and the statistical model based on Laplacian mixture are utilized to extract audio feature. These features are fused at the late fusion stage and input to a support vector machine (SVM) to learn semantic concepts from a given video database. Based on our experimental results, the proposed system implementing the SVM-based fusion technique achieves high classification accuracy when applied to a large volume database containing Hollywood movies.

show abstract

References

2014

Unsupervised Learning

View full text Add to dashboard Cite

Adaptive video indexing and automatic/semi-automatic relevance feedback

Cited by 10 publications

References 31 publications

SVM-based Relevance Feedback for semantic video retrieval

SVM-based Relevance Feedback for semantic video retrieval

A New Learning Algorithm for the Fusion of Adaptive Audio–Visual Features for the Retrieval and Classification of Movie Clips

References

Contact Info

Product

Resources

About