Movie Content Analysis, Indexing and Skimming Via Multimodal Information

Liu, Ying; Narayanan, Shrikanth; Kuo, Chunghui

doi:10.1007/978-1-4757-6928-9_5

Cited by 5 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…User studies are employed for evaluating keyframe extraction techniques in [4,6,8,17,21,29]. These studies involve independent users judging the quality of generated video summaries, and are probably the most useful and realistic form of evaluation (especially when keyframes are extracted for user-based interactive tasks such as content browsing and navigation).…”

Section: Quantitative Evaluationmentioning

confidence: 99%

VSUMM: An Approach for Automatic Video Summarization and Quantitative Evaluation

Avila

Luz

Araújo

et al. 2008

2008 XXI Brazilian Symposium on Computer Graphics and Image Processing

View full text Add to dashboard Cite

In this paper, we propose an approach for video summarization (VSUMM). The video summaries are generated based on visual features. A factorial experiment is designed to analyze the relative impact of the attributes. We demonstrate the validity of the VSUMM approach by testing it on a collection of videos from Open Video Project. We provide a comparison among results of the proposed summarization technique with Open Video storyboard. A subjective evaluation showed that the summaries are produced with good quality.

show abstract

Section: Quantitative Evaluationmentioning

confidence: 99%

VSUMM: An Approach for Automatic Video Summarization and Quantitative Evaluation

Avila

Luz

Araújo

et al. 2008

2008 XXI Brazilian Symposium on Computer Graphics and Image Processing

View full text Add to dashboard Cite

show abstract

“…As the author indicated in the paper, the system typically split the same actor into different sets due to the various appearances of that actor in the movie. In [3], the system exploited the global structural information of a scene. They built "shot sinks" to classify a scene into one of three scenarios, "two speaker dialog", "multi-speaker dialog", and "others".…”

Section: Related Workmentioning

confidence: 99%

Conversation detection in feature films using finite state machines

Zhai¹,

Rasheed²,

Shah³

2004

Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.

View full text Add to dashboard Cite

In this paper, we address the problem of detecting the conversation scenes from feature films and propose and efficient and robust method for the stated problem. This method utilizes the structural information of the movie scenes with the combination of the low-level and mid-level features. We propose and demonstrate that a Finite State Machine (FSM) is suitable for detecting movie scenes with conversational settings. Tow major characteristics of motion pictures, motion and audio, are used in our approach. The transitions of the FSM are determined by two mid-level features of each shot in the scene: the activity intensity and the face identity. Our FSM has been experimented on over 50 clips with both positive and negative examples and produces convincing results.

show abstract

Video scene segmentation and semantic representation using a novel scheme

Zhu

Liu

2008

Multimed Tools Appl

View full text Add to dashboard Cite

Movie Content Analysis, Indexing and Skimming Via Multimodal Information

Cited by 5 publications

References 15 publications

VSUMM: An Approach for Automatic Video Summarization and Quantitative Evaluation

VSUMM: An Approach for Automatic Video Summarization and Quantitative Evaluation

Conversation detection in feature films using finite state machines

Video scene segmentation and semantic representation using a novel scheme

Contact Info

Product

Resources

About